For full functionality of this site it is necessary to enable JavaScript. Here are the instructions how to enable JavaScript in your web browser.

Position within the page tree

Michael Weyrich

Prof. Dr.-Ing. Dr. h. c.

Head of institute
Institute of Industrial Automation and Software Engineering

Contact

+49 711 685 67301
Email

Pfaffenwaldring 47
70569 Stuttgart
Germany
Room: 2.116

Publications

Journals and Conferences:

2025
1. P. Heinzelmann, S. Baum, K. R. Riedmüller, M. Liewald, and M. Weyrich, “A Comprehensive Benchmark Dataset for Sheet Metal Forming: Advancing Machine Learning and Surrogate Modelling in Pro-cess Simulations,” MATEC Web of Conferences, vol. 408, p. 1090, 2025.
  - Abstract
  - BibTeX
  Abstract
  FEM simulations are widely used for process development in the field of sheet metal forming to streamline tool design, shorten development cycles and minimize costly try-out processes. However, significant manual adjustments remain necessary due to deviations between simulation predictions and actual production outcomes, stemming from modelling simplifications. To further accelerate development cycles and try-out phases, it is essential to improve simulation accuracy and reduce computational demands. Here, surrogate models derived from simulation data by using machine learning provide a promising solution. In this context, the present paper introduces a comprehensive dataset designed to train surrogate models for optimizing sheet metal forming processes. The dataset includes extensive FE simulation data of deep-drawn sheet metal parts with an example geometry, considering diverse material and process parameters. It captures interactions among the tool geometry, material properties and process conditions, providing insights into stress distributions and strain paths. An example application demonstrates using the dataset to model the impact of material and process parameters on the forming limit diagram (FLD) of a deep-drawn part. The dataset, along with detailed documentation of the simulation setup, parameter scope and data formats, is available to the scientific community to facilitate further research in sheet metal forming optimization.
  BibTeX
  @article{Heinzelmann2025, abstract = {FEM simulations are widely used for process development in the field of sheet metal forming to streamline tool design, shorten development cycles and minimize costly try-out processes. However, significant manual adjustments remain necessary due to deviations between simulation predictions and actual production outcomes, stemming from modelling simplifications. To further accelerate development cycles and try-out phases, it is essential to improve simulation accuracy and reduce computational demands. Here, surrogate models derived from simulation data by using machine learning provide a promising solution. In this context, the present paper introduces a comprehensive dataset designed to train surrogate models for optimizing sheet metal forming processes. The dataset includes extensive FE simulation data of deep-drawn sheet metal parts with an example geometry, considering diverse material and process parameters. It captures interactions among the tool geometry, material properties and process conditions, providing insights into stress distributions and strain paths. An example application demonstrates using the dataset to model the impact of material and process parameters on the forming limit diagram (FLD) of a deep-drawn part. The dataset, along with detailed documentation of the simulation setup, parameter scope and data formats, is available to the scientific community to facilitate further research in sheet metal forming optimization.}, author = {Heinzelmann, Pascal and Baum, Sebastian and Riedmüller, Kim Rouven and Liewald, Mathias and Weyrich, Michael}, doi = {10.1051/matecconf/202540801090}, issn = {2261-236X}, journal = {MATEC Web of Conferences}, pages = 01090, publisher = {EDP Sciences}, title = {A Comprehensive Benchmark Dataset for Sheet Metal Forming: Advancing Machine Learning and Surrogate Modelling in Pro-cess Simulations}, volume = 408, year = 2025 }
2. P. Heinzelmann, S. Baum, K. R. Riedmüller, M. Liewald, and M. Weyrich, “A Data-Driven Surrogate Model for Predicting Springback in Deep Drawing Processes,” Journal of Physics: Conference Series, vol. 3104, p. 12060, Sep. 2025.
  - Abstract
  - BibTeX
  Abstract
  The design of deep drawing processes for high-quality sheet metal forming products requires substantial expertise in product design, process optimisation, and equipment selection. Here, a special focus lies on predicting the material behaviour during the forming process, particularly the springback behaviour after deep drawing, which remains a major challenge due to stochastic process deviations. Currently, the prediction of springback is associated with complex and time-consuming simulations. Hence, in this context, this paper proposes a data-driven surrogate model utilising simulation data from synthetic finite element analysis (FEA) to compensate for the computational effort in predictive manufacturing. The simulation contains surface data on the deep-drawing and trimming process for both the loaded and unloaded part. This provides necessary information on the springback of the part. By representing simulation data through graph-based representations with multidimensional edge features, this model allows complex relationships between part geometry, process parameters and springback effects to be identified without relying on restrictive domain assumptions. The proposed methodology demonstrates significant potential for reducing simulation-based prediction times and enhancing deep-drawing tool design and optimisation. Furthermore, the modelling approach incorporates differentiable properties, enabling the application of gradient-based optimisation techniques. This facilitates the precise prediction of springback effects.
  BibTeX
  @article{Heinzelmann2025, abstract = {The design of deep drawing processes for high-quality sheet metal forming products requires substantial expertise in product design, process optimisation, and equipment selection. Here, a special focus lies on predicting the material behaviour during the forming process, particularly the springback behaviour after deep drawing, which remains a major challenge due to stochastic process deviations. Currently, the prediction of springback is associated with complex and time-consuming simulations. Hence, in this context, this paper proposes a data-driven surrogate model utilising simulation data from synthetic finite element analysis (FEA) to compensate for the computational effort in predictive manufacturing. The simulation contains surface data on the deep-drawing and trimming process for both the loaded and unloaded part. This provides necessary information on the springback of the part. By representing simulation data through graph-based representations with multidimensional edge features, this model allows complex relationships between part geometry, process parameters and springback effects to be identified without relying on restrictive domain assumptions. The proposed methodology demonstrates significant potential for reducing simulation-based prediction times and enhancing deep-drawing tool design and optimisation. Furthermore, the modelling approach incorporates differentiable properties, enabling the application of gradient-based optimisation techniques. This facilitates the precise prediction of springback effects.}, author = {Heinzelmann, Pascal and Baum, Sebastian and Riedmüller, Kim Rouven and Liewald, Mathias and Weyrich, Michael}, doi = {10.1088/1742-6596/3104/1/012060}, issn = {1742-6588}, journal = {Journal of Physics: Conference Series}, month = {09}, number = 1, pages = 012060, publisher = {IOP Publishing}, title = {A Data-Driven Surrogate Model for Predicting Springback in Deep Drawing Processes}, volume = 3104, year = 2025 }
3. A. Narla, D. Dittler, N. Jazdi, and M. Weyrich, “A Framework for Interoperability in Software Defined Vehicles using Asset Administration Shells,” in 2025 IEEE 8th International Conference on Industrial Cyber-Physical Systems (ICPS), 2025, pp. 1–4.
  - Abstract
  - BibTeX
  Abstract
  The automotive domain is undergoing a significant transformation driven by the Software-Defined Vehicle (SDV) concept and the increasing complexity of the mobility ecosystem. Achieving seamless interoperability between heterogeneous systems poses a substantial challenge, compounded by diverse data formats, integrating mixed-criticality functionalities, and the lack of unified frameworks leading to fragmented systems. This paper investigates the potential of Asset Administration Shell (AAS), as a complementary solution to existing vehicle interoperability technologies. Using a systematic analysis, we examine how AAS can enable abstraction, modularity, interoperable communication, and cross-platform data integration, thereby addressing key challenges of interoperability in vehicular systems. However, implementing AAS introduces challenges such as data complexity, real-time, and security issues. Despite these challenges, AAS offers opportunities in abstracting sensors and synchronizing communication in distributed testing scenarios. This paper highlights the AAS's potential to complement existing solutions, paving the way for scalable and interoperable automotive systems in the SDV era.
  BibTeX
  @inproceedings{Narla2025, abstract = {The automotive domain is undergoing a significant transformation driven by the Software-Defined Vehicle (SDV) concept and the increasing complexity of the mobility ecosystem. Achieving seamless interoperability between heterogeneous systems poses a substantial challenge, compounded by diverse data formats, integrating mixed-criticality functionalities, and the lack of unified frameworks leading to fragmented systems. This paper investigates the potential of Asset Administration Shell (AAS), as a complementary solution to existing vehicle interoperability technologies. Using a systematic analysis, we examine how AAS can enable abstraction, modularity, interoperable communication, and cross-platform data integration, thereby addressing key challenges of interoperability in vehicular systems. However, implementing AAS introduces challenges such as data complexity, real-time, and security issues. Despite these challenges, AAS offers opportunities in abstracting sensors and synchronizing communication in distributed testing scenarios. This paper highlights the AAS's potential to complement existing solutions, paving the way for scalable and interoperable automotive systems in the SDV era.}, author = {Narla, Akshay and Dittler, Daniel and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE 8th International Conference on Industrial Cyber-Physical Systems (ICPS)}, doi = {10.1109/icps65515.2025.11087876}, month = {05}, pages = {1--4}, publisher = {IEEE}, title = {A Framework for Interoperability in Software Defined Vehicles using Asset Administration Shells}, year = 2025 }
4. M. Weiß, F. Sautter, M. Artelt, P. Grimmeisen, N. Jazdi, and M. Weyrich, “A Review on Anomaly Detection for Connected Vehicles Using Deep Reinforcement Learning,” in 2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA), 2025, pp. 1–8.
  - Abstract
  - BibTeX
  Abstract
  The transition to connected vehicles (CVs) is shaping the future of autonomous and highly connected vehicles. As the vehicles’ reliance on increasingly complex software increases, more central points of failure are introduced. This necessitates more thorough and scalable anomaly and intrusion detection systems. Conventional approaches can struggle with the complex and dynamic structures of CVs while not providing any automatic response actions. Therefore, machine learning-based anomaly detection methods are gaining popularity. Reinforcement Learning especially has shown the potential to increase configurability and provide end-to-end solutions. Thus, this paper presents a Systematic Literature Review (SLR) on Reinforcement Learning (RL) for anomaly and intrusion detection, applicable for CVs. In it, different RL algorithms and the analysis of how they can be used for training and detecting anomalies are presented. The problem formulations for different approaches are compared, their advantages and challenges are discussed. Additionally, the potential of using RL to react to anomalies is presented, discussed and advocated for. The results of the survey indicate that many of the identified RL formulations are not inherently superior from supervised learning approaches. However, RL techniques can result in better configurability of anomaly detection system, enabling site reliability engineers to efficiently adjust the model via reward functions. Furthermore, it becomes evident that the strengths of RL-based anomaly detection are best leveraged when used for reacting to anomalies. Therefore, the authors propose to focus on the contextual or sequential decision making formulation including corrective actions, compared to the classification-based detection formulations using RL.
  BibTeX
  @inproceedings{Wei2025, abstract = {The transition to connected vehicles (CVs) is shaping the future of autonomous and highly connected vehicles. As the vehicles’ reliance on increasingly complex software increases, more central points of failure are introduced. This necessitates more thorough and scalable anomaly and intrusion detection systems. Conventional approaches can struggle with the complex and dynamic structures of CVs while not providing any automatic response actions. Therefore, machine learning-based anomaly detection methods are gaining popularity. Reinforcement Learning especially has shown the potential to increase configurability and provide end-to-end solutions. Thus, this paper presents a Systematic Literature Review (SLR) on Reinforcement Learning (RL) for anomaly and intrusion detection, applicable for CVs. In it, different RL algorithms and the analysis of how they can be used for training and detecting anomalies are presented. The problem formulations for different approaches are compared, their advantages and challenges are discussed. Additionally, the potential of using RL to react to anomalies is presented, discussed and advocated for. The results of the survey indicate that many of the identified RL formulations are not inherently superior from supervised learning approaches. However, RL techniques can result in better configurability of anomaly detection system, enabling site reliability engineers to efficiently adjust the model via reward functions. Furthermore, it becomes evident that the strengths of RL-based anomaly detection are best leveraged when used for reacting to anomalies. Therefore, the authors propose to focus on the contextual or sequential decision making formulation including corrective actions, compared to the classification-based detection formulations using RL.}, author = {Weiß, Matthias and Sautter, Friedrich and Artelt, Maurice and Grimmeisen, Philipp and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}, doi = {10.1109/etfa65518.2025.11205543}, month = {09}, pages = {1--8}, publisher = {IEEE}, title = {A Review on Anomaly Detection for Connected Vehicles Using Deep Reinforcement Learning}, year = 2025 }
5. M. Weiß, A. Schön, M. Lück, M. Schnierle, S. Carosella, N. Jazdi, C. Constantinescu, P. Middendorf, and M. Weyrich, “An Approach for a Human-Assisted Data Loop in Connected Manufacturing Systems,” in ARENA2036, Springer Nature Switzerland, 2025, pp. 257–267.
  - Abstract
  - BibTeX
  Abstract
  Abstract Today’s production is characterized by shorter innovation cycles, leading to a highly dynamic shop floor environment. To tackle the need for fast and flexible adaptation, it is aimed for a complete digital integration of machines and a comprehensive data management. Benefiting from the vast amounts of heterogeneous data collected requires a thorough understanding of their dependencies and correlations as well as a human-assisted, yet automated analysis process. Still, up to this date, the realization of this vision proves to be very challenging in practice and requires a myriad of different new methods and technologies. Therefore, the scope of this paper is to provide an outline of how such an end-to-end connectivity can be achieved along the real-world example of a lightweight construction process. As such, it is shown how its machines are upgraded and connected to the network in order to allow for collection of time series data using a central agent. A context provider is introduced, with which external data sources, such as wearables, can be integrated. After collecting and merging the data, its storage and sharing are managed using a Data Lakehouse. The data is analyzed by using a human-assisted feedback loop, effectively integrating expert knowledge into the learning process. Using the so-gained knowledge, optimization of the shop floor, intralogistics and IT infrastructure can be achieved. Preliminary results from parts of this loop already in operation suggest significant potential benefits, paving the way for more comprehensive integration across production systems.
  BibTeX
  @incollection{Wei2025, abstract = {Abstract Today’s production is characterized by shorter innovation cycles, leading to a highly dynamic shop floor environment. To tackle the need for fast and flexible adaptation, it is aimed for a complete digital integration of machines and a comprehensive data management. Benefiting from the vast amounts of heterogeneous data collected requires a thorough understanding of their dependencies and correlations as well as a human-assisted, yet automated analysis process. Still, up to this date, the realization of this vision proves to be very challenging in practice and requires a myriad of different new methods and technologies. Therefore, the scope of this paper is to provide an outline of how such an end-to-end connectivity can be achieved along the real-world example of a lightweight construction process. As such, it is shown how its machines are upgraded and connected to the network in order to allow for collection of time series data using a central agent. A context provider is introduced, with which external data sources, such as wearables, can be integrated. After collecting and merging the data, its storage and sharing are managed using a Data Lakehouse. The data is analyzed by using a human-assisted feedback loop, effectively integrating expert knowledge into the learning process. Using the so-gained knowledge, optimization of the shop floor, intralogistics and IT infrastructure can be achieved. Preliminary results from parts of this loop already in operation suggest significant potential benefits, paving the way for more comprehensive integration across production systems.}, author = {Weiß, Matthias and Schön, Alexander and Lück, Matthias and Schnierle, Maximilian and Carosella, Stefan and Jazdi, Nasser and Constantinescu, Carmen and Middendorf, Peter and Weyrich, Michael}, booktitle = {ARENA2036}, doi = {10.1007/978-3-031-88831-1_21}, isbn = {9783031888304}, issn = {2524-7247}, pages = {257--267}, publisher = {Springer Nature Switzerland}, title = {An Approach for a Human-Assisted Data Loop in Connected Manufacturing Systems}, year = 2025 }
6. Y. Xia, N. Jazdi, and M. Weyrich, “An Architecture for Integrating Large Language Models with Digital Twins and Automation Systems,” in 2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA), 2025, pp. 1–8.
  - Abstract
  - BibTeX
  Abstract
  Large Language Models (LLMs) offer flexible reasoning capability but lack physical embodiment, while traditional automation systems can execute physical processes yet lack cognitive capability. This paper presents a layered architecture that bridges this gap by integrating LLMs with digital twins and physical automation systems, with reference to practical case studies as proof of concept. The proposed architecture comprises three layers: a cognitive layer powered by LLMs, a bridging layer based on digital twins, and a physical layer consisting of technical process and automation system. Within the digital twin layer, we introduce three design paradigms for structuring information to support effective LLM integration: state snapshot modeling, event message modeling, and plan sequence modeling. These paradigms are demonstrated through prototypical case studies on robotic automation control and process simulation. To address challenges such as hallucination, task complexity, and system reliability, we distill a set of practical strategies, including multi-agent system design, human validation, and test-driven development. Additionally, we propose the concept of "Return on Intelligence" as a conceptual tool for evaluating the efficacy of investments in intelligent automation. This research contributes to the theoretical foundation and the architecture design for developing intelligent, adaptive automation systems powered by LLMs.
  BibTeX
  @inproceedings{Xia2025, abstract = {Large Language Models (LLMs) offer flexible reasoning capability but lack physical embodiment, while traditional automation systems can execute physical processes yet lack cognitive capability. This paper presents a layered architecture that bridges this gap by integrating LLMs with digital twins and physical automation systems, with reference to practical case studies as proof of concept. The proposed architecture comprises three layers: a cognitive layer powered by LLMs, a bridging layer based on digital twins, and a physical layer consisting of technical process and automation system. Within the digital twin layer, we introduce three design paradigms for structuring information to support effective LLM integration: state snapshot modeling, event message modeling, and plan sequence modeling. These paradigms are demonstrated through prototypical case studies on robotic automation control and process simulation. To address challenges such as hallucination, task complexity, and system reliability, we distill a set of practical strategies, including multi-agent system design, human validation, and test-driven development. Additionally, we propose the concept of "Return on Intelligence" as a conceptual tool for evaluating the efficacy of investments in intelligent automation. This research contributes to the theoretical foundation and the architecture design for developing intelligent, adaptive automation systems powered by LLMs.}, author = {Xia, Yuchen and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}, doi = {10.1109/etfa65518.2025.11205636}, month = {09}, pages = {1--8}, publisher = {IEEE}, title = {An Architecture for Integrating Large Language Models with Digital Twins and Automation Systems}, year = 2025 }
7. M. Weiß, A. Navalgund, J. Stümpfle, F. Dettinger, and M. Weyrich, “An OpenSource CI/CD Pipeline for Variant-Rich Software-Defined Vehicles,” in 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025, pp. 1–6.
  - Abstract
  - BibTeX
  Abstract
  Software-defined vehicles (SDVs) offer a wide range of connected functionalities, including enhanced driving behavior and fleet management. These features are continuously updated via over-the-air (OTA) mechanisms, resulting in a growing number of software versions and variants due to the diversity of vehicles, cloud/edge environments, and stakeholders involved. The lack of a unified integration environment further complicates development, as connected mobility solutions are often built in isolation. To ensure reliable operations across heterogeneous systems, a dynamic orchestration of functions that considers hardware and software variability is essential. This paper presents an open-source CI/CD pipeline tailored for SDVs. It automates the build, test, and deployment phases using a combination of containerized open-source tools, creating a standardized, portable, and scalable ecosystem accessible to all stakeholders. Additionally, a custom OTA middleware distributes software updates and supports rollbacks across vehicles and backend services. Update variants are derived based on deployment target dependencies and hardware configurations. The pipeline also supports continuous development and deployment of AI models for autonomous driving features. Its effectiveness is evaluated using an automated valet parking (AVP) scenario involving TurtleBots and a coordinating backend server. Two object detection variants are developed and deployed to match hardware-specific requirements. Results demonstrate seamless OTA updates, correct variant selection, and successful orchestration across all targets. Overall, the proposed pipeline provides a scalable and efficient solution for managing software variants and OTA updates in SDVs, contributing to the advancement of future mobility technologies.
  BibTeX
  @inproceedings{Wei2025, abstract = {Software-defined vehicles (SDVs) offer a wide range of connected functionalities, including enhanced driving behavior and fleet management. These features are continuously updated via over-the-air (OTA) mechanisms, resulting in a growing number of software versions and variants due to the diversity of vehicles, cloud/edge environments, and stakeholders involved. The lack of a unified integration environment further complicates development, as connected mobility solutions are often built in isolation. To ensure reliable operations across heterogeneous systems, a dynamic orchestration of functions that considers hardware and software variability is essential. This paper presents an open-source CI/CD pipeline tailored for SDVs. It automates the build, test, and deployment phases using a combination of containerized open-source tools, creating a standardized, portable, and scalable ecosystem accessible to all stakeholders. Additionally, a custom OTA middleware distributes software updates and supports rollbacks across vehicles and backend services. Update variants are derived based on deployment target dependencies and hardware configurations. The pipeline also supports continuous development and deployment of AI models for autonomous driving features. Its effectiveness is evaluated using an automated valet parking (AVP) scenario involving TurtleBots and a coordinating backend server. Two object detection variants are developed and deployed to match hardware-specific requirements. Results demonstrate seamless OTA updates, correct variant selection, and successful orchestration across all targets. Overall, the proposed pipeline provides a scalable and efficient solution for managing software variants and OTA updates in SDVs, contributing to the advancement of future mobility technologies.}, author = {Weiß, Matthias and Navalgund, Anish and Stümpfle, Johannes and Dettinger, Falk and Weyrich, Michael}, booktitle = {2025 IEEE International Automated Vehicle Validation Conference (IAVVC)}, doi = {10.1109/iavvc61942.2025.11219546}, month = {09}, pages = {1--6}, publisher = {IEEE}, title = {An OpenSource CI/CD Pipeline for Variant-Rich Software-Defined Vehicles}, year = 2025 }
8. J. Stümpfle, A. K. V. Narla, N. Jazdi, and M. Weyrich, “Android Automotive for Software-Defined Vehicles: An Assessment of Capabilities, Limitations, and Future Directions,” in 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025, pp. 1–6.
  - Abstract
  - BibTeX
  Abstract
  The automotive industry is rapidly shifting towards software-defined vehicles (SDVs), with automotive operating systems becoming central to system integration. Android Automotive Operating System (AAOS) has gained significant adoption from manufacturers due to its developer ecosystem, Over-the-Air capabilities, and Hardware Abstraction Layer that decouples software from hardware. Despite its growing industry presence, a gap exists in academic research examining AAOS's role in the SDV transformation. This paper provides a technical assessment of AAOS through code analysis, architecture review, and implementation on an intelligent cockpit platform. We examine AAOS's potential beyond infotainment to more integral roles in automotive architecture, identifying both strengths—software flexibility, scalability, and cloud integration—and limitations—realtime performance constraints, Google ecosystem dependency, and safety-critical function capabilities. Our contributions include a systematic architecture review focused on HAL implementation, identification of technical limitations for broader automotive applications, documentation of implementation challenges through our case study, and extended architecture components addressing identified limitations. This research informs both academic discourse and industry practice regarding AAOS's role in the evolution towards fully software-defined vehicles.
  BibTeX
  @inproceedings{Stmpfle2025, abstract = {The automotive industry is rapidly shifting towards software-defined vehicles (SDVs), with automotive operating systems becoming central to system integration. Android Automotive Operating System (AAOS) has gained significant adoption from manufacturers due to its developer ecosystem, Over-the-Air capabilities, and Hardware Abstraction Layer that decouples software from hardware. Despite its growing industry presence, a gap exists in academic research examining AAOS's role in the SDV transformation. This paper provides a technical assessment of AAOS through code analysis, architecture review, and implementation on an intelligent cockpit platform. We examine AAOS's potential beyond infotainment to more integral roles in automotive architecture, identifying both strengths—software flexibility, scalability, and cloud integration—and limitations—realtime performance constraints, Google ecosystem dependency, and safety-critical function capabilities. Our contributions include a systematic architecture review focused on HAL implementation, identification of technical limitations for broader automotive applications, documentation of implementation challenges through our case study, and extended architecture components addressing identified limitations. This research informs both academic discourse and industry practice regarding AAOS's role in the evolution towards fully software-defined vehicles.}, author = {Stümpfle, Johannes and Narla, Akshay Kumar Venkatesha and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE International Automated Vehicle Validation Conference (IAVVC)}, doi = {10.1109/iavvc61942.2025.11219511}, month = {09}, pages = {1--6}, publisher = {IEEE}, title = {Android Automotive for Software-Defined Vehicles: An Assessment of Capabilities, Limitations, and Future Directions}, year = 2025 }
9. L. Hettich, T. Pett, A.-T. Nägele, M. Schindewolf, H. Eriş, S. Wagner, E. Sax, I. Schaefer, and M. Weyrich, “Automated Test Process for Highly Configurable Software-Defined Mobility Systems in CI/CD,” in 2025 Stuttgart International Symposium, 2025, vol. 1, pp. 2025–1.
  - Abstract
  - BibTeX
  Abstract
  In the pursuit of customizability and evolvability of vehicle functions, manufacturers shift towards software-defined vehicles to enable flexible customization and over-the-air updates. This results in multiple variants and versions of a vehicle model. While shifting to software-defined vehicles (SDVs) adds value and flexibility for customers, manufacturers struggle with homologating new and updated functionality because existing testing processes do not scale for high-frequency release cycles that limit available testing resources. Overcoming this challenge by using a coherent test process designed for testing continuously evolving variant-rich systems will be one of the key enablers. This paper presents an innovative end-to-end pipeline for efficient and comprehensive testing of variant-rich vehicle functionality tailored to an application in continuous development. Our transferable test pipeline employs sample-based variant selection, a software-in-the-loop environment for executing selected variants, and scenario-based testing using mutation-based scenario fuzzing. A central test controller is responsible for managing the process. We evaluate our test pipeline with regard to its fault detection capability, using the YOLO object detection algorithm as a variant-rich test object in the CARLA simulator. Our results show that the testing process outperforms random variant sampling and scenario mutation in detecting faults.
  BibTeX
  @inproceedings{Hettich2025, abstract = {In the pursuit of customizability and evolvability of vehicle functions, manufacturers shift towards software-defined vehicles to enable flexible customization and over-the-air updates. This results in multiple variants and versions of a vehicle model. While shifting to software-defined vehicles (SDVs) adds value and flexibility for customers, manufacturers struggle with homologating new and updated functionality because existing testing processes do not scale for high-frequency release cycles that limit available testing resources. Overcoming this challenge by using a coherent test process designed for testing continuously evolving variant-rich systems will be one of the key enablers. This paper presents an innovative end-to-end pipeline for efficient and comprehensive testing of variant-rich vehicle functionality tailored to an application in continuous development. Our transferable test pipeline employs sample-based variant selection, a software-in-the-loop environment for executing selected variants, and scenario-based testing using mutation-based scenario fuzzing. A central test controller is responsible for managing the process. We evaluate our test pipeline with regard to its fault detection capability, using the YOLO object detection algorithm as a variant-rich test object in the CARLA simulator. Our results show that the testing process outperforms random variant sampling and scenario mutation in detecting faults.}, author = {Hettich, Lennard and Pett, Tobias and Nägele, Ann-Therese and Schindewolf, Marc and Eriş, Halit and Wagner, Stefan and Sax, Eric and Schaefer, Ina and Weyrich, Michael}, booktitle = {2025 Stuttgart International Symposium}, doi = {10.4271/2025-01-0297}, issn = {0148-7191}, month = {07}, pages = {2025-01-0297}, publisher = {SAE International}, title = {Automated Test Process for Highly Configurable Software-Defined Mobility Systems in CI/CD}, volume = 1, year = 2025 }
10. Y. Xia, N. Jazdi, J. Zhang, C. Shah, and M. Weyrich, “Control Industrial Automation System with Large Language Model Agents,” in 2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA), 2025, pp. 1–8.
  - Abstract
  - BibTeX
  Abstract
  Traditional industrial automation systems require specialized expertise to operate and complex reprogramming to adapt to new processes. Large language models offer the intelligence to make them more flexible and easier to use. However, LLMs’ application in industrial automation settings is underexplored. This paper introduces a framework for integrating LLMs to achieve end-to-end control of industrial automation systems. At the core of the framework is an agent system designed for industrial automation tasks. A structured prompting method and an event-driven modeling mechanism provide the information for LLMs to perform reasoning on different context levels, allowing them to semantically interpret the information, generate production plans, and control operations on the automation system. Furthermore, this framework facilitates the creation of structured datasets for fine-tuning LLMs on this specific downstream application. Our contribution includes a formal system design, proof-of-concept implementation, and a method for generating task-specific datasets for LLM fine-tuning and testing. This approach enables a more adaptive automation system that can respond to spontaneous events, allowing intuitive system operation and configuration through natural language. Demo videos and detailed evaluation data are accessible on GitHub: https://github.com/YuchenXia/LLM4IAS.
  BibTeX
  @inproceedings{Xia2025, abstract = {Traditional industrial automation systems require specialized expertise to operate and complex reprogramming to adapt to new processes. Large language models offer the intelligence to make them more flexible and easier to use. However, LLMs’ application in industrial automation settings is underexplored. This paper introduces a framework for integrating LLMs to achieve end-to-end control of industrial automation systems. At the core of the framework is an agent system designed for industrial automation tasks. A structured prompting method and an event-driven modeling mechanism provide the information for LLMs to perform reasoning on different context levels, allowing them to semantically interpret the information, generate production plans, and control operations on the automation system. Furthermore, this framework facilitates the creation of structured datasets for fine-tuning LLMs on this specific downstream application. Our contribution includes a formal system design, proof-of-concept implementation, and a method for generating task-specific datasets for LLM fine-tuning and testing. This approach enables a more adaptive automation system that can respond to spontaneous events, allowing intuitive system operation and configuration through natural language. Demo videos and detailed evaluation data are accessible on GitHub: https://github.com/YuchenXia/LLM4IAS.}, author = {Xia, Yuchen and Jazdi, Nasser and Zhang, Jize and Shah, Chaitanya and Weyrich, Michael}, booktitle = {2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}, doi = {10.1109/etfa65518.2025.11205539}, month = {09}, pages = {1--8}, publisher = {IEEE}, title = {Control Industrial Automation System with Large Language Model Agents}, year = 2025 }
11. F. Dettinger, M. Weiß, M. Weyrich, D. Baumann, and M. Sommer, “Directives for Function Offloading in 5G Networks Based on a Performance Characteristics Analysis,” in 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025, pp. 1–8.
  - Abstract
  - BibTeX
  Abstract
  Cloud-based offloading helps address energy consumption and performance challenges in executing resourceintensive vehicle algorithms. Utilizing 5G, with its low latency and high bandwidth, enables seamless vehicle-to-cloud integration. Currently, only non-standalone 5G is publicly available, and realworld applications remain underexplored compared to theoretical studies. This paper evaluates 5G non-standalone networks for cloud execution of vehicle functions, focusing on latency, Round Trip Time, and packet delivery. Tests used two AI-based algorithms—emotion recognition and object recognition—along an 8.8 km route in Baden-Württemberg, Germany, encompassing urban, rural, and forested areas. Two platforms were analyzed: a cloudlet in Frankfurt and a cloud in Mannheim, employing various deployment strategies like conventional applications and containerized and container-orchestrated setups. Key findings highlight an average signal quality of 84 %, with no connectivity interruptions despite minor drops in built-up areas. Packet analysis revealed a Packet Error Rate below 0.1 % for both algorithms. Transfer times varied significantly depending on the geographical location and the backend servers' network connections, while processing times were mainly influenced by the computation hardware in use. Additionally, cloud offloading seems only be a suitable option, when a round trip time of more than 150 ms is possible.
  BibTeX
  @inproceedings{Dettinger2025, abstract = {Cloud-based offloading helps address energy consumption and performance challenges in executing resourceintensive vehicle algorithms. Utilizing 5G, with its low latency and high bandwidth, enables seamless vehicle-to-cloud integration. Currently, only non-standalone 5G is publicly available, and realworld applications remain underexplored compared to theoretical studies. This paper evaluates 5G non-standalone networks for cloud execution of vehicle functions, focusing on latency, Round Trip Time, and packet delivery. Tests used two AI-based algorithms—emotion recognition and object recognition—along an 8.8 km route in Baden-Württemberg, Germany, encompassing urban, rural, and forested areas. Two platforms were analyzed: a cloudlet in Frankfurt and a cloud in Mannheim, employing various deployment strategies like conventional applications and containerized and container-orchestrated setups. Key findings highlight an average signal quality of 84 %, with no connectivity interruptions despite minor drops in built-up areas. Packet analysis revealed a Packet Error Rate below 0.1 % for both algorithms. Transfer times varied significantly depending on the geographical location and the backend servers' network connections, while processing times were mainly influenced by the computation hardware in use. Additionally, cloud offloading seems only be a suitable option, when a round trip time of more than 150 ms is possible.}, author = {Dettinger, Falk and Weiß, Matthias and Weyrich, Michael and Baumann, Daniel and Sommer, Martin}, booktitle = {2025 IEEE International Automated Vehicle Validation Conference (IAVVC)}, doi = {10.1109/iavvc61942.2025.11219471}, month = {09}, pages = {1--8}, publisher = {IEEE}, title = {Directives for Function Offloading in 5G Networks Based on a Performance Characteristics Analysis}, year = 2025 }
12. A. Narla, J. Stümpfle, S. Saha, N. Jazdi, and M. Weyrich, “Evaluating Hardware Abstraction Layer Concepts for Software Defined Vehicles: Insights into Applicability and Effectiveness,” in 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025, pp. 1–6.
  - Abstract
  - BibTeX
  Abstract
  The emergence of Software-Defined Vehicles (SDVs) represents a fundamental shift in automotive design, prioritizing software-centric architectures over traditional hardware-driven models. SDVs require modularity, interoperability, real-time processing, and over-the-air update capabilities throughout the vehicle lifecycle. However, current vehicle systems, characterized by tightly coupled software and hardware, struggle to meet these demands due to their complexity and heterogeneity. A critical first step toward enabling SDVs is the decoupling of software from hardware, which can be facilitated through a robust Hardware Abstraction Layer (HAL). While existing HALs offer hardware independence and standardized interfaces, their applicability and effectiveness in SDV contexts, characterized by multi-vendor ecosystems, safety-critical requirements, and cloud-edge usage, remain uncertain. This paper systematically evaluates current automotive HALs and explores HAL mechanisms from non-automotive domains—including smartphones, networking, and industrial automation—to extract cross-domain insights relevant to SDV development. A criteria-driven evaluation framework is developed to assess HALs against SDV-specific needs. Findings reveal that while middleware-based HALs offer portability and modularity, hypervisor-based approaches better support safety, OTA readiness, and hardware efficiency. Limitations in both approaches are identified, prompting recommendations for a hybrid HAL design that integrates hypervisor isolation with middleware standardization. This paper contributes to the ongoing developments on automotive software architecture by offering insights into the applicability and effectiveness of current HAL strategies. It provides actionable guidance for designing flexible, scalable, and future-ready HALs to support SDVs across their lifecycle. The study supports industry-wide standardization efforts and aims to ensure long-term adaptability of automotive platforms in a connected and rapidly evolving mobility ecosystem.
  BibTeX
  @inproceedings{Narla2025, abstract = {The emergence of Software-Defined Vehicles (SDVs) represents a fundamental shift in automotive design, prioritizing software-centric architectures over traditional hardware-driven models. SDVs require modularity, interoperability, real-time processing, and over-the-air update capabilities throughout the vehicle lifecycle. However, current vehicle systems, characterized by tightly coupled software and hardware, struggle to meet these demands due to their complexity and heterogeneity. A critical first step toward enabling SDVs is the decoupling of software from hardware, which can be facilitated through a robust Hardware Abstraction Layer (HAL). While existing HALs offer hardware independence and standardized interfaces, their applicability and effectiveness in SDV contexts, characterized by multi-vendor ecosystems, safety-critical requirements, and cloud-edge usage, remain uncertain. This paper systematically evaluates current automotive HALs and explores HAL mechanisms from non-automotive domains—including smartphones, networking, and industrial automation—to extract cross-domain insights relevant to SDV development. A criteria-driven evaluation framework is developed to assess HALs against SDV-specific needs. Findings reveal that while middleware-based HALs offer portability and modularity, hypervisor-based approaches better support safety, OTA readiness, and hardware efficiency. Limitations in both approaches are identified, prompting recommendations for a hybrid HAL design that integrates hypervisor isolation with middleware standardization. This paper contributes to the ongoing developments on automotive software architecture by offering insights into the applicability and effectiveness of current HAL strategies. It provides actionable guidance for designing flexible, scalable, and future-ready HALs to support SDVs across their lifecycle. The study supports industry-wide standardization efforts and aims to ensure long-term adaptability of automotive platforms in a connected and rapidly evolving mobility ecosystem.}, author = {Narla, Akshay and Stümpfle, Johannes and Saha, Souvik and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE International Automated Vehicle Validation Conference (IAVVC)}, doi = {10.1109/iavvc61942.2025.11219503}, month = {09}, pages = {1--6}, publisher = {IEEE}, title = {Evaluating Hardware Abstraction Layer Concepts for Software Defined Vehicles: Insights into Applicability and Effectiveness}, year = 2025 }
13. B. C. Gül, S. Nadig, S. Tziampazis, N. Jazdi, and M. Weyrich, “FedMultiEmo: Real-Time Emotion Recognition via Multimodal Federated Learning,” in 2025 5th International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2025, pp. 1–8.
  - Abstract
  - BibTeX
  Abstract
  In-vehicle emotion recognition underpins adaptive driver-assistance systems and, ultimately, occupant safety. However, practical deployment is hindered by (i) modality fragility—poor lighting and occlusions degrade vision-based methods; (ii) physiological variability-heart-rate and skin-conductance patterns differ across individuals; and (iii) privacy risk—centralized training requires transmission of sensitive data. To address these challenges, we present FedMultiEmo, a privacy-preserving framework that fuses two complementary modalities at the decision level: visual features extracted by a Convolutional Neural Network from facial images, and physiological cues (heart rate, electrodermal activity, and skin temperature) classified by a Random Forest. FedMultiEmo builds on three key elements: (1) a multimodal federated learning pipeline with majority-vote fusion, (2) an end-to-end edge-to-cloud prototype on Raspberry Pi clients and a Flower server, and (3) a personalized Federated Averaging scheme that weights client updates by local data volume. Evaluated on FER2013 and a custom physiological dataset, the federated Convolutional Neural Network attains 77% accuracy, the Random Forest 74%, and their fusion 87%, matching a centralized baseline while keeping all raw data local. The developed system converges in 18 rounds, with an average round time of 120 s and a per-client memory footprint below 200 MB. These results indicate that FedMultiEmo offers a practical approach to real-time, privacy-aware emotion recognition in automotive settings.
  BibTeX
  @inproceedings{Gl2025, abstract = {In-vehicle emotion recognition underpins adaptive driver-assistance systems and, ultimately, occupant safety. However, practical deployment is hindered by (i) modality fragility—poor lighting and occlusions degrade vision-based methods; (ii) physiological variability-heart-rate and skin-conductance patterns differ across individuals; and (iii) privacy risk—centralized training requires transmission of sensitive data. To address these challenges, we present FedMultiEmo, a privacy-preserving framework that fuses two complementary modalities at the decision level: visual features extracted by a Convolutional Neural Network from facial images, and physiological cues (heart rate, electrodermal activity, and skin temperature) classified by a Random Forest. FedMultiEmo builds on three key elements: (1) a multimodal federated learning pipeline with majority-vote fusion, (2) an end-to-end edge-to-cloud prototype on Raspberry Pi clients and a Flower server, and (3) a personalized Federated Averaging scheme that weights client updates by local data volume. Evaluated on FER2013 and a custom physiological dataset, the federated Convolutional Neural Network attains 77% accuracy, the Random Forest 74%, and their fusion 87%, matching a centralized baseline while keeping all raw data local. The developed system converges in 18 rounds, with an average round time of 120 s and a per-client memory footprint below 200 MB. These results indicate that FedMultiEmo offers a practical approach to real-time, privacy-aware emotion recognition in automotive settings.}, author = {Gül, Baran Can and Nadig, Suraksha and Tziampazis, Stefanos and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 5th International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)}, doi = {10.1109/iceccme64568.2025.11277502}, month = {10}, pages = {1--8}, publisher = {IEEE}, title = {FedMultiEmo: Real-Time Emotion Recognition via Multimodal Federated Learning}, year = 2025 }
14. G. Hildebrandt, R. Drath, and M. Weyrich, “Flexible Data Integration Pipelines in Digital Twins using LLMs,” IFAC-PapersOnLine, vol. 59, pp. 161–166, 2025.
  - Abstract
  - BibTeX
  Abstract
  Ongoing digitalization, accelerated by concepts such as Industry 4.0 and the Internet of Things, is leading to increasingly interconnected production systems. A key enabler of this development is the Digital Twin, serving as a digital representation of an asset, using real-time data to support forecasting, monitoring, and optimization tasks. As connectivity increases, so does the diversity of available data sources for Digital Twins. Integrating this data requires transformation pipelines that convert raw data into formats suitable for Digital Twin models. While various tools exist for manually constructing such pipe- lines, limited research has been conducted on their automated discovery and generation. As a result, indus- trial connectivity is often hindered by the high engineering effort required for manual integration, making such efforts economically impractical. In this paper, we propose an approach that encapsulates data trans- formations into modular, reusable transformation units, which can be flexibly combined to form integration pipelines. This concept is further enhanced by leveraging Large Language Models (LLMs) to automatically generate appropriate transformation routes based on available data sources, algorithms, and model require- ments. A prototypical implementation within a robot-based gluing scenario demonstrates the feasibility. The presented system enables Digital Twins to evaluate and integrate external data sources dynamically, supporting a more scalable and efficient realization of interconnected production systems.
  BibTeX
  @article{Hildebrandt2025, abstract = {Ongoing digitalization, accelerated by concepts such as Industry 4.0 and the Internet of Things, is leading to increasingly interconnected production systems. A key enabler of this development is the Digital Twin, serving as a digital representation of an asset, using real-time data to support forecasting, monitoring, and optimization tasks. As connectivity increases, so does the diversity of available data sources for Digital Twins. Integrating this data requires transformation pipelines that convert raw data into formats suitable for Digital Twin models. While various tools exist for manually constructing such pipe- lines, limited research has been conducted on their automated discovery and generation. As a result, indus- trial connectivity is often hindered by the high engineering effort required for manual integration, making such efforts economically impractical. In this paper, we propose an approach that encapsulates data trans- formations into modular, reusable transformation units, which can be flexibly combined to form integration pipelines. This concept is further enhanced by leveraging Large Language Models (LLMs) to automatically generate appropriate transformation routes based on available data sources, algorithms, and model require- ments. A prototypical implementation within a robot-based gluing scenario demonstrates the feasibility. The presented system enables Digital Twins to evaluate and integrate external data sources dynamically, supporting a more scalable and efficient realization of interconnected production systems.}, author = {Hildebrandt, Gary and Drath, Rainer and Weyrich, Michael}, doi = {10.1016/j.ifacol.2025.11.942}, issn = {2405-8963}, journal = {IFAC-PapersOnLine}, number = 25, pages = {161--166}, publisher = {Elsevier BV}, title = {Flexible Data Integration Pipelines in Digital Twins using LLMs}, volume = 59, year = 2025 }
15. B. C. Gül, K. I. Ajay Menon, N. Jazdi, and M. Weyrich, “Integration of Asset Administration Shells and Federated Learning into Software-defined Mobile Assets,” IFAC-PapersOnLine, vol. 59, pp. 167–172, 2025.
  - BibTeX
  - Link
  BibTeX
  @article{G_l_2025, author = {Gül, Baran Can and Ajay Menon, Kannanthodath Induchoodan and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.ifacol.2025.11.859}, issn = {2405-8963}, journal = {IFAC-PapersOnLine}, number = 24, pages = {167–172}, publisher = {Elsevier BV}, title = {Integration of Asset Administration Shells and Federated Learning into Software-defined Mobile Assets}, url = {http://dx.doi.org/10.1016/j.ifacol.2025.11.859}, volume = 59, year = 2025 }
  Link
  http://dx.doi.org/10.1016/j.ifacol.2025.11.859
16. J. Stümpfle, D. Atray, N. Jazdi, and M. Weyrich, “Large Language Model assisted Transformation of Software Variants into a Software Product Line,” in 2025 IEEE/ACM 22nd International Conference on Software and Systems Reuse (ICSR), 2025, pp. 12–20.
  - Abstract
  - BibTeX
  Abstract
  Software systems often evolve into multiple variants to meet diverse requirements. This is usually achieved with the clone-and-own approach, where an existing variant is copied and modified. While efficient in the short term, this approach presents challenges for long-term maintenance. A suitable solution to overcome this, is to re-engineer the variants into a software product line (SPL). However, this process is labor-intensive and prone to errors. Although initial studies explore the use of large language models (LLMs) to assist in the re-engineering tasks, they do not address challenges such as hallucination and limited context windows, which restricts the applicability.In this paper, we present a novel approach to assist the transformation of cloned software variants into an SPL using an LLM. To mitigate hallucination, we propose a self-refinement feedback loop to validate the generated SPL. Additionally, we introduce a variation point filtering technique that reduces the input size, while preserving essential information. To quantify and evaluate the generated output, we propose the use of existing metrics that can be employed for the evaluation. Our evaluation demonstrates the effectiveness of the self-refinement feedback loop and variation point filtering based on an existing case study. The results, benchmarked against the proposed variability metrics, indicate that the generated SPL maintains equivalent complexity and potential for reusability, to the system it is compared against.
  BibTeX
  @inproceedings{Stmpfle2025, abstract = {Software systems often evolve into multiple variants to meet diverse requirements. This is usually achieved with the clone-and-own approach, where an existing variant is copied and modified. While efficient in the short term, this approach presents challenges for long-term maintenance. A suitable solution to overcome this, is to re-engineer the variants into a software product line (SPL). However, this process is labor-intensive and prone to errors. Although initial studies explore the use of large language models (LLMs) to assist in the re-engineering tasks, they do not address challenges such as hallucination and limited context windows, which restricts the applicability.In this paper, we present a novel approach to assist the transformation of cloned software variants into an SPL using an LLM. To mitigate hallucination, we propose a self-refinement feedback loop to validate the generated SPL. Additionally, we introduce a variation point filtering technique that reduces the input size, while preserving essential information. To quantify and evaluate the generated output, we propose the use of existing metrics that can be employed for the evaluation. Our evaluation demonstrates the effectiveness of the self-refinement feedback loop and variation point filtering based on an existing case study. The results, benchmarked against the proposed variability metrics, indicate that the generated SPL maintains equivalent complexity and potential for reusability, to the system it is compared against.}, author = {Stümpfle, Johannes and Atray, Devansh and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE/ACM 22nd International Conference on Software and Systems Reuse (ICSR)}, doi = {10.1109/icsr66718.2025.00008}, month = {04}, pages = {12--20}, publisher = {IEEE}, title = {Large Language Model assisted Transformation of Software Variants into a Software Product Line}, year = 2025 }
17. D. Dittler, P. Frank, G. Hildebrandt, L. Peterson, N. Jazdi, and M. Weyrich, “Model-Based Control for Power-to-X Platforms: Knowledge Integration for Digital Twins,” in 2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA), 2025, pp. 1–4.
  - Abstract
  - BibTeX
  Abstract
  Offshore Power-to-X platforms enable flexible conversion of renewable energy, but place high demands on adaptive process control due to volatile operating conditions. To face this challenge, using Digital Twins in Power-to-X platforms is a promising approach. Comprehensive knowledge integration in Digital Twins requires the combination of heterogeneous models and a structured representation of model information. The proposed approach uses a standardized description of behavior models, semantic technologies and a graph-based model understanding to enable automatic adaption and selection of suitable models. It is implemented using a graph-based knowledge representation with Neo4j, automatic data extraction from Asset Administration Shells and port matching to ensure compatible model configurations.
  BibTeX
  @inproceedings{Dittler2025, abstract = {Offshore Power-to-X platforms enable flexible conversion of renewable energy, but place high demands on adaptive process control due to volatile operating conditions. To face this challenge, using Digital Twins in Power-to-X platforms is a promising approach. Comprehensive knowledge integration in Digital Twins requires the combination of heterogeneous models and a structured representation of model information. The proposed approach uses a standardized description of behavior models, semantic technologies and a graph-based model understanding to enable automatic adaption and selection of suitable models. It is implemented using a graph-based knowledge representation with Neo4j, automatic data extraction from Asset Administration Shells and port matching to ensure compatible model configurations.}, author = {Dittler, Daniel and Frank, Peter and Hildebrandt, Gary and Peterson, Luisa and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}, doi = {10.1109/etfa65518.2025.11205688}, month = {09}, pages = {1--4}, publisher = {IEEE}, title = {Model-Based Control for Power-to-X Platforms: Knowledge Integration for Digital Twins}, year = 2025 }
18. S. Tziampazis, B. Can Gül, N. Jazdi, and M. Weyrich, “OracleFed: Latency-Aware Federated Learning via Dynamic Recovery and Causal Aggregation,” IEEE Access, vol. 13, pp. 188064–188083, 2025.
  - Abstract
  - BibTeX
  Abstract
  As federated learning (FL) continues to expand across wide-area, heterogeneous networks, preserving true training chronology grows complex, particularly in time-sensitive applications where network delays can obscure causal ordering and degrade global-model fidelity. Current aggregation schemes seldom account for temporal dynamics: they either stall on stragglers, discard late updates, or rely on arrival-based heuristics that conflate communication latency with training staleness. In light of this limitation, we introduce OracleFed—Order-Respecting Aggregation with Causality and Latency Equalization, a framework in which training-time lag is decoupled from network-transport delay and elevated as the primary driver of aggregation. Leveraging a hybrid design that integrates dual timestamping with system-wide synchronization, the framework continuously recalibrates the server’s waiting window and re-indexes arrivals by their generation timestamps, thereby preserving causal order. Rather than treating late arrivals as inherently stale, OracleFed discounts only genuine training staleness, allowing high-latency clients to contribute proportionally to their computational freshness. We benchmark the proposed framework against existing synchronous and asynchronous schemes across eight evaluation metrics in a distributed, in-vehicle emotion-recognition setting. Paired $t$ - and Wilcoxon signed-rank analyses of twenty Monte-Carlo replicates verify that OracleFed combines the coordination advantages of both paradigms and achieves higher predictive quality, lower staleness, and fairer client participation than the baselines.
  BibTeX
  @article{Tziampazis2025, abstract = {As federated learning (FL) continues to expand across wide-area, heterogeneous networks, preserving true training chronology grows complex, particularly in time-sensitive applications where network delays can obscure causal ordering and degrade global-model fidelity. Current aggregation schemes seldom account for temporal dynamics: they either stall on stragglers, discard late updates, or rely on arrival-based heuristics that conflate communication latency with training staleness. In light of this limitation, we introduce OracleFed—Order-Respecting Aggregation with Causality and Latency Equalization, a framework in which training-time lag is decoupled from network-transport delay and elevated as the primary driver of aggregation. Leveraging a hybrid design that integrates dual timestamping with system-wide synchronization, the framework continuously recalibrates the server’s waiting window and re-indexes arrivals by their generation timestamps, thereby preserving causal order. Rather than treating late arrivals as inherently stale, OracleFed discounts only genuine training staleness, allowing high-latency clients to contribute proportionally to their computational freshness. We benchmark the proposed framework against existing synchronous and asynchronous schemes across eight evaluation metrics in a distributed, in-vehicle emotion-recognition setting. Paired $t$ - and Wilcoxon signed-rank analyses of twenty Monte-Carlo replicates verify that OracleFed combines the coordination advantages of both paradigms and achieves higher predictive quality, lower staleness, and fairer client participation than the baselines.}, author = {Tziampazis, Stefanos and Can Gül, Baran and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/access.2025.3627490}, issn = {2169-3536}, journal = {IEEE Access}, pages = {188064--188083}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, title = {OracleFed: Latency-Aware Federated Learning via Dynamic Recovery and Causal Aggregation}, volume = 13, year = 2025 }
19. G. Hildebrandt, R. Drath, and M. Weyrich, “Requirements on Data Processing for Simulation Models in connected Industrial Digital Twins,” in 2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA), 2025, pp. 1–4.
  - Abstract
  - BibTeX
  Abstract
  In the automation industry, concepts such as Digital Twins, representing virtual counterparts of physical assets, enhance efficiency, sustainability, and economic viability by enabling e.g., optimizations, advanced monitoring, and predictive maintenance. To achieve this, Digital Twins rely on models (including simulation models), which in turn depend on data describing the current state of the physical asset. As connectivity increases, the available data extends beyond the data of the sensors of the asset itself. It extends to data from the surrounding environment and even beyond. This introduces new challenges for Digital Twins and their models in terms of data integration. In previous research it was shown that current implementations are not adequately prepared for this scenario. Currently, no analysis in the literature addresses how interaction within a connected environment alters the requirements for Digital Twins. Therefore, this paper explicitly identifies the emerging challenges associated with extending the information acquisition scope of Digital Twins beyond the immediate physical asset. This is accomplished through a systematic analysis of potential scenarios that consider the inclusion of external data. Our analysis reveals several new requirements, such as the need for an extended description of the model’s purpose and the specific requirements for the data input. Digital Twins must possess enhanced capabilities to identify appropriate data sources within a dynamic production environment, as well as methods to manage multiple, potentially redundant data streams effectively. Through this analysis, we aim to highlight potential research directions for Digital Twins in the automation industry and advocate for the integration of interconnectivity into Digital Twin systems.
  BibTeX
  @inproceedings{Hildebrandt2025, abstract = {In the automation industry, concepts such as Digital Twins, representing virtual counterparts of physical assets, enhance efficiency, sustainability, and economic viability by enabling e.g., optimizations, advanced monitoring, and predictive maintenance. To achieve this, Digital Twins rely on models (including simulation models), which in turn depend on data describing the current state of the physical asset. As connectivity increases, the available data extends beyond the data of the sensors of the asset itself. It extends to data from the surrounding environment and even beyond. This introduces new challenges for Digital Twins and their models in terms of data integration. In previous research it was shown that current implementations are not adequately prepared for this scenario. Currently, no analysis in the literature addresses how interaction within a connected environment alters the requirements for Digital Twins. Therefore, this paper explicitly identifies the emerging challenges associated with extending the information acquisition scope of Digital Twins beyond the immediate physical asset. This is accomplished through a systematic analysis of potential scenarios that consider the inclusion of external data. Our analysis reveals several new requirements, such as the need for an extended description of the model’s purpose and the specific requirements for the data input. Digital Twins must possess enhanced capabilities to identify appropriate data sources within a dynamic production environment, as well as methods to manage multiple, potentially redundant data streams effectively. Through this analysis, we aim to highlight potential research directions for Digital Twins in the automation industry and advocate for the integration of interconnectivity into Digital Twin systems.}, author = {Hildebrandt, Gary and Drath, Rainer and Weyrich, Michael}, booktitle = {2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}, doi = {10.1109/etfa65518.2025.11205596}, month = {09}, pages = {1--4}, publisher = {IEEE}, title = {Requirements on Data Processing for Simulation Models in connected Industrial Digital Twins}, year = 2025 }
20. M. Weiß, F. Dettinger, and M. Weyrich, “SDVDiag: A Modular Platform for the Diagnosis of Connected Vehicle Functions,” in 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025, pp. 1–7.
  - Abstract
  - BibTeX
  Abstract
  Connected and software-defined vehicles promise to offer a broad range of services and advanced functions to customers, aiming to increase passenger comfort and support autonomous driving capabilities. Due to the high reliability and availability requirements of connected vehicles, it is crucial to resolve any occurring failures quickly. To achieve this however, a complex cloud/edge architecture with a mesh of dependencies must be navigated to diagnose the responsible root cause. As such, manual analyses become unfeasible since they would significantly delay the troubleshooting. To address this challenge, this paper presents SDVDiag, an extensible platform for the automated diagnosis of connected vehicle functions. The platform enables the creation of pipelines that cover all steps from initial data collection to the tracing of potential root causes. In addition, SDVDiag supports selfadaptive behavior by the ability to exchange modules at runtime. Dependencies between functions are detected and continuously updated, resulting in a dynamic graph view of the system. In addition, vital system metrics are monitored for anomalies. Whenever an incident is investigated, a snapshot of the graph is taken and augmented by relevant anomalies. Finally, the analysis is performed by traversing the graph and creating a ranking of the most likely causes. To evaluate the platform, it is deployed inside an 5G test fleet environment for connected vehicle functions. The results show that injected faults can be detected reliably. As such, the platform offers the potential to gain new insights and reduce downtime by identifying problems and their causes at an early stage.
  BibTeX
  @inproceedings{Wei2025, abstract = {Connected and software-defined vehicles promise to offer a broad range of services and advanced functions to customers, aiming to increase passenger comfort and support autonomous driving capabilities. Due to the high reliability and availability requirements of connected vehicles, it is crucial to resolve any occurring failures quickly. To achieve this however, a complex cloud/edge architecture with a mesh of dependencies must be navigated to diagnose the responsible root cause. As such, manual analyses become unfeasible since they would significantly delay the troubleshooting. To address this challenge, this paper presents SDVDiag, an extensible platform for the automated diagnosis of connected vehicle functions. The platform enables the creation of pipelines that cover all steps from initial data collection to the tracing of potential root causes. In addition, SDVDiag supports selfadaptive behavior by the ability to exchange modules at runtime. Dependencies between functions are detected and continuously updated, resulting in a dynamic graph view of the system. In addition, vital system metrics are monitored for anomalies. Whenever an incident is investigated, a snapshot of the graph is taken and augmented by relevant anomalies. Finally, the analysis is performed by traversing the graph and creating a ranking of the most likely causes. To evaluate the platform, it is deployed inside an 5G test fleet environment for connected vehicle functions. The results show that injected faults can be detected reliably. As such, the platform offers the potential to gain new insights and reduce downtime by identifying problems and their causes at an early stage.}, author = {Weiß, Matthias and Dettinger, Falk and Weyrich, Michael}, booktitle = {2025 IEEE International Automated Vehicle Validation Conference (IAVVC)}, doi = {10.1109/iavvc61942.2025.11219581}, month = {09}, pages = {1--7}, publisher = {IEEE}, title = {SDVDiag: A Modular Platform for the Diagnosis of Connected Vehicle Functions}, year = 2025 }
21. C. Hackenbeck, A. Walz, P. Hirmer, S. Wagner, and M. Weyrich, “Semantic Interface Modeling for Automotive Architectures Using a Domain-Driven Approach,” IFAC-PapersOnLine, vol. 59, pp. 125–130, 2025.
  - Abstract
  - BibTeX
  Abstract
  This paper presents a domain-driven design-inspired methodology for modeling semantically meaningful interfaces in automotive architectures, focusing on software-defined vehicles as cyber-physical systems. Using a safety-critical life presence detection use case, the approach systematically identifies bounded contexts, separates domain, application, and infrastructure layers, and derives semantic interface characterizations across abstraction levels. The characterization model enables reasoning about timing, criticality, and platform binding, supporting modularity and cross-domain traceability. The methodology complements standards such as AUTOSAR and SysML by offering a lightweight conceptual framework for early-phase system integration, architectural evolution, and scalable design.
  BibTeX
  @article{Hackenbeck2025, abstract = {This paper presents a domain-driven design-inspired methodology for modeling semantically meaningful interfaces in automotive architectures, focusing on software-defined vehicles as cyber-physical systems. Using a safety-critical life presence detection use case, the approach systematically identifies bounded contexts, separates domain, application, and infrastructure layers, and derives semantic interface characterizations across abstraction levels. The characterization model enables reasoning about timing, criticality, and platform binding, supporting modularity and cross-domain traceability. The methodology complements standards such as AUTOSAR and SysML by offering a lightweight conceptual framework for early-phase system integration, architectural evolution, and scalable design.}, author = {Hackenbeck, Christian and Walz, Alexander and Hirmer, Pascal and Wagner, Stefan and Weyrich, Michael}, doi = {10.1016/j.ifacol.2025.11.936}, issn = {2405-8963}, journal = {IFAC-PapersOnLine}, number = 25, pages = {125--130}, publisher = {Elsevier BV}, title = {Semantic Interface Modeling for Automotive Architectures Using a Domain-Driven Approach}, volume = 59, year = 2025 }
22. F. Dettinger, A. Narla, and M. Weyrich, “Situation Awareness for Intelligent Data Distribution in Connected Vehicles,” in 2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring), 2025, pp. 1–5.
  - Abstract
  - BibTeX
  Abstract
  The limitations of on-board sensors and blind spots caused by occlusion cause the reduction of perception quality in autonomous vehicles. In such cases, cooperative perception provides additional data via Vehicle-to-Everything communication to enhance local perception, causing a large volume of data transmission. The vehicle can focus on acquiring and utilizing relevant data according to the prevailing road context by identifying the current traffic situation. To achieve this, we propose a concept for the situation identification of the vehicle using Bird's-Eye-View images. Firstly, the situation around the vehicle is identified using object detection with semantic segmentation, followed by understanding the context of the traffic using a situation identification module consisting of an open-source projective transformation network Cam2BEV and a situation identification neural network. The concept was evaluated and validated by running the software on the CARLA simulator using the in-built RGB camera and the semantic segmentation camera. Additionally, the portability of the situation identification module for real-world applications was verified on Cityscapes and nuScenes urban driving datasets. Overall, the proposed situation identification approach enables efficient sensor data management by prioritizing relevant data to the current traffic situation. The source code is available in the following link: https://github.com/akshaynarla/DySi_Select
  BibTeX
  @inproceedings{Dettinger2025, abstract = {The limitations of on-board sensors and blind spots caused by occlusion cause the reduction of perception quality in autonomous vehicles. In such cases, cooperative perception provides additional data via Vehicle-to-Everything communication to enhance local perception, causing a large volume of data transmission. The vehicle can focus on acquiring and utilizing relevant data according to the prevailing road context by identifying the current traffic situation. To achieve this, we propose a concept for the situation identification of the vehicle using Bird's-Eye-View images. Firstly, the situation around the vehicle is identified using object detection with semantic segmentation, followed by understanding the context of the traffic using a situation identification module consisting of an open-source projective transformation network Cam2BEV and a situation identification neural network. The concept was evaluated and validated by running the software on the CARLA simulator using the in-built RGB camera and the semantic segmentation camera. Additionally, the portability of the situation identification module for real-world applications was verified on Cityscapes and nuScenes urban driving datasets. Overall, the proposed situation identification approach enables efficient sensor data management by prioritizing relevant data to the current traffic situation. The source code is available in the following link: https://github.com/akshaynarla/DySi_Select}, author = {Dettinger, Falk and Narla, Akshay and Weyrich, Michael}, booktitle = {2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring)}, doi = {10.1109/vtc2025-spring65109.2025.11174528}, month = {06}, pages = {1--5}, publisher = {IEEE}, title = {Situation Awareness for Intelligent Data Distribution in Connected Vehicles}, year = 2025 }
23. L. Hettich, J. Stümpfle, N. Jazdi, and M. Weyrich, “Speed Things Up: Leveraging GPU Processing Capabilities for Faster Sampling of Software Product Lines,” in SPLC-A ’25: 29th ACM International Systems and Software Product Line Conference - Volume A, 2025, pp. 172–183.
  - Abstract
  - BibTeX
  Abstract
  Software plays an increasingly important role in modern technical systems. For the broad applicability and to appeal to a wide range of customers, software often provides an enormous degree of configurability. In addition, software is under continuous development, further increasing complexity and introducing additional configuration options. Software testers face significant challenges in this context. While product-wise testing of all possible software variants is no longer feasible, alternative testing approaches that are both efficient and effective in detecting potential software faults are required. Here, t-wise interaction sampling is established as a systematic testing approach to ensure coverage of the configuration space. However, current sampling approaches suffer from severe scalability issues, often requiring hours or even days of computation when applied to large-scale Software Product Lines (SPLs). In this paper, we present a novel technique for pairwise sampling and are the first to address the enormous computational effort required to sample large-scale SPLs with the parallel computing capabilities offered by consumer graphics processing units (GPUs). We build upon techniques used in existing sampling approaches, such as SAT solvers and local search strategies, extending these traditionally sequential techniques for parallel execution. Furthermore, we present a novel, highly efficient sample optimization strategy based on Quadratic Integer Programming (QIP) as an advancement. We evaluate our sampling approach SAMParallel on a diverse set of 20 medium- and large-scale configurable software systems from the existing literature. We show that SAMParallel can generate competitive pairwise covering samples with reliably smaller sizes compared to current sampling approaches, while considerably reducing the time investment previously required. Beyond the practical implications of our contribution regarding faster sampling, the presented technique offers various hyper-parameters to further balance sampling times and sample sizes. As a result, software testers can adapt the sampling process to their specific needs.
  BibTeX
  @inproceedings{Hettich2025, abstract = {Software plays an increasingly important role in modern technical systems. For the broad applicability and to appeal to a wide range of customers, software often provides an enormous degree of configurability. In addition, software is under continuous development, further increasing complexity and introducing additional configuration options. Software testers face significant challenges in this context. While product-wise testing of all possible software variants is no longer feasible, alternative testing approaches that are both efficient and effective in detecting potential software faults are required. Here, t-wise interaction sampling is established as a systematic testing approach to ensure coverage of the configuration space. However, current sampling approaches suffer from severe scalability issues, often requiring hours or even days of computation when applied to large-scale Software Product Lines (SPLs). In this paper, we present a novel technique for pairwise sampling and are the first to address the enormous computational effort required to sample large-scale SPLs with the parallel computing capabilities offered by consumer graphics processing units (GPUs). We build upon techniques used in existing sampling approaches, such as SAT solvers and local search strategies, extending these traditionally sequential techniques for parallel execution. Furthermore, we present a novel, highly efficient sample optimization strategy based on Quadratic Integer Programming (QIP) as an advancement. We evaluate our sampling approach SAMParallel on a diverse set of 20 medium- and large-scale configurable software systems from the existing literature. We show that SAMParallel can generate competitive pairwise covering samples with reliably smaller sizes compared to current sampling approaches, while considerably reducing the time investment previously required. Beyond the practical implications of our contribution regarding faster sampling, the presented technique offers various hyper-parameters to further balance sampling times and sample sizes. As a result, software testers can adapt the sampling process to their specific needs.}, author = {Hettich, Lennard and Stümpfle, Johannes and Jazdi, Nasser and Weyrich, Michael}, booktitle = {SPLC-A '25: 29th ACM International Systems and Software Product Line Conference - Volume A}, doi = {10.1145/3744915.3748475}, month = {08}, pages = {172--183}, publisher = {ACM}, title = {Speed Things Up: Leveraging GPU Processing Capabilities for Faster Sampling of Software Product Lines}, year = 2025 }
24. B. C. Gül, S. Tziampazis, N. Jazdi, and M. Weyrich, “SyncFed: Time-Aware Federated Learning through Explicit Timestamping and Synchronization,” in 2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA), 2025, pp. 1–8.
  - Abstract
  - BibTeX
  Abstract
  As Federated Learning (FL) expands to larger and more distributed environments, consistency in training is challenged by network-induced delays, clock unsynchronicity, and variability in client updates. This combination of factors may contribute to misaligned contributions that undermine model reliability and convergence. Existing methods like staleness-aware aggregation and model versioning address lagging updates heuristically, yet lack mechanisms to quantify staleness, especially in latency-sensitive and cross-regional deployments. In light of these considerations, we introduce SyncFed, a time-aware FL framework that employs explicit synchronization and times-tamping to establish a common temporal reference across the system. Staleness is quantified numerically based on exchanged timestamps under the Network Time Protocol (NTP), enabling the server to reason about the relative freshness of client updates and apply temporally informed weighting during aggregation. Our empirical evaluation on a geographically distributed testbed shows that, under SyncFed, the global model evolves within a stable temporal context, resulting in improved accuracy and information freshness compared to round-based baselines devoid of temporal semantics.
  BibTeX
  @inproceedings{Gl2025, abstract = {As Federated Learning (FL) expands to larger and more distributed environments, consistency in training is challenged by network-induced delays, clock unsynchronicity, and variability in client updates. This combination of factors may contribute to misaligned contributions that undermine model reliability and convergence. Existing methods like staleness-aware aggregation and model versioning address lagging updates heuristically, yet lack mechanisms to quantify staleness, especially in latency-sensitive and cross-regional deployments. In light of these considerations, we introduce SyncFed, a time-aware FL framework that employs explicit synchronization and times-tamping to establish a common temporal reference across the system. Staleness is quantified numerically based on exchanged timestamps under the Network Time Protocol (NTP), enabling the server to reason about the relative freshness of client updates and apply temporally informed weighting during aggregation. Our empirical evaluation on a geographically distributed testbed shows that, under SyncFed, the global model evolves within a stable temporal context, resulting in improved accuracy and information freshness compared to round-based baselines devoid of temporal semantics.}, author = {Gül, Baran Can and Tziampazis, Stefanos and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}, doi = {10.1109/etfa65518.2025.11205776}, month = {09}, pages = {1--8}, publisher = {IEEE}, title = {SyncFed: Time-Aware Federated Learning through Explicit Timestamping and Synchronization}, year = 2025 }
25. J. Stümpfle, J. Sigel, M. Weiß, B. C. Gül, F. Dettinger, N. Jazdi, M. Hoßfeld, and M. Weyrich, “The Software-Defined Vehicle: A Comprehensive Study on Current Trends and Challenges,” IEEE Engineering Management Review, pp. 1–15, 2025.
  - Abstract
  - BibTeX
  Abstract
  The automotive industry is undergoing an exten- sive transition from hardware-centric development to software- defined vehicles (SDVs). This paradigm shift requires innovative technical solutions and fundamentally different approaches for vehicle design. Together, these developments introduce substantial challenges for an entire industry, affecting both development processes and operations. Although SDVs have attracted con- siderable attention and widespread industry involvement, prior research has primarily emphasized systematic literature reviews identifying emerging academic trends. Consequently, little at- tention has been paid to industry and economic developments that influence how SDV technologies evolve in practice and are crucial for future advancement. In response, this paper provides a different, industry-oriented view of the current trends and associated challenges of SDVs. To achieve this, we conducted a comprehensive analysis of the SDV from an industry-based perspective. We analyzed three sources of information to identify the current trends in SDV development: expert interviews with automotive IT specialists, a study on major automotive trade fairs and workshops, and insights gained from the authors’ professional experience. Based upon, we derive specific challenges arising from these trends. Our findings offer a comprehensive
  BibTeX
  @article{Stmpfle2025, abstract = {The automotive industry is undergoing an exten- sive transition from hardware-centric development to software- defined vehicles (SDVs). This paradigm shift requires innovative technical solutions and fundamentally different approaches for vehicle design. Together, these developments introduce substantial challenges for an entire industry, affecting both development processes and operations. Although SDVs have attracted con- siderable attention and widespread industry involvement, prior research has primarily emphasized systematic literature reviews identifying emerging academic trends. Consequently, little at- tention has been paid to industry and economic developments that influence how SDV technologies evolve in practice and are crucial for future advancement. In response, this paper provides a different, industry-oriented view of the current trends and associated challenges of SDVs. To achieve this, we conducted a comprehensive analysis of the SDV from an industry-based perspective. We analyzed three sources of information to identify the current trends in SDV development: expert interviews with automotive IT specialists, a study on major automotive trade fairs and workshops, and insights gained from the authors’ professional experience. Based upon, we derive specific challenges arising from these trends. Our findings offer a comprehensive}, author = {Stümpfle, Johannes and Sigel, Johannes and Weiß, Matthias and Gül, Baran Can and Dettinger, Falk and Jazdi, Nasser and Hoßfeld, Max and Weyrich, Michael}, doi = {10.1109/emr.2025.3636574}, issn = {0360-8581}, journal = {IEEE Engineering Management Review}, pages = {1--15}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, title = {The Software-Defined Vehicle: A Comprehensive Study on Current Trends and Challenges}, year = 2025 }
26. C. Hackenbeck, P. Hirmer, A. Walz, S. Wagner, and M. Weyrich, “Towards Standardized Interfaces for Software-Defined Vehicles in Automotive,” in 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), 2025, pp. 1–7.
  - Abstract
  - BibTeX
  Abstract
  The emergence of software-defined vehicles (SDVs) presents a significant challenge for the role of software in managing complex automotive systems, complicating maintenance and upgrades. The software interfaces between components and systems are key throughout the vehicle which enable communication and allow for data flows in SDVs. As of now, the interfaces in the vehicle are stiff and mostly based on the AUTOSAR standard. Service-oriented architecture (SOA), proven in enterprise and consumer computer systems, is now adopted in automotive to address this complexity. This literature review assesses the current state of SOA in the automotive industry, highlighting solutions to solve the interface challenges. The static interface definitions in AUTOSAR limit adaptability, while nonstandardized approaches offer greater flexibility. We identify a gap in how service interfaces interact with internal architecture and external non-SOA components, hindering seamless software-hardware integration. Realizing SOA's potential requires standardized interface patterns and hardware abstraction layers to integrate services and components better.
  BibTeX
  @inproceedings{Hackenbeck2025, abstract = {The emergence of software-defined vehicles (SDVs) presents a significant challenge for the role of software in managing complex automotive systems, complicating maintenance and upgrades. The software interfaces between components and systems are key throughout the vehicle which enable communication and allow for data flows in SDVs. As of now, the interfaces in the vehicle are stiff and mostly based on the AUTOSAR standard. Service-oriented architecture (SOA), proven in enterprise and consumer computer systems, is now adopted in automotive to address this complexity. This literature review assesses the current state of SOA in the automotive industry, highlighting solutions to solve the interface challenges. The static interface definitions in AUTOSAR limit adaptability, while nonstandardized approaches offer greater flexibility. We identify a gap in how service interfaces interact with internal architecture and external non-SOA components, hindering seamless software-hardware integration. Realizing SOA's potential requires standardized interface patterns and hardware abstraction layers to integrate services and components better.}, author = {Hackenbeck, Christian and Hirmer, Pascal and Walz, Alexander and Wagner, Stefan and Weyrich, Michael}, booktitle = {2025 IEEE International Automated Vehicle Validation Conference (IAVVC)}, doi = {10.1109/iavvc61942.2025.11219518}, month = {09}, pages = {1--7}, publisher = {IEEE}, title = {Towards Standardized Interfaces for Software-Defined Vehicles in Automotive}, year = 2025 }
27. T. Schey, K. Karoonlatifi, M. Weyrich, and A. Morozov, “Uncertainty-Guided Live Measurement Sequencing for Fast SAR ADC Linearity Testing,” in 2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD), 2025, pp. 1–9.
  - Abstract
  - BibTeX
  Abstract
  This paper introduces a novel closed-loop testing methodology for efficient linearity testing of high-resolution Successive Approximation Register (SAR) Analog-to-Digital Converters (ADCs). Existing test strategies, including histogram-based approaches, sine wave testing, and model-driven reconstruction, often rely on dense data acquisition followed by offline post-processing, which increases overall test time and complexity. To overcome these limitations, we propose an adaptive approach that utilizes an iterative behavioral model refined by an Extended Kalman Filter (EKF) in real time, enabling direct estimation of capacitor mismatch parameters that determine INL behavior. Our algorithm dynamically selects measurement points based on current model uncertainty, maximizing information gain with respect to parameter confidence and narrowing sampling intervals as estimation progresses. By providing immediate feedback and adaptive targeting, the proposed method eliminates the need for large-scale data collection and post-measurement analysis. Experimental results demonstrate substantial reductions in total test time and computational overhead, highlighting the method’s suitability for integration in production environments.
  BibTeX
  @inproceedings{Schey2025, abstract = {This paper introduces a novel closed-loop testing methodology for efficient linearity testing of high-resolution Successive Approximation Register (SAR) Analog-to-Digital Converters (ADCs). Existing test strategies, including histogram-based approaches, sine wave testing, and model-driven reconstruction, often rely on dense data acquisition followed by offline post-processing, which increases overall test time and complexity. To overcome these limitations, we propose an adaptive approach that utilizes an iterative behavioral model refined by an Extended Kalman Filter (EKF) in real time, enabling direct estimation of capacitor mismatch parameters that determine INL behavior. Our algorithm dynamically selects measurement points based on current model uncertainty, maximizing information gain with respect to parameter confidence and narrowing sampling intervals as estimation progresses. By providing immediate feedback and adaptive targeting, the proposed method eliminates the need for large-scale data collection and post-measurement analysis. Experimental results demonstrate substantial reductions in total test time and computational overhead, highlighting the method’s suitability for integration in production environments.}, author = {Schey, Thorben and Karoonlatifi, Khaled and Weyrich, Michael and Morozov, Andrey}, booktitle = {2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)}, doi = {10.1109/iccad66269.2025.11240665}, month = {10}, pages = {1--9}, publisher = {IEEE}, title = {Uncertainty-Guided Live Measurement Sequencing for Fast SAR ADC Linearity Testing}, year = 2025 }
28. J. Ruhnau, M. Sommer, F. Dettinger, D. Kraus, S. Becker, E. Sax, and M. Weyrich, “Vehicle Function Offloading: Finding the Optimal Cloud/Edge Application Model (OptiCAM),” in Lecture Notes in Networks and Systems, Springer Nature Switzerland, 2025, pp. 556–571.
  - Abstract
  - BibTeX
  Abstract
  Connecting the vehicle with cloud or edge systems enables new features for the customer. Additionally, existing vehicle functions or software components (SWCs) can also be oﬄoaded to this network ecosystem. For example, it is envisaged that due to cost-intensive vehicle hardware, individual functions will not continue to run in the vehicle but will be executed in the cloud or edge. This means that the functions and their SWCs no longer remain statically deployed and executed on onboard hardware like an electronic control unit (ECU) but can be rede- ployed during the vehicle’s life cycle. To make this possible, application models that take into account the individual requirements of automotive functions are needed. This paper proposes ﬁve diﬀerent application mod- els in addition to the standard in-vehicle application. The various fea- tures of the application models are predestined for the multiple-criteria decision-making (MCDM) approach. We propose OptiCAM, a MCDM model that helps software developers or electrical/electronic (E/E) archi- tects ﬁnding the best application model for SWCs based on technical and economical criteria. State-of-the-art vehicle functions are ﬁnally used to test OptiCAM and analyze the results.
  BibTeX
  @incollection{Ruhnau2025, abstract = {Connecting the vehicle with cloud or edge systems enables new features for the customer. Additionally, existing vehicle functions or software components (SWCs) can also be oﬄoaded to this network ecosystem. For example, it is envisaged that due to cost-intensive vehicle hardware, individual functions will not continue to run in the vehicle but will be executed in the cloud or edge. This means that the functions and their SWCs no longer remain statically deployed and executed on onboard hardware like an electronic control unit (ECU) but can be rede- ployed during the vehicle’s life cycle. To make this possible, application models that take into account the individual requirements of automotive functions are needed. This paper proposes ﬁve diﬀerent application mod- els in addition to the standard in-vehicle application. The various fea- tures of the application models are predestined for the multiple-criteria decision-making (MCDM) approach. We propose OptiCAM, a MCDM model that helps software developers or electrical/electronic (E/E) archi- tects ﬁnding the best application model for SWCs based on technical and economical criteria. State-of-the-art vehicle functions are ﬁnally used to test OptiCAM and analyze the results.}, author = {Ruhnau, Jan and Sommer, Martin and Dettinger, Falk and Kraus, David and Becker, Steffen and Sax, Eric and Weyrich, Michael}, booktitle = {Lecture Notes in Networks and Systems}, doi = {10.1007/978-3-031-84457-7_34}, isbn = {9783031844560}, issn = {2367-3370}, pages = {556--571}, publisher = {Springer Nature Switzerland}, title = {Vehicle Function Offloading: Finding the Optimal Cloud/Edge Application Model (OptiCAM)}, year = 2025 }
2024
1. J. Stümpfle, S. Baum, D. Dittler, N. Jazdi, and M. Weyrich, 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA) Automating Software Product Line Adoption Based on Feature Models Using Large Language Models. 2024, pp. 1–4.
  - Abstract
  - BibTeX
  Abstract
  Software-intensive systems emerge in a multitude of variations to meet diverse customer requirements. To develop such variant-rich software systems, software product line (SPL) Engineering has emerged as a key strategy for managing the variability. However, the adoption of SPLs is highly complex due to the diversity of feature model formats and specifications, and the complexity of implementing variability. Leveraging the capabilities of powerful large language models (LLMs) can facilitate the adoption of SPLs. Nonetheless, these LLMs often lack knowledge of the various specifications of potential feature models as well as efficient implementation of different variability mechanisms. To address these challenges, we propose a novel method based on retrieval-augmented generation. This method generates reusable artefacts and a corresponding feature mapping based on a given feature model, thereby aiding system engineers in adopting an SPL.
  BibTeX
  @book{inproceedings, abstract = {Software-intensive systems emerge in a multitude of variations to meet diverse customer requirements. To develop such variant-rich software systems, software product line (SPL) Engineering has emerged as a key strategy for managing the variability. However, the adoption of SPLs is highly complex due to the diversity of feature model formats and specifications, and the complexity of implementing variability. Leveraging the capabilities of powerful large language models (LLMs) can facilitate the adoption of SPLs. Nonetheless, these LLMs often lack knowledge of the various specifications of potential feature models as well as efficient implementation of different variability mechanisms. To address these challenges, we propose a novel method based on retrieval-augmented generation. This method generates reusable artefacts and a corresponding feature mapping based on a given feature model, thereby aiding system engineers in adopting an SPL.}, author = {Stümpfle, Johannes and Baum, Sebastian and Dittler, Daniel and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ETFA61755.2024.10710832}, month = {09}, pages = {1-4}, title = {2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA) Automating Software Product Line Adoption Based on Feature Models Using Large Language Models }, year = 2024 }
2. A. Shoshi, Y. Xia, A. Fieschi, T. Ackermann, P. Reimann, M. Weyrich, B. Mitschang, T. Bauernhansl, and R. Miehe, “A Flexible Digital Twin Framework for ATMP Production – Towards an efficient CAR T Cell Manufacturing,” Procedia CIRP, vol. 125, pp. 124–129, Jan. 2024.
  - BibTeX
  BibTeX
  @article{Shoshi2024, author = {Shoshi, Arber and Xia, Yuchen and Fieschi, Andrea and Ackermann, Thomas and Reimann, Peter and Weyrich, Michael and Mitschang, Bernhard and Bauernhansl, Thomas and Miehe, Robert}, doi = {10.1016/J.PROCIR.2024.08.022}, issn = {2212-8271}, journal = {Procedia CIRP}, month = {01}, pages = {124-129}, publisher = {Elsevier}, title = {A Flexible Digital Twin Framework for ATMP Production – Towards an efficient CAR T Cell Manufacturing}, volume = 125, year = 2024 }
3. P. Häbig, D. Dittler, M. Fey, T. Müller, N. Mößner, N. Jazdi, M. Weyrich, and K. Hufendiek, “A Modular System Architecture for an Offshore Off-grid Platform for Climate-neutral Power-to-X Production in H2Mare,” Procedia CIRP, vol. 126, pp. 909–914, 2024.
  Abstract
  Power-to-X (PtX) products constitute a promising solution component in the defossilisation of hard-to-abate sectors. Where direct electrification is not possible, they can find application as chemical feedstock, easy to transport energy carriers and storage. In this contribution, a modular system architecture for a highly automated operation of an offshore off-grid PtX production platform consisting of five layers (asset, control, communication, digital, application) is presented. The assumed advantage of such an off-grid platform is the good scalability worldwide as well as easy exploitation of renewable potentials in any location. Using the example of a power-to-methanol process, a simplified prototype is outlined.
  BibTeX
  @article{HABIG2024909, abstract = {Power-to-X (PtX) products constitute a promising solution component in the defossilisation of hard-to-abate sectors. Where direct electrification is not possible, they can find application as chemical feedstock, easy to transport energy carriers and storage. In this contribution, a modular system architecture for a highly automated operation of an offshore off-grid PtX production platform consisting of five layers (asset, control, communication, digital, application) is presented. The assumed advantage of such an off-grid platform is the good scalability worldwide as well as easy exploitation of renewable potentials in any location. Using the example of a power-to-methanol process, a simplified prototype is outlined.}, author = {Häbig, Pascal and Dittler, Daniel and Fey, Maximilian and Müller, Timo and Mößner, Nikola and Jazdi, Nasser and Weyrich, Michael and Hufendiek, Kai}, doi = {https://doi.org/10.1016/j.procir.2024.08.348}, issn = {2212-8271}, journal = {Procedia CIRP}, note = {17th CIRP Conference on Intelligent Computation in Manufacturing Engineering (CIRP ICME ‘23)}, pages = {909-914}, title = {A Modular System Architecture for an Offshore Off-grid Platform for Climate-neutral Power-to-X Production in H2Mare}, url = {https://www.sciencedirect.com/science/article/pii/S221282712400920X}, volume = 126, year = 2024 }
  Link
  https://www.sciencedirect.com/science/article/pii/S221282712400920X
4. Y. Xia, N. Jazdi, and M. Weyrich, “Applying Large Language Models for Intelligent Industrial Automation: From Theory to Application: Towards Autonomous Systems with Large Language Models,” atp magazin, vol. 66, pp. 62–71, Jul. 2024.
  Abstract
  Dieser Artikel erforscht das transformative Potenzial großer Sprachmodelle (Large Language Models, LLMs) in der industriellen Automatisierung und stellt umfassende Ansätze für ihre Integration in komplexe Industriesysteme vor. Wir beginnen mit einem theoretischen Überblick über LLMs und erläutern ihre entscheidenden Fähigkeiten wie Interpretation, Aufgabenautomatisierung und autonome Agentenfunktionalität. Eine generische Methodik zur Integration von LLMs in industrielle Anwendungen wird dargelegt, die erläutert, wie LLMs für spezifische Aufgaben angewendet werden können. Vier Fallstudien demonstrieren den praktischen Einsatz von LLMs in verschiedenen industriellen Umgebungen: die Umwandlung unstrukturierter Daten in strukturierte Daten als Verwaltungsschalen-Modell, die Verbesserung des Wissensmanagements mit Dokumentendatenbanken durch ein Chat-system, die autonome Produktionsplanung und -steuerung für Automatisierungssysteme und die Interaktion mit Simulationsmodellen zur Bestimmung der Parametrisierung des Prozesses. Die Studien veranschaulichen die Fähigkeit von LLMs, diverse Aufgaben zu bewältigen und mit digitalen Zwillingen und Automatisierungssystemen zu interagieren, was nahlegt, dass Effizienz- und Produktivitätssteigerungen durch den strategischen Einsatz von LLM-Technologien in industriellen Umgebungen erreicht werden können.
  BibTeX
  @article{Xia2024, abstract = {Dieser Artikel erforscht das transformative Potenzial großer Sprachmodelle (Large Language Models, LLMs) in der industriellen Automatisierung und stellt umfassende Ansätze für ihre Integration in komplexe Industriesysteme vor. Wir beginnen mit einem theoretischen Überblick über LLMs und erläutern ihre entscheidenden Fähigkeiten wie Interpretation, Aufgabenautomatisierung und autonome Agentenfunktionalität. Eine generische Methodik zur Integration von LLMs in industrielle Anwendungen wird dargelegt, die erläutert, wie LLMs für spezifische Aufgaben angewendet werden können. Vier Fallstudien demonstrieren den praktischen Einsatz von LLMs in verschiedenen industriellen Umgebungen: die Umwandlung unstrukturierter Daten in strukturierte Daten als Verwaltungsschalen-Modell, die Verbesserung des Wissensmanagements mit Dokumentendatenbanken durch ein Chat-system, die autonome Produktionsplanung und -steuerung für Automatisierungssysteme und die Interaktion mit Simulationsmodellen zur Bestimmung der Parametrisierung des Prozesses. Die Studien veranschaulichen die Fähigkeit von LLMs, diverse Aufgaben zu bewältigen und mit digitalen Zwillingen und Automatisierungssystemen zu interagieren, was nahlegt, dass Effizienz- und Produktivitätssteigerungen durch den strategischen Einsatz von LLM-Technologien in industriellen Umgebungen erreicht werden können.}, author = {Xia, Yuchen and Jazdi, Nasser and Weyrich, Michael}, doi = {10.17560/ATP.V66I6-7.2739}, issn = {2364-3137}, journal = {atp magazin}, month = {07}, number = {6-7}, pages = {62-71}, publisher = {Vulkan-Verlag GmbH}, title = {Applying Large Language Models for Intelligent Industrial Automation: From Theory to Application: Towards Autonomous Systems with Large Language Models}, url = {https://ojs.di-verlag.de/index.php/atp_edition/article/view/2739}, volume = 66, year = 2024 }
  Link
  https://ojs.di-verlag.de/index.php/atp_edition/article/view/2739
5. D. Baumann, M. Sommer, F. Dettinger, T. Rösch, M. Weyrich, and E. Sax, “Connected vehicle: ontology, taxonomy and use cases,” in 2024 IEEE International Systems Conference (SysCon), 2024, pp. 1–6.
  - BibTeX
  BibTeX
  @inproceedings{baumann2024connected, author = {Baumann, Daniel and Sommer, Martin and Dettinger, Falk and R{\"o}sch, Tobias and Weyrich, Michael and Sax, Eric}, booktitle = {2024 IEEE International Systems Conference (SysCon)}, organization = {IEEE}, pages = {1--6}, title = {Connected vehicle: ontology, taxonomy and use cases}, year = 2024 }
6. Y. Xia, N. Jazdi, J. Zhang, C. Shah, and M. Weyrich, “Control Industrial Automation System with Large Language Models,” Sep. 2024.
  Abstract
  Traditional industrial automation systems require specialized expertise to operate and complex reprogramming to adapt to new processes. Large language models offer the intelligence to make them more flexible and easier to use. However, LLMs' application in industrial settings is underexplored. This paper introduces a framework for integrating LLMs to achieve end-to-end control of industrial automation systems. At the core of the framework are an agent system designed for industrial tasks, a structured prompting method, and an event-driven information modeling mechanism that provides real-time data for LLM inference. The framework supplies LLMs with real-time events on different context semantic levels, allowing them to interpret the information, generate production plans, and control operations on the automation system. It also supports structured dataset creation for fine-tuning on this downstream application of LLMs. Our contribution includes a formal system design, proof-of-concept implementation, and a method for generating task-specific datasets for LLM fine-tuning and testing. This approach enables a more adaptive automation system that can respond to spontaneous events, while allowing easier operation and configuration through natural language for more intuitive human-machine interaction. We provide demo videos and detailed data on GitHub: https://github.com/YuchenXia/LLM4IAS
  BibTeX
  @article{Xia2024, abstract = {Traditional industrial automation systems require specialized expertise to operate and complex reprogramming to adapt to new processes. Large language models offer the intelligence to make them more flexible and easier to use. However, LLMs' application in industrial settings is underexplored. This paper introduces a framework for integrating LLMs to achieve end-to-end control of industrial automation systems. At the core of the framework are an agent system designed for industrial tasks, a structured prompting method, and an event-driven information modeling mechanism that provides real-time data for LLM inference. The framework supplies LLMs with real-time events on different context semantic levels, allowing them to interpret the information, generate production plans, and control operations on the automation system. It also supports structured dataset creation for fine-tuning on this downstream application of LLMs. Our contribution includes a formal system design, proof-of-concept implementation, and a method for generating task-specific datasets for LLM fine-tuning and testing. This approach enables a more adaptive automation system that can respond to spontaneous events, while allowing easier operation and configuration through natural language for more intuitive human-machine interaction. We provide demo videos and detailed data on GitHub: https://github.com/YuchenXia/LLM4IAS}, author = {Xia, Yuchen and Jazdi, Nasser and Zhang, Jize and Shah, Chaitanya and Weyrich, Michael}, month = {09}, title = {Control Industrial Automation System with Large Language Models}, url = {https://arxiv.org/abs/2409.18009v1}, year = 2024 }
  Link
  https://arxiv.org/abs/2409.18009v1
7. Y. Xia, N. Jazdi, and M. Weyrich, “Enhance FMEA with Large Language Models for Assisted Risk Management in Technical Processes and Products,” 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA), pp. 1–4, Sep. 2024.
  - BibTeX
  - Link
  BibTeX
  @article{xia2024enhance, author = {Xia, Yuchen and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ETFA61755.2024.10710996}, editor = {IEEE}, isbn = {979-8-3503-6123-0}, journal = {2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)}, month = {09}, organization = {IEEE}, pages = {1--4}, title = {Enhance FMEA with Large Language Models for Assisted Risk Management in Technical Processes and Products}, url = {https://ieeexplore.ieee.org/document/10710996/}, year = 2024 }
  Link
  https://ieeexplore.ieee.org/document/10710996/
8. F. Dettinger, M. Weiß, and M. Weyrich, Future Use Cases for Vehicular Communication based on Connected Functions. 2024, pp. 1–5.
  - BibTeX
  BibTeX
  @book{10757637, author = {Dettinger, Falk and Weiß, Matthias and Weyrich, Michael}, booktitle = {2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall)}, doi = {10.1109/VTC2024-Fall63153.2024.10757637}, pages = {1-5}, title = {Future Use Cases for Vehicular Communication based on Connected Functions}, year = 2024 }
9. Y. Xia, Z. Xiao, N. Jazdi, and M. Weyrich, “Generation of Asset Administration Shell With Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0,” IEEE Access, vol. 12, pp. 84863–84877, 2024.
  - Abstract
  - BibTeX
  Abstract
  This research introduces a novel approach for achieving semantic interoperability in digital twins and assisting the creation of Asset Administration Shell (AAS) as digital twin model within the context of Industry 4.0. The foundational idea of our research is that the communication based on semantics and the generation of meaningful textual data are directly linked, and we posit that these processes are equivalent if the exchanged information can be serialized in text form. Based on this, we construct a 'semantic node' data structure in our research to capture the semantic essence of textual data. Then, a system powered by large language models is designed and implemented to process the 'semantic node' and generate standardized digital twin models (AAS instance models in the context of Industry 4.0) from raw textual data collected from datasheets describing technical assets. Our evaluation demonstrates an effective generation rate of 62-79%, indicating a substantial proportion of the information from the source text can be translated error-free to the target digital twin instance model with the generative capability of large language models. This result has a direct application in the context of Industry 4.0, and the designed system is implemented as a data model generation tool for reducing the manual effort in creating AAS model by automatically translating unstructured textual data into a standardized AAS model. The generated AAS model can be integrated into AAS-compliant digital twin software for seamless information exchange and communication. In our evaluation, a comparative analysis of different LLMs and an in-depth ablation study of Retrieval-Augmented Generation (RAG) mechanisms provide insights into the effectiveness of LLM systems for interpreting technical concepts and translating data. Our findings emphasize LLMs' capability to automate AAS instance creation and contribute to the broader field of semantic interoperability for digital twins in industrial applications. The prototype implementation and evaluation results are presented on our GitHub Repository: https://github.com/YuchenXia/AASbyLLM.
  BibTeX
  @article{Xia2024, abstract = {This research introduces a novel approach for achieving semantic interoperability in digital twins and assisting the creation of Asset Administration Shell (AAS) as digital twin model within the context of Industry 4.0. The foundational idea of our research is that the communication based on semantics and the generation of meaningful textual data are directly linked, and we posit that these processes are equivalent if the exchanged information can be serialized in text form. Based on this, we construct a 'semantic node' data structure in our research to capture the semantic essence of textual data. Then, a system powered by large language models is designed and implemented to process the 'semantic node' and generate standardized digital twin models (AAS instance models in the context of Industry 4.0) from raw textual data collected from datasheets describing technical assets. Our evaluation demonstrates an effective generation rate of 62-79%, indicating a substantial proportion of the information from the source text can be translated error-free to the target digital twin instance model with the generative capability of large language models. This result has a direct application in the context of Industry 4.0, and the designed system is implemented as a data model generation tool for reducing the manual effort in creating AAS model by automatically translating unstructured textual data into a standardized AAS model. The generated AAS model can be integrated into AAS-compliant digital twin software for seamless information exchange and communication. In our evaluation, a comparative analysis of different LLMs and an in-depth ablation study of Retrieval-Augmented Generation (RAG) mechanisms provide insights into the effectiveness of LLM systems for interpreting technical concepts and translating data. Our findings emphasize LLMs' capability to automate AAS instance creation and contribute to the broader field of semantic interoperability for digital twins in industrial applications. The prototype implementation and evaluation results are presented on our GitHub Repository: https://github.com/YuchenXia/AASbyLLM.}, author = {Xia, Yuchen and Xiao, Zhewen and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ACCESS.2024.3415470}, editor = {of Electrical, Institute and Inc., Electronics Engineers}, issn = {21693536}, journal = {IEEE Access}, pages = {84863-84877}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, title = {Generation of Asset Administration Shell With Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0}, volume = 12, year = 2024 }
10. Y. Xia, J. Zhang, N. Jazdi, and M. Weyrich, “Incorporating Large Language Models into Production Systems for Enhanced Task Automation and Flexibility,” Automation 2024, Jul. 2024.
  Abstract
  This paper introduces a novel approach to integrating large language model (LLM) agents into automated production systems, aimed at enhancing task automation and flexibility. We organize production operations within a hierarchical framework based on the automation pyramid. Atomic operation functionalities are modeled as microservices, which are executed through interface invocation within a dedicated digital twin system. This allows for a scalable and flexible foundation for orchestrating production processes. In this digital twin system, low-level, hardware-specific data is semantically enriched and made interpretable for LLMs for production planning and control tasks. Large language model agents are systematically prompted to interpret these production-specific data and knowledge. Upon receiving a user request or identifying a triggering event, the LLM agents generate a process plan. This plan is then decomposed into a series of atomic operations, executed as microservices within the real-world automation system. We implement this overall approach on an automated modular production facility at our laboratory, demonstrating how the LLMs can handle production planning and control tasks through a concrete case study. This results in an intuitive production facility with higher levels of task automation and flexibility. Finally, we reveal the several limitations in realizing the full potential of the large language models in autonomous systems and point out promising benefits. Demos of this series of ongoing research series can be accessed at: https://github.com/YuchenXia/GPT4IndustrialAutomation
  BibTeX
  @article{Xia2024, abstract = {This paper introduces a novel approach to integrating large language model (LLM) agents into automated production systems, aimed at enhancing task automation and flexibility. We organize production operations within a hierarchical framework based on the automation pyramid. Atomic operation functionalities are modeled as microservices, which are executed through interface invocation within a dedicated digital twin system. This allows for a scalable and flexible foundation for orchestrating production processes. In this digital twin system, low-level, hardware-specific data is semantically enriched and made interpretable for LLMs for production planning and control tasks. Large language model agents are systematically prompted to interpret these production-specific data and knowledge. Upon receiving a user request or identifying a triggering event, the LLM agents generate a process plan. This plan is then decomposed into a series of atomic operations, executed as microservices within the real-world automation system. We implement this overall approach on an automated modular production facility at our laboratory, demonstrating how the LLMs can handle production planning and control tasks through a concrete case study. This results in an intuitive production facility with higher levels of task automation and flexibility. Finally, we reveal the several limitations in realizing the full potential of the large language models in autonomous systems and point out promising benefits. Demos of this series of ongoing research series can be accessed at: https://github.com/YuchenXia/GPT4IndustrialAutomation}, author = {Xia, Yuchen and Zhang, Jize and Jazdi, Nasser and Weyrich, Michael}, doi = {10.51202/9783181024379}, journal = {Automation 2024}, month = {07}, publisher = {VDI Verlag}, title = {Incorporating Large Language Models into Production Systems for Enhanced Task Automation and Flexibility}, url = {http://arxiv.org/abs/2407.08550 http://dx.doi.org/10.51202/9783181024379}, year = 2024 }
  Link
  http://arxiv.org/abs/2407.08550 http://dx.doi.org/10.51202/9783181024379
11. M. Schindewolf, M. Kuebler, T. Pett, L. Hettich, H. Agh, J. Lorenz, S. Wagner, M. Weyrich, I. Schaefer, T. Düser, and others, “Integrated Approach for High-quality Software Development of Upgradeable Vehicles,” in International Stuttgart Symposium, 2024, pp. 202–217.
  - BibTeX
  BibTeX
  @inproceedings{schindewolf2024integrated, author = {Schindewolf, Marc and Kuebler, Maximilian and Pett, Tobias and Hettich, Lennard and Agh, Halimeh and Lorenz, Julian and Wagner, Stefan and Weyrich, Michael and Schaefer, Ina and D{\"u}ser, Tobias and others}, booktitle = {International Stuttgart Symposium}, organization = {Springer}, pages = {202--217}, title = {Integrated Approach for High-quality Software Development of Upgradeable Vehicles}, year = 2024 }
12. L. Hettich and M. Weyrich, “Intelligent Sensors in Dynamically Reconfigurable Automotive Architectures: A Proof of Concept,” in 2024 Stuttgart International Symposium on Automotive and Engine Technology, Wiesbaden, 2024, pp. 3–19.
  - Abstract
  - BibTeX
  Abstract
  The necessity of a reconfigurable software-defined vehicle platform that is no longer sold as a one-off, but can be continuously adapted to dynamic customer requirements during its lifetime, is becoming increasingly clear. Political and economic institutions have become aware of these needs and initiated actions in the context of contested markets with declining sales figures. However, according to our research, existing vehicle architecture concepts and frameworks do not cover the upgradeability, dynamic reconfigurability at runtime and continuous adaptability aspects of vehicle sensors to the necessary extent. Vehicle sensor technology constitutes the fundamental basis for safe decisions of autonomous driving functions, we therefore consider the importance of this topic to be significant. Building upon the existing service-oriented E/E architecture framework ROSMARIN, we want to contribute a concept extension, allowing the seamless integration of intelligent sensors in vehicles. In addition to requirements for intelligent sensor technology in flexible architectures such as Plug-and-Play of sensor hardware, upgradeability through virtualization of sensor software and runtime resilience, our concept furthermore integrates a novel generalized approach for dynamic sensor calibration and fusion. We prove our concept on a physical demonstrator setup with ultrasonic, LiDAR and camera sensors and demonstrate the upgradeability and reconfigurability of sensor hardware and software. In addition, we show the dynamic online fusion of camera and LiDAR data with minimal effort, while also proving the resilience and automatic adaptability of our approach in case of unforeseeable events like sensor failures.
  BibTeX
  @inproceedings{10.1007/978-3-658-45010-6_1, abstract = {The necessity of a reconfigurable software-defined vehicle platform that is no longer sold as a one-off, but can be continuously adapted to dynamic customer requirements during its lifetime, is becoming increasingly clear. Political and economic institutions have become aware of these needs and initiated actions in the context of contested markets with declining sales figures. However, according to our research, existing vehicle architecture concepts and frameworks do not cover the upgradeability, dynamic reconfigurability at runtime and continuous adaptability aspects of vehicle sensors to the necessary extent. Vehicle sensor technology constitutes the fundamental basis for safe decisions of autonomous driving functions, we therefore consider the importance of this topic to be significant. Building upon the existing service-oriented E/E architecture framework ROSMARIN, we want to contribute a concept extension, allowing the seamless integration of intelligent sensors in vehicles. In addition to requirements for intelligent sensor technology in flexible architectures such as Plug-and-Play of sensor hardware, upgradeability through virtualization of sensor software and runtime resilience, our concept furthermore integrates a novel generalized approach for dynamic sensor calibration and fusion. We prove our concept on a physical demonstrator setup with ultrasonic, LiDAR and camera sensors and demonstrate the upgradeability and reconfigurability of sensor hardware and software. In addition, we show the dynamic online fusion of camera and LiDAR data with minimal effort, while also proving the resilience and automatic adaptability of our approach in case of unforeseeable events like sensor failures.}, address = {Wiesbaden}, author = {Hettich, Lennard and Weyrich, Michael}, booktitle = {2024 Stuttgart International Symposium on Automotive and Engine Technology}, editor = {Kulzer, Andr{\'e} Casal and Reuss, Hans-Christian and Wagner, Andreas}, isbn = {978-3-658-45010-6}, pages = {3--19}, publisher = {Springer Fachmedien Wiesbaden}, title = {Intelligent Sensors in Dynamically Reconfigurable Automotive Architectures: A Proof of Concept}, year = 2024 }
13. Y. Xia, D. Dittler, N. Jazdi, H. Chen, and M. Weyrich, “LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins,” 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA), pp. 1–4, Sep. 2024.
  - BibTeX
  - Link
  BibTeX
  @article{Xia2024, author = {Xia, Yuchen and Dittler, Daniel and Jazdi, Nasser and Chen, Haonan and Weyrich, Michael}, doi = {10.1109/ETFA61755.2024.10710900}, isbn = {979-8-3503-6123-0}, journal = {2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)}, month = {09}, pages = {1-4}, publisher = {IEEE}, title = {LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins}, url = {https://ieeexplore.ieee.org/document/10710900/}, year = 2024 }
  Link
  https://ieeexplore.ieee.org/document/10710900/
14. M. Sommer, D. Baumann, T. Rösch, F. Dettinger, E. Sax, and M. Weyrich, “Process for the Identification of Vehicle Functions for Cloud Offloading,” 2024.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Sommer, Martin and Baumann, Daniel and Rösch, Tobias and Dettinger, Falk and Sax, Eric and Weyrich, Michael}, doi = {10.1007/978-3-031-62277-9_38}, isbn = {978-3-031-62276-2}, month = {06}, title = {Process for the Identification of Vehicle Functions for Cloud Offloading}, year = 2024 }
15. M. Sommer, D. Baumann, T. Rösch, F. Dettinger, E. Sax, and M. Weyrich, “Process for the Identification of Vehicle Functions for Cloud Offloading,” in Science and Information Conference, 2024, pp. 596–608.
  - BibTeX
  BibTeX
  @inproceedings{sommer2024process, author = {Sommer, Martin and Baumann, Daniel and R{\"o}sch, Tobias and Dettinger, Falk and Sax, Eric and Weyrich, Michael}, booktitle = {Science and Information Conference}, organization = {Springer}, pages = {596--608}, title = {Process for the Identification of Vehicle Functions for Cloud Offloading}, year = 2024 }
16. J. Stümpfle, N. Jazdi, and M. Weyrich, “Tackling Erosion in Variant-Rich Software Systems: Challenges and Approaches,” in Procedia CIRP, 2024, vol. 128, pp. 633–637.
  - BibTeX
  - Link
  BibTeX
  @inproceedings{stümpfle2024tacklingerosionvariantrichsoftware, archiveprefix = {arXiv}, author = {Stümpfle, Johannes and Jazdi, Nasser and Weyrich, Michael}, eprint = {2407.03914}, journal = {Procedia CIRP}, pages = {633--637}, primaryclass = {cs.SE}, publisher = {Elsevier}, title = {Tackling Erosion in Variant-Rich Software Systems: Challenges and Approaches}, url = {https://arxiv.org/abs/2407.03914}, volume = 128, year = 2024 }
  Link
  https://arxiv.org/abs/2407.03914
2023
1. V. Stegmaier, T. Eberhardt, W. Schaaf, N. Jazdi, and M. Weyrich, “A behavior model for Digital Twins of vacuum suction cups,” Procedia CIRP, vol. 118, pp. 958–963, 2023.
  Abstract
  Vacuum handling systems are widely used in production systems. Most of the systems key performance indicators (KPIs) relevant for industry 4.0 use cases can be derived from its vacuum level characteristics. Vacuum suction cups are key components of vacuum gripping systems and have a significant influence on the system behavior. For modelling suction cups, mainly constant volume chambers are currently used. However, these do not represent the suction cups dynamic behavior exactly enough. Therefore, a novel model is presented allowing the vacuum curve simulation mainly based on the force-displacement characteristic curve. The presented model is validated in an industrially relevant scenario.
  BibTeX
  @article{STEGMAIER2023958, abstract = {Vacuum handling systems are widely used in production systems. Most of the systems key performance indicators (KPIs) relevant for industry 4.0 use cases can be derived from its vacuum level characteristics. Vacuum suction cups are key components of vacuum gripping systems and have a significant influence on the system behavior. For modelling suction cups, mainly constant volume chambers are currently used. However, these do not represent the suction cups dynamic behavior exactly enough. Therefore, a novel model is presented allowing the vacuum curve simulation mainly based on the force-displacement characteristic curve. The presented model is validated in an industrially relevant scenario.}, author = {Stegmaier, Valentin and Eberhardt, Tobias and Schaaf, Walter and Jazdi, Nasser and Weyrich, Michael}, doi = {https://doi.org/10.1016/j.procir.2023.06.165}, issn = {2212-8271}, journal = {Procedia CIRP}, note = {16th CIRP Conference on Intelligent Computation in Manufacturing Engineering}, pages = {958-963}, title = {A behavior model for Digital Twins of vacuum suction cups}, url = {https://www.sciencedirect.com/science/article/pii/S221282712300392X}, volume = 118, year = 2023 }
  Link
  https://www.sciencedirect.com/science/article/pii/S221282712300392X
2. G. Ghasemi, D. Braun, N. Jazdi, M. Weyrich, S. Holtkotte, N. Richter, and J. Birk, “A data-driven approach to analyze industrial process alarms using the association analysis method,” 2023, pp. 777–790.
  - BibTeX
  BibTeX
  @inbook{inbook, author = {Ghasemi, Golsa and Braun, Dominik and Jazdi, Nasser and Weyrich, Michael and Holtkotte, S. and Richter, N. and Birk, J.}, doi = {10.51202/9783181024195-777}, isbn = {9783181024195}, month = {06}, pages = {777-790}, title = {A data-driven approach to analyze industrial process alarms using the association analysis method}, year = 2023 }
3. P. Häbig, D. Dittler, M. Fey, T. Müller, N. Mößner, N. Jazdi, M. Weyrich, and K. Hufendiek, “A Modular System Architecture for an Offshore Off-grid Platform for Climate-neutral Power-to-X Production in H2Mare,” May 2023.
  - BibTeX
  BibTeX
  @article{unknown, author = {Häbig, Pascal and Dittler, Daniel and Fey, Maximilian and Müller, Timo and Mößner, Nikola and Jazdi, Nasser and Weyrich, Michael and Hufendiek, Kai}, doi = {10.48550/arXiv.2305.16285}, month = {05}, title = {A Modular System Architecture for an Offshore Off-grid Platform for Climate-neutral Power-to-X Production in H2Mare}, year = 2023 }
4. S. Kamm, P. Suthandhira, N. Jazdi, and M. Weyrich, “A Novel Architecture for Robust and Adaptive Machine Learning Using Heterogeneous Data in Condition Monitoring of Automation Systems,” 2023, pp. 1–8.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Kamm, Simon and Suthandhira, Paveen and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275533}, month = {09}, pages = {1-8}, title = {A Novel Architecture for Robust and Adaptive Machine Learning Using Heterogeneous Data in Condition Monitoring of Automation Systems}, year = 2023 }
5. D. Dittler, P. Lierhammer, D. Braun, T. Müller, N. Jazdi, and M. Weyrich, “A Novel Model Adaption Approach for intelligent Digital Twins of Modular Production Systems,” 2023, pp. 1–8.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Dittler, Daniel and Lierhammer, Peter and Braun, Dominik and Müller, Timo and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275384}, month = {09}, pages = {1-8}, title = {A Novel Model Adaption Approach for intelligent Digital Twins of Modular Production Systems}, year = 2023 }
6. S. Kamm, S. S. Veekati, T. Müller, N. Jazdi, and M. Weyrich, “A survey on machine learning based analysis of heterogeneous data in industrial automation,” Computers in Industry, vol. 149, Aug. 2023.
  Abstract
  In many application domains data from different sources are increasingly available to thoroughly monitor and describe a system or device. Especially within the industrial automation domain, heterogeneous data and its analysis gain a lot of attention from research and industry, since it has the potential to improve or enable tasks like diagnostics, predictive maintenance, and condition monitoring. For data analysis, machine learning based approaches are mostly used in recent literature, as these algorithms allow us to learn complex correlations within the data. To analyze even heterogeneous data and gain benefits from it in an application, data from different sources need to be integrated, stored, and managed to apply machine learning algorithms. In a setting with heterogeneous data sources, the analysis algorithms should also be able to handle data source failures or newly added data sources. In addition, existing knowledge should be used to improve the machine learning based analysis or its training process. To find existing approaches for the machine learning based analysis of heterogeneous data in the industrial automation domain, this paper presents the result of a systematic literature review. The publications were reviewed, evaluated, and discussed concerning five requirements that are derived in this paper. We identified promising solutions and approaches and outlined open research challenges, which are not yet covered sufficiently in the literature.
  BibTeX
  @article{kamm2023survey, abstract = {In many application domains data from different sources are increasingly available to thoroughly monitor and describe a system or device. Especially within the industrial automation domain, heterogeneous data and its analysis gain a lot of attention from research and industry, since it has the potential to improve or enable tasks like diagnostics, predictive maintenance, and condition monitoring. For data analysis, machine learning based approaches are mostly used in recent literature, as these algorithms allow us to learn complex correlations within the data. To analyze even heterogeneous data and gain benefits from it in an application, data from different sources need to be integrated, stored, and managed to apply machine learning algorithms. In a setting with heterogeneous data sources, the analysis algorithms should also be able to handle data source failures or newly added data sources. In addition, existing knowledge should be used to improve the machine learning based analysis or its training process. To find existing approaches for the machine learning based analysis of heterogeneous data in the industrial automation domain, this paper presents the result of a systematic literature review. The publications were reviewed, evaluated, and discussed concerning five requirements that are derived in this paper. We identified promising solutions and approaches and outlined open research challenges, which are not yet covered sufficiently in the literature.}, author = {Kamm, Simon and Veekati, Sushma Sri and Müller, Timo and Jazdi, Nasser and Weyrich, Michael}, doi = {https://doi.org/10.1016/j.compind.2023.103930}, issn = {0166-3615}, journal = {Computers in Industry}, month = {08}, title = {A survey on machine learning based analysis of heterogeneous data in industrial automation }, url = {https://www.sciencedirect.com/science/article/pii/S0166361523000805?via%3Dihub}, volume = 149, year = 2023 }
  Link
  https://www.sciencedirect.com/science/article/pii/S0166361523000805?via%3Dihub
7. S. Kamm, P. Kumar, N. Jazdi, and M. Weyrich, “An Architecture for Adaptive Machine Learning Models using Adversarial and Transfer Learning,” Procedia CIRP, vol. 120, pp. 1451–1456, Jan. 2023.
  - BibTeX
  BibTeX
  @article{article, author = {Kamm, Simon and Kumar, Praveen and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.procir.2023.09.192}, journal = {Procedia CIRP}, month = {01}, pages = {1451-1456}, title = {An Architecture for Adaptive Machine Learning Models using Adversarial and Transfer Learning}, volume = 120, year = 2023 }
8. F. Listl, J. Fischer, and M. Weyrich, “An Architecture for Knowledge Graph based Simulation Support,” 2023, pp. 1–8.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Listl, Franz and Fischer, Jan and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275514}, month = {09}, pages = {1-8}, title = {An Architecture for Knowledge Graph based Simulation Support}, year = 2023 }
9. V. Stegmaier, T. Eberhardt, W. Schaaf, N. Jazdi, M. Weyrich, A. Verl, and J. Gmbh, “Automated Configuration of Optimized Customer Specific Mechatronic Systems Using Behavior Models,” Jan-2023.
  - BibTeX
  BibTeX
  @preprint{unknown, author = {Stegmaier, Valentin and Eberhardt, Tobias and Schaaf, Walter and Jazdi, Nasser and Weyrich, Michael and Verl, Alexander and Gmbh, J}, doi = {10.13140/RG.2.2.21121.22889}, month = {01}, title = {Automated Configuration of Optimized Customer Specific Mechatronic Systems Using Behavior Models}, year = 2023 }
10. G. Hildebrandt, P. Habiger, D. Dittler, R. Drath, and M. Weyrich, “Automated Integration of External Data into Digital Twins for Manufacturing Processes,” 2023, pp. 1–8.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Hildebrandt, Gary and Habiger, Pascal and Dittler, Daniel and Drath, Rainer and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275696}, month = {09}, pages = {1-8}, title = {Automated Integration of External Data into Digital Twins for Manufacturing Processes}, year = 2023 }
11. S. Bickelhaupt, M. Hahn, N. Nuding, A. Morozov, and M. Weyrich, “Challenges and Opportunities of Future Vehicle Diagnostics in Software-Defined Vehicles,” 2023.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Bickelhaupt, Sandra and Hahn, Michael and Nuding, Nikolai and Morozov, Andrey and Weyrich, Michael}, doi = {10.4271/2023-01-0847}, month = {04}, title = {Challenges and Opportunities of Future Vehicle Diagnostics in Software-Defined Vehicles}, year = 2023 }
12. G. Ghasemi, M. Müller, N. Jazdi, and M. Weyrich, “Complexity estimation service for change management in industrial automation systems using Digital Twin,” Procedia CIRP, vol. 119, pp. 1011–1016, 2023.
  - BibTeX
  - Link
  BibTeX
  @article{GHASEMI20231011, author = {Ghasemi, Golsa and Müller, Manuel and Jazdi, Nasser and Weyrich, Michael}, doi = {https://doi.org/10.1016/j.procir.2023.02.176}, issn = {2212-8271}, journal = {Procedia CIRP}, note = {The 33rd CIRP Design Conference}, pages = {1011-1016}, title = {Complexity estimation service for change management in industrial automation systems using Digital Twin}, url = {https://www.sciencedirect.com/science/article/pii/S221282712300611X}, volume = 119, year = 2023 }
  Link
  https://www.sciencedirect.com/science/article/pii/S221282712300611X
13. S. Bickelhaupt, M. Hahn, N. Nuding, A. Morozov, and M. Weyrich, “Comprehensive Evaluation of Logging Frameworks for Future Vehicle Diagnostics,” 2023.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Bickelhaupt, Sandra and Hahn, Michael and Nuding, Nikolai and Morozov, Andrey and Weyrich, Michael}, doi = {10.4271/2023-01-1223}, month = {06}, title = {Comprehensive Evaluation of Logging Frameworks for Future Vehicle Diagnostics}, year = 2023 }
14. M. Weiß, M. Müller, F. Dettinger, N. Jazdi, and M. Weyrich, “Continuous Analysis and Optimization of Vehicle Software Updates using the Intelligent Digital Twin,” 2023, pp. 1–7.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Weiß, Matthias and Müller, Manuel and Dettinger, Falk and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275489}, month = {09}, pages = {1-7}, title = {Continuous Analysis and Optimization of Vehicle Software Updates using the Intelligent Digital Twin}, year = 2023 }
15. F. Dettinger, H. Wei, M. Weiß, N. Jazdi, and M. Weyrich, “Dateneffiziente Vervollständigung des Umgebungsmodells von autonomen vernetzten Systemen mittels Sensorfusion,” 2023, pp. 513–524.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Dettinger, Falk and Wei, Han and Weiß, Matthias and Jazdi, Nasser and Weyrich, Michael}, doi = {10.51202/9783181024195-513}, isbn = {9783181024195}, month = {06}, pages = {513-524}, title = {Dateneffiziente Vervollständigung des Umgebungsmodells von autonomen vernetzten Systemen mittels Sensorfusion}, year = 2023 }
16. M. Weiß, F. Dettinger, N. Jazdi, and M. Weyrich, “DevOps als Enabler der kontinuierlichen Funktionsverbesserung und automatisierten Update-Analyse in software-definierten Systemen,” 2023, pp. 487–500.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Weiß, Matthias and Dettinger, Falk and Jazdi, Nasser and Weyrich, Michael}, doi = {10.51202/9783181024195-487}, isbn = {9783181024195}, month = {06}, pages = {487-500}, title = {DevOps als Enabler der kontinuierlichen Funktionsverbesserung und automatisierten Update-Analyse in software-definierten Systemen}, year = 2023 }
17. M. Artelt, D. Dittler, G. Hildebrandt, D. Braun, N. Jazdi, and M. Weyrich, “Dynamic Production Scheduling with Intelligent Products in a Modular Production System,” 2023, pp. 1–4.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Artelt, Maurice and Dittler, Daniel and Hildebrandt, Gary and Braun, Dominik and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275613}, month = {09}, pages = {1-4}, title = {Dynamic Production Scheduling with Intelligent Products in a Modular Production System}, year = 2023 }
18. S. Wagner, C. Gonnermann, M. Wegmann, F. Listl, G. Reinhart, and M. Weyrich, “From framework to industrial implementation: the digital twin in process planning,” Journal of Intelligent Manufacturing, pp. 1–21, Dec. 2023.
  - BibTeX
  BibTeX
  @article{article, author = {Wagner, Sarah and Gonnermann, Clemens and Wegmann, Marc and Listl, Franz and Reinhart, Gunther and Weyrich, Michael}, doi = {10.1007/s10845-023-02268-0}, journal = {Journal of Intelligent Manufacturing}, month = {12}, pages = {1-21}, title = {From framework to industrial implementation: the digital twin in process planning}, year = 2023 }
19. G. Hildebrandt, P. Habiger, R. Drath, and M. Weyrich, “Hybrides Engineering für modulare Fertigungsanlagen mittels Mixed Reality - Hybrid Engineering for Modular Production Systems through Mixed Reality,” 2023.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Hildebrandt, Gary and Habiger, Pascal and Drath, Rainer and Weyrich, Michael}, month = {06}, title = {Hybrides Engineering für modulare Fertigungsanlagen mittels Mixed Reality - Hybrid Engineering for Modular Production Systems through Mixed Reality}, year = 2023 }
20. V. Stegmaier, D. Dittler, N. Jazdi, and M. Weyrich, “Influence of Solvers and their Characteristics on Simulation Time and Accuracy Exemplified for a Vacuum Gripping System,” Procedia CIRP, vol. 120, pp. 714–719, Jan. 2023.
  - BibTeX
  BibTeX
  @article{article, author = {Stegmaier, Valentin and Dittler, Daniel and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.procir.2023.09.064}, journal = {Procedia CIRP}, month = {01}, pages = {714-719}, title = {Influence of Solvers and their Characteristics on Simulation Time and Accuracy Exemplified for a Vacuum Gripping System}, volume = 120, year = 2023 }
21. J. Stümpfle, N. Sahlab, S. Kamm, P. Grimmeisen, N. Jazdi, and M. Weyrich, “InteLiv: An Architecture for Graph-Based Dynamic Context Modeling for Smart Living,” 2023, pp. 1–8.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Stümpfle, Johannes and Sahlab, Nada and Kamm, Simon and Grimmeisen, Philipp and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275388}, month = {09}, pages = {1-8}, title = {InteLiv: An Architecture for Graph-Based Dynamic Context Modeling for Smart Living}, year = 2023 }
22. V. Stegmaier, T. Eberhardt, W. Schaaf, N. Jazdi, M. Weyrich, and A. Verl, “Literature Review and Model Proposal on the Machine Life Cycle in Industrial Automation from Different Perspectives,” Procedia CIRP, vol. 120, pp. 690–695, Jan. 2023.
  - BibTeX
  BibTeX
  @article{article, author = {Stegmaier, Valentin and Eberhardt, Tobias and Schaaf, Walter and Jazdi, Nasser and Weyrich, Michael and Verl, Alexander}, doi = {10.1016/j.procir.2023.09.060}, journal = {Procedia CIRP}, month = {01}, pages = {690-695}, title = {Literature Review and Model Proposal on the Machine Life Cycle in Industrial Automation from Different Perspectives}, volume = 120, year = 2023 }
23. F. Dettinger, N. Jazdi, M. Weyrich, L. Brandl, H.-C. Reuss, U. Pecha, N. Parspour, S. Li, M. Frey, F. Gauterin, A.-T. Nägele, V. Lüntzel, and E. Sax, “Machine-Learning-Based Fault Detection in Electric Vehicle Powertrains Using a Digital Twin,” 2023.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Dettinger, Falk and Jazdi, Nasser and Weyrich, Michael and Brandl, Lukas and Reuss, Hans-Christian and Pecha, Urs and Parspour, Nejila and Li, Shiqing and Frey, Michael and Gauterin, Frank and Nägele, Ann-Therese and Lüntzel, Vitus and Sax, Eric}, doi = {10.4271/2023-01-1214}, month = {06}, title = {Machine-Learning-Based Fault Detection in Electric Vehicle Powertrains Using a Digital Twin}, year = 2023 }
24. D. Braun, N. Jazdi, W. Schloegl, and M. Weyrich, “Qualitative and quantitative evaluation of a methodology for the Digital Twin creation of brownfield production systems,” 2023, pp. 1–8.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Braun, Dominik and Jazdi, Nasser and Schloegl, Wolfgang and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275451}, month = {09}, pages = {1-8}, title = {Qualitative and quantitative evaluation of a methodology for the Digital Twin creation of brownfield production systems}, year = 2023 }
25. G. Ghasemi, M. Müller, N. Jazdi, and M. Weyrich, “Quality Analysis Framework based on Complexity for Change Management Using Intelligent Digital Twin,” Procedia CIRP, vol. 120, pp. 1516–1521, Jan. 2023.
  - BibTeX
  BibTeX
  @article{article, author = {Ghasemi, Golsa and Müller, Manuel and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.procir.2023.09.207}, journal = {Procedia CIRP}, month = {01}, pages = {1516-1521}, title = {Quality Analysis Framework based on Complexity for Change Management Using Intelligent Digital Twin}, volume = 120, year = 2023 }
26. T. Müller, B. Caesar, M. Weiß, S. Ferhat, N. Sahlab, A. Fay, R. Oger, N. Jazdi-Motlagh, and M. Weyrich, “Reconfiguration management in manufacturing : A systematic literature review,” Automatisierungstechnik, vol. 71, pp. 330–350, 2023.
  - BibTeX
  BibTeX
  @article{muller2023reconfiguration, affiliation = {Muller, T (Corresponding Author), Univ Stuttgart, Inst Ind Automat \& Software Engn, Pfaffenwaldring 47, D-70550 Stuttgart, Germany. Mueller, Timo; Weiss, Matthias; Sahlab, Nada; Jazdi, Nasser; Weyrich, Michael, Univ Stuttgart, Inst Ind Automat \& Software Engn, Pfaffenwaldring 47, D-70550 Stuttgart, Germany. Caesar, Birte; Fay, Alexander, Helmut Schmidt Univ, Inst Automat Technol, Holstenhofweg 85, D-22043 Hamburg, Germany. Ferhat, Selma; Oger, Raphael, IMT Mines Albi Carnaux, Ctr Genie Ind All Sci, F-81000 Albi, France. Ferhat, Selma, MINES ParisTech, Ctr Gest Sci, 60 Blvd St Michel, F-75272 Paris 06, France.}, author = {Müller, Timo and Caesar, Birte and Weiß, Matthias and Ferhat, Selma and Sahlab, Nada and Fay, Alexander and Oger, Raphaël and Jazdi-Motlagh, Nasser and Weyrich, Michael}, doi = {10.1515/auto-2022-0139}, issn = {{0178-2312} and {2196-677X}}, journal = {Automatisierungstechnik}, language = {eng}, number = 5, pages = {330-350}, publisher = {De Gruyter}, research-areas = {Automation \& Control Systems}, title = {Reconfiguration management in manufacturing : A systematic literature review}, unique-id = {WOS:000982913200002}, volume = 71, year = 2023 }
27. M. Müller, T. Ruppert, N. Jazdi, and M. Weyrich, “Self-improving situation awareness for human--robot-collaboration using intelligent Digital Twin,” Journal of Intelligent Manufacturing, pp. 1–19, 2023.
  - BibTeX
  BibTeX
  @article{muller2023self, author = {M{\"u}ller, Manuel and Ruppert, Tam{\'a}s and Jazdi, Nasser and Weyrich, Michael}, journal = {Journal of Intelligent Manufacturing}, pages = {1--19}, publisher = {Springer}, title = {Self-improving situation awareness for human--robot-collaboration using intelligent Digital Twin}, year = 2023 }
28. G. Ghasemi, M. Kharde, M. Müller, N. Jazdi, and M. Weyrich, “Simulation Model Selection Process Using Complexity Measurement,” 2023, pp. 1–6.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Ghasemi, Golsa and Kharde, Mandar and Müller, Manuel and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1109/CASE56687.2023.10260593}, month = {08}, pages = {1-6}, title = {Simulation Model Selection Process Using Complexity Measurement}, year = 2023 }
29. H. Vietz, M. Hirth, S. Baum, and M. Weyrich, “Synthetic Data Generation for improving Deep Learning-based 5G Indoor Positioning,” 2023, pp. 1–7.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Vietz, Hannes and Hirth, Manuel and Baum, Sebastian and Weyrich, Michael}, doi = {10.1109/ETFA54631.2023.10275437}, month = {09}, pages = {1-7}, title = {Synthetic Data Generation for improving Deep Learning-based 5G Indoor Positioning}, year = 2023 }
30. A. Schuster, R. Hagmanns, I. Sonji, A. Löcklin, J. Petereit, C. Ebert, and M. Weyrich, “Synthetic data generation for the continuous development and testing of autonomous construction machinery,” at - Automatisierungstechnik, vol. 71, pp. 953–968, Nov. 2023.
  - BibTeX
  BibTeX
  @article{article, author = {Schuster, Alexander and Hagmanns, Raphael and Sonji, Iman and Löcklin, Andreas and Petereit, Janko and Ebert, Christof and Weyrich, Michael}, doi = {10.1515/auto-2023-0026}, journal = {at - Automatisierungstechnik}, month = {11}, pages = {953-968}, title = {Synthetic data generation for the continuous development and testing of autonomous construction machinery}, volume = 71, year = 2023 }
31. Y. Xia, M. Shenoy, N. Jazdi, and M. Weyrich, “Towards autonomous system: flexible modular production system enhanced with large language model agents,” Apr. 2023.
  - BibTeX
  BibTeX
  @article{unknown, author = {Xia, Yuchen and Shenoy, Manthan and Jazdi, Nasser and Weyrich, Michael}, month = {04}, title = {Towards autonomous system: flexible modular production system enhanced with large language model agents}, year = 2023 }
32. B. C. Gül, N. Devarakonda, D. Dittler, N. Jazdi, and M. Weyrich, “Using Federated Learning in the Context of Software-Defined Mobility Systems for Predictive Quality of Service,” AUTOMATION 2023, pp. 591–610.
  - BibTeX
  BibTeX
  @article{gul2023using, author = {Gül, Baran Can and Devarakonda, Neeharika and Dittler, Daniel and Jazdi, Nasser and Weyrich, Michael}, doi = {doi.org/10.51202/9783181024195}, isbn = {978-3-18-092419-9}, journal = {AUTOMATION 2023}, pages = {591–610}, title = {Using Federated Learning in the Context of Software-Defined Mobility Systems for Predictive Quality of Service}, year = {2023 } }
33. F. Listl, J. Fischer, A. Sohr, D. Dittler, N. Jazdi, and M. Weyrich, “Utilizing ISA-95 in an Industrial Knowledge Graph for Material Flow Simulation - Semantic Model Extensions and Efficient Data Integration,” Procedia CIRP, vol. 120, pp. 1558–1563, Jan. 2023.
  - BibTeX
  BibTeX
  @article{article, author = {Listl, Franz and Fischer, Jan and Sohr, Annelie and Dittler, Daniel and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.procir.2023.09.214}, journal = {Procedia CIRP}, month = {01}, pages = {1558-1563}, title = {Utilizing ISA-95 in an Industrial Knowledge Graph for Material Flow Simulation - Semantic Model Extensions and Efficient Data Integration}, volume = 120, year = 2023 }
2022
1. V. Stegmaier, T. Eberhardt, W. Schaaf, N. Jazdi, and M. Weyrich, “A behavior model for Digital Twins of vacuum suction cups,” 16th CIRP Conference on Intelligent Computation in Manufacturing Engineering, Gulf of Naples, Italy, Mai 2022, 2022.
  Abstract
  Vacuum handling systems are widely used in production systems. Most of the systems key performance indicators (KPIs) relevant for industry 4.0 use cases can be derived from its vacuum level characteristics. Vacuum suction cups are key components of vacuum gripping systems and have a significant influence on the system behavior. For modelling suction cups, mainly constant volume chambers are currently used. However, these do not represent the suction cups dynamic behavior exactly enough. Therefore, a novel model is presented allowing the vacuum curve simulation mainly based on the force-displacement characteristic curve. The presented model is validated in an industrially relevant scenario.
  BibTeX
  @article{stegmaier2022behavior, abstract = {Vacuum handling systems are widely used in production systems. Most of the systems key performance indicators (KPIs) relevant for industry 4.0 use cases can be derived from its vacuum level characteristics. Vacuum suction cups are key components of vacuum gripping systems and have a significant influence on the system behavior. For modelling suction cups, mainly constant volume chambers are currently used. However, these do not represent the suction cups dynamic behavior exactly enough. Therefore, a novel model is presented allowing the vacuum curve simulation mainly based on the force-displacement characteristic curve. The presented model is validated in an industrially relevant scenario.}, author = {Stegmaier, Valentin and Eberhardt, Tobias and Schaaf, Walter and Jazdi, Nasser and Weyrich, Michael}, doi = {10.13140/RG.2.2.10480.94721}, journal = {16th CIRP Conference on Intelligent Computation in Manufacturing Engineering, Gulf of Naples, Italy, Mai 2022}, title = {A behavior model for Digital Twins of vacuum suction cups }, url = {https://www.researchgate.net/publication/360396870_A_behavior_model_for_Digital_Twins_of_vacuum_suction_cups }, year = 2022 }
  Link
  https://www.researchgate.net/publication/360396870_A_behavior_model_for_Digital_Twins_of_vacuum_suction_cups
2. S. Kamm, N. Sahlab, N. Jazdi, and M. Weyrich, “A Concept for Dynamic and Robust Machine Learning with Contex Modeling for Heterogeneous Manufacturing Data,” 16th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME ’22, Italy, 2022.
  Abstract
  With the increasing amount of available and connected data sources, industrial automation applications such as condition monitoring of a production machine can be improved by considering various data. To gain insights from this data and make it useable, heterogeneous data has to be analyzed intensively. Limited machine learning approaches exist in industrial automation and manufacturing for analyzing data acquired from multiple sources. In this paper, first, a suitable concept for handling heterogeneous data from integration to analysis is presented as well as a multi-layer architecture for the concept’s realization. The architecture encapsulates functionalities into the different layers and allows easy extendability and modifiability. Afterwards, a context modeling approach for managing heterogeneous data and existing approaches and algorithms for analyzing this data robustly and dynamically analyzing it are presented.
  BibTeX
  @article{kamm2022concept, abstract = {With the increasing amount of available and connected data sources, industrial automation applications such as condition monitoring of a production machine can be improved by considering various data. To gain insights from this data and make it useable, heterogeneous data has to be analyzed intensively. Limited machine learning approaches exist in industrial automation and manufacturing for analyzing data acquired from multiple sources. In this paper, first, a suitable concept for handling heterogeneous data from integration to analysis is presented as well as a multi-layer architecture for the concept’s realization. The architecture encapsulates functionalities into the different layers and allows easy extendability and modifiability. Afterwards, a context modeling approach for managing heterogeneous data and existing approaches and algorithms for analyzing this data robustly and dynamically analyzing it are presented.}, author = {Kamm, Simon and Sahlab, Nada and Jazdi, Nasser and Weyrich, Michael}, doi = {10.13140/RG.2.2.32657.10084}, journal = {16th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME ‘22, Italy}, title = {A Concept for Dynamic and Robust Machine Learning with Contex Modeling for Heterogeneous Manufacturing Data }, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022-A_Concept_for_Dynamic_and_Robust_Machine_Learning_with_Contex_Modeling_for_Heterogeneous_Manufacturing_Data.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022-A_Concept_for_Dynamic_and_Robust_Machine_Learning_with_Contex_Modeling_for_Heterogeneous_Manufacturing_Data.pdf
3. F. Hermann, B. Chen, G. Ghasemi, V. Stegmaier, T. Ackermann, P. Reimann, S. Vogt, T. Graf, and M. Weyrich, “A Digital Twin Approach for the Prediction of the Geometry of Single Tracks Produced by Laser Metal Deposition,” in 55th CIRP Conference on Manufacturing Systems, Lugano, Switzerland, Juni 2022, 2022.
  Abstract
  A key performance indicator for sensors in production systems is their accuracy. In order to respond to the flexible requirements posed to production systems, there are currently two possibilities to realize the needed accuracy. Either the sensors can be changed frequently, so that the lowest still sufficient accuracy can always be achieved or the production system can be equipped directly with highly accurate sensors. These two options come with high costs, originating from the manual effort and the proportionality of accuracy and cost for most of the commonly used sensors. Industrially used resistance-based sensors such as pressure, force or temperature sensors represent a special case here, because their inaccuracy traces back to few major sources. To eliminate some of these sources or to decrease their impacts, instance-specific characteristics are used in an accuracy model provided by an intelligent Digital Twin. Using varying accuracy models provides different levels of accuracy. The presented concept provides the needed accuracy permanently or as a service for periods the production system needs the higher accuracy, called Accuracy-as-a-Service (AaaS), benefiting setup efficiency, costs and flexibility. To validate the presented concept, the proposed model is used for an analog pressure sensor in a fluidic test setup. The control unit of the system is provided with a standard model as well as a more accurate one. It is demonstrated in the paper how the usage of the individual model can improve the accuracy of a special sensor significantly by a factor of four.
  BibTeX
  @conference{hermann2022digital, abstract = {A key performance indicator for sensors in production systems is their accuracy. In order to respond to the flexible requirements posed to production systems, there are currently two possibilities to realize the needed accuracy. Either the sensors can be changed frequently, so that the lowest still sufficient accuracy can always be achieved or the production system can be equipped directly with highly accurate sensors. These two options come with high costs, originating from the manual effort and the proportionality of accuracy and cost for most of the commonly used sensors. Industrially used resistance-based sensors such as pressure, force or temperature sensors represent a special case here, because their inaccuracy traces back to few major sources. To eliminate some of these sources or to decrease their impacts, instance-specific characteristics are used in an accuracy model provided by an intelligent Digital Twin. Using varying accuracy models provides different levels of accuracy. The presented concept provides the needed accuracy permanently or as a service for periods the production system needs the higher accuracy, called Accuracy-as-a-Service (AaaS), benefiting setup efficiency, costs and flexibility. To validate the presented concept, the proposed model is used for an analog pressure sensor in a fluidic test setup. The control unit of the system is provided with a standard model as well as a more accurate one. It is demonstrated in the paper how the usage of the individual model can improve the accuracy of a special sensor significantly by a factor of four.}, author = {Hermann, Florian and Chen, Bowen and Ghasemi, Golsa and Stegmaier, Valentin and Ackermann, Thomas and Reimann, Peter and Vogt, Sabrina and Graf, Thomas and Weyrich, Michael}, booktitle = {55th CIRP Conference on Manufacturing Systems, Lugano, Switzerland, Juni 2022}, doi = {10.1016/j.procir.2022.04.014}, title = {A Digital Twin Approach for the Prediction of the Geometry of Single Tracks Produced by Laser Metal Deposition }, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_A_Digital_Twin_Approach_For_The_Prediction_Of_The_Geometry_Of_Single_Tracks_Produced_By_Laser_Metal_Deposition.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_A_Digital_Twin_Approach_For_The_Prediction_Of_The_Geometry_Of_Single_Tracks_Produced_By_Laser_Metal_Deposition.pdf
4. D. Braun, T. Müller, N. Sahlab, N. Jazdi, W. Schloegl, and M. Weyrich, “A graph-based knowledge representation and pattern mining supporting the Digital Twin creation of existing manufacturing systems,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022, 2022.
  - Abstract
  - BibTeX
  Abstract
  The creation of a Digital Twin for existing manufacturing systems, so-called brownfield systems, is a challenging task due to the needed expert knowledge about the structure of brownfield systems and the effort to realize the digital models. Several approaches and methods have already been proposed that at least partially digitalize the information about a brownfield manufacturing system. A Digital Twin requires linked information from multiple sources. This paper presents a graph-based approach to merge information from heterogeneous sources. Furthermore, the approach provides a way to automatically identify templates using graph structure analysis to facilitate further work with the resulting Digital Twin and its further enhancement.
  BibTeX
  @conference{braun2022graphbased, abstract = {The creation of a Digital Twin for existing manufacturing systems, so-called brownfield systems, is a challenging task due to the needed expert knowledge about the structure of brownfield systems and the effort to realize the digital models. Several approaches and methods have already been proposed that at least partially digitalize the information about a brownfield manufacturing system. A Digital Twin requires linked information from multiple sources. This paper presents a graph-based approach to merge information from heterogeneous sources. Furthermore, the approach provides a way to automatically identify templates using graph structure analysis to facilitate further work with the resulting Digital Twin and its further enhancement.}, author = {Braun, Dominik and Müller, Timo and Sahlab, Nada and Jazdi, Nasser and Schloegl, Wolfgang and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022 }, title = {A graph-based knowledge representation and pattern mining supporting the Digital Twin creation of existing manufacturing systems }, year = 2022 }
5. N. Sahlab, H. Kahoul, N. Jazdi, and M. Weyrich, “A Knowledge Graph-Based Method for Automating Systematic Literature Reviews,” in 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022), Oktober 2022, 2022.
  Abstract
  Systematic Literature Reviews aim at investigating current approaches to conclude a research gap or determine a futuristic approach. They represent a significant part of a research activity, from which new concepts stem. However, with the massive availability of publications at a rapid growing rate, especially digitally, it becomes challenging to efficiently screen and assess relevant publications. Another challenge is the continuous assessment of related work over a long period of time and the consequent need for a continuous update, which can be a time-consuming task. Knowledge graphs model entities in a connected manner and enable new insights using different reasoning and analysis methods. The objective of this work is to present an approach to partially automate the conduction of a Systematic Literature Review as well as classify and visualize the results as a knowledge graph. The designed software prototype was used for the conduction of a review on context-awareness in automation systems with considerably accurate results compared to a manual conduction.
  BibTeX
  @conference{sahlab2022knowledge, abstract = {Systematic Literature Reviews aim at investigating current approaches to conclude a research gap or determine a futuristic approach. They represent a significant part of a research activity, from which new concepts stem. However, with the massive availability of publications at a rapid growing rate, especially digitally, it becomes challenging to efficiently screen and assess relevant publications. Another challenge is the continuous assessment of related work over a long period of time and the consequent need for a continuous update, which can be a time-consuming task. Knowledge graphs model entities in a connected manner and enable new insights using different reasoning and analysis methods. The objective of this work is to present an approach to partially automate the conduction of a Systematic Literature Review as well as classify and visualize the results as a knowledge graph. The designed software prototype was used for the conduction of a review on context-awareness in automation systems with considerably accurate results compared to a manual conduction.}, author = {Sahlab, Nada and Kahoul, Hesham and Jazdi, Nasser and Weyrich, Michael}, booktitle = {26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022), Oktober 2022}, title = {A Knowledge Graph-Based Method for Automating Systematic Literature Reviews}, url = {https://www.sciencedirect.com/science/article/pii/S1877050922012285}, year = 2022 }
  Link
  https://www.sciencedirect.com/science/article/pii/S1877050922012285
6. D. Braun, M. Riedhammer, N. Jazdi, W. Schlögl, and M. Weyrich, “A methodology for the detection of functional relations of mechatronic components and assemblies in brownfield systems,” in 55th CIRP Conference on Manufacturing Systems, 29. Juni – 1. Juli 2022, Lugano, Juni 2022, 2022.
  Abstract
  The huge potential of the Digital Twin and its benefits in use cases such as virtual commissioning or reconfiguration planning for production systems is often described and well known. One reason that the usage of Digital Twins is becoming increasingly important are current trends, such as individualized mass production, which lead to more frequent reconfigurations of production systems or require higher flexibility. At the same time, many production systems have been in productive use for some time, so-called brownfield systems. Most of them do not have a Digital Twin, but would benefit from one, if available. However, the creation of a Digital Twin is a significant additional effort, due to the creation of the underlying models and the relations between them. Some promising approaches for the creation of domain-specific models already exist, which can be used for the creation of the unconnected parts of a Digital Twin. However, there are still few results for the creation of inter-domain relations, which cause problems in the creation of Digital Twins. This paper therefore presents a methodology for the automated reconstruction of functional relations as well as the separation of functionally related component groups of the plant and its software. For this purpose, the methodology imports the native PLC code via XML, extracts the relevant information from the code and enriches the resulting information model with explicit information about implicit relations in the code. Based on this, various elements of the PLC code are analyzed and the relationship of individual mechatronic components, that are available as signals, are examined and quantified. Thus, a part of the required relations for a Digital Twin is recognized automatically. The methodology and its benefits for the Digital Twin creation is presented and explained using a modular production system with several manufacturing stations as a proof-of-concept.
  BibTeX
  @conference{braun2022methodology, abstract = {The huge potential of the Digital Twin and its benefits in use cases such as virtual commissioning or reconfiguration planning for production systems is often described and well known. One reason that the usage of Digital Twins is becoming increasingly important are current trends, such as individualized mass production, which lead to more frequent reconfigurations of production systems or require higher flexibility. At the same time, many production systems have been in productive use for some time, so-called brownfield systems. Most of them do not have a Digital Twin, but would benefit from one, if available. However, the creation of a Digital Twin is a significant additional effort, due to the creation of the underlying models and the relations between them. Some promising approaches for the creation of domain-specific models already exist, which can be used for the creation of the unconnected parts of a Digital Twin. However, there are still few results for the creation of inter-domain relations, which cause problems in the creation of Digital Twins. This paper therefore presents a methodology for the automated reconstruction of functional relations as well as the separation of functionally related component groups of the plant and its software. For this purpose, the methodology imports the native PLC code via XML, extracts the relevant information from the code and enriches the resulting information model with explicit information about implicit relations in the code. Based on this, various elements of the PLC code are analyzed and the relationship of individual mechatronic components, that are available as signals, are examined and quantified. Thus, a part of the required relations for a Digital Twin is recognized automatically. The methodology and its benefits for the Digital Twin creation is presented and explained using a modular production system with several manufacturing stations as a proof-of-concept.}, author = {Braun, Dominik and Riedhammer, Michael and Jazdi, Nasser and Schlögl, Wolfgang and Weyrich, Michael}, booktitle = {55th CIRP Conference on Manufacturing Systems, 29. Juni – 1. Juli 2022, Lugano, Juni 2022}, doi = {10.1016/j.procir.2022.04.020}, title = {A methodology for the detection of functional relations of mechatronic components and assemblies in brownfield systems }, url = {https://doi.org/10.1016/j.procir.2022.04.020}, year = 2022 }
  Link
  https://doi.org/10.1016/j.procir.2022.04.020
7. D. Dittler, D. Braun, T. Müller, V. Stegmaier, N. Jazdi, and M. Weyrich, “A procedure for the derivation of project-specific intelligent Digital Twin implementations in industrial automation,” in EKA 2022 - Entwurf komplexer Automatisierungssysteme, 17. Fachtagung“, Magdeburg, Deutschland, Juni 2022, 2022.
  Abstract
  Digital Twins, which serve as virtual representations, are becoming increasingly important to meet the needs of future industrial automation. Digital Twins are mostly created for specific use cases, facing various requirements e.g. reliable intellectual property protection, interoperability, flexibility, or extendability during implementation. For this purpose, decisions regarding structure and technology have to be made before implementation. In this paper, we discuss relevant requirements based on a proposed procedure for the derivation of project-specific intelligent Digital Twin implementations. The influences and correlations of project requirements are discussed concerning the choice of intelligent Digital Twins implementation structure and technology. In addition, the paper outlines their advantages and disadvantages. The proposed procedure is exemplarily illustrated using an intelligent Digital Twin utilized for a modular offshore-platform producing green hydrogen and derivatives.
  BibTeX
  @conference{dittler2022procedure, abstract = {Digital Twins, which serve as virtual representations, are becoming increasingly important to meet the needs of future industrial automation. Digital Twins are mostly created for specific use cases, facing various requirements e.g. reliable intellectual property protection, interoperability, flexibility, or extendability during implementation. For this purpose, decisions regarding structure and technology have to be made before implementation. In this paper, we discuss relevant requirements based on a proposed procedure for the derivation of project-specific intelligent Digital Twin implementations. The influences and correlations of project requirements are discussed concerning the choice of intelligent Digital Twins implementation structure and technology. In addition, the paper outlines their advantages and disadvantages. The proposed procedure is exemplarily illustrated using an intelligent Digital Twin utilized for a modular offshore-platform producing green hydrogen and derivatives.}, author = {Dittler, Daniel and Braun, Dominik and Müller, Timo and Stegmaier, Valentin and Jazdi, Nasser and Weyrich, Michael}, booktitle = {EKA 2022 - Entwurf komplexer Automatisierungssysteme, 17. Fachtagung“, Magdeburg, Deutschland, Juni 2022}, title = {A procedure for the derivation of project-specific intelligent Digital Twin implementations in industrial automation }, url = {https://www.researchgate.net/publication/361743435_A_procedure_for_the_derivation_of_project-specific_intelligent_Digital_Twin_implementations_in_industrial_automation}, year = 2022 }
  Link
  https://www.researchgate.net/publication/361743435_A_procedure_for_the_derivation_of_project-specific_intelligent_Digital_Twin_implementations_in_industrial_automation
8. V. Stegmaier, D. Dittler, N. Jazdi, and M. Weyrich, “A structure of modelling depths in behavior models for Digital Twins,” in 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022, 2022.
  Abstract
  Behavior models in the Digital Twin are relevant to many use cases such as digital product development, virtual system optimization or virtual commissioning. However, such behavior models are structured in the literature according to different criteria and levels, which complicates the selection of the correct properties for specific use cases. One criterion that is discussed very differently is the modeling depth of behavior models. This paper presents different approaches to structure behavior models from literature and introduces a new concept with focus on the modeling depth. These levels of modeling depth, as well as the characteristics of the different modeling depths, are then illustrated using a representative industry scenario.
  BibTeX
  @conference{stegmaier2022structure, abstract = {Behavior models in the Digital Twin are relevant to many use cases such as digital product development, virtual system optimization or virtual commissioning. However, such behavior models are structured in the literature according to different criteria and levels, which complicates the selection of the correct properties for specific use cases. One criterion that is discussed very differently is the modeling depth of behavior models. This paper presents different approaches to structure behavior models from literature and introduces a new concept with focus on the modeling depth. These levels of modeling depth, as well as the characteristics of the different modeling depths, are then illustrated using a representative industry scenario.}, author = {Stegmaier, Valentin and Dittler, Daniel and Jazdi, Nasser and Weyrich, Michael}, booktitle = {27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022}, title = {A structure of modelling depths in behavior models for Digital Twins}, url = {https://www.researchgate.net/publication/360256481_A_structure_of_modelling_depths_in_behavior_models_for_Digital_Twins }, year = 2022 }
  Link
  https://www.researchgate.net/publication/360256481_A_structure_of_modelling_depths_in_behavior_models_for_Digital_Twins
9. V. Stegmaier, G. Ghasemi, N. Jazdi, and M. Weyrich, “An approach enabling Accuracy-as-a-Service for resistance-based sensors using intelligent Digital Twins,” in 55th CIRP Conference on Manufacturing Systems, Lugano, Switzerland, Juni 2022, 2022.
  Abstract
  A key performance indicator for sensors in production systems is their accuracy. In order to respond to the flexible requirements posed to production systems, there are currently two possibilities to realize the needed accuracy. Either the sensors can be changed frequently, so that the lowest still sufficient accuracy can always be achieved or the production system can be equipped directly with highly accurate sensors. These two options come with high costs, originating from the manual effort and the proportionality of accuracy and cost for most of the commonly used sensors. Industrially used resistance-based sensors such as pressure, force or temperature sensors represent a special case here, because their inaccuracy traces back to few major sources. To eliminate some of these sources or to decrease their impacts, instance-specific characteristics are used in an accuracy model provided by an intelligent Digital Twin. Using varying accuracy models provides different levels of accuracy. The presented concept provides the needed accuracy permanently or as a service for periods the production system needs the higher accuracy, called Accuracy-as-a-Service (AaaS), benefiting setup efficiency, costs and flexibility. To validate the presented concept, the proposed model is used for an analog pressure sensor in a fluidic test setup. The control unit of the system is provided with a standard model as well as a more accurate one. It is demonstrated in the paper how the usage of the individual model can improve the accuracy of a special sensor significantly by a factor of four.
  BibTeX
  @conference{stegmaier2022approach, abstract = {A key performance indicator for sensors in production systems is their accuracy. In order to respond to the flexible requirements posed to production systems, there are currently two possibilities to realize the needed accuracy. Either the sensors can be changed frequently, so that the lowest still sufficient accuracy can always be achieved or the production system can be equipped directly with highly accurate sensors. These two options come with high costs, originating from the manual effort and the proportionality of accuracy and cost for most of the commonly used sensors. Industrially used resistance-based sensors such as pressure, force or temperature sensors represent a special case here, because their inaccuracy traces back to few major sources. To eliminate some of these sources or to decrease their impacts, instance-specific characteristics are used in an accuracy model provided by an intelligent Digital Twin. Using varying accuracy models provides different levels of accuracy. The presented concept provides the needed accuracy permanently or as a service for periods the production system needs the higher accuracy, called Accuracy-as-a-Service (AaaS), benefiting setup efficiency, costs and flexibility. To validate the presented concept, the proposed model is used for an analog pressure sensor in a fluidic test setup. The control unit of the system is provided with a standard model as well as a more accurate one. It is demonstrated in the paper how the usage of the individual model can improve the accuracy of a special sensor significantly by a factor of four.}, author = {Stegmaier, Valentin and Ghasemi, Golsa and Jazdi, Nasser and Weyrich, Michael}, booktitle = {55th CIRP Conference on Manufacturing Systems, Lugano, Switzerland, Juni 2022}, title = {An approach enabling Accuracy-as-a-Service for resistance-based sensors using intelligent Digital Twins}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_An_Approach_Enabling_Accuracy_As_A_Service_For_Resistance_Based_Sensors_Using_Intelligent_Digital_Twins.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_An_Approach_Enabling_Accuracy_As_A_Service_For_Resistance_Based_Sensors_Using_Intelligent_Digital_Twins.pdf
10. N. Sahlab, N. Jazdi, and M. Weyrich, “An Overview on Designs and Applications of Context-Aware Automation Systems,” in 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022), Oktober 2022, 2022.
  Abstract
  Automation systems are increasingly being used in dynamic and various operating conditions. With higher flexibility demands, they need to promptly respond to surrounding dynamic changes by adapting their operation. Context information collected during runtime can be useful to enhance the system's adaptability. Context-aware systems represent a design paradigm for modeling and applying context in various applications such as decision-making. In order to address context for automation systems, a state-of-the-art assessment of existing approaches is necessary. Thus, the objective of this work is to provide an overview on the design and applications of context and context models for automation systems. A systematic literature review has been conducted, the results of which are represented as a knowledge graph.
  BibTeX
  @conference{sahlab2022overview, abstract = {Automation systems are increasingly being used in dynamic and various operating conditions. With higher flexibility demands, they need to promptly respond to surrounding dynamic changes by adapting their operation. Context information collected during runtime can be useful to enhance the system's adaptability. Context-aware systems represent a design paradigm for modeling and applying context in various applications such as decision-making. In order to address context for automation systems, a state-of-the-art assessment of existing approaches is necessary. Thus, the objective of this work is to provide an overview on the design and applications of context and context models for automation systems. A systematic literature review has been conducted, the results of which are represented as a knowledge graph.}, author = {Sahlab, Nada and Jazdi, Nasser and Weyrich, Michael}, booktitle = {26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022), Oktober 2022}, title = {An Overview on Designs and Applications of Context-Aware Automation Systems }, url = {https://www.sciencedirect.com/science/article/pii/S1877050922011887 }, year = 2022 }
  Link
  https://www.sciencedirect.com/science/article/pii/S1877050922011887
11. V. Stegmaier, W. Schaaf, N. Jazdi, and M. Weyrich, “Anwendungsfälle und Ansatz zur Erstellung des Digitalen Zwillings aus Sicht eines Komponentenherstellers,” Automation 2022 At: Baden-Baden, Deutschland, Juni 2022, 2022.
  Abstract
  Neben Herausforderungen bei der Erstellung bieten sich Komponentenherstellern durch den Digitalen Zwilling viele potenzielle Mehrwerte. Auf die Anwendungsfälle, um die entsprechenden Mehrwerte zu realisieren, soll im Folgenden näher eingegangen werden. Für eine effiziente Erstellung aus Sicht des Komponentenherstellers wird ein Konzept präsentiert. Dieses nutzt bestehende Informationen und erstellt häufig fehlende Verhaltensmodelle automatisiert. Zur Veranschaulichung potenzieller Mehrwerte der Verhaltensmodelle wird der Luftverbrauch eines Vakuum-Greifsystems beispielhaft analysiert.
  BibTeX
  @article{stegmaier2022anwendungsflle, abstract = {Neben Herausforderungen bei der Erstellung bieten sich Komponentenherstellern durch den Digitalen Zwilling viele potenzielle Mehrwerte. Auf die Anwendungsfälle, um die entsprechenden Mehrwerte zu realisieren, soll im Folgenden näher eingegangen werden. Für eine effiziente Erstellung aus Sicht des Komponentenherstellers wird ein Konzept präsentiert. Dieses nutzt bestehende Informationen und erstellt häufig fehlende Verhaltensmodelle automatisiert. Zur Veranschaulichung potenzieller Mehrwerte der Verhaltensmodelle wird der Luftverbrauch eines Vakuum-Greifsystems beispielhaft analysiert. }, author = {Stegmaier, Valentin and Schaaf, Walter and Jazdi, Nasser and Weyrich, Michael}, journal = {Automation 2022 At: Baden-Baden, Deutschland, Juni 2022}, title = {Anwendungsfälle und Ansatz zur Erstellung des Digitalen Zwillings aus Sicht eines Komponentenherstellers}, url = {https://www.researchgate.net/publication/361745809_Anwendungsfalle_und_Ansatz_zur_Erstellung_des_Digitalen_Zwillings_aus_Sicht_eines_Komponentenherstellers}, year = 2022 }
  Link
  https://www.researchgate.net/publication/361745809_Anwendungsfalle_und_Ansatz_zur_Erstellung_des_Digitalen_Zwillings_aus_Sicht_eines_Komponentenherstellers
12. D. Dittler, T. Müller, V. Stegmaier, N. Jazdi, and M. Weyrich, “Anwendungsoptimierte Modelladaption des Digitalen Zwillings eines modularen Produktionssystems während der Betriebsphase,” in Automation 2022 At: Baden-Baden, Deutschland, Juni, 2022, 2022.
  Abstract
  Während der Engineering- und Betriebsphase modularer Produktionssysteme entstehen zunehmend Modelle. Der Digitale Zwilling kann diese Modelle für Anwendungen wie die virtuelle Inbetriebnahme, Optimierung, Prognose oder betriebsparallele Simulation zur Verfügung stellen. Durch unvorhersehbare Veränderungen in der Betriebsphase verschlechtert sich die Realitätsnähe der Modelle des Digitalen Zwillings, bspw. aufgrund von Anforderungsänderungen, neuen Anwendungen oder sich ändernden Umwelteinflüssen wie etwa Temperatur- oder Druckschwankungen und eine Modelladaption wird notwendig. Die Adaption der Modelle des Digitalen Zwillings weist einige Herausforderungen auf, die in diesem Beitrag aufgezeigt werden. Um diesen Herausforderungen zu begegnen und dem Adaptionsaufwand während der Betriebsphase entgegenzuwirken, wird ein Konzept präsentiert, welches es dem Digitalen Zwilling ermöglicht, die Abweichung zur Realität zu erkennen und sich durch eine anschließende Modelladaption realitätsnah zu halten.
  BibTeX
  @conference{dittler2022automation, abstract = {Während der Engineering- und Betriebsphase modularer Produktionssysteme entstehen zunehmend Modelle. Der Digitale Zwilling kann diese Modelle für Anwendungen wie die virtuelle Inbetriebnahme, Optimierung, Prognose oder betriebsparallele Simulation zur Verfügung stellen. Durch unvorhersehbare Veränderungen in der Betriebsphase verschlechtert sich die Realitätsnähe der Modelle des Digitalen Zwillings, bspw. aufgrund von Anforderungsänderungen, neuen Anwendungen oder sich ändernden Umwelteinflüssen wie etwa Temperatur- oder Druckschwankungen und eine Modelladaption wird notwendig. Die Adaption der Modelle des Digitalen Zwillings weist einige Herausforderungen auf, die in diesem Beitrag aufgezeigt werden. Um diesen Herausforderungen zu begegnen und dem Adaptionsaufwand während der Betriebsphase entgegenzuwirken, wird ein Konzept präsentiert, welches es dem Digitalen Zwilling ermöglicht, die Abweichung zur Realität zu erkennen und sich durch eine anschließende Modelladaption realitätsnah zu halten.}, author = {Dittler, Daniel and Müller, Timo and Stegmaier, Valentin and Jazdi, Nasser and Weyrich, Michael}, booktitle = {Automation 2022 At: Baden-Baden, Deutschland, Juni, 2022}, doi = {10.51202/9783181023990-545}, title = {Anwendungsoptimierte Modelladaption des Digitalen Zwillings eines modularen Produktionssystems während der Betriebsphase }, url = {https://www.researchgate.net/publication/361749638_Anwendungsoptimierte_Modelladaption_des_Digitalen_Zwillings_eines_modularen_Produktionssystems_wahrend_der_Betriebsphase}, year = 2022 }
  Link
  https://www.researchgate.net/publication/361749638_Anwendungsoptimierte_Modelladaption_des_Digitalen_Zwillings_eines_modularen_Produktionssystems_wahrend_der_Betriebsphase
13. T. Müller, S. Kamm, A. Löcklin, D. White, M. Mellinger, N. Jazdi, and M. Weyrich, “Architecture and knowledge modelling for self-organized reconfiguration management of cyber-physical production systems,” International Journal of Computer Integrated Manufacturing, September, 2022, 2022.
  Abstract
  The demand for reconfigurations of production systems is increasing, driven by shorter innovation and product life cycles and economic volatility. Another trend in the domain of industrial automation is the emergence of cyber-physical production systems, which offer promising potentials, for example, self-organization capabilities. A suitable cyber-physical production system architecture that incorporates knowledge modelling and management concerns, plus a reconfiguration management methodology, is crucial for realizing self-organized reconfiguration management. In this paper, first reference architectures, architectural patterns, and basic principles, as well as knowledge modelling and management approaches, are discussed in general. Afterwards, these are examined concerning the reconfiguration management use case focusing on UML/XML-based and ontology-based approaches. A novel approach comprising a multi-agent system and the MAPE-K concept for reconfiguration management is presented. In addition, the approach contains a service-oriented architecture for a deterministic plant control within a layered architecture. The knowledge modelling is realized through a UML information model, which can be integrated into the system utilizing XML files. Furthermore, the provided tool support is described. It enables a user to describe system components in an effort-reduced manner and conform to the schema defined by the information model and its restrictions via a GUI.
  BibTeX
  @article{muller2022architecture, abstract = {The demand for reconfigurations of production systems is increasing, driven by shorter innovation and product life cycles and economic volatility. Another trend in the domain of industrial automation is the emergence of cyber-physical production systems, which offer promising potentials, for example, self-organization capabilities. A suitable cyber-physical production system architecture that incorporates knowledge modelling and management concerns, plus a reconfiguration management methodology, is crucial for realizing self-organized reconfiguration management. In this paper, first reference architectures, architectural patterns, and basic principles, as well as knowledge modelling and management approaches, are discussed in general. Afterwards, these are examined concerning the reconfiguration management use case focusing on UML/XML-based and ontology-based approaches. A novel approach comprising a multi-agent system and the MAPE-K concept for reconfiguration management is presented. In addition, the approach contains a service-oriented architecture for a deterministic plant control within a layered architecture. The knowledge modelling is realized through a UML information model, which can be integrated into the system utilizing XML files. Furthermore, the provided tool support is described. It enables a user to describe system components in an effort-reduced manner and conform to the schema defined by the information model and its restrictions via a GUI. }, author = {Müller, Timo and Kamm, Simon and Löcklin, Andreas and White, Dustin and Mellinger, Marius and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1080/0951192X.2022.2121425}, journal = {International Journal of Computer Integrated Manufacturing, September, 2022}, title = {Architecture and knowledge modelling for self-organized reconfiguration management of cyber-physical production systems}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Architecture_and_knowledge_modelling_for_self-organized_reconfiguration_management_of_cyber-physical_production_systems.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Architecture_and_knowledge_modelling_for_self-organized_reconfiguration_management_of_cyber-physical_production_systems.pdf
14. T. Müller, N. Sahlab, S. Kamm, D. Braun, C. Köhler, N. Jazdi, and M. Weyrich, “Context-enriched modeling using Knowledge Graphs for intelligent Digital Twins of Production Systems,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022, 2022.
  - Abstract
  - BibTeX
  Abstract
  Current industrial automation systems are facing increasing dynamics. Thus, acquiring and managing heterogeneous data within the Digital Twin to enable decision making is necessary although challenging. Knowledge Graphs unify and relate data, enabling the derivation of new insights. In this contribution, an approach for context-enriched modeling of cyber-physical production systems is proposed, in order to realize a Knowledge Graph enhanced intelligent Digital Twin further considering the context. Therefore, the modeling approach of the Knowledge Graph considers context and serves as a base for the graph embeddings to gain further knowledge about the production system. This knowledge is used within the architecture of the intelligent Digital Twin. The resulting benefits, i.e. diverse manifestations of an improved decision making, are highlighted by the use case of self-organized reconfiguration management.
  BibTeX
  @conference{muller2022contextenriched, abstract = {Current industrial automation systems are facing increasing dynamics. Thus, acquiring and managing heterogeneous data within the Digital Twin to enable decision making is necessary although challenging. Knowledge Graphs unify and relate data, enabling the derivation of new insights. In this contribution, an approach for context-enriched modeling of cyber-physical production systems is proposed, in order to realize a Knowledge Graph enhanced intelligent Digital Twin further considering the context. Therefore, the modeling approach of the Knowledge Graph considers context and serves as a base for the graph embeddings to gain further knowledge about the production system. This knowledge is used within the architecture of the intelligent Digital Twin. The resulting benefits, i.e. diverse manifestations of an improved decision making, are highlighted by the use case of self-organized reconfiguration management. }, author = {Müller, Timo and Sahlab, Nada and Kamm, Simon and Braun, Dominik and Köhler, Christian and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022}, title = {Context-enriched modeling using Knowledge Graphs for intelligent Digital Twins of Production Systems }, year = 2022 }
15. H. Vietz, A. Löcklin, H. Ben Haj Ammar, and M. Weyrich, “Deep learning-based 5G indoor positioning in a manufacturing environment,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022, 2022.
  - Abstract
  - BibTeX
  Abstract
  Indoor positioning systems are an enabling technology for many current developments in the manufacturing field like digital twins and robot fleet management. Utilizing 5G for positioning promises high accuracy, reliability, and costefficiency due to shared hardware usage for communication and positioning. Which positioning technique suits 5G-bases positioning best for manufacturing is still an open research question. This paper presents a deep learning approach for 5Gbased positioning. The first results of our research work in progress obtained at the research factory ARENA 2036 indicate a positioning accuracy in the centimeter range.
  BibTeX
  @conference{vietz2022learningbased, abstract = {Indoor positioning systems are an enabling technology for many current developments in the manufacturing field like digital twins and robot fleet management. Utilizing 5G for positioning promises high accuracy, reliability, and costefficiency due to shared hardware usage for communication and positioning. Which positioning technique suits 5G-bases positioning best for manufacturing is still an open research question. This paper presents a deep learning approach for 5Gbased positioning. The first results of our research work in progress obtained at the research factory ARENA 2036 indicate a positioning accuracy in the centimeter range.}, author = {Vietz, Hannes and Löcklin, Andreas and Ben Haj Ammar, Hamza and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022 }, title = {Deep learning-based 5G indoor positioning in a manufacturing environment}, year = 2022 }
16. D. Dittler, P. Häbig, G. Demirel, N. Mößner, T. Müller, N. Jazdi, K. Hufendiek, and M. Weyrich, “Digitaler Zwilling für eine modulare Offshore-Plattform: Effizienzsteigerung grüner Power-to-X-Produktionsprozesse,” atp magazin, Vol. 63, No. 6-7, pp. 72-80, June 2022, 2022.
  Abstract
  Die Produktion von Wasserstoff und Folgeprodukten unter Nutzung erneuerbarer Energien gilt als großer Hoffnungsträger für das Erreichen einer Klimaneutralität. Im Rahmen des Leitprojekts H2Mare soll der Betrieb einer Offshore-Plattform für Power-to-X-Produktionsprozesse erforscht und erprobt werden. Im vorliegenden Beitrag wird zunächst das Projektkonzept einer modularen Offshore-Plattform skizziert. Anschließend werden mit dem Digitalen Zwilling und dem System zur optimalen Betriebsführung zwei Forschungsansätze präsentiert, die zur Effizienzsteigerung dieser Produktionsprozesse beitragen sollen.
  BibTeX
  @article{noauthororeditor2022digitaler, abstract = {Die Produktion von Wasserstoff und Folgeprodukten unter Nutzung erneuerbarer Energien gilt als großer Hoffnungsträger für das Erreichen einer Klimaneutralität. Im Rahmen des Leitprojekts H2Mare soll der Betrieb einer Offshore-Plattform für Power-to-X-Produktionsprozesse erforscht und erprobt werden. Im vorliegenden Beitrag wird zunächst das Projektkonzept einer modularen Offshore-Plattform skizziert. Anschließend werden mit dem Digitalen Zwilling und dem System zur optimalen Betriebsführung zwei Forschungsansätze präsentiert, die zur Effizienzsteigerung dieser Produktionsprozesse beitragen sollen.}, author = {Dittler, Daniel and Häbig, Pascal and Demirel, Gökhan and Mößner, Nikola and Müller, Timo and Jazdi, Nasser and Hufendiek, Kai and Weyrich, Michael}, journal = {atp magazin, Vol. 63, No. 6-7, pp. 72-80, June 2022}, title = {Digitaler Zwilling für eine modulare Offshore-Plattform: Effizienzsteigerung grüner Power-to-X-Produktionsprozesse }, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Digitaler_Zwilling_fuer_eine_modulare_Offshore-Plattform.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Digitaler_Zwilling_fuer_eine_modulare_Offshore-Plattform.pdf
17. V. Stegmaier, W. Schaaf, N. Jazdi, and M. Weyrich, “Efficient creation of behavior models for Digital Twins exemplified for vacuum gripping systems,” in 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022, 2022.
  Abstract
  The use of Digital Twins is versatile and offers a wide range of advantages. However, the creation is often a manual process and therefore very time-consuming and cost-intensive. The creation of behavior models stands out as particularly time-consuming. Therefore, this paper deals with the creation of Digital Twins from the perspective of an industrial component manufacturer, with a particular focus on the creation of behavior models. An automatic approach based on libraries is presented. This concept, in particular for the creation of behavior models, is validated in an industry-relevant application scenario and compared with the manual creation process.
  BibTeX
  @conference{stegmaier2022efficient, abstract = {The use of Digital Twins is versatile and offers a wide range of advantages. However, the creation is often a manual process and therefore very time-consuming and cost-intensive. The creation of behavior models stands out as particularly time-consuming. Therefore, this paper deals with the creation of Digital Twins from the perspective of an industrial component manufacturer, with a particular focus on the creation of behavior models. An automatic approach based on libraries is presented. This concept, in particular for the creation of behavior models, is validated in an industry-relevant application scenario and compared with the manual creation process.}, author = {Stegmaier, Valentin and Schaaf, Walter and Jazdi, Nasser and Weyrich, Michael}, booktitle = {27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022}, title = {Efficient creation of behavior models for Digital Twins exemplified for vacuum gripping systems}, url = {https://www.researchgate.net/publication/360312342_Efficient_creation_of_behavior_models_for_Digital_Twins_exemplified_for_vacuum_gripping_systems }, year = 2022 }
  Link
  https://www.researchgate.net/publication/360312342_Efficient_creation_of_behavior_models_for_Digital_Twins_exemplified_for_vacuum_gripping_systems
18. N. Sahlab, D. Braun, C. Köhler, N. Jazdi, and M. Weyrich, “Extending the Intelligent Digital Twin with a context modeling service: A decision support use case,” 55th CIRP Conference on Manufacturing Systems, 29. Juni – 1. Juli 2022, Lugano, 2022.
  Abstract
  The huge potential of the Digital Twin and its benefits in use cases such as virtual commissioning or reconfiguration planning for production systems is often described and well known. One reason that the usage of Digital Twins is becoming increasingly important are current trends, such as individualized mass production, which lead to more frequent reconfigurations of production systems or require higher flexibility. At the same time, many production systems have been in productive use for some time, so-called brownfield systems. Most of them do not have a Digital Twin, but would benefit from one, if available. However, the creation of a Digital Twin is a significant additional effort, due to the creation of the underlying models and the relations between them. Some promising approaches for the creation of domain-specific models already exist, which can be used for the creation of the unconnected parts of a Digital Twin. However, there are still few results for the creation of inter-domain relations, which cause problems in the creation of Digital Twins. This paper therefore presents a methodology for the automated reconstruction of functional relations as well as the separation of functionally related component groups of the plant and its software. For this purpose, the methodology imports the native PLC code via XML, extracts the relevant information from the code and enriches the resulting information model with explicit information about implicit relations in the code. Based on this, various elements of the PLC code are analyzed and the relationship of individual mechatronic components, that are available as signals, are examined and quantified. Thus, a part of the required relations for a Digital Twin is recognized automatically. The methodology and its benefits for the Digital Twin creation is presented and explained using a modular production system with several manufacturing stations as a proof-of-concept.
  BibTeX
  @article{sahlab2022extending, abstract = {The huge potential of the Digital Twin and its benefits in use cases such as virtual commissioning or reconfiguration planning for production systems is often described and well known. One reason that the usage of Digital Twins is becoming increasingly important are current trends, such as individualized mass production, which lead to more frequent reconfigurations of production systems or require higher flexibility. At the same time, many production systems have been in productive use for some time, so-called brownfield systems. Most of them do not have a Digital Twin, but would benefit from one, if available. However, the creation of a Digital Twin is a significant additional effort, due to the creation of the underlying models and the relations between them. Some promising approaches for the creation of domain-specific models already exist, which can be used for the creation of the unconnected parts of a Digital Twin. However, there are still few results for the creation of inter-domain relations, which cause problems in the creation of Digital Twins. This paper therefore presents a methodology for the automated reconstruction of functional relations as well as the separation of functionally related component groups of the plant and its software. For this purpose, the methodology imports the native PLC code via XML, extracts the relevant information from the code and enriches the resulting information model with explicit information about implicit relations in the code. Based on this, various elements of the PLC code are analyzed and the relationship of individual mechatronic components, that are available as signals, are examined and quantified. Thus, a part of the required relations for a Digital Twin is recognized automatically. The methodology and its benefits for the Digital Twin creation is presented and explained using a modular production system with several manufacturing stations as a proof-of-concept.}, author = {Sahlab, Nada and Braun, Dominik and Köhler, Christian and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.procir.2022.05.009}, journal = {55th CIRP Conference on Manufacturing Systems, 29. Juni – 1. Juli 2022, Lugano}, title = {Extending the Intelligent Digital Twin with a context modeling service: A decision support use case }, url = {https://doi.org/10.1016/j.procir.2022.04.020}, year = 2022 }
  Link
  https://doi.org/10.1016/j.procir.2022.04.020
19. N. Sahlab, I. Sonji, and M. Weyrich, “Graph-based association rule learning for context-based health monitoring to enable user-centered assistance,” Artificial Intelligence in Medicine, November 2022, 2022.
  Abstract
  In response to the demographic change and the accompanying challenges for effective healthcare, approaches to enable using advancements of digitalization and IoT infrastructures as well as AI methods to deliver results in the field of personalized health assistance are necessary. In our research, we aim at enabling user-centered assistance with the help of networked sensors and Health Assistance Systems as well as learning methods based on connected graph data that model the shared system, user, and environmental context. In particular, this paper demonstrates a graph-based dynamic context model for a medication assistance system and presents an association rule learning method using Apriori algorithm to learn correlations between user vitals, activities as well as medication intake behavior. An application scenario for context-based heart rate monitoring is consequently presented as proof of concept, where associated contextual elements from the modeled context relating surges in monitored heart rate to environmental and user activity are shown.
  BibTeX
  @article{sahlab2022graphbased, abstract = {In response to the demographic change and the accompanying challenges for effective healthcare, approaches to enable using advancements of digitalization and IoT infrastructures as well as AI methods to deliver results in the field of personalized health assistance are necessary. In our research, we aim at enabling user-centered assistance with the help of networked sensors and Health Assistance Systems as well as learning methods based on connected graph data that model the shared system, user, and environmental context. In particular, this paper demonstrates a graph-based dynamic context model for a medication assistance system and presents an association rule learning method using Apriori algorithm to learn correlations between user vitals, activities as well as medication intake behavior. An application scenario for context-based heart rate monitoring is consequently presented as proof of concept, where associated contextual elements from the modeled context relating surges in monitored heart rate to environmental and user activity are shown. }, author = {Sahlab, Nada and Sonji, Iman and Weyrich, Michael}, doi = {10.1016/j.artmed.2022.102455}, journal = {Artificial Intelligence in Medicine, November 2022}, title = {Graph-based association rule learning for context-based health monitoring to enable user-centered assistance}, url = {https://www.sciencedirect.com/science/article/pii/S093336572200207X?via%3Dihub}, year = 2022 }
  Link
  https://www.sciencedirect.com/science/article/pii/S093336572200207X?via%3Dihub
20. B. Maschler, T. Hasan, C. Bitter, H. Vietz, T. Meisen, and M. Weyrich, “Industrielles Transfer-Lernen - Von der Wissenschaft in die Praxis,” atp-Magazin, August 2022, pp.86-93, Juni 2022, 2022.
  Abstract
  Trotz hoher Lösungspotentiale des maschinellen Lernens für gängige Probleme der Automatisierungstechnik, finden sich in der Praxis wenig Anwendungsbeispiele. Um der Ursache hierfür auf den Grund zu gehen, zeigen die Autoren anhand von vier beispielhaften Anwendungsfällen die Hürden für konventionelles maschinelles Lernen auf und benennen Lösungsansätze mittels industriellem Transfer-Lernen. Zum großflächigen Einsatz derartiger Ansätze, fehlt es an Voraussetzungen, deren Schaffung jedoch anders als beim konventionellen maschinellen Lernen grundsätzlich möglich ist. Der Artikel schließt mit einer Betrachtung dieser Voraussetzungen und macht Vorschläge, wie sie zu erfüllen sind.
  BibTeX
  @article{maschler2022industrielles, abstract = {Trotz hoher Lösungspotentiale des maschinellen Lernens für gängige Probleme der Automatisierungstechnik, finden sich in der Praxis wenig Anwendungsbeispiele. Um der Ursache hierfür auf den Grund zu gehen, zeigen die Autoren anhand von vier beispielhaften Anwendungsfällen die Hürden für konventionelles maschinelles Lernen auf und benennen Lösungsansätze mittels industriellem Transfer-Lernen. Zum großflächigen Einsatz derartiger Ansätze, fehlt es an Voraussetzungen, deren Schaffung jedoch anders als beim konventionellen maschinellen Lernen grundsätzlich möglich ist. Der Artikel schließt mit einer Betrachtung dieser Voraussetzungen und macht Vorschläge, wie sie zu erfüllen sind.}, author = {Maschler, Benjamin and Hasan, Tercan and Bitter, Christian and Vietz, Hannes and Meisen, Tobias and Weyrich, Michael}, doi = {10.17560/atp.v63i9.2588}, journal = {atp-Magazin, August 2022, pp.86-93, Juni 2022}, title = {Industrielles Transfer-Lernen - Von der Wissenschaft in die Praxis}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/ 2022_Industrielles_Transfer-Lernen-PREPRINT.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/ 2022_Industrielles_Transfer-Lernen-PREPRINT.pdf
21. B. Maschler, H. Vietz, H. Tercan, C. Bitter, T. Meisen, and M. Weyrich, “Insights and Example Use Cases on Industrial Transfer Learning,” in 55th CIRP Conference on Manufacturing Systems (CIRP CMS), Lugano, Switzerland, 29. Juni 2022, 2022.
  Abstract
  Despite the high solution potential of machine learning for common problems in automation technology, there are only few examples of its application in real-world manufacturing practice. In order to find the reason for this phenomenon, the authors identify the hurdles for conventional machine learning using four exemplary use cases namely self-learning robots, wear prediction, visual object detection, and predictive quality in manufacturing. While these use-cases differ in principle, the problems engineers face when using conventional machine learning approaches to solve them are related, such as the lack of manifold training data or high dynamics of industrial processes. The authors showcase that utilizing deep transfer learning and continual learning approaches in the industrial context – subsumed under the term industrial transfer learning – can overcome these hurdles. Even for industrial transfer learning, there is a deficiency regarding preconditions for the large-scale deployment of such approaches, but unlike in conventional machine learning, it is principally possible to establish those. The article concludes with a discussion of these prerequisites and makes suggestions as to how they could be fulfilled.
  BibTeX
  @conference{maschler2022insights, abstract = {Despite the high solution potential of machine learning for common problems in automation technology, there are only few examples of its application in real-world manufacturing practice. In order to find the reason for this phenomenon, the authors identify the hurdles for conventional machine learning using four exemplary use cases namely self-learning robots, wear prediction, visual object detection, and predictive quality in manufacturing. While these use-cases differ in principle, the problems engineers face when using conventional machine learning approaches to solve them are related, such as the lack of manifold training data or high dynamics of industrial processes. The authors showcase that utilizing deep transfer learning and continual learning approaches in the industrial context – subsumed under the term industrial transfer learning – can overcome these hurdles. Even for industrial transfer learning, there is a deficiency regarding preconditions for the large-scale deployment of such approaches, but unlike in conventional machine learning, it is principally possible to establish those. The article concludes with a discussion of these prerequisites and makes suggestions as to how they could be fulfilled.}, author = {Maschler, Benjamin and Vietz, Hannes and Tercan, Hasan and Bitter, Christian and Meisen, Tobias and Weyrich, Michael}, booktitle = {55th CIRP Conference on Manufacturing Systems (CIRP CMS), Lugano, Switzerland, 29. Juni 2022}, doi = {10.1016/j.procir.2022.05.017}, title = {Insights and Example Use Cases on Industrial Transfer Learning}, url = {https://doi.org/10.1016/j.procir.2022.05.017 }, year = 2022 }
  Link
  https://doi.org/10.1016/j.procir.2022.05.017
22. T. Müller, B. Maschler, D. Dittler, N. Jazdi, and M. Weyrich, “Intelligent Exploration of Solution Spaces Exemplified by Industrial Reconfiguration Management,” Jul. 2022.
  - BibTeX
  BibTeX
  @article{unknown, author = {Müller, Timo and Maschler, Benjamin and Dittler, Daniel and Jazdi, Nasser and Weyrich, Michael}, doi = {10.48550/arXiv.2207.01693}, month = {07}, title = {Intelligent Exploration of Solution Spaces Exemplified by Industrial Reconfiguration Management}, year = 2022 }
23. M. Müller, T. Jung, N. Jazdi, and M. Weyrich, “Safeguarding autonomous systems: emerging approaches, assumptions and metrics – a systematic literature review,” 11th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes, 29 July 2022, 2022.
  Abstract
  Autonomous systems gain more and more interest in research and society. However, they bring new challenges in safeguarding these systems. This contribution orders those new challenges and provides an overview of already existing concepts and approaches to solve those challenges of safeguarding autonomous systems. Moreover, existing metrics for safeguarding of autonomous systems are systematically reviewed. The presented concepts and approaches are of different domains, namely, ground, nautical and aerial vehicles, industrial robots and smart manufacturing, and medical and healthcare. Finally, the concepts and approaches are discussed concerning the following points: Main ideas, parallels existing in different domains, which ideas can be transferred from one domain to another, which high-level tasks were adressed and which assumptions were made.
  BibTeX
  @article{muller2022safeguarding, abstract = {Autonomous systems gain more and more interest in research and society. However, they bring new challenges in safeguarding these systems. This contribution orders those new challenges and provides an overview of already existing concepts and approaches to solve those challenges of safeguarding autonomous systems. Moreover, existing metrics for safeguarding of autonomous systems are systematically reviewed. The presented concepts and approaches are of different domains, namely, ground, nautical and aerial vehicles, industrial robots and smart manufacturing, and medical and healthcare. Finally, the concepts and approaches are discussed concerning the following points: Main ideas, parallels existing in different domains, which ideas can be transferred from one domain to another, which high-level tasks were adressed and which assumptions were made. }, author = {Müller, Manuel and Jung, Tobias and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.ifacol.2022.07.216}, journal = {11th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes, 29 July 2022}, title = {Safeguarding autonomous systems: emerging approaches, assumptions and metrics – a systematic literature review}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Safeguarding_autonomous_systems_emerging_approaches_assumptions_and_metricsa_systematic_literature_review.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Safeguarding_autonomous_systems_emerging_approaches_assumptions_and_metricsa_systematic_literature_review.pdf

Teaching

Lecturer Module Automatisierungstechnik I
Lecturer Module Automatisierungstechnik II
Lecturer Module Grundlagen der Softwaresysteme
Lecturer Module Technologien und Methoden der Softwaresysteme I
Lecturer Module Technologien und Methoden der Softwaresysteme II
Lecturer Module Industrial Automation Systems

Lecturer Module Praktische Übungen im Labor Automatisierungstechnik
Lecturer Module Fachpraktikum Softwaretechnik
Lecturer Module Fachpraktikum Einführung in die Programmierung von Mikrocontrollern
Lecturer Module Grundlagenpraktikum
Lecturer Module Laboratory Course Industrial Automation

Prof. Weyrich studied electrical engineering, specialising at the University of Applied Science Saarbrücken, University of Westminster (London, U.K.) and at the Ruhr-University Bochum, focussing on automation technology.
Thereafter, he worked as a Research Assistant with Prof. Dr.-Ing. Paul Drews of the European Centre of Mechatronics and was awarded a doctoral degree in 1999 from the RWTH Aachen.

Prof. Weyrich worked with Daimler AG for eight years, where he assumed the leadership of the “End-to-End Process Flexible Manufacturing” project and later had a technical management function in the “CAx Process Chain – Production” of the Information Technology Management division. From 2004 onward, he was the head of “IT for Engineering” at DaimlerChrysler Research and Technology Bangalore (India).
After his return to Germany, he joined Siemens AG as department leader with direct report to the Business Unit Head of Motion Control in Erlangen for 2 years, focussing on innovative technologies.

In 2009, he was appointed as Professor for the Chair of Automation in Manufacturing at the University of Siegen and as Director of the Automotive Centre Südwestfalen.
Prof. Weyrich assumed the role of Director of the Institute of Industrial Automation and Software Engineering at the University of Stuttgart in 2013.

He is very interested in research in cyber physical systems for industrial application. He has published over 100 papers and is very active in research and is a member of the Board of the German Engineering foundation VDI/VDE GMA. Additionally, he is an appointed reviewer for the European Commission, the German Research Foundation, DFG and a number of other institutions.

Further attributes

Accredited Expert with the DFG, European Commission, DAAD, AiF, project executing organisation of the BMWi und BMBF
Member of the Advisory Board of the VDI/VDE-Gesellschaft für Mess- und Automatisierungstechnik (GMA)
Chairman of the VDI/VDE professional committee 7.25 “Testen vernetzter Systeme für die Industrie 4.0”
Chair of the Subcommittee on Internet and Information Technologies in Factory Automation of the IEEE-IES TC on Factory Automation
Member of the IEEE-IES Technical Committee on Industrial Agents
Advisor for the Journal “Automatisierungstechnische Praxis” (atp edition)
Member of the Programme Committee of the following Conferences:
- IEEE International Conference on Emerging Technologies and Factory
- VDI/VDE Automation scientific forum
- VDI/VDE scientific forum “Industrie 4.0”
- Mates – Multiagent System Technologies, in cooperation with the SIG on Distributed Artificial Intelligence of the German Computer Society GI
- as well as numerous other international conferences and journals

Presentations

Find here the Presentations of Prof. Weyrich.

Interviews

08.07.2018

Datengetriebene Prozesse richtig bewerten

– Prof. Michael Weyrich in den VDI-Nachrichten zu Industrie 4.0 in der Produktion –

Wie die Qualität von Software in der Produktion sichergestellt werden kann, erklären drei Experten anlässlich des VDI-Kongresses Automation 2018.

Prof. Michael Weyrich, Prof. Birgit Vogel-Heuser und Dr. Kurt D. Bettenhausen diskutierten auf dem VDI-Kongress Automation am 3. und 4. Juli in Baden-Baden über relevante Kennzahlen (KPI) für Industrie 4.0. Mehr...

13.03.2017

Michael Weyrich

Contact

Publications

2025

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

BibTeX

Link

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

Abstract

BibTeX

2024

Abstract

BibTeX

BibTeX

Abstract

BibTeX

Link

Abstract

BibTeX

Link

BibTeX

Abstract

BibTeX

Link

BibTeX

Link

BibTeX

Abstract

BibTeX

Abstract