Position within the page tree

Andrey Morozov

Jun.-Prof. Dr.-Ing.

Junior professorship
Institute of Industrial Automation and Software Engineering

Contact

+49 711 685 67312
+49 711 685 67302
Email

Pfaffenwaldring 47
70550 Stuttgart
Germany
Room: 2.139

Publications

Journals and Conferences :

2024
1. G. Siedel, E. Gupta, and A. Morozov, “A practical approach to evaluating the adversarial distance for machine learning classifiers.” 2024.
  - BibTeX
  - Link
  BibTeX
  @misc{siedel2024practicalapproachevaluatingadversarial, archiveprefix = {arXiv}, author = {Siedel, Georg and Gupta, Ekagra and Morozov, Andrey}, eprint = {2409.03598}, primaryclass = {cs.LG}, title = {A practical approach to evaluating the adversarial distance for machine learning classifiers}, url = {https://arxiv.org/abs/2409.03598}, year = 2024 }
  Link
  https://arxiv.org/abs/2409.03598
2. P. Grimmeisen, F. Sautter, and A. Morozov, “Concept: Dynamic Risk Assessment for AI-Controlled Robotic Systems.” 2024.
  - BibTeX
  - Link
  BibTeX
  @misc{grimmeisen2024conceptdynamicriskassessment, archiveprefix = {arXiv}, author = {Grimmeisen, Philipp and Sautter, Friedrich and Morozov, Andrey}, eprint = {2401.14147}, primaryclass = {cs.RO}, title = {Concept: Dynamic Risk Assessment for AI-Controlled Robotic Systems}, url = {https://arxiv.org/abs/2401.14147}, year = 2024 }
  Link
  https://arxiv.org/abs/2401.14147
3. V. Naik, T. Fabarisov, and A. Morozov, “Machine Learning Based Search for Access Points in Anomaly Detection Model,” 2024.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Naik, Vishnu and Fabarisov, Tagir and Morozov, Andrey}, doi = {10.1115/IMECE2023-113438}, month = {02}, title = {Machine Learning Based Search for Access Points in Anomaly Detection Model}, year = 2024 }
4. Y. Ma, J. Liu, I. Mamaev, and A. Morozov, “Multimodal Failure Prediction for Vision-based Manipulation Tasks with Camera Faults,” 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2951–2957, 2024.
  - BibTeX
  - Link
  BibTeX
  @article{Ma2024MultimodalFP, author = {Ma, Yuliang and Liu, Jingyi and Mamaev, Ilshat and Morozov, Andrey}, journal = {2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, pages = {2951-2957}, title = {Multimodal Failure Prediction for Vision-based Manipulation Tasks with Camera Faults}, url = {https://api.semanticscholar.org/CorpusID:275018822}, year = 2024 }
  Link
  https://api.semanticscholar.org/CorpusID:275018822
2023
1. J. Grimstad and A. Morozov, “Adversarial Multi-Agent Reinforcement Learning for Fault-Tolerant Design of Complex Systems,” 2023, pp. 3399–3405.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Grimstad, Joachim and Morozov, Andrey}, doi = {10.3850/978-981-18-8071-1_P375-cd}, month = {01}, pages = {3399-3405}, title = {Adversarial Multi-Agent Reinforcement Learning for Fault-Tolerant Design of Complex Systems}, year = 2023 }
2. P. Grimmeisen, R. Golwalkar, Y. Ma, and A. Morozov, “Automated and Continuous Risk Assessment for ROS-Based Software-Defined Robotic Systems,” 2023, pp. 1–7.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Grimmeisen, Philipp and Golwalkar, Rucha and Ma, Yuliang and Morozov, Andrey}, doi = {10.1109/CASE56687.2023.10260416}, month = {08}, pages = {1-7}, title = {Automated and Continuous Risk Assessment for ROS-Based Software-Defined Robotic Systems}, year = 2023 }
3. S. Ding, A. Wolf, and A. Morozov, “Automated and Self-Adapting Approach to AI-based Anomaly Detection,” 2023, pp. 3056–3063.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Ding, Sheng and Wolf, Adrian and Morozov, Andrey}, doi = {10.3850/978-981-18-8071-1_P472-cd}, month = {01}, pages = {3056-3063}, title = {Automated and Self-Adapting Approach to AI-based Anomaly Detection}, year = 2023 }
4. Y. Ma, P. Grimmeisen, and A. Morozov, “Case Study: ROS-Based Fault Injection for Risk Analysis of Robotic Manipulator,” in 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), 2023, pp. 1–6.
  - BibTeX
  BibTeX
  @inproceedings{ma_case_2023, author = {Ma, Yuliang and Grimmeisen, Philipp and Morozov, Andrey}, booktitle = {2023 {IEEE} 19th {International} {Conference} on {Automation} {Science} and {Engineering} ({CASE})}, doi = {10.1109/CASE56687.2023.10260634}, pages = {1--6}, shorttitle = {Case {Study}}, title = {Case {Study}: {ROS}-{Based} {Fault} {Injection} for {Risk} {Analysis} of {Robotic} {Manipulator}}, year = 2023 }
5. 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 }
6. 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 }
7. B. Schürrle, P. Grimmeisen, J. Pfeiffer, T. Zimmermann, A. Morozov, and A. Wortmann, “Educating Future Software Engineers for Industrial Robotics,” 2023.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Schürrle, Berit and Grimmeisen, Philipp and Pfeiffer, Jerome and Zimmermann, Thilo and Morozov, Andrey and Wortmann, Andreas}, month = {09}, title = {Educating Future Software Engineers for Industrial Robotics}, year = 2023 }
8. A. Aghaei Attar, T. Fabarisov, A. Morozov, M. Artelt, and I. Mamaev, “Hybrid Lightweight Deep Learning-Based Error Detection Model on Edge Computing Devices,” 2023, pp. 1–4.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Aghaei Attar, Arman and Fabarisov, Tagir and Morozov, Andrey and Artelt, Maurice and Mamaev, Ilshat}, doi = {10.1109/ETFA54631.2023.10275725}, month = {09}, pages = {1-4}, title = {Hybrid Lightweight Deep Learning-Based Error Detection Model on Edge Computing Devices}, year = 2023 }
9. S. Ding, A. Wolf, and A. Morozov, “Interpretation of Influential Factors for AI-Based Anomaly Detection,” 2023, pp. 1762–1769.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Ding, Sheng and Wolf, Adrian and Morozov, Andrey}, doi = {10.3850/978-981-18-8071-1_P475-cd}, month = {01}, pages = {1762-1769}, title = {Interpretation of Influential Factors for AI-Based Anomaly Detection}, year = 2023 }
10. G. Siedel, S. Vock, and A. Morozov, “Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions,” May 2023.
  - BibTeX
  BibTeX
  @article{unknown, author = {Siedel, Georg and Vock, Silvia and Morozov, Andrey}, doi = {10.48550/arXiv.2305.05400}, month = {05}, title = {Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions}, year = 2023 }
11. J. Grimstad, T. Ruppert, J. Abonyi, and A. Morozov, “Preventive Risk-based Maintenance Scheduling using Discrete-Time Markov Chain Models,” 2023, pp. 1135–1142.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Grimstad, Joachim and Ruppert, Tamas and Abonyi, János and Morozov, Andrey}, doi = {10.3850/978-981-18-8071-1_P367-cd}, month = {01}, pages = {1135-1142}, title = {Preventive Risk-based Maintenance Scheduling using Discrete-Time Markov Chain Models}, year = 2023 }
12. T. Fabarisov, V. Naik, A. Aghaei Attar, and A. Morozov, “Remedy: Automated Design and Deployment of Hybrid Deep Learning-based Error Detectors,” 2023, pp. 1–8.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Fabarisov, Tagir and Naik, Vishnu and Aghaei Attar, Arman and Morozov, Andrey}, doi = {10.1109/IECON51785.2023.10312506}, month = {10}, pages = {1-8}, title = {Remedy: Automated Design and Deployment of Hybrid Deep Learning-based Error Detectors}, year = 2023 }
13. B. Schürrle, V. Sankarappan, and A. Morozov, “SynthiCAD: Generation of Industrial Image Data Sets for Resilience Evaluation of Safety-Critical Classifiers,” 2023, pp. 2199–2206.
  - BibTeX
  BibTeX
  @inproceedings{inproceedings, author = {Schürrle, Berit and Sankarappan, Venkatesh and Morozov, Andrey}, doi = {10.3850/978-981-18-8071-1_P400-cd}, month = {01}, pages = {2199-2206}, title = {SynthiCAD: Generation of Industrial Image Data Sets for Resilience Evaluation of Safety-Critical Classifiers}, year = 2023 }
2022
1. P. Grimmeisen, M. Diaconeasa, Y. Ma, and A. Morozov, “Automated Generation of Hybrid Probabilistic Risk Models from SysML v2 Models of Software-Defined Manufacturing Systems,” in Morozov ASME 2022 International Mechanical Engineering Congress & Exposition (IMECE 2022), 30.Oct-3. Nov. 2022, 2022, 2022.
  - BibTeX
  BibTeX
  @conference{grimmeisen2022automated, author = {Grimmeisen, Philipp and Diaconeasa, Mihai and Ma, Yuliang and Morozov, Andrey}, booktitle = {Morozov ASME 2022 International Mechanical Engineering Congress & Exposition (IMECE 2022), 30.Oct-3. Nov. 2022, 2022}, title = {Automated Generation of Hybrid Probabilistic Risk Models from SysML v2 Models of Software-Defined Manufacturing Systems}, year = 2022 }
2. P. Grimmeisen, A. Morozov, T. Fabarisov, A. Wortmann, and C. H. Koo, “Automated Model-Based Reliability Assessment of Software-Defined Manufacturing,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022, 2022.
  - BibTeX
  BibTeX
  @conference{grimmeisen2022automated, author = {Grimmeisen, Philipp and Morozov, Andrey and Fabarisov, Tagir and Wortmann, Andreas and Koo, Chee Hung}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022}, title = {Automated Model-Based Reliability Assessment of Software-Defined Manufacturing}, year = 2022 }
3. P. Grimmeisen, A. Wortmann, and A. Morozov, “Case study on automated and continuous reliability assessment of software-defined manufacturing based on digital twins,” MODELS ’22: Proceedings of the 25th International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings, 2022.
  - BibTeX
  BibTeX
  @article{grimmeisen2022study, author = {Grimmeisen, Philipp and Wortmann, Andreas and Morozov, Andrey}, journal = {MODELS '22: Proceedings of the 25th International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings}, title = {Case study on automated and continuous reliability assessment of software-defined manufacturing based on digital twins}, year = 2022 }
4. Y. Ma, P. Grimmeisen, and A. Morozov, “Detection and classification of robotic manipulator anomalies using MLSTM-FCN models,” ASME 2022 International Mechanical Engineering Congress & Exposition (IMECE 2022), 30.Oct-3. Nov. 2022, 2022, 2022.
  - BibTeX
  BibTeX
  @article{noauthororeditor2022detection, author = {Ma, Yuliang and Grimmeisen, Philipp and Morozov, Andrey}, journal = {ASME 2022 International Mechanical Engineering Congress & Exposition (IMECE 2022), 30.Oct-3. Nov. 2022, 2022}, title = {Detection and classification of robotic manipulator anomalies using MLSTM-FCN models}, year = 2022 }
5. T. Fabarisov, A. Morozov, I. Mamaev, and P. Grimmeisen, “FIDGET: Deep Learning-Based Fault Injection Framework for Safety Analysis and Intelligent Generation of Labeled Training Data,” 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022, 2022.
  - BibTeX
  BibTeX
  @article{fabarisov2022fidget, author = {Fabarisov, Tagir and Morozov, Andrey and Mamaev, Ilshat and Grimmeisen, Philipp}, journal = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022}, title = {FIDGET: Deep Learning-Based Fault Injection Framework for Safety Analysis and Intelligent Generation of Labeled Training Data}, year = 2022 }
6. S. Ding, N. Chakraborty, and A. Morozov, “IMU Sensor Faults Detection for UAV using Machine Learning,” in European Conference on Safety and Reliability 2022, 28 Aug - 3 Sept. 2022, Dublin, Ireland, 2022, 2022.
  - BibTeX
  BibTeX
  @conference{ding2022sensor, author = {Ding, S. and Chakraborty, N. and Morozov, A.}, journal = {European Conference on Safety and Reliability 2022, 28 Aug - 3 Sept. 2022, Dublin, Ireland, 2022}, title = {IMU Sensor Faults Detection for UAV using Machine Learning}, year = 2022 }
7. S. Ding, S. Ayoub, and A. Morozov, “Tool Paper: Time Series Anomaly Detection Platform for MATLAB Simulink,” In: 8th International Symposium on Model-Based Safety Assessment, 5-7 Sept. 2022, Munich, Germany, 2022, 2022.
  - BibTeX
  BibTeX
  @article{ding2022paper, author = {Ding, S. and Ayoub, S. and Morozov, A.}, journal = {In: 8th International Symposium on Model-Based Safety Assessment, 5-7 Sept. 2022, Munich, Germany, 2022}, title = {Tool Paper: Time Series Anomaly Detection Platform for MATLAB Simulink}, year = 2022 }
8. G. Siedel, S. Vock, A. Morozov, and S. Voß, “Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers,” The IJCAI-ECAI-22 Workshop on Artificial Intelligence Safety (AISafety 2022), 2022.
  - BibTeX
  BibTeX
  @article{siedel2022utilizing, author = {Siedel, G. and Vock, S. and Morozov, A. and Voß, S.}, journal = {The IJCAI-ECAI-22 Workshop on Artificial Intelligence Safety (AISafety 2022)}, title = {Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers}, year = 2022 }
2021
1. Y. Ma, A. Morozov, and S. Ding, “Anomaly Detection for Cyber Physical Systems using Transformers,” The International Mechanical Engineering Congress and Exposition, IMECE, 2021.
  - BibTeX
  BibTeX
  @article{ma2021anomaly, abstract = {Safety and reliability are two critical factors of modern Cyber-Physical Systems (CPS). However, the increasing structural and behavioral complexity of modern automation systems significantly increases the possibility of system errors and failures, which can easily lead to economic loss or even hazardous events. Anomaly Detection (AD) techniques provide a potential solution to this problem, and conventional methods, e.g., Autoregressive Integrated Moving Average model (ARIMA), are no longer the best choice for anomaly detection for modern complex CPS. Recently, Deep Learning (DL) and Machine Learning (ML) anomaly detection methods became more popular, and numerous practical applications have been presented in many industrial scenarios. Most of the modern DL-based anomaly detection methods use the prediction approach and LSTM architecture. The Transformer is a new neural network architecture that outperforms LSTM in natural language processing. In this paper, we show that the Transformer-based deep learning model, which has received much attention recently, can be applied to the anomaly detection of industrial automation systems. Specifically, we collect time-series data from a system of two industrial robots using a Simulink model. Then, we feed these data into our Transformer-based model and train it to be a time-series data predictor. The paper presents the experimental results that show the comparison of precision and speed of a Long-Short Time Memory (LSTM) predictor and our Transformer-based predictor.}, author = {Ma, Y. and Morozov, A. and Ding, Sheng}, journal = {The International Mechanical Engineering Congress and Exposition, IMECE}, title = {Anomaly Detection for Cyber Physical Systems using Transformers}, year = 2021 }
2. T. Fabarisov, I. Mamaev, A. Morozov, and K. Janschek, “Deep Learning-based Error Mitigation for Assistive Exoskeleton with Computational-Resource-Limited Platform and Edge Tensor Processing Unit,” in The International Mechanical Engineering Congress and Exposition, IMECE, 2021.
  - BibTeX
  BibTeX
  @conference{fabarisov2021learningbased, abstract = {Recently we introduced a new model-based fault injection method implemented as a highly-customizable Simulink block called FIBlock. It supports the injection of typical faults of essential heterogeneous components of Cyber-Physical Systems, such as sensors, computing hardware, and network. The FIBlock allows to tune a fault type and configure multiple parameters to tune error magnitude, fault activation time, and fault exposure duration. We demonstrated its performance to generate highly adjustable and various CPS fault types on a Simulink case study representing a lower-limb EXO-LEGS exoskeleton, an assistive device for the elderly in everyday life. In our previous paper we discovered the spatial and temporal thresholds for different fault types. Upon exceeding said thresholds, the Dynamic Movement Primitives-based control system could no longer adequately compensate these errors. In this paper we proposed a Deep Learning-based approach for the system failure prevention. We employed the Long Short-Term Memory (LSTM) network for error detection and mitigation. Error detection was performed using data prediction. The LSTM models were mitigating the detected errors with computed predictions only when they were subject to the imminent failure (i.e., exceeded the aforementioned thresholds). To compare our approach with previous findings, we trained two LSTM models on angular position and on angular velocity signals. For evaluation, we performed fault injection experiments with varying fault effect parameters. The ’Stuck-at current value’ fault was injected into angular position sensor, and the ’Stuck-at 0’ fault was injected into angular velocity sensor. Presented Deep Learning-based approach prevented system failure even when the injected faults were substantially exceeding thresholds. In addition, a reasoning for data access point choice has been evaluated. We compared two options: (i) the input data for LSTM is provided from the controller output and (ii) from the sensor output. In the paper the pros and cons for both options are presented. We deployed the trained LSTM models on an Edge Tensor Processing Unit. For that, the models have been quantized, i.e. all the 32-bit floating-point numbers (such as weights and activation outputs) were converted to the nearest 8-bit fixed-point numbers and converted to the TensorFlow Lite models. The Coral USB Accelerator was coupled with a Raspberry Pi 4B for signal processing. The result proves the feasibility of the proposed method. Because the LSTM models were converted to the 8-bit integer TensorFlow Lite models, it allowed real-time error mitigation. Furthermore, the light weight of the system and a minimal power consumption allows its integration into wearable robotic systems.}, author = {Fabarisov, T. and Mamaev, I. and Morozov, A. and Janschek, K.}, booktitle = {The International Mechanical Engineering Congress and Exposition, IMECE}, title = {Deep Learning-based Error Mitigation for Assistive Exoskeleton with Computational-Resource-Limited Platform and Edge Tensor Processing Unit}, year = 2021 }
3. S. Ding, A. Morozov, T. Fabarisov, and S. Vock, “KrakenBox: Deep Learning based Error Detector for Industrial Cyber-Physical Systems,” in The International Mechanical Engineering Congress and Exposition, IMECE, 2021.
  - BibTeX
  BibTeX
  @conference{noauthororeditor2021krakenbox, abstract = {Online error detection helps to reduce the risk of failure of safety-critical systems. However, due to the increasing complexity of modern Cyber-Physical Systems and the sophisticated interaction of their heterogeneous components, it becomes harder to apply traditional error detection methods. Nowadays, the popularity of Deep Learning-based error detection snowballs. DL-based methods achieved significant progress along with better results. This paper introduces the KrakenBox, a deep learning-based error detector for industrial Cyber-Physical Systems (CPS). It provides conceptual and technical details of the KrakenBox hardware, software, and a case study. The KrakenBox hardware is based on NVIDIA Jetson AGX Xavier, designed to empower the deep learning-based application and the extended alarm module. The KrakenBox software consists of several programs capable of collecting, processing, storing, and analyzing time-series data. The KrakenBox can be connected to the networked automation system either via Ethernet or wirelessly. The paper presents the KrakenBox architecture and results of experiments that allow the evaluation of the error detection performance for varying error magnitude. The results of these experiments demonstrate that the KrakenBox is able to improve the safety of a networked automation system.}, author = {Ding, Sheng and Morozov, A. and Fabarisov, T. and Vock, S.}, booktitle = {The International Mechanical Engineering Congress and Exposition, IMECE}, title = {KrakenBox: Deep Learning based Error Detector for Industrial Cyber-Physical Systems}, year = 2021 }
2020
1. A. Morozov, M. A. Diaconeasa, and M. Steurer, “A Hybrid Methodology For Model-based Probabilistic Resilience, Evaluation Of Dynamic Systems,” in International Mechanical Engineering Congress and Exposition (IMECE 2020 - Virtual Conference), 15-19 Nov. 2020, Portland, OR, USA, 2020.
  - BibTeX
  BibTeX
  @conference{morozov2020hybrid, author = {Morozov, A. and Diaconeasa, M. A. and Steurer, M.}, booktitle = {International Mechanical Engineering Congress and Exposition (IMECE 2020 - Virtual Conference), 15-19 Nov. 2020, Portland, OR, USA}, title = {A Hybrid Methodology For Model-based Probabilistic Resilience, Evaluation Of Dynamic Systems}, year = 2020 }
2. A. Morozov, M. B. Emil Valiev, L. G. Kai Ding, and C. Schorn, “Bayesian Model for Trustworthiness Analysis of Deep Learning Classifiers,” in Proceedings of the Workshop on Artificial Intelligence Safety 2020 co-located with the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI 2020), 2020.
  - BibTeX
  BibTeX
  @conference{morozov2020bayesian, author = {Morozov, Andrey and Emil Valiev, Michael Beyer and Kai Ding, Lydia Gauerhof and Schorn, Christoph}, booktitle = {Proceedings of the Workshop on Artificial Intelligence Safety 2020 co-located with the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI 2020)}, title = {Bayesian Model for Trustworthiness Analysis of Deep Learning Classifiers}, year = 2020 }
3. E. Valiev, N. Yusupova, A. Morozov, K. Janschek, and M. Beyer, “Evaluation of the Impact of Random Computing Hardware Faults on the Performance of Convolutional Neural Networks,” in In: Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020), Atlantis Press, pp. 307-312, 2020.
  - BibTeX
  BibTeX
  @conference{valiev2020evaluation, author = {Valiev, Emil and Yusupova, Nafisa and Morozov, Andrey and Janschek, Klaus and Beyer, Michael}, booktitle = {In: Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020), Atlantis Press, pp. 307-312 }, title = {Evaluation of the Impact of Random Computing Hardware Faults on the Performance of Convolutional Neural Networks}, year = 2020 }
4. M. Moradi, B. J. Oakes, M. Saraoglu, A. Morozov, K. Janschek, and J. Denil, “Exploring Fault Parameter Space Using Reinforcement Learning-based Fault Injection,” in 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W - Virtual Conference), 29 June - 2 July 2020, Valencia, Spain, pp. 102-109, 2020.
  - BibTeX
  - Link
  BibTeX
  @conference{moradi2020exploring, abstract = {Assessing the safety of complex Cyber-Physical Systems (CPS) is a challenge in any industry. Fault Injection (FI) is a proven technique for safety analysis and is recommended by the automotive safety standard ISO 26262. Traditional FI methods require a considerable amount of effort and cost as FI is applied late in the development cycle and is driven by manual effort or random algorithms. In this paper, we propose a Reinforcement Learning (RL) approach to explore the fault space and find critical faults. During the learning process, the RL agent injects and parameterizes faults in the system to cause catastrophic behavior. The fault space is explored based on a reward function that evaluates previous simulation results such that the RL technique tries to predict improved fault timing and values. In this paper, we apply our technique on an Adaptive Cruise Controller with sensor fusion and compare the proposed method with Monte Carlo-based fault injection. The proposed technique is more efficient in terms of fault coverage and time to find the first critical fault.}, author = {Moradi, Mehrdad and Oakes, Bentley James and Saraoglu, Mustafa and Morozov, Andrey and Janschek, Klaus and Denil, Joachim}, booktitle = {50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W - Virtual Conference), 29 June - 2 July 2020, Valencia, Spain, pp. 102-109}, doi = {10.1109/DSN-W50199.2020.00028}, title = {Exploring Fault Parameter Space Using Reinforcement Learning-based Fault Injection}, url = {https://ieeexplore.ieee.org/abstract/document/9151674}, year = 2020 }
  Link
  https://ieeexplore.ieee.org/abstract/document/9151674
5. M. Beyer, A. Morozov, E. Valiev, C. Schorn, L. Gauerhof, K. Ding, and K. Janschek, “Fault Injectors for TensorFlow: Evaluation of the Impact of Random Hardware Faults on Deep CNNs,” in 30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, 2020.
  - BibTeX
  - Link
  BibTeX
  @conference{beyer2020fault, abstract = {Today, Deep Learning (DL) enhances almost every industrial sector, including safety-critical areas. The next generation of safety standards will define appropriate verification techniques for DL-based applications and propose adequate fault tolerance mechanisms. DL-based applications, like any other software, are susceptible to common random hardware faults such as bit flips, which occur in RAM and CPU registers. Such faults can lead to silent data corruption. Therefore, it is crucial to develop methods and tools that help to evaluate how DL components operate under the presence of such faults. In this paper, we introduce two new Fault Injection (FI) frameworks InjectTF and InjectTF2 for TensorFlow 1 and TensorFlow 2, respectively. Both frameworks are available on GitHub and allow the configurable injection of random faults into Neural Networks (NN). In order to demonstrate the feasibility of the frameworks, we also present the results of FI experiments conducted on four VGG-based Convolutional NNs using two image sets. The results demonstrate how random bit flips in the output of particular mathematical operations and layers of NNs affect the classification accuracy. These results help to identify the most critical operations and layers, compare the reliability characteristics of functionally similar NNs, and introduce selective fault tolerance mechanisms.}, author = {Beyer, Michael and Morozov, Andrey and Valiev, Emil and Schorn, Christoph and Gauerhof, Lydia and Ding, Kai and Janschek, Klaus}, booktitle = {30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy}, title = {Fault Injectors for TensorFlow: Evaluation of the Impact of Random Hardware Faults on Deep CNNs}, url = {https://www.rpsonline.com.sg/proceedings/esrel2020/html/5754.xml}, year = 2020 }
  Link
  https://www.rpsonline.com.sg/proceedings/esrel2020/html/5754.xml
6. C. Dubslaff, A. Morozov, C. Baier, and K. Janschek, “Iterative Variable Reordering: Taming Huge System Families,” Proceedings of the 4th Workshop on Models for Formal Analysis of Real Systems (MARS 2020), pp. 121-133, 2020.
  - BibTeX
  - Link
  BibTeX
  @article{dubslaff2020, abstract = {For the verification of systems using model-checking techniques, symbolic representations based on binary decision diagrams (BDDs) often help to tackle the well-known state-space explosion problem. Symbolic BDD-based representations have been also shown to be successful for the analysis of families of systems that arise, e.g., through configurable parameters or following the feature-oriented modeling approach. The state space of such system families face an additional exponential blowup in the number of parameters or features. It is well known that the order of variables in ordered BDDs is crucial for the size of the model representation. Especially for automatically generated models from real-world systems, family models might even be not constructible due to bad variable orders. In this paper we describe a technique, called iterative variable reordering, that can enable the construction of large-scale family models. We exemplify feasibility of our approach by means of an aircraft velocity control system with redundancy mechanisms modeled in the input language of the probabilistic model checker PRISM. We show that standard reordering and dynamic reordering techniques fail to construct the family model due to memory and time constraints, respectively, while the new iterative approach succeeds to generate a symbolic family model.}, author = {Dubslaff, C. and Morozov, A. and Baier, C. and Janschek, K.}, doi = {10.4204/EPTCS.316.5}, journal = {Proceedings of the 4th Workshop on Models for Formal Analysis of Real Systems (MARS 2020), pp. 121-133}, title = {Iterative Variable Reordering: Taming Huge System Families}, url = {https://arxiv.org/abs/2004.13287}, year = 2020 }
  Link
  https://arxiv.org/abs/2004.13287
7. T. Mutzke, M. Steurer, A. Morozov, and K. Janschek, “Model-based Analysis of Timing Errors for Reliable UAV Design,” in 30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, pp. 2057-2064, 2020.
  - BibTeX
  - Link
  BibTeX
  @conference{mutzke2020modelbased, abstract = {Unmanned aerial vehicles are safety-critical systems. A failure in the system behavior may lead to hazards and serious consequences. The assessment of the system dependability characteristics that include safety and reliability early in the design phase is a beneficial task that helps to avoid expensive redesign and iterations in later design phases. Unmanned aerial vehicles typically comprise several independent components that communicate and share data via a network. Adequate timing is crucial for proper system behavior. However, the timing is affected by various system faults, e. g., network induced delays, which typically have a stochastic nature. The focus of this paper is on the effective model-based application of the previously published method for the analysis of timing errors to a realistic case study model of a quadcopter. The holistic solution proposed in this paper integrates the SysML modeling and annotating approach, the automated transformation of the SysML model to a Stochastic Petri Net, and the identification, formalization, and analysis of timing properties. The case study model is annotated with the timing parameters recorded from a real-world system. The results of the conducted sensitivity analysis reveal the effects of parameter changes in the annotated timing properties. These quantitative results may be used as input for the error propagation analysis, allow the assessment of the system dependability and enable to compare different design options concerning the occurrence of timing errors. Keywords: UAV, Dependability, SysML Activity, Petri net, Timing analysis, Safety-Critical system.}, author = {Mutzke, T. and Steurer, M. and Morozov, A. and Janschek, K.}, booktitle = {30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, pp. 2057-2064}, title = {Model-based Analysis of Timing Errors for Reliable UAV Design}, url = {https://www.rpsonline.com.sg/proceedings/esrel2020/html/5414.xml}, year = 2020 }
  Link
  https://www.rpsonline.com.sg/proceedings/esrel2020/html/5414.xml
8. M. Steurer, A. Morozov, K. Janschek, and K.-P. Neitzke, “Model-Based Dependability Assessment of Phased-Mission Unmanned Aerial Vehicles,” in 21st IFAC World Congress (Virtual Conference), 11-17 July 2020, Berlin, 2020.
  - BibTeX
  BibTeX
  @conference{msteureramorozov2020modelbased, author = {Steurer, M. and Morozov, A. and Janschek, K. and Neitzke, K.-P.}, booktitle = {21st IFAC World Congress (Virtual Conference), 11-17 July 2020, Berlin}, title = {Model-Based Dependability Assessment of Phased-Mission Unmanned Aerial Vehicles}, year = 2020 }
9. S. Ding, A. Morozov, S. Vock, M. Weyrich, and K. Janschek, “Model-Based Error Detection for Industrial Automation Systems Using LSTM Networks,” In: International Symposium on Model-Based Safety and Assessment, pp. 212-226. Springer, Cham, 2020.
  - BibTeX
  - Link
  BibTeX
  @article{ding2020modelbased, abstract = {The increasing complexity of modern automation systems leads to inevitable faults. At the same time, structural variability and untrivial interaction of the sophisticated components makes it harder and harder to apply traditional fault detection methods. Consequently, the popularity of Deep Learning (DL) fault detection methods grows. Model-based system design tools such as Simulink allow the development of executable system models. Besides the design flexibility, these models can provide the training data for DL-based error detectors. This paper describes the application of an LSTM-based error detector for a system of two industrial robotic manipulators. A detailed Simulink model provides the training data for an LSTM predictor. Error detection is achieved via intelligent processing of the residual between the original signal and the LSTM prediction using two methods. The first method is based on the non-parametric dynamic thresholding. The second method exploits the Gaussian distribution of the residual. The paper presents the results of extensive model-based fault injection experiments that allow the comparison of these methods and the evaluation of the error detection performance for varying error magnitude.}, author = {Ding, Sheng and Morozov, Andrey and Vock, Silvia and Weyrich, Michael and Janschek, Klaus}, journal = {In: International Symposium on Model-Based Safety and Assessment, pp. 212-226. Springer, Cham}, title = {Model-Based Error Detection for Industrial Automation Systems Using LSTM Networks}, url = {https://link.springer.com/chapter/10.1007/978-3-030-58920-2_14}, year = 2020 }
  Link
  https://link.springer.com/chapter/10.1007/978-3-030-58920-2_14
10. A. M. T. Fabarisov, I. Mamaev and K. Janschek, “Model-based Fault Injection Experiments for the Safety Analysis of Exoskeleton System,” in 30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, 2020.
  - BibTeX
  - Link
  BibTeX
  @conference{tfabarisovimamaev2020modelbased, abstract = {Model-based fault injection methods are widely used for the evaluation of fault tolerance in safety-critical control systems. In this paper, we introduce a new model-based fault injection method implemented as a highlycustomizable Simulink block called FIBlock. It supports the injection of typical faults of essential heterogeneous components of Cyber-Physical Systems, such as sensors, computing hardware, and network. The FIBlock GUI allows the user to select a fault type and configure multiple parameters to tune error magnitude, fault activation time, and fault exposure duration. Additional trigger inputs and outputs of the block enable the modeling of conditional faults. Furthermore, two or more FIBlocks connected with these trigger signals can model chained errors. The proposed fault injection method is demonstrated with a lower-limb EXO-LEGS exoskeleton, an assistive device for the elderly in everyday life. The EXO-LEGS model-based dynamic control is realized in the Simulink environment and allows easy integration of the aforementioned FIBlocks. Exoskeletons, in general, being a complex CPS with multiple sensors and actuators, are prone to hardware and software faults. In the case study, three types of faults were investigated: 1) sensor freeze, 2) stuck-at-0, 3) bit-flip. The fault injection experiments helped to determine faults that have the most significant effects on the overall system reliability and identify the fine line for the critical fault duration after that the controller could no longer mitigate faults.}, author = {{T. Fabarisov, I. Mamaev}, A. Morozov and Janschek, K.}, booktitle = {30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy}, title = {Model-based Fault Injection Experiments for the Safety Analysis of Exoskeleton System}, url = {https://www.rpsonline.com.sg/proceedings/esrel2020/html/5770.xml}, year = 2020 }
  Link
  https://www.rpsonline.com.sg/proceedings/esrel2020/html/5770.xml
11. T. Fabarisov, N. Yusupova, K. Ding, A. Morozov, and K. Janschek, “Model-based Stochastic Error Propagation Analysis for Cyber-Physical Systems,” Acta Polytechnica Hungarica, 17(8), pp.15-28, 2020.
  - BibTeX
  - Link
  BibTeX
  @article{fabarisov2020modelbased, abstract = {Industry 4.0 is the current trend of automation and data exchange in manufacturing technologies that is focusing on the creation of smart factories with the modular structured Cyber-Physical Systems (CPS), in tight cooperation with humans. This trend also implies that the systems become more complex, heterogeneous, and distributed especially their network and software parts. This makes the CPS highly critical subject to failures at different levels, including software, hardware, and human operators. Consequently, ensuring reliable and safe operation under the presence of non-avoidable threats also becomes a more complicated task. The proper analysis of the CPS requires thorough comprehension of both the dependability properties of system components and their interactions as well as structural and behavioral aspects of the complete system. Such an analysis of complex and mutually interlinked system properties puts considerable challenges on appropriate methods for modeling and analysis, as well as, on the related applied software tools. The Dual-graph Error Propagation Model (DEPM), developed in our lab, is a mathematical abstraction of the main future system’s properties, which are vital for the determination of the error propagation processes. It is a useful analytical instrument for the evaluation of the influence of particular faults and errors to the overall system behavior. OpenErrorPro is our analytical software tool for stochastic error propagation analysis that supports the DEPM framework. Using OpenErrorPro, a DTMC model could be automatically generated from a DEPM, and the reliability metrics, in addition to, error propagation path, can be computed. This could be implemented for the analysis of the heterogeneous CPS components. The necessary steps for the DEPM framework extension, required for such an implementation, are discussed in this paper.}, author = {Fabarisov, T. and Yusupova, N. and Ding, K. and Morozov, A. and Janschek, K.}, booktitle = {Acta Polytechnica Hungarica, 17(8), pp.15-28}, title = {Model-based Stochastic Error Propagation Analysis for Cyber-Physical Systems}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2020-Model-based_Stochastic_Error_Propagation_Analysis_for_Cyber-Physical_Systems.pdf}, year = 2020 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2020-Model-based_Stochastic_Error_Propagation_Analysis_for_Cyber-Physical_Systems.pdf
12. C. Dubslaff, A. Morozov, C. Baier, and K. Janschek, “Reduction Methods on Probabilistic Control-flow Programs for Reliability Analysis,” in 30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, pp. 4843-4850, 2020.
  - BibTeX
  - Link
  BibTeX
  @conference{dubslaff2020, abstract = {Modern safety-critical systems are heterogeneous, complex, and highly dynamic. They require reliability evaluation methods that go beyond the classical static methods such as fault trees, event trees, or reliability block diagrams. Promising dynamic reliability analysis methods employ probabilistic model checking on various probabilistic statebased models. However, such methods have to tackle the well-known state-space explosion problem. To compete with this problem, reduction methods such as symmetry reduction and partial-order reduction have been successfully applied to probabilistic models by means of discrete Markov chains or Markov decision processes. Such models are usually specified using probabilistic programs provided in guarded command language. In this paper, we propose two automated reduction methods for probabilistic programs that operate on a purely syntactic level: reset value optimization and register allocation optimization. The presented techniques rely on concepts well known from compiler construction such as live range analysis and register allocation through interference graph coloring. Applied on a redundancy system model for an aircraft velocity control loop modeled in SIMULINK, we show effectiveness of our implementation of the reduction methods. We demonstrate that model-size reductions in three orders of magnitude are possible and show that we can achieve significant speedups for a reliability analysis.}, author = {Dubslaff, C. and Morozov, A. and Baier, C. and Janschek, K.}, booktitle = {30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, pp. 4843-4850}, title = {Reduction Methods on Probabilistic Control-flow Programs for Reliability Analysis}, url = {https://www.rpsonline.com.sg/proceedings/esrel2020/html/4489.xml}, year = 2020 }
  Link
  https://www.rpsonline.com.sg/proceedings/esrel2020/html/4489.xml
13. M. Steurer, T. Mutzke, A. Morozov, K. Janschek, and K.-P. Neitzke, “Utilizing Model-based Timing Analysis for Holistic Dependability Assessment of Unmanned Aerial Vehicle,” in 30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, pp. 2065-2072, 2020.
  - BibTeX
  - Link
  BibTeX
  @conference{steurer2020, abstract = {A failure in the behavior of safety-critical systems such as Unmanned Aerial Vehicles (UAV) may lead to hazards and serious consequences. Therefore UAVs must perform correctly throughout their intended life cycle. However, the functional system specification is not sufficient to ensure proper performance.The assessment of non-functional reliability, safety, or timing requirements in the early development phases helps to prevent conceptually wrong decisions. UAVs usually contain complex and tightly coupled hardware and software components that influence each other. Hence, a holistic approach to analyze the non-functional properties is preferable. The concept of phased mission systems enables the specification of individual requirements for different phases. This allows more accurate predictions of the success or failure of a mission.This paper presents a holistic model-based dependability assessment approach that supports system-software co-engineering for UAVs. The approach combines stochastic timing analysis and the data error propagation analysis and enables the consideration of phase-specific requirements as well as the identification, formalization, and analysis of timing properties. The solution proposed in this paper is centered around the Systems Modeling Language (SysML) and the systematic transformation of annotated SysML models to Probabilistic Model Checking (PMC) accessible Markov chain models}, author = {Steurer, M. and Mutzke, T. and Morozov, A. and Janschek, K. and Neitzke, K.-P.}, booktitle = {30th European Safety and Reliability Conference (ESREL - Virtual Conference), 1-5 Nov. 2020, Venice, Italy, pp. 2065-2072}, title = {Utilizing Model-based Timing Analysis for Holistic Dependability Assessment of Unmanned Aerial Vehicle}, url = {https://www.rpsonline.com.sg/proceedings/esrel2020/html/5757.xml}, year = 2020 }
  Link
  https://www.rpsonline.com.sg/proceedings/esrel2020/html/5757.xml
14. M. Saraoğlu, Q. Shi, A. Morozov, and K. Janschek, “Virtual validation of autonomous vehicle safety through simulation-based testing,” In 20. In: Internationales Stuttgarter Symposium, pp. 419-434, Springer Vieweg, Wiesbaden, 2020.
  - BibTeX
  - Link
  BibTeX
  @article{saraoglu2020virtual, abstract = {Full validation of the safety of an autonomous vehicle requires excessive amounts of testing and driving hours, which is impossible to achieve without virtual simulations. Therefore, companies seek efficient and smart testing strategies to virtually validate the safety of autonomous vehicle functions aiming to achieve lower costs and less time to market. Simulation-based testing for autonomous and connected vehicles is essential for the future generation of transportation systems.}, author = {Saraoğlu, Mustafa and Shi, Qihang and Morozov, Andrey and Janschek, Klaus}, journal = {In 20. In: Internationales Stuttgarter Symposium, pp. 419-434, Springer Vieweg, Wiesbaden}, title = {Virtual validation of autonomous vehicle safety through simulation-based testing}, url = {https://link.springer.com/chapter/10.1007/978-3-658-29943-9_33}, year = 2020 }
  Link
  https://link.springer.com/chapter/10.1007/978-3-658-29943-9_33
2019
1. T. Fabarisov, N. Yusupova, K. Ding, A. Morozov, and K. Janschek, “Analytical toolset for model-based stochastic error propagation analysis: extension and optimization towards industrial requirements,” Системная инженерия и информационные технологии, 1(1), pp.41-46, 2019.
  - BibTeX
  - Link
  BibTeX
  @article{fabarisov2019, abstract = {Model-Based System Engineering (MBSE) is a popular mathematical and visual approach to the design of complex control, signal processing, and communication systems. It is used in safety critical industrial domains including aerospace, automotive, transportation, medical and robotics applications. Our group develops methods and tools for model-based system reliability and safety analysis with the main focuses on stochastic modelling of error propagation processes. This article is devoted to the optimisation and extensions to our analytical toolset. We have investigated the key modeling paradigms, requirements and industrial needs and have formulated the list of particular extensions.}, author = {Fabarisov, T. and Yusupova, N. and Ding, K. and Morozov, A. and Janschek, K.}, journal = {Системная инженерия и информационные технологии, 1(1), pp.41-46}, title = {Analytical toolset for model-based stochastic error propagation analysis: extension and optimization towards industrial requirements}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2019_ANALYTICAL_TOOLSET_FOR_MODEL-BASED_STOCHASTIC_ERROR_PROPAGATION_ANALYSIS-EXTENSION_AND_OPTIMIZATION_TOWARDS_INDUSTRIAL_REQUIREMENTS.pdf}, year = 2019 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2019_ANALYTICAL_TOOLSET_FOR_MODEL-BASED_STOCHASTIC_ERROR_PROPAGATION_ANALYSIS-EXTENSION_AND_OPTIMIZATION_TOWARDS_INDUSTRIAL_REQUIREMENTS.pdf
2. K. Ding, S. Ding, A. Morozov, T. Fabarisov, and K. Janschek, “On-line error detection and mitigation for time-series data of cyber-physical systems using deep learning based methods,” in 2019 15th European Dependable Computing Conference (EDCC) (pp. 7-14). IEEE, 2019.
  - BibTeX
  - Link
  BibTeX
  @conference{ding2019online, abstract = {A cyber-physical system consists of sensors, micro-controller, networks, and actuators that interact with each other, generate a substantial amount of data, and form extremely complex system operational profiles. These heterogeneous components are subject to errors, e.g. spikes, off-sets, or delays, that may result in system failures. As the complexity of modern systems increases, it becomes a challenge to apply traditional fault detection and isolation methods to such complex systems. Deep learning based methods have surpassed traditional methods in terms of performance as the data size and complexity increase. The signals of cyber-physical systems are mainly time-series data. In this paper, we propose a new on-line error detection and mitigation approach for common sensor, computing hardware, and network errors of cyber-physical systems using deep learning based methods. More specifically, we train a Long Short-Term Memory (LSTM) network as a single step prediction model for the detection and mitigation of errors, like spikes, or offsets. In order to detect the long-duration errors that show no sharp change (a sudden drop or rise) between two successive data samples when errors occurred, e.g. network delays, we train an LSTM encoder-decoder as a multi-step prediction model. We also introduce the on-line error mitigation approach. Automatic recovery is achieved by replacing the detected errors with the predicted values. Finally, we demonstrate on-line error detection and mitigation capabilities of the trained single step and multi-step predictors using representative case studies.}, author = {Ding, K. and Ding, Sheng and Morozov, A. and Fabarisov, T. and Janschek, K.}, booktitle = {2019 15th European Dependable Computing Conference (EDCC) (pp. 7-14). IEEE}, doi = {https://ieeexplore.ieee.org/abstract/document/8893390}, title = {On-line error detection and mitigation for time-series data of cyber-physical systems using deep learning based methods}, url = {https://ieeexplore.ieee.org/abstract/document/8893390}, year = 2019 }
  Link
  https://ieeexplore.ieee.org/abstract/document/8893390
2018
1. T. Fabarisov, N. Yusupova, K. Ding, A. Morozov, and K. Janschek, “The efficiency comparison of the prism and storm probabilistic model checkers for error propagation analysis tasks,” Industry 4.0, 3(5), pp.229-231., 2018.
  - BibTeX
  - Link
  BibTeX
  @article{fabarisov2018efficiency, abstract = {Dual-graph Error Propagation Model (DEPM) is a stochastic framework developed in our lab that captures system properties relevant to error propagation processes such as control and data flow structures and reliability characteristics of single components. The DEPM helps to estimate the impact of a fault of a particular component on the overall system reliability. The probability of a system failure, Mean Time Between Failures and Mean Time to Repair, and the expected number of failures are the quantitative results of the DEPM-based analysis. In addition, the DEPM provides an access to the powerful techniques from Probabilistic Model Checking (PMC) that allow the evaluation of advanced, highly customizable, time-related reliability properties, e.g., “the probability of a system failure during certain time units after the occurrence of a certain combination of errors in certain system components”. For this reason, the DEPM models are automatically transformed to discrete-time Markov chain (DTMC) models and are analyzed using the state of the art probabilistic model checker PRISM. However, the new promising model checker Storm has been recently released. This paper presents the results of the efficiency comparison of these two model checkers based on the automatically generated set of the DTMC models that are typical for the error propagation analysis tasks. Several computation engines that are supported by both model checkers have been taking into account. The paper also gives the general description of the DEPM workflow with the focus on the PMC interface.}, author = {Fabarisov, T. and Yusupova, N. and Ding, K. and Morozov, A. and Janschek, K.}, journal = {Industry 4.0, 3(5), pp.229-231.}, title = {The efficiency comparison of the prism and storm probabilistic model checkers for error propagation analysis tasks}, url = {https://stumejournals.com/journals/i4/2018/5/pdf}, year = 2018 }
  Link
  https://stumejournals.com/journals/i4/2018/5/pdf

The research interest of Jun.-Prof. Morozov lies at the intersection of three domains, namely, (i) Networked Automation Systems (NAS), (ii) Dependability, and (iii) Artificial Intelligence (AI). Modern NAS is a particular case of Cyber-Physical Systems (CPS) with the focus on the cooperation of heterogeneous industrial robotic systems. Accurate assessment of reliability, safety, and resilience is essential for NAS because of the high cost of downtime and strict safety requirements. However, the analytical capabilities of dependability evaluation methods, which are currently applied in the industry, are far behind the technical level of the systems in question. These methods cannot adequately describe sophisticated failure scenarios of highly dynamic and intelligent NAS. Besides that, future NAS will include more and more AI components. However, the reliability and safety analysis of AI is an entirely open question at the moment. An inevitable revolution in the dependability methods is expected in the next years. So, the main goal is to build a strong research team capable of taking a leading role in the development of the next generation of dependability analysis methods for modern and future NAS.

Teaching

Jun.-Prof. Morozov takes over the "Technologien und Methoden der Softwaresysteme I" course for bachelor students from the winter term 2020-2021. Besides that, he is creating a new 4SWS course "Modeling and Analysis of Automation Systems (MAAS)" for master students of the study programs “Autonome Systeme”, “Elektrotechnik und Informationstechnologie”, and “Electrical Engineering”.

About

Jun.-Prof. Andrey Morozov has started at IAS in April 2020. He holds a six-years tenure-track position. During this time, he has to establish a new professorship for "Networked Automation Systems" and achieve the research and teaching goals defined by the rectorate.

Jun.-Prof. Morozov received his diploma in Computer Science and Mathematics from Ufa State Aviation Technical University in 2007 in Ufa, Russia. In 2009 he moved to Germany and, in 2012, got a doctoral degree (Dr.-Ing.) in the Institute of Automation (IfA), Faculty of Electrical and Computer Engineering, Technische Universität Dresden. After that, being a postdoc researcher, he worked on several R&D projects funded by DLR, ESA, NASA, and DFG. In 2014, Jun.-Prof. Morozov built a new research group at IfA with the main focus on the model-based analysis of safety-critical mechatronic systems. Jun.-Prof. Morozov has published 40 research papers and made more than 20 scientific talks, including the presentations in research centers of ESA, DLR, Bosch, MathWorks, Sandford Research Institute, and the University of California Los Angeles.

Andrey Morozov

Contact

Publications

2024

BibTeX

Link

BibTeX

Link

BibTeX

BibTeX

Link

2023

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

2022

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

2021

BibTeX

BibTeX

BibTeX

2020

BibTeX

BibTeX

BibTeX

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

2019

BibTeX

Link

BibTeX

Link

2018

BibTeX

Link

Research

Teaching

About

Presentations

Here you can reach us

Audience

Formalities

Services

Organization