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
+49 711 685 67302
Email

Pfaffenwaldring 47
70550 Stuttgart
Germany
Room: 2.116

Publications

Journals and Conferences:

2024
1. Y. Xia, Z. Xiao, N. Jazdi, and M. Weyrich, “Generation of Asset Administration Shell with Large Language Model Agents: Interoperability in Digital Twins with Semantic Node,” arXiv preprint arXiv:2403.17209, 2024.
  - BibTeX
  BibTeX
  @article{xia2024generation, author = {Xia, Yuchen and Xiao, Zhewen and Jazdi, Nasser and Weyrich, Michael}, doi = {10.48550/arXiv.2403.17209}, journal = {arXiv preprint arXiv:2403.17209}, title = {Generation of Asset Administration Shell with Large Language Model Agents: Interoperability in Digital Twins with Semantic Node}, year = 2024 }
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, no. 5, 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, 2023.
  - 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
24. M. Müller, N. Jazdi, and M. Weyrich, “Self-improving Models for the Intelligent Digital Twin: Towards Closing the Reality-to-Simulation Gap,” in 14th IFAC Workshop on Intelligent Manufacturing Systems, 5 May 2022, 2022.
  Abstract
  This paper presents a novel approach to ensure the quality of the Digital Twin models that modern Cyber-Physical Manufacturing Systems (CPMS) rely on. CPMS are configurable and intelligent. Environmental and system parameters change frequently. Thus, static models are inadequate. Autonomous mobile robots and the simulation of their movement are important elements of these CPMS. Based on our reinforcement learning-based methodology, we use these robots as an example to show how the Digital Twin automatically improves models that do not perfectly represent the physical asset, making it an intelligent Digital Twin. In our scenario, the behavior of the asset deviates from the simulated prediction, i.e., a simulation gap occurs. The presented approach closes this simulation gap through a three-step mechanism. First, it makes the simulated data and the real data comparable and synchronizes it. Second, it applies reinforcement learning to find patterns in the deviations between the simulated and real data. Third, it learns to compensate for them. The evaluation of this example shows promising results.
  BibTeX
  @conference{muller2022selfimproving, abstract = {This paper presents a novel approach to ensure the quality of the Digital Twin models that modern Cyber-Physical Manufacturing Systems (CPMS) rely on. CPMS are configurable and intelligent. Environmental and system parameters change frequently. Thus, static models are inadequate. Autonomous mobile robots and the simulation of their movement are important elements of these CPMS. Based on our reinforcement learning-based methodology, we use these robots as an example to show how the Digital Twin automatically improves models that do not perfectly represent the physical asset, making it an intelligent Digital Twin. In our scenario, the behavior of the asset deviates from the simulated prediction, i.e., a simulation gap occurs. The presented approach closes this simulation gap through a three-step mechanism. First, it makes the simulated data and the real data comparable and synchronizes it. Second, it applies reinforcement learning to find patterns in the deviations between the simulated and real data. Third, it learns to compensate for them. The evaluation of this example shows promising results. }, author = {Müller, Manuel and Jazdi, Nasser and Weyrich, Michael}, booktitle = {14th IFAC Workshop on Intelligent Manufacturing Systems, 5 May 2022 }, doi = {10.1016/j.ifacol.2022.04.181}, title = {Self-improving Models for the Intelligent Digital Twin: Towards Closing the Reality-to-Simulation Gap}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Self-improving_Models_for_the_Intelligent_Digital_Twin_Towards_Closing_the_Reality-to-Simulation_Gap.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Self-improving_Models_for_the_Intelligent_Digital_Twin_Towards_Closing_the_Reality-to-Simulation_Gap.pdf
25. V. Stegmaier, W. Schaaf, N. Jazdi, and M. Weyrich, “Simulation Model for Digital Twins of Pneumatic Vacuum Ejectors,” Chemical Engineering & Technology, Band 45, September 2022, 2022.
  Abstract
  Increasing productivity, as well as flexibility, is required for the industrial production sector. To meet these challenges, concepts in the field of “Industry 4.0” are arising, such as the concept of Digital Twins. Vacuum handling systems are a widespread technology for material handling in industry and face the same challenges and opportunities. In this field, a key issue is the lack of Digital Twins containing behavior models for vacuum handling systems and their components in different applications and use cases. Therefore, the object of this paper is to propose a novel concept for modeling and simulating the fluidic behavior of pneumatic vacuum ejectors as key components of vacuum handling systems. In order to increase the simulation accuracy, the concept can access instance‐specific data of the used asset instead of object‐specific data. The model and the data are part of the Digital Twins of pneumatic vacuum ejectors, which shall be able to be combined with other components to represent a Digital Twin of entire vacuum handling systems. The proposed model is validated in an experimental test set‐up and in an industrial application delivering sufficiently accurate results.
  BibTeX
  @article{stegmaier2022simulation, abstract = {Increasing productivity, as well as flexibility, is required for the industrial production sector. To meet these challenges, concepts in the field of “Industry 4.0” are arising, such as the concept of Digital Twins. Vacuum handling systems are a widespread technology for material handling in industry and face the same challenges and opportunities. In this field, a key issue is the lack of Digital Twins containing behavior models for vacuum handling systems and their components in different applications and use cases. Therefore, the object of this paper is to propose a novel concept for modeling and simulating the fluidic behavior of pneumatic vacuum ejectors as key components of vacuum handling systems. In order to increase the simulation accuracy, the concept can access instance‐specific data of the used asset instead of object‐specific data. The model and the data are part of the Digital Twins of pneumatic vacuum ejectors, which shall be able to be combined with other components to represent a Digital Twin of entire vacuum handling systems. The proposed model is validated in an experimental test set‐up and in an industrial application delivering sufficiently accurate results.}, author = {Stegmaier, Valentin and Schaaf, Walter and Jazdi, Nasser and Weyrich, Michael}, journal = {Chemical Engineering & Technology, Band 45, September 2022}, title = {Simulation Model for Digital Twins of Pneumatic Vacuum Ejectors}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Simulation_Model_for_Digital_Twins_of_Pneumatic_Vacuum_Ejectors.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Simulation_Model_for_Digital_Twins_of_Pneumatic_Vacuum_Ejectors.pdf
26. S. Kamm, S. Bickelhaupt, K. Sharma, N. Jazdi, I. Kallfass, and M. Weyrich, “Simulation-to-Reality based Transfer Learning for the Failure Analysis of SiC Power Transistors,” in 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022, 2022.
  Abstract
  Failure analysis is essential for improving the reliability and manufacturability of electronic devices. With the time-domain reflectometry method, failures can be analyzed non-destructively. The method enables the detection, location, and characterization of hard interconnection failures (open or shorts) as well as of soft interconnection failures, which can give an outlook on imminent hard failures. Generating measurement data from real failed devices is costly since failed devices need to be selected and the measurements need to be performed and prepared. In contrast, simulation models are often available where all possible kinds of failures can be created. Therefore, we propose simulation to real transfer learning for the failure analysis on time-domain reflectometry data. A deep learning model shall first be trained on time-domain reflectometry simulation data and then be transferred to measurement data of a power transistor. We investigate different possibilities of transfer and evaluate the performance of a SiC power transistor.
  BibTeX
  @conference{kamm2022simulationtoreality, abstract = {Failure analysis is essential for improving the reliability and manufacturability of electronic devices. With the time-domain reflectometry method, failures can be analyzed non-destructively. The method enables the detection, location, and characterization of hard interconnection failures (open or shorts) as well as of soft interconnection failures, which can give an outlook on imminent hard failures. Generating measurement data from real failed devices is costly since failed devices need to be selected and the measurements need to be performed and prepared. In contrast, simulation models are often available where all possible kinds of failures can be created. Therefore, we propose simulation to real transfer learning for the failure analysis on time-domain reflectometry data. A deep learning model shall first be trained on time-domain reflectometry simulation data and then be transferred to measurement data of a power transistor. We investigate different possibilities of transfer and evaluate the performance of a SiC power transistor.}, author = {Kamm, Simon and Bickelhaupt, Sandra and Sharma, Kanuj and Jazdi, Nasser and Kallfass, Ingmar and Weyrich, Michael}, booktitle = {27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022}, title = {Simulation-to-Reality based Transfer Learning for the Failure Analysis of SiC Power Transistors}, url = {https://doi.org/10.1109/ETFA52439.2022.9921681}, year = 2022 }
  Link
  https://doi.org/10.1109/ETFA52439.2022.9921681
27. M. Müller, N. Jazdi, and M. Weyrich, “Situation-based Identification of Probable Loss Scenarios of Industrial Mobile Robots,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022, 2022.
  - Abstract
  - BibTeX
  Abstract
  In the production of the future, people and robots will work together in dynamic environments. Industrial mobile robots drive past workers and obstacles to the assemblers' workstations, pick up workpieces and deliver them to the next free workstation. To ensure reliable production, robots must carefully consider their actions based on the current situation to minimize losses. In order to reason about losses, it is necessary to identify loss scenarios that are likely to arise from the system's situation. In this paper, the authors propose a novel methodology for identifying these likely loss scenarios based on fault injectors. The fault injectors are trained using reinforcement learning. Based on a probability model of disruptive events (faults), the agents learn to destabilize the system by simulating such events. When a chain of these events leads to a loss, a loss scenario is found. The higher the probability of the loss scenario, the higher the reward for the agent. In this way, the fault injectors optimize for maximally likely loss scenarios. After describing the methodology, the authors propose a framework for systematically classifying different types of fault injectors and give advice on how to build them. Finally, the authors demonstrate reinforcement learning-based fault injectors on the path planning of the mobile robot platform Robotino.
  BibTeX
  @conference{muller2022adaptive, abstract = {In the production of the future, people and robots will work together in dynamic environments. Industrial mobile robots drive past workers and obstacles to the assemblers' workstations, pick up workpieces and deliver them to the next free workstation. To ensure reliable production, robots must carefully consider their actions based on the current situation to minimize losses. In order to reason about losses, it is necessary to identify loss scenarios that are likely to arise from the system's situation. In this paper, the authors propose a novel methodology for identifying these likely loss scenarios based on fault injectors. The fault injectors are trained using reinforcement learning. Based on a probability model of disruptive events (faults), the agents learn to destabilize the system by simulating such events. When a chain of these events leads to a loss, a loss scenario is found. The higher the probability of the loss scenario, the higher the reward for the agent. In this way, the fault injectors optimize for maximally likely loss scenarios. After describing the methodology, the authors propose a framework for systematically classifying different types of fault injectors and give advice on how to build them. Finally, the authors demonstrate reinforcement learning-based fault injectors on the path planning of the mobile robot platform Robotino.}, author = {Müller, Manuel and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022}, title = {Situation-based Identification of Probable Loss Scenarios of Industrial Mobile Robots}, year = 2022 }
28. M. Müller, G. Ghasemi, N. Jazdi, and M. Weyrich, “Situational Risk Assessment Design for Autonomous Mobile Robots,” 32nd CIRP Design Conference 2022, Procedia CIRP, Vol. 109, pp. 72-77, 21. Juni 2022, 2022.
  Abstract
  The emerging autonomous mobile robots promise a new level of efficiency and flexibility. However, because these types of systems operate in the same space as humans, mobile robots must cope with dynamic changes and heterogeneously structured environments. To ensure safety, new approaches are needed that model risk at runtime. This risk depends on the situation and is therefore a situational risk. In this paper, we propose a new methodology to model situational risk based on multi-agent adversarial reinforcement learning. In this methodology, two competing groups of reinforcement learning agents, namely the protagonists and the adversaries, fight against each other in the simulation. The adversaries represent the disruptive and destabilizing factors, while the protagonists try to compensate for them. The situational risk is then derived from the outcome of the simulated struggle. At this point, the system’s Digital Twin provides up-to-date and relevant models for simulation and synchronizes the simulation with the real asset. Our risk modeling differentiates the four steps of intelligent information processing: sense, analyze, process, and execute. To find the appropriate adversaries and actors for each of these steps, this methodology builds on Systems Theoretic Process Analysis (STPA). Using STPA, we identify critical signals that lead to losses when a disturbance under certain conditions or in certain situations occurs. At this point, the challenge of managing the complexity arises. We face this issue using training effort as a metric to evaluate it. Through statistical analysis of the identified signals, we derive a procedure for defining action spaces and rewards for the agents in question. We validate the methodology using the example of a Robotino 3 Premium from Festo, an autonomous mobile robot.
  BibTeX
  @article{muller2022situational, abstract = {The emerging autonomous mobile robots promise a new level of efficiency and flexibility. However, because these types of systems operate in the same space as humans, mobile robots must cope with dynamic changes and heterogeneously structured environments. To ensure safety, new approaches are needed that model risk at runtime. This risk depends on the situation and is therefore a situational risk. In this paper, we propose a new methodology to model situational risk based on multi-agent adversarial reinforcement learning. In this methodology, two competing groups of reinforcement learning agents, namely the protagonists and the adversaries, fight against each other in the simulation. The adversaries represent the disruptive and destabilizing factors, while the protagonists try to compensate for them. The situational risk is then derived from the outcome of the simulated struggle. At this point, the system’s Digital Twin provides up-to-date and relevant models for simulation and synchronizes the simulation with the real asset. Our risk modeling differentiates the four steps of intelligent information processing: sense, analyze, process, and execute. To find the appropriate adversaries and actors for each of these steps, this methodology builds on Systems Theoretic Process Analysis (STPA). Using STPA, we identify critical signals that lead to losses when a disturbance under certain conditions or in certain situations occurs. At this point, the challenge of managing the complexity arises. We face this issue using training effort as a metric to evaluate it. Through statistical analysis of the identified signals, we derive a procedure for defining action spaces and rewards for the agents in question. We validate the methodology using the example of a Robotino 3 Premium from Festo, an autonomous mobile robot. }, author = {Müller, Manuel and Ghasemi, Golsa and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.procir.2022.05.216}, journal = {32nd CIRP Design Conference 2022, Procedia CIRP, Vol. 109, pp. 72-77, 21. Juni 2022}, title = {Situational Risk Assessment Design for Autonomous Mobile Robots}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Situational_Risk_Assessment_Design_for_Autonomous_Mobile_Robots.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Situational_Risk_Assessment_Design_for_Autonomous_Mobile_Robots.pdf
29. H. Vietz, T. Rauch, and M. Weyrich, “Synthetic Training Data Generation for Convolutional Neural Networks in Vision Applications,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), 2022.
  - Abstract
  - BibTeX
  Abstract
  Vision applications are becoming increasingly important for product quality surveillance in manufacturing. Training consistently well-performing visual detection algorithms based on convolutional neural networks is very challenging. Typically, there is too much training data for engineers to keep track of possible gaps in it. But even small cases of missing training data e.g. certain viewing angles can lead to trained CNNs that are unable to detect objects, that seem obvious to engineers i.e. cognition gaps. This paper presents how synthetic training data can be created in a targeted manner to close cognitive gaps of a CNN for specific use-cases. The proposed methodology uses 3D rendering to create new image data by variating scene parameters. The created data is used to reveal a cognition gap of a CNN. We show that by using this created synthetic data to train the CNN the cognition gap can be successfully closed. This is evaluated with the well-known AlexNet CNN used as a visual bicycle detector. The bicycle example is used as a stand-in for a geometrically interesting, but simple product, that is manufactured in large and growing amounts.
  BibTeX
  @conference{vietz2022synthetic, abstract = {Vision applications are becoming increasingly important for product quality surveillance in manufacturing. Training consistently well-performing visual detection algorithms based on convolutional neural networks is very challenging. Typically, there is too much training data for engineers to keep track of possible gaps in it. But even small cases of missing training data e.g. certain viewing angles can lead to trained CNNs that are unable to detect objects, that seem obvious to engineers i.e. cognition gaps. This paper presents how synthetic training data can be created in a targeted manner to close cognitive gaps of a CNN for specific use-cases. The proposed methodology uses 3D rendering to create new image data by variating scene parameters. The created data is used to reveal a cognition gap of a CNN. We show that by using this created synthetic data to train the CNN the cognition gap can be successfully closed. This is evaluated with the well-known AlexNet CNN used as a visual bicycle detector. The bicycle example is used as a stand-in for a geometrically interesting, but simple product, that is manufactured in large and growing amounts.}, author = {Vietz, Hannes and Rauch, Tristan and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)}, title = {Synthetic Training Data Generation for Convolutional Neural Networks in Vision Applications}, year = 2022 }
30. C. Ebert, D. Bajaj, and M. Weyrich, “Testing Software Systems,” IEEE SOFTWARE, July/August 2022, 2022.
  Abstract
  Testing is often considered boring. Wrong! Testing matters for many reasons. Not only is it the area where most of the money goes across the product life cycle but new challanges, such as adaptive software, agile deployment, and artificial intelligence (AI)-driven systems, demand bnovel test technologies. Michael Weyrich, Divith Bajaj, and I evaluate current technologies for software testing, providing an overview of methods and tools, including systematic risk assesment for each test activity. A case study for testing AI systems provides insight into novel intelligent testing stratigies.
  BibTeX
  @article{ebert2022testing, abstract = {Testing is often considered boring. Wrong! Testing matters for many reasons. Not only is it the area where most of the money goes across the product life cycle but new challanges, such as adaptive software, agile deployment, and artificial intelligence (AI)-driven systems, demand bnovel test technologies. Michael Weyrich, Divith Bajaj, and I evaluate current technologies for software testing, providing an overview of methods and tools, including systematic risk assesment for each test activity. A case study for testing AI systems provides insight into novel intelligent testing stratigies.}, author = {Ebert, Christof and Bajaj, Divith and Weyrich, Michael}, journal = {IEEE SOFTWARE, July/August 2022}, title = {Testing Software Systems}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Testing_Software_Systems.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Testing_Software_Systems.pdf
31. B. Maschler, T. Knodel, and M. Weyrich, “Towards Deep Industrial Transfer Learning: Clustering for Transfer Case Selection,” in 27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022, 2022.
  - Abstract
  - BibTeX
  Abstract
  Industrial transfer learning increases the adaptability of deep learning algorithms towards heterogenous and dynamic industrial use cases without high manual efforts. The appropriate selection of what to transfer can vastly improve a transfer’s results. In this paper, a transfer case selection based upon clustering is presented. Founded on a survey of clustering algorithms, the BIRCH algorithm is selected for this purpose. It is evaluated on an industrial time series dataset from a discrete manufacturing scenario. Results underline the approaches’ applicability caused by its results’ reproducibility and practical indifference to sequence, size and dimensionality of (sub-)datasets to be clustered sequentially.
  BibTeX
  @conference{maschler2022towards, abstract = {Industrial transfer learning increases the adaptability of deep learning algorithms towards heterogenous and dynamic industrial use cases without high manual efforts. The appropriate selection of what to transfer can vastly improve a transfer’s results. In this paper, a transfer case selection based upon clustering is presented. Founded on a survey of clustering algorithms, the BIRCH algorithm is selected for this purpose. It is evaluated on an industrial time series dataset from a discrete manufacturing scenario. Results underline the approaches’ applicability caused by its results’ reproducibility and practical indifference to sequence, size and dimensionality of (sub-)datasets to be clustered sequentially.}, author = {Maschler, Benjamin and Knodel, Tim and Weyrich, Michael}, booktitle = {27th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, Germany, September 2022}, title = {Towards Deep Industrial Transfer Learning: Clustering for Transfer Case Selection }, year = 2022 }
32. M. Müller, N. Jazdi, and M. Weyrich, “Towards Situative Risk Assessment for Industrial Mobile Robots,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022, 2022.
  - Abstract
  - BibTeX
  Abstract
  Industrial mobile robots increasingly operate in dynamic and complex environments, resulting in risks that arise from the situation. Consequently, mobile robots need knowledge about the situative risk to make responsible decisions, e.g., when planning a trajectory. In this paper, the authors present a new approach to evaluate these situative risks at runtime. To compute the situative risk, the proposed approach uses multi-agent adversarial reinforcement learning. Unlike the usual approach that uses the self-play mechanism to harden the agents against disturbances, the approach directly uses the self-play to determine the confidence that the system can handle the current situation. Based on the evaluation of the strength of the perceived perturbations, the robot's digital twin calibrates the action space of the adversarial agents. In this way, the adversarial agents represent the disturbances that are likely to occur. From the simulation results of the competing agents, the digital twin infers the confidence with which the system can handle the situation. In the event that the system cannot handle the situation and crashes in the simulation, the digital twin calculates the probability that the simulated scenario will occur in reality. To calculate this probability, the authors propose the method of game-theoretic event trees. Combining the probability of an accident scenario with the damage caused by the simulated hazard, the results of situative risk are obtained. The approach is qualitatively evaluated using a case study. In this case study, a industrial mobile robot called Robotino is considered that connects workstations in a matrix production system. The case study shows that the approach is promising.
  BibTeX
  @conference{muller2022towards, abstract = {Industrial mobile robots increasingly operate in dynamic and complex environments, resulting in risks that arise from the situation. Consequently, mobile robots need knowledge about the situative risk to make responsible decisions, e.g., when planning a trajectory. In this paper, the authors present a new approach to evaluate these situative risks at runtime. To compute the situative risk, the proposed approach uses multi-agent adversarial reinforcement learning. Unlike the usual approach that uses the self-play mechanism to harden the agents against disturbances, the approach directly uses the self-play to determine the confidence that the system can handle the current situation. Based on the evaluation of the strength of the perceived perturbations, the robot's digital twin calibrates the action space of the adversarial agents. In this way, the adversarial agents represent the disturbances that are likely to occur. From the simulation results of the competing agents, the digital twin infers the confidence with which the system can handle the situation. In the event that the system cannot handle the situation and crashes in the simulation, the digital twin calculates the probability that the simulated scenario will occur in reality. To calculate this probability, the authors propose the method of game-theoretic event trees. Combining the probability of an accident scenario with the damage caused by the simulated hazard, the results of situative risk are obtained. The approach is qualitatively evaluated using a case study. In this case study, a industrial mobile robot called Robotino is considered that connects workstations in a matrix production system. The case study shows that the approach is promising.}, author = {Müller, Manuel and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September, 2022 }, title = {Towards Situative Risk Assessment for Industrial Mobile Robots}, year = 2022 }
33. A. Löcklin, M. Artelt, T. Ruppert, H. Vietz, N. Jazdi, and M. Weyrich, “Trajectory Prediction of Moving Workers for Autonomous Mobile Robots on the Shop Floor,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022, 2022.
  - Abstract
  - BibTeX
  Abstract
  In partially automated manufacturing, humans work together with mobile robots. Trajectory prediction, i.e. predicting future positions of human workers, improves collaboration and coexistence between humans and robots on the shop floor. In this paper, we discuss the interrelated research questions of how human motion trajectories can be predicted and how mobile robots such as Autonomous Mobile Robots and Automated Guided Vehicles can take such predictions into account in their pathfinding and navigation. On the robot side, advanced D* pathfinding algorithms allow robots to take dynamic obstacles into account. For trajectory prediction, the position of human workers is determined by an Ultra-Wideband-based Real-Time Locating System. A trajectory prediction framework is introduced to support the implementation and use of pattern- and planning-based trajectory prediction algorithms. The evaluation is based on scenarios from the addressed problem area of manufacturing.
  BibTeX
  @conference{locklin2022trajectory, abstract = {In partially automated manufacturing, humans work together with mobile robots. Trajectory prediction, i.e. predicting future positions of human workers, improves collaboration and coexistence between humans and robots on the shop floor. In this paper, we discuss the interrelated research questions of how human motion trajectories can be predicted and how mobile robots such as Autonomous Mobile Robots and Automated Guided Vehicles can take such predictions into account in their pathfinding and navigation. On the robot side, advanced D* pathfinding algorithms allow robots to take dynamic obstacles into account. For trajectory prediction, the position of human workers is determined by an Ultra-Wideband-based Real-Time Locating System. A trajectory prediction framework is introduced to support the implementation and use of pattern- and planning-based trajectory prediction algorithms. The evaluation is based on scenarios from the addressed problem area of manufacturing.}, author = {Löcklin, Andreas and Artelt, Maurice and Ruppert, Tamás and Vietz, Hannes and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), September 2022}, doi = {10.1109/ETFA52439.2022.9921493}, title = {Trajectory Prediction of Moving Workers for Autonomous Mobile Robots on the Shop Floor}, year = 2022 }
34. A. Löcklin, F. Dettinger, M. Artelt, N. Jazdi, and M. Weyrich, “Trajectory Prediction of Workers to Improve AGV and AMR Operation based on the Manufacturing Schedule,” Procedia CIRP, Vol. 107, pp. 283-288, Mai, 2022, 2022.
  Abstract
  In semi-automated manufacturing, an increasing amount of intelligent mobile robots operate in close proximity to human workers. Considering future positions of humans allows to further improve the efficiency in terms of throughput of Autonomous Mobile Robots (AMR) and Automated Guided Vehicles (AGV). The longer the prediction horizon, i.e. the more position values of humans can be predicted in the near and distant future, the more a robot can adjust its route accordingly and optimize the process. This paper discusses the challenges of human motion trajectory prediction in manufacturing and presents a schedule-based approach that uses real-time schedule data obtained from Manufacturing Execution Systems (MES). Schedule-awareness in human motion trajectory prediction extends semantic mapping approaches and effectively reduces the number of probable destinations by considering which process steps are next for the currently produced goods. With a reduced set of destinations, the performance of forward-planning trajectory prediction can be improved. For evaluation, a commercial MES is used together with an Ultra-wideband-based Real-Time Locating System (RTLS) for obtaining position data of humans. On this basis, a naive Bayes classifier utilizes MES-schedule and real-time position data to predict human motion intentions. Abstract activity modeling ensures that only a few training data sets are required for deployment, thus making this approach suitable for rapidly changing manufacturing environments such as in flexible manufacturing.
  BibTeX
  @article{locklin2022trajectory, abstract = {In semi-automated manufacturing, an increasing amount of intelligent mobile robots operate in close proximity to human workers. Considering future positions of humans allows to further improve the efficiency in terms of throughput of Autonomous Mobile Robots (AMR) and Automated Guided Vehicles (AGV). The longer the prediction horizon, i.e. the more position values of humans can be predicted in the near and distant future, the more a robot can adjust its route accordingly and optimize the process. This paper discusses the challenges of human motion trajectory prediction in manufacturing and presents a schedule-based approach that uses real-time schedule data obtained from Manufacturing Execution Systems (MES). Schedule-awareness in human motion trajectory prediction extends semantic mapping approaches and effectively reduces the number of probable destinations by considering which process steps are next for the currently produced goods. With a reduced set of destinations, the performance of forward-planning trajectory prediction can be improved. For evaluation, a commercial MES is used together with an Ultra-wideband-based Real-Time Locating System (RTLS) for obtaining position data of humans. On this basis, a naive Bayes classifier utilizes MES-schedule and real-time position data to predict human motion intentions. Abstract activity modeling ensures that only a few training data sets are required for deployment, thus making this approach suitable for rapidly changing manufacturing environments such as in flexible manufacturing.}, author = {Löcklin, Andreas and Dettinger, Falk and Artelt, Maurice and Jazdi, Nasser and Weyrich, Michael}, booktitle = {Procedia CIRP, Vol. 107, pp. 283-288, Mai, 2022}, doi = {10.1016/j.procir.2022.04.046}, issn = {2212-8271}, title = {Trajectory Prediction of Workers to Improve AGV and AMR Operation based on the Manufacturing Schedule}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Trajectory_Prediction_of_Workers_to_Improve_AGV_and_AMR_Operation_based_on_the_Manufacturing_Schedule.pdf}, year = 2022 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022_Trajectory_Prediction_of_Workers_to_Improve_AGV_and_AMR_Operation_based_on_the_Manufacturing_Schedule.pdf
35. D. White, M. Weiß, N. Jazdi-Motlagh, and M. Weyrich, “Variant generation of software-defined mechatronic systems in model-based systems engineering,” in 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), Stuttgart, 2022.
  - BibTeX
  BibTeX
  @inproceedings{white2022variant, address = {Piscataway}, affiliation = {White, D (Corresponding Author), Univ Stuttgart, Inst Ind Automat \& Software Engn, Stuttgart, Germany. White, Dustin; Weiss, Matthias; Jazdi, Nasser; Weyrich, Michael, Univ Stuttgart, Inst Ind Automat \& Software Engn, Stuttgart, Germany.}, author = {White, Dustin and Weiß, Matthias and Jazdi-Motlagh, Nasser and Weyrich, Michael}, booktitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)}, doi = {10.1109/ETFA52439.2022.9921483}, eventdate = {2022-09-06/2022-09-09}, eventtitle = {2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)}, isbn = {{978-1-6654-9996-5} and {978-1-6654-9997-2}}, language = {eng}, publisher = {IEEE}, research-areas = {Automation \& Control Systems; Engineering}, title = {Variant generation of software-defined mechatronic systems in model-based systems engineering}, unique-id = {WOS:000934103900055}, venue = {Stuttgart}, year = 2022 }
2021
1. D. Braun, F. Biesinger, N. Jazdi, and M. Weyrich, “A concept for the automated layout generation of an existing production line within the Digital Twin,” 8th CIRP Conference on Assembly Technology and Systems, 29 September-1 October 2020, Athens, 2021.
  - Abstract
  - BibTeX
  Abstract
  The use of the Digital Twin as a promising technology during the reconfiguration of automated systems enables to meet the challenges of increasing product diversity and shortening product life cycles in today's industry. The use of Digital Twins supports engineers in all phases of the life cycle of a production line. Over time, however, production facilities are often modified and improved, while at the same time the created models during the engineering process of the system remain unchanged and no longer correspond to the real facility. Manual updating of the positions in the digital layout is very time-consuming and therefore expensive. This paper presents a concept for the automatic update of the layout of a production line. In this concept, the positions of the robots and their active and passive peripheral devices are automatically positioned in a digital plant model using information from the current configuration of the robots in a production line. Therefore, engineers can use the resulting synchronized digital plant model, Digital Twin of the system, to further optimize or expand the production plant.
  BibTeX
  @article{braun2021concept, abstract = {The use of the Digital Twin as a promising technology during the reconfiguration of automated systems enables to meet the challenges of increasing product diversity and shortening product life cycles in today's industry. The use of Digital Twins supports engineers in all phases of the life cycle of a production line. Over time, however, production facilities are often modified and improved, while at the same time the created models during the engineering process of the system remain unchanged and no longer correspond to the real facility. Manual updating of the positions in the digital layout is very time-consuming and therefore expensive. This paper presents a concept for the automatic update of the layout of a production line. In this concept, the positions of the robots and their active and passive peripheral devices are automatically positioned in a digital plant model using information from the current configuration of the robots in a production line. Therefore, engineers can use the resulting synchronized digital plant model, Digital Twin of the system, to further optimize or expand the production plant.}, author = {Braun, Dominik and Biesinger, Florian and Jazdi, Nasser and Weyrich, Michael}, doi = {10.1016/j.procir.2020.05.242}, journal = {8th CIRP Conference on Assembly Technology and Systems, 29 September-1 October 2020, Athens}, title = {A concept for the automated layout generation of an existing production line within the Digital Twin}, year = 2021 }
2. S. Kamm, K. Sharma, N. Jazdi, and M. Weyrich, “A Hybrid Modelling Approach for Parameter Estimation of Analytical Reflection Models in the Failure Analysis Process of Semiconductors,” in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23-27 August 2021, 2021, pp. 417–422.
  Abstract
  Electronic devices are one of the key factors for recent advances in smart production systems or automotive. Reliability and robustness are key issues. To further increase this reliability, occurring failures in an electronic device has to be investigated in post-production failure analysis processes. One recent technique to detect and locate failures in electronic components is Time-Domain Reflectometry. This method offers the chance to detect several kinds of failures (e.g. a hard or soft failure) and localize the failure nondestructively. In theory, this can be determined following defined physical formulas. Nevertheless, the received signals are not perfect and mixed with noise from the measurement device or disturbed by nonoptimal material properties. In addition, complex architectures of devices are hard to model based on analytical models. Thus, these models solely are not sufficient for the failure analysis process. For this reason, a hybrid modeling approach is proposed, using a Machine Learning model in combination with physical models to detect and characterize the failure and its exact position. The Machine Learning model will be trained with simulated Time-Domain Reflectometry data.
  BibTeX
  @conference{kamm2021, abstract = {Electronic devices are one of the key factors for recent advances in smart production systems or automotive. Reliability and robustness are key issues. To further increase this reliability, occurring failures in an electronic device has to be investigated in post-production failure analysis processes. One recent technique to detect and locate failures in electronic components is Time-Domain Reflectometry. This method offers the chance to detect several kinds of failures (e.g. a hard or soft failure) and localize the failure nondestructively. In theory, this can be determined following defined physical formulas. Nevertheless, the received signals are not perfect and mixed with noise from the measurement device or disturbed by nonoptimal material properties. In addition, complex architectures of devices are hard to model based on analytical models. Thus, these models solely are not sufficient for the failure analysis process. For this reason, a hybrid modeling approach is proposed, using a Machine Learning model in combination with physical models to detect and characterize the failure and its exact position. The Machine Learning model will be trained with simulated Time-Domain Reflectometry data.}, author = {Kamm, Simon and Sharma, Kanuj and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23-27 August 2021 }, doi = {10.1109/CASE49439.2021.9551454}, pages = { 417-422}, title = {A Hybrid Modelling Approach for Parameter Estimation of Analytical Reflection Models in the Failure Analysis Process of Semiconductors}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_A_Hybrid_Modelling_Approach_for_Parameter_Estimation_of_Analytical_Reflection_Models_in_the_Failure_Analysis_Process_of_Semiconductors.pdf}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_A_Hybrid_Modelling_Approach_for_Parameter_Estimation_of_Analytical_Reflection_Models_in_the_Failure_Analysis_Process_of_Semiconductors.pdf
3. H. Vietz, T. Rauch, A. Löcklin, N. Jazdi, and M. Weyrich, “A Methodology to Identify Cognition Gaps in Visual Recognition Applications Based on Convolutional Neural Network,” in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23-27 August 2021, 2021, pp. 2045–2050.
  - Abstract
  - BibTeX
  Abstract
  Developing consistently well performing visual recognition applications based on convolutional neural networks, e.g. for autonomous driving, is very challenging. One of the obstacles during the development is the opaqueness of their cognitive behaviour. A considerable amount of literature has been published which describes irrational behaviour of trained CNNs showcasing gaps in their cognition. In this paper, a methodology is presented that creates worst-case images using image augmentation techniques. If the CNN's cognitive performance on such images is weak while the augmentation techniques are supposedly harmless, a potential gap in the cognition has been found. The presented worst-case image generator is using adversarial search approaches to efficiently identify the most challenging (worst) image. This is evaluated with the well-known AlexNet CNN using images depicting a typical driving scenario.
  BibTeX
  @conference{vietz2021methodology, abstract = {Developing consistently well performing visual recognition applications based on convolutional neural networks, e.g. for autonomous driving, is very challenging. One of the obstacles during the development is the opaqueness of their cognitive behaviour. A considerable amount of literature has been published which describes irrational behaviour of trained CNNs showcasing gaps in their cognition. In this paper, a methodology is presented that creates worst-case images using image augmentation techniques. If the CNN's cognitive performance on such images is weak while the augmentation techniques are supposedly harmless, a potential gap in the cognition has been found. The presented worst-case image generator is using adversarial search approaches to efficiently identify the most challenging (worst) image. This is evaluated with the well-known AlexNet CNN using images depicting a typical driving scenario.}, author = {Vietz, Hannes and Rauch, Tristan and Löcklin, Andreas and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23-27 August 2021}, doi = {10.1109/CASE49439.2021.9551605}, pages = {2045-2050}, title = {A Methodology to Identify Cognition Gaps in Visual Recognition Applications Based on Convolutional Neural Network}, year = 2021 }
4. B. Lindemann, B. Maschler, N. Sahlab, and M. Weyrich, “A survey on anomaly detection for technical systems using LSTM networks,” Computers in Industry, vol. 131, pp. 103498, June 2021, 2021.
  Abstract
  Anomalies represent deviations from the intended system operation and can lead to decreased efficiency as well as partial or complete system failure. As the causes of anomalies are often unknown due to complex system dynamics, efficient anomaly detection is necessary. Conventional detection approaches rely on statistical and time-invariant methods that fail to address the complex and dynamic nature of anomalies. With advances in artificial intelligence and increasing importance for anomaly detection and prevention in various domains, artificial neural network approaches enable the detection of more com-plex anomaly types while considering temporal and contextual characteristics. In this article, a survey on state-of-the-art anomaly detection using deep neural and especially long short-term memory networks is conducted. The investigated approaches are evaluated based on the application scenario, data and anomaly types as well as further metrics. To highlight the potential of upcoming anomaly detection techniques, graph-based and transfer learning approaches are also included in the survey, enabling the analysis of heterogeneous data as well as compensating for its shortage and improving the handling of dynamic processes.
  BibTeX
  @article{lindemann2021survey, abstract = {Anomalies represent deviations from the intended system operation and can lead to decreased efficiency as well as partial or complete system failure. As the causes of anomalies are often unknown due to complex system dynamics, efficient anomaly detection is necessary. Conventional detection approaches rely on statistical and time-invariant methods that fail to address the complex and dynamic nature of anomalies. With advances in artificial intelligence and increasing importance for anomaly detection and prevention in various domains, artificial neural network approaches enable the detection of more com-plex anomaly types while considering temporal and contextual characteristics. In this article, a survey on state-of-the-art anomaly detection using deep neural and especially long short-term memory networks is conducted. The investigated approaches are evaluated based on the application scenario, data and anomaly types as well as further metrics. To highlight the potential of upcoming anomaly detection techniques, graph-based and transfer learning approaches are also included in the survey, enabling the analysis of heterogeneous data as well as compensating for its shortage and improving the handling of dynamic processes.}, author = {Lindemann, Benjamin and Maschler, Benjamin and Sahlab, Nada and Weyrich, Michael}, doi = {doi.org/10.1016/j.compind.2021.103498}, issn = {0166-3615}, journal = {Computers in Industry, vol. 131, pp. 103498, June 2021}, title = {A survey on anomaly detection for technical systems using LSTM networks}, url = {https://doi.org/10.1016/j.compind.2021.103498}, year = 2021 }
  Link
  https://doi.org/10.1016/j.compind.2021.103498
5. N. Sahlab, D. Braun, T. Jung, N. Jazdi, and M. Weyrich, “A Tier-based Model for Realizing Context-Awareness of Digital Twins,” in 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 07-10 Sept. 2021, Västerås, Sweden, 2021.
  - Abstract
  - BibTeX
  Abstract
  Digital Twins are being increasingly used in manufacturing industry to support the whole plant lifecycle. The constantly changing environmental parameters, interactions between various systems and their Digital Twin as well as changes inside the Digital Twin influences the context of the available information. This context information is insufficiently considered to analyze process and optimize the interaction. This article presents an approach to model the internal and external context of a system using a graph-based context tier model. The usage and benefits.
  BibTeX
  @conference{sahlab2021tierbased, abstract = {Digital Twins are being increasingly used in manufacturing industry to support the whole plant lifecycle. The constantly changing environmental parameters, interactions between various systems and their Digital Twin as well as changes inside the Digital Twin influences the context of the available information. This context information is insufficiently considered to analyze process and optimize the interaction. This article presents an approach to model the internal and external context of a system using a graph-based context tier model. The usage and benefits.}, author = {Sahlab, Nada and Braun, Dominik and Jung, Tobias and Jazdi, Nasser and Weyrich, Michael}, booktitle = {26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 07-10 Sept. 2021, Västerås, Sweden}, title = {A Tier-based Model for Realizing Context-Awareness of Digital Twins}, year = 2021 }
6. M. Müller, N. Jazdi, A. Löcklin, L. Hettich, and M. Weyrich, “Adaptive Models for Safe Maintenance Planning of Cyber-physical Systems,” in 15 th CIRP Conference on Intelligent Computation and Manufacturing Engineering, Gulf of Naples, Italy, July 2021, 2021.
  Abstract
  The progress of digitalization and Internet of Things enables more and more complex, networked and powerful Cyber-physical Systems (CPS) operating in uncertain environments. This complexity and uncertainty, however, makes it unfeasible to model every aspect in advance. This causes the models to leave their scope and reach their capability limits. Specifically, in safe maintenance planning for highly-automated trucks, this fact causes waste of valuable resource, since maintenance models are often more rule-of-thumb (e.g. operation hours) than precise. In order to counteract this issue, we propose extending the digital twin concept by artificial intelligence such that the models become dynamic and adaptive. Having described the general approach and its architecture, we showcase and evaluate the approach in a highly-automated truck scenario.
  BibTeX
  @conference{muller2022adaptive, abstract = {The progress of digitalization and Internet of Things enables more and more complex, networked and powerful Cyber-physical Systems (CPS) operating in uncertain environments. This complexity and uncertainty, however, makes it unfeasible to model every aspect in advance. This causes the models to leave their scope and reach their capability limits. Specifically, in safe maintenance planning for highly-automated trucks, this fact causes waste of valuable resource, since maintenance models are often more rule-of-thumb (e.g. operation hours) than precise. In order to counteract this issue, we propose extending the digital twin concept by artificial intelligence such that the models become dynamic and adaptive. Having described the general approach and its architecture, we showcase and evaluate the approach in a highly-automated truck scenario.}, author = {Müller, Manuel and Jazdi, Nasser and Löcklin, Andreas and Hettich, Lennard and Weyrich, Michael}, booktitle = {15 th CIRP Conference on Intelligent Computation and Manufacturing Engineering, Gulf of Naples, Italy, July 2021}, title = {Adaptive Models for Safe Maintenance Planning of Cyber-physical Systems}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022-Adaptive_Models_for_Safe_Maintenance_Planning_of_Cyber-physical_Systems.pdf}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2022-Adaptive_Models_for_Safe_Maintenance_Planning_of_Cyber-physical_Systems.pdf
7. N. Sahlab, N. Jazdi, and M. Weyrich, “An Approach for Context-Aware Cyber-Physical Automation Systems,” in 4th IFAC Conference on Embedded Systems, Computational Intelligence and Telematics in Control, Juli 2021, 2021.
  Abstract
  Future automation systems, operating under increasing dynamic conditions need to be equipped with methods to enhance their adaptability accordingly. Context-aware systems model and apply contextual parameters influencing the interpretation of situations to adapt their operation accordingly. Designing context-aware automation systems requires methods to acquire and process heterogeneous and distributed data in a dynamic and continuous manner. In this contribution, a methodology for processing multimodal data in a flexible and reusable context-model is demonstrated, using concepts of data aggregation and integration, semantic labeling and graph modeling. Based on this approach, the use case of a context-aware medication assistance system is subsequently presented.
  BibTeX
  @conference{sahlab2021approach, abstract = {Future automation systems, operating under increasing dynamic conditions need to be equipped with methods to enhance their adaptability accordingly. Context-aware systems model and apply contextual parameters influencing the interpretation of situations to adapt their operation accordingly. Designing context-aware automation systems requires methods to acquire and process heterogeneous and distributed data in a dynamic and continuous manner. In this contribution, a methodology for processing multimodal data in a flexible and reusable context-model is demonstrated, using concepts of data aggregation and integration, semantic labeling and graph modeling. Based on this approach, the use case of a context-aware medication assistance system is subsequently presented.}, author = {Sahlab, Nada and Jazdi, Nasser and Weyrich, Michael}, booktitle = {4th IFAC Conference on Embedded Systems, Computational Intelligence and Telematics in Control, Juli 2021}, doi = {10.1016/j.ifacol.2021.10.029}, title = {An Approach for Context-Aware Cyber-Physical Automation Systems}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_An_Approach_for_Context-Aware_Cyber-Physical_Automation_Systems.pdf}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_An_Approach_for_Context-Aware_Cyber-Physical_Automation_Systems.pdf
8. A. Löcklin, T. Jung, N. Jazdi, T. Ruppert, and M. Weyrich, “Architecture of a Human-Digital Twin as Common Interface for Operator 4.0 Applications,” Procedia CIRP, Vol. 104, pp. 458-463, September 2021, 2021.
  Abstract
  At collaborative workspaces, humans and robots share the shop floor and work closely together. Operator 4.0 is a wide research topic and its solutions aim at the creation of Human-centered Cyber-Physical Systems that improve operators’ capabilities. Such applications require a bi directional flow of information and need data, models and simulations of machines as well as humans. To realize a common interface for information, the concept of Digital Twin is promising. This paper therefore discusses the adaption of conventional Digital Twin architectures and presents a derived Human-centered Digital Twin (H-DT) architecture designed for operators in production and intralogistics.
  BibTeX
  @article{locklin2021architecture, abstract = {At collaborative workspaces, humans and robots share the shop floor and work closely together. Operator 4.0 is a wide research topic and its solutions aim at the creation of Human-centered Cyber-Physical Systems that improve operators’ capabilities. Such applications require a bi directional flow of information and need data, models and simulations of machines as well as humans. To realize a common interface for information, the concept of Digital Twin is promising. This paper therefore discusses the adaption of conventional Digital Twin architectures and presents a derived Human-centered Digital Twin (H-DT) architecture designed for operators in production and intralogistics.}, author = {Löcklin, Andreas and Jung, Tobias and Jazdi, Nasser and Ruppert, Tamás and Weyrich, Michael}, doi = {10.1016/j.procir.2021.11.077}, issn = {2212-8271}, journal = {Procedia CIRP, Vol. 104, pp. 458-463, September 2021}, title = {Architecture of a Human-Digital Twin as Common Interface for Operator 4.0 Applications}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Architecture_of_a_Human-Digital_Twin_as_Common_Interface_for_Operator_4_0_Applications.pdf}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Architecture_of_a_Human-Digital_Twin_as_Common_Interface_for_Operator_4_0_Applications.pdf
9. D. Braun, W. Schloegl, and M. Weyrich, “Automated data-driven creation of the Digital Twin of a brownfield plant,” in 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 07-10 Sept. 2021, Västerås, Sweden, 2021.
  - Abstract
  - BibTeX
  Abstract
  The success of the reconfiguration of existing manufacturing systems, so called brownfield systems, heavily relies on the knowledge about the system. Reconfiguration can be planned, supported and simplified with the Digital Twin of the system providing this knowledge. However, digital models as the basis of a Digital Twin are usually missing for these plants. This article presents a data-driven approach to gain knowledge about a brownfield system to create the digital models of a Digital Twin and their relations. Finally, a proof of concept shows that process data and position data as data sources deliver the relations between the models of the Digital Twin.
  BibTeX
  @conference{braun2021automated, abstract = {The success of the reconfiguration of existing manufacturing systems, so called brownfield systems, heavily relies on the knowledge about the system. Reconfiguration can be planned, supported and simplified with the Digital Twin of the system providing this knowledge. However, digital models as the basis of a Digital Twin are usually missing for these plants. This article presents a data-driven approach to gain knowledge about a brownfield system to create the digital models of a Digital Twin and their relations. Finally, a proof of concept shows that process data and position data as data sources deliver the relations between the models of the Digital Twin. }, author = {Braun, Dominik and Schloegl, Wolfgang and Weyrich, Michael}, booktitle = {26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 07-10 Sept. 2021, Västerås, Sweden}, title = {Automated data-driven creation of the Digital Twin of a brownfield plant }, year = 2021 }
10. S. Kamm, N. Jazdi, and M. Weyrich, “Automatisierte Datenintegration für den Fehleranalyseprozess von Halbleiterbauelementen mithilfe von Ontologien und Graphen,” in VDI-Kongress Automation 2021, 29.-30.06.2021, Virtuell, 2021.
  Abstract
  Im Sinne der Qualitätssicherung sollen zukünftig produzierte Halbleiterbauelemente den steigenden Anforderungen an Zuverlässigkeit, Konnektivität und Automatisierung standhalten. Dazu ist ein Fehleranalyseprozess notwendig. Um die Effizienz zu steigern und die Fehleranfälligkeit zu reduzieren, soll der Fehleranalyseprozesses mit dazugehöriger Datenanalyse automatisiert werden. Dafür muss zunächst ein Konzept für die automatisierte Integration heterogener Daten aus unterschiedlichen Datenquellen auf Basis aktueller Daten Engineering Methoden entwickelt werden. Die Daten aus unterschiedlichen Quellen (z.B. Produktionsdaten, Datenblätter, Analyseverfahren) müssen eindeutig einem Bauelement zugeordnet werden können und neue Daten oder Analyseergebnisse diesem hinzugefügt werden können. In diesem Beitrag wird für die automatisierte Datenintegration des Fehleranalyseprozesses von Halbleiterbauelementen ein Konzept mithilfe von Ontologien und Graphen vorgestellt und dessen Mehrwerte anhand eines Anwendungsfalls mit einer prototypischen Umsetzung diskutiert. Dafür wird ein hybrider Ontologie-Ansatz genutzt, um die heterogenen Daten in einem Knowledge Graphen zu verknüpfen. Der vorgestellte Ansatz ermöglicht sowohl eine lokale als auch eine globale Datenanalyse. Dadurch können sowohl bisher entwickelte Datenanalyse-Ansätze genutzt werden, als euch neue Algorithmen aufgebaut werden.
  BibTeX
  @conference{kamm2021automatisierte, abstract = {Im Sinne der Qualitätssicherung sollen zukünftig produzierte Halbleiterbauelemente den steigenden Anforderungen an Zuverlässigkeit, Konnektivität und Automatisierung standhalten. Dazu ist ein Fehleranalyseprozess notwendig. Um die Effizienz zu steigern und die Fehleranfälligkeit zu reduzieren, soll der Fehleranalyseprozesses mit dazugehöriger Datenanalyse automatisiert werden. Dafür muss zunächst ein Konzept für die automatisierte Integration heterogener Daten aus unterschiedlichen Datenquellen auf Basis aktueller Daten Engineering Methoden entwickelt werden. Die Daten aus unterschiedlichen Quellen (z.B. Produktionsdaten, Datenblätter, Analyseverfahren) müssen eindeutig einem Bauelement zugeordnet werden können und neue Daten oder Analyseergebnisse diesem hinzugefügt werden können. In diesem Beitrag wird für die automatisierte Datenintegration des Fehleranalyseprozesses von Halbleiterbauelementen ein Konzept mithilfe von Ontologien und Graphen vorgestellt und dessen Mehrwerte anhand eines Anwendungsfalls mit einer prototypischen Umsetzung diskutiert. Dafür wird ein hybrider Ontologie-Ansatz genutzt, um die heterogenen Daten in einem Knowledge Graphen zu verknüpfen. Der vorgestellte Ansatz ermöglicht sowohl eine lokale als auch eine globale Datenanalyse. Dadurch können sowohl bisher entwickelte Datenanalyse-Ansätze genutzt werden, als euch neue Algorithmen aufgebaut werden.}, author = {Kamm, Simon and Jazdi, Nasser and Weyrich, Michael}, booktitle = {VDI-Kongress Automation 2021, 29.-30.06.2021}, eventdate = {29.-30.06.2021}, isbn = {978-3-18-092392-4}, issn = {0083-5560}, title = {Automatisierte Datenintegration für den Fehleranalyseprozess von Halbleiterbauelementen mithilfe von Ontologien und Graphen}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Automatisierte_Datenintegration_fuer_den_Fehleranalyseprozess_von_Halbleiterbauelementen_mithilfe_von_Ontologien_und_Graphen.pdf}, venue = {Virtuell}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Automatisierte_Datenintegration_fuer_den_Fehleranalyseprozess_von_Halbleiterbauelementen_mithilfe_von_Ontologien_und_Graphen.pdf
11. T. Müller, N. Jazdi, J.-P. Schmidt, and M. Weyrich, “Cyber-physical production systems: enhancement with a self-organized reconfiguration management,” in 14th CIRP Conference on Intelligent Computation in Manufacturing Engineering, Gulf of Naples, Italy, 2021.
  Abstract
  The frequency of changes in production requirements is continuously increasing due to economic volatility, shorter innovation cycles and product life cycles. Therefore, a prediction of all goals of a production system at development time is impossible, which is leading to an increased reconfiguration demand during operation. Currently, there are still some weaknesses concerning the reconfiguration of production systems, which are highlighted in this article. The future of industrial automation will be dominated by Cyber-Physical Production Systems, which offer many promising potentials. Hence, this contribution discusses the Cyber-Physical Production Systems and some of their potentials regarding the reconfiguration issues. Corresponding concepts are required to utilize these theoretical potentials. Therefore, this research provides a basic concept for self-organized reconfiguration management.
  BibTeX
  @conference{muller2021cyberphysical, abstract = {The frequency of changes in production requirements is continuously increasing due to economic volatility, shorter innovation cycles and product life cycles. Therefore, a prediction of all goals of a production system at development time is impossible, which is leading to an increased reconfiguration demand during operation. Currently, there are still some weaknesses concerning the reconfiguration of production systems, which are highlighted in this article. The future of industrial automation will be dominated by Cyber-Physical Production Systems, which offer many promising potentials. Hence, this contribution discusses the Cyber-Physical Production Systems and some of their potentials regarding the reconfiguration issues. Corresponding concepts are required to utilize these theoretical potentials. Therefore, this research provides a basic concept for self-organized reconfiguration management.}, author = {Müller, Timo and Jazdi, Nasser and Schmidt, Jan-Philipp and Weyrich, Michael}, booktitle = {14th CIRP Conference on Intelligent Computation in Manufacturing Engineering, Gulf of Naples, Italy}, doi = {10.1016/j.procir.2021.03.075}, title = {Cyber-physical production systems: enhancement with a self-organized reconfiguration management}, url = {https://www.sciencedirect.com/science/article/pii/S2212827121003620}, year = 2021 }
  Link
  https://www.sciencedirect.com/science/article/pii/S2212827121003620
12. A. Löcklin, H. Vietz, D. White, T. Ruppert, N. Jazdi, and M. Weyrich, “Data administration shell for data-science-driven development,” Procedia CIRP, vol. 100, pp. 115-120, Mai 2021, 2021.
  Abstract
  Data-science-driven development projects are increasingly gaining the attention of small and medium sized enterprises. Since SME are often lacking the necessary competencies in data science, cooperation with other companies or universities is required. The efficient handling of data is one of the main challenges in joint cross-enterprise development projects. Actual cost driver is the development of data by labeling and classifying the data by domain experts, which is very time-consuming and labor-intensive with large amounts of data. Furthermore, clearance processes also have a high potential to cause delays before data can be shared with project partners. Moreover, before the actual work can begin, it is often necessary to clean up and repair incomplete or noisy data. The concept of Data Administration Shell presented in this paper addresses the challenge of structured information sharing and information management in joint cross-enterprise engineering. The Data Administration Shell links data sets to information regarding data origin and already performed analyses including their results and program scripts. Adding relations and documentation facilitates the reuse of data sets for subsequent projects. For this purpose, the Data Administration Shell adapts the concepts serving the information sharing in the research field of manufacturing and Digital Twin. The evaluation of the Data Administration Shell was based on time-series measurement data from a production process optimization scenario. Here, the Data Administration Shell manages the data sets of time series data and facilitates the joint cross-enterprise engineering of data-driven solutions.
  BibTeX
  @article{locklin2021administration, abstract = {Data-science-driven development projects are increasingly gaining the attention of small and medium sized enterprises. Since SME are often lacking the necessary competencies in data science, cooperation with other companies or universities is required. The efficient handling of data is one of the main challenges in joint cross-enterprise development projects. Actual cost driver is the development of data by labeling and classifying the data by domain experts, which is very time-consuming and labor-intensive with large amounts of data. Furthermore, clearance processes also have a high potential to cause delays before data can be shared with project partners. Moreover, before the actual work can begin, it is often necessary to clean up and repair incomplete or noisy data. The concept of Data Administration Shell presented in this paper addresses the challenge of structured information sharing and information management in joint cross-enterprise engineering. The Data Administration Shell links data sets to information regarding data origin and already performed analyses including their results and program scripts. Adding relations and documentation facilitates the reuse of data sets for subsequent projects. For this purpose, the Data Administration Shell adapts the concepts serving the information sharing in the research field of manufacturing and Digital Twin. The evaluation of the Data Administration Shell was based on time-series measurement data from a production process optimization scenario. Here, the Data Administration Shell manages the data sets of time series data and facilitates the joint cross-enterprise engineering of data-driven solutions.}, author = {Löcklin, Andreas and Vietz, Hannes and White, Dustin and Ruppert, Tamás and Jazdi, Nasser and Weyrich, Michael}, booktitle = {Procedia CIRP, vol. 100, pp. 115-120, Mai 2021}, issn = {2212-8271}, title = {Data administration shell for data-science-driven development}, url = {https://doi.org/10.1016/j.procir.2021.05.019 }, year = 2021 }
  Link
  https://doi.org/10.1016/j.procir.2021.05.019
13. F. G. Listl, J. Fischer, R. Rosen, A. Sohr, J. C. Wehrstedt, and M. Weyrich, “Decision Support on the Shop Floor Using Digital Twins: Architecture and Functional Components for Simulation-Based Assistance,” in International Conference on Advances in Production Management Systems, (APMS), Nantes, Frances, 5-9 Sept. 2021, published in: Dolgui A., Bernard A., Lemoine D., von Cieminski G., Romero D. (eds) Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilent Production Systems IFIPAICT, vol. 630, pp. 284-292, Springer, Cham, 2021.
  Abstract
  Increased flexibility and improved resilience in production and manufacturing processes are goals that are becoming more and more important in the context of Industry 4.0 and from the experience of the Covid-19 pandemic. At the same time, efficient operation of production must be guaranteed to achieve economic as well as ecological objectives. Intelligent assistance systems follow the idea to support stakeholders of production systems in their decisions and can thus be useful applications for helping to master the various challenges and to meet these goals. In this paper, we describe functional components of these decision support systems: data provision and data extraction, knowledge base, simulation models, model execution and analytics, and application and user interaction. We show the underlying technologies and illustrate why these assistant systems are valuable for several stakeholders.
  BibTeX
  @conference{listl2021decision, abstract = {Increased flexibility and improved resilience in production and manufacturing processes are goals that are becoming more and more important in the context of Industry 4.0 and from the experience of the Covid-19 pandemic. At the same time, efficient operation of production must be guaranteed to achieve economic as well as ecological objectives. Intelligent assistance systems follow the idea to support stakeholders of production systems in their decisions and can thus be useful applications for helping to master the various challenges and to meet these goals. In this paper, we describe functional components of these decision support systems: data provision and data extraction, knowledge base, simulation models, model execution and analytics, and application and user interaction. We show the underlying technologies and illustrate why these assistant systems are valuable for several stakeholders.}, author = {Listl, Franz Georg and Fischer, Jan and Rosen, Roland and Sohr, Annelie and Wehrstedt, Jan Christoph and Weyrich, Michael}, booktitle = {International Conference on Advances in Production Management Systems, (APMS), Nantes, Frances, 5-9 Sept. 2021, published in: Dolgui A., Bernard A., Lemoine D., von Cieminski G., Romero D. (eds) Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilent Production Systems IFIPAICT, vol. 630, pp. 284-292, Springer, Cham}, doi = {10.1007/978-3-030-85874-2_30}, title = {Decision Support on the Shop Floor Using Digital Twins: Architecture and Functional Components for Simulation-Based Assistance}, url = {https://link.springer.com/chapter/10.1007%2F978-3-030-85874-2_30}, year = 2021 }
  Link
  https://link.springer.com/chapter/10.1007%2F978-3-030-85874-2_30
14. B. Maschler, S. Kamm, and M. Weyrich, “Deep industrial transfer learning at runtime for image recognition,” at - Automatisierungstechnik, vol. 69, no. 3, pp. 211-220, 03.2021, 2021.
  Abstract
  The utilization of deep learning in the field of industrial automation is hindered by two factors: The amount and diversity of training data needed as well as the need to continuously retrain as the use case changes over time. Both problems can be addressed by industrial deep transfer learning allowing for the performant, continuous and potentially distributed training on small, dispersed datasets. As a specific example, a dual memory algorithm for computer vision problems is developed and evaluated. It shows the potential for state-of-the-art performance while being trained only on fractions of the complete ImageNet dataset at multiple locations at once.
  BibTeX
  @article{maschler2021industrial, abstract = {The utilization of deep learning in the field of industrial automation is hindered by two factors: The amount and diversity of training data needed as well as the need to continuously retrain as the use case changes over time. Both problems can be addressed by industrial deep transfer learning allowing for the performant, continuous and potentially distributed training on small, dispersed datasets. As a specific example, a dual memory algorithm for computer vision problems is developed and evaluated. It shows the potential for state-of-the-art performance while being trained only on fractions of the complete ImageNet dataset at multiple locations at once.}, author = {Maschler, Benjamin and Kamm, Simon and Weyrich, Michael}, doi = {10.1515/auto-2020-0119}, issn = {2196-677X}, journal = {at - Automatisierungstechnik, vol. 69, no. 3, pp. 211-220, 03.2021 }, title = {Deep industrial transfer learning at runtime for image recognition}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Deep_industrial_transfer_learning_at_runtime_for_image_recognition.pdf}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Deep_industrial_transfer_learning_at_runtime_for_image_recognition.pdf
15. B. Maschler and M. Weyrich, “Deep Transfer Learning for Industrial Automation,” IEEE Industrial Electronics Magazine, vol. 15, no. 2, pp. 65-75, June 2021, 2021.
  Abstract
  In this article, the concepts of transfer and continual learning are introduced. The ensuing review reveals promising approaches for industrial deep transfer learning, utilizing methods of both classes of algorithms. In the field of computer vision, it is already state-of-the-art. In others, e.g. fault prediction, it is barely starting. However, over all fields, the abstract differentiation between continual and transfer learning is not benefitting their practical use. In contrast, both should be brought together to create robust learning algorithms fulfilling the industrial automation sector’s requirements. To better describe these requirements, base use cases of industrial transfer learning are introduced.
  BibTeX
  @article{maschler2021transfer, abstract = {In this article, the concepts of transfer and continual learning are introduced. The ensuing review reveals promising approaches for industrial deep transfer learning, utilizing methods of both classes of algorithms. In the field of computer vision, it is already state-of-the-art. In others, e.g. fault prediction, it is barely starting. However, over all fields, the abstract differentiation between continual and transfer learning is not benefitting their practical use. In contrast, both should be brought together to create robust learning algorithms fulfilling the industrial automation sector’s requirements. To better describe these requirements, base use cases of industrial transfer learning are introduced.}, author = {Maschler, Benjamin and Weyrich, Michael}, doi = {doi.org/10.1109/MIE.2020.3034884}, issn = {1932-4529}, journal = {IEEE Industrial Electronics Magazine, vol. 15, no. 2, pp. 65-75, June 2021}, title = {Deep Transfer Learning for Industrial Automation}, url = {https://doi.org/10.1109/MIE.2020.3034884}, year = 2021 }
  Link
  https://doi.org/10.1109/MIE.2020.3034884
16. D. Braun, W. Schlögl, and M. Weyrich, “Eine Methodik zur Erstellung multi-dimensionaler Modelle des Digitalen Zwillings für automatisierte Produktionssysteme,” Automation 2021, VDI Verlag GmbH Düsseldorf, pp. 29-42, 29. und 30 June 2021, 2021.
  Abstract
  Der Digitale Zwillinge einer Produktionsanlage kann für viele Use Cases sehr hilfreich sein. Dazu muss die Synchronität des Digitalen Zwillings mit dem realen Produktionssystem sichergestellt werden. Diese herausfordernde Aufgabe kann durch unterschiedliche Methoden unterstützt oder (teil-) automatisiert werden. Ein wichtiger Aspekt, der für Digitale Zwillinge beachtet werden muss, sind die Relationen zwischen den einzelnen Modellen der Dimensionen Mechanik, Elektrik und Software. Daher werden die gängigen Methoden zur Synchronisierung und Erstellung digitaler Modelle aus multiplen Dimensionen vorgestellt und die Relationsbildung betrachtet. Die Ankerpunktmethode als vielversprechendste Methode wird anschließen an einer Beispielsanlage untersucht und deren Grenze aufgezeigt. Basierend auf diesen Ergebnissen wird eine Methodik vorgestellt, die sich mit der Rekonstruktion der digitalen Modelle und deren Relationen beschäftigt. Dabei liegt der Fokus auf bereits existierenden, produktiv eingesetzten Produktionssystemen, sogenannte Brownfield Anlagen, als das häufigste Einsatzfeld.
  BibTeX
  @article{braun2021methodik, abstract = {Der Digitale Zwillinge einer Produktionsanlage kann für viele Use Cases sehr hilfreich sein. Dazu muss die Synchronität des Digitalen Zwillings mit dem realen Produktionssystem sichergestellt werden. Diese herausfordernde Aufgabe kann durch unterschiedliche Methoden unterstützt oder (teil-) automatisiert werden. Ein wichtiger Aspekt, der für Digitale Zwillinge beachtet werden muss, sind die Relationen zwischen den einzelnen Modellen der Dimensionen Mechanik, Elektrik und Software. Daher werden die gängigen Methoden zur Synchronisierung und Erstellung digitaler Modelle aus multiplen Dimensionen vorgestellt und die Relationsbildung betrachtet. Die Ankerpunktmethode als vielversprechendste Methode wird anschließen an einer Beispielsanlage untersucht und deren Grenze aufgezeigt. Basierend auf diesen Ergebnissen wird eine Methodik vorgestellt, die sich mit der Rekonstruktion der digitalen Modelle und deren Relationen beschäftigt. Dabei liegt der Fokus auf bereits existierenden, produktiv eingesetzten Produktionssystemen, sogenannte Brownfield Anlagen, als das häufigste Einsatzfeld.}, author = {Braun, Dominik and Schlögl, Wolfgang and Weyrich, Michael}, doi = {10.51202/9783181023921-29}, isbn = {978-3-18-092392-4}, issn = {0083-5560}, journal = {Automation 2021, VDI Verlag GmbH Düsseldorf, pp. 29-42, 29. und 30 June 2021}, title = {Eine Methodik zur Erstellung multi-dimensionaler Modelle des Digitalen Zwillings für automatisierte Produktionssysteme}, url = {https://doi.org/10.51202/9783181023921-29}, year = 2021 }
  Link
  https://doi.org/10.51202/9783181023921-29
17. T. Müller, B. Lindemann, T. Jung, N. Jazdi, and M. Weyrich, “Enhancing an Intelligent Digital Twin with a Self-organized Reconfiguration Management based on Adaptive Process Models,” in 54th CIRP Conference on Manufacturing Systems, Athens, Greece, November 2021, 2021.
  Abstract
  Shorter product life cycles and increasing individualization of production leads to an increased reconfiguration demand in the domain of industrial automation systems, which will be dominated by cyber-physical production systems in the future. In constantly changing systems, however, not all configuration alternatives of the almost infinite state space are fully understood. Thus, certain configurations can lead to process instability, a reduction in quality or machine failures. Therefore, this paper presents an approach that enhances an intelligent Digital Twin with a self-organized reconfiguration management based on adaptive process models in order to find optimized configurations more comprehensively.
  BibTeX
  @conference{muller2021enhancing, abstract = {Shorter product life cycles and increasing individualization of production leads to an increased reconfiguration demand in the domain of industrial automation systems, which will be dominated by cyber-physical production systems in the future. In constantly changing systems, however, not all configuration alternatives of the almost infinite state space are fully understood. Thus, certain configurations can lead to process instability, a reduction in quality or machine failures. Therefore, this paper presents an approach that enhances an intelligent Digital Twin with a self-organized reconfiguration management based on adaptive process models in order to find optimized configurations more comprehensively.}, author = {Müller, Timo and Lindemann, Benjamin and Jung, Tobias and Jazdi, Nasser and Weyrich, Michael}, booktitle = {54th CIRP Conference on Manufacturing Systems, Athens, Greece, November 2021}, doi = {10.1016/j.procir.2021.11.132}, title = {Enhancing an Intelligent Digital Twin with a Self-organized Reconfiguration Management based on Adaptive Process Models}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021-Enhancing_an_Intelligent_Digital_Twin_with_a_Self-organized_Reconfiguration_Management_based_on_Adaptive_Process_Models.pdf}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021-Enhancing_an_Intelligent_Digital_Twin_with_a_Self-organized_Reconfiguration_Management_based_on_Adaptive_Process_Models.pdf
18. D. White, N. Sahlab, N. Jazdi, and M. Weyrich, “Environment modeling for evaluating system variants in model-based systems engineering,” in 54th CIRP Conference on Manufacturing Systems, Athens, Greece, September 2021, 2021.
  - Abstract
  - BibTeX
  Abstract
  Model-based systems engineering is a methodology for the interdisciplinary system development using different domain models. Considering the intended system’s environment and context of usage in early design phases is a way of bridging the gap from system’s design to its real-life applicability. Simulations represent a possible approach to consider different constellations but are effortful. Therefore, we present a generic environment modeling approach to evaluate different environmental models with their respective environmental, user and system’s impact based on generated system variants derived from system requirements. In this sequential process, we consistently link and evaluate system variants to possible system contexts.
  BibTeX
  @conference{white2021environment, abstract = {Model-based systems engineering is a methodology for the interdisciplinary system development using different domain models. Considering the intended system’s environment and context of usage in early design phases is a way of bridging the gap from system’s design to its real-life applicability. Simulations represent a possible approach to consider different constellations but are effortful. Therefore, we present a generic environment modeling approach to evaluate different environmental models with their respective environmental, user and system’s impact based on generated system variants derived from system requirements. In this sequential process, we consistently link and evaluate system variants to possible system contexts.}, author = {White, Dustin and Sahlab, Nada and Jazdi, Nasser and Weyrich, Michael}, booktitle = {54th CIRP Conference on Manufacturing Systems, Athens, Greece, September 2021}, title = {Environment modeling for evaluating system variants in model-based systems engineering}, year = 2021 }
19. S. Kamm, K. Sharma, I. Kallfass, N. Jazdi, and M. Weyrich, “Hybrid Modelling for the Failure Analysis of SiC Power Transistors on Time-Domain Reflectometry Data,” in 2021 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA), 2021.
  Abstract
  Ensuring and improving the reliability of electronic devices requires post-production failure analysis processes. One of the techniques to perform failure analysis for electronic devices is Time-Domain Reflectometry. With this method, failures can be detected, located, and characterized non-destructively. It enables not only the detection of hard interconnection failures (such as an open or a short) but also the detection and characterization of soft failures. For Time-Domain Reflectometry, known physical equations can be applied to model the ideal behavior of a signal for different failures. However, since electronic device architectures and thus the data become more and more complex and measurements are disturbed by noise or nonoptimal material properties, these models solely are not sufficient for failure analysis. Therefore we propose hybrid modeling, where machine learning models (e.g. convolutional neural networks) work together with physical models to detect, locate, classify and characterize the failure. The first approach is shown on simulated microstrip line data and then transferred to SiC transistors for evaluation.
  BibTeX
  @conference{kamm2021hybrid, abstract = {Ensuring and improving the reliability of electronic devices requires post-production failure analysis processes. One of the techniques to perform failure analysis for electronic devices is Time-Domain Reflectometry. With this method, failures can be detected, located, and characterized non-destructively. It enables not only the detection of hard interconnection failures (such as an open or a short) but also the detection and characterization of soft failures. For Time-Domain Reflectometry, known physical equations can be applied to model the ideal behavior of a signal for different failures. However, since electronic device architectures and thus the data become more and more complex and measurements are disturbed by noise or nonoptimal material properties, these models solely are not sufficient for failure analysis. Therefore we propose hybrid modeling, where machine learning models (e.g. convolutional neural networks) work together with physical models to detect, locate, classify and characterize the failure. The first approach is shown on simulated microstrip line data and then transferred to SiC transistors for evaluation.}, author = {Kamm, Simon and Sharma, Kanuj and Kallfass, Ingmar and Jazdi, Nasser and Weyrich, Michael}, booktitle = {2021 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA)}, doi = {10.1109/IPFA53173.2021.9617401}, title = {Hybrid Modelling for the Failure Analysis of SiC Power Transistors on Time-Domain Reflectometry Data}, url = {https://doi.org/10.1109/IPFA53173.2021.9617401}, year = 2021 }
  Link
  https://doi.org/10.1109/IPFA53173.2021.9617401
20. T. Müller, S. Walth, N. Jazdi, and M. Weyrich, “Identification of Reconfiguration Demand and Generation of Alternative Configurations for Cyber-Physical Production Systems,” in Advances in Automotive Production Technology–Theory and Application, June 2021, 2021.
  Abstract
  Ensuring high availability despite the growing frequency of changes in production requirements leads to an increased reconfiguration demand in the domain of industrial automation systems, which will be dominated by Cyber-Physical Production Systems (CPPS) in the future. Therefore, a concept, covering a methodology containing four steps, is utilized to answer the research question how to enhance CPPS with a self-organized reconfiguration management. This contribution focuses on the first two steps of this concept: the identification of reconfiguration demand and the generation of alternative configurations. A condensed presentation of the related work reveals that an interface-oriented formalized process description depicts an appropriate conceptual basis. Building upon this, the presented concept contains a capability model of the CPPS and the reasoning to determine a potential reconfiguration demand, as well as a procedure for the generation of alternative configurations. To evaluate the concept, an agent-based implementation is given, which uses an OPC-UA controlled simulated modular production system as a substitute CPPS in discrete manufacturing.
  BibTeX
  @inproceedings{muller2021identification, abstract = {Ensuring high availability despite the growing frequency of changes in production requirements leads to an increased reconfiguration demand in the domain of industrial automation systems, which will be dominated by Cyber-Physical Production Systems (CPPS) in the future. Therefore, a concept, covering a methodology containing four steps, is utilized to answer the research question how to enhance CPPS with a self-organized reconfiguration management. This contribution focuses on the first two steps of this concept: the identification of reconfiguration demand and the generation of alternative configurations. A condensed presentation of the related work reveals that an interface-oriented formalized process description depicts an appropriate conceptual basis. Building upon this, the presented concept contains a capability model of the CPPS and the reasoning to determine a potential reconfiguration demand, as well as a procedure for the generation of alternative configurations. To evaluate the concept, an agent-based implementation is given, which uses an OPC-UA controlled simulated modular production system as a substitute CPPS in discrete manufacturing.}, author = {Müller, Timo and Walth, Simon and Jazdi, Nasser and Weyrich, Michael}, booktitle = {Advances in Automotive Production Technology–Theory and Application, June 2021}, doi = {10.1007/978-3-662-62962-8_8}, title = {Identification of Reconfiguration Demand and Generation of Alternative Configurations for Cyber-Physical Production Systems}, url = {https://doi.org/10.1007/978-3-662-62962-8_8}, year = 2021 }
  Link
  https://doi.org/10.1007/978-3-662-62962-8_8
21. M. Müller, T. Müller, B. A. Talkhestani, P. Marks, N. Jazdi, and M. Weyrich, “Industrial autonomous systems: a survey on definitions, characteristics and abilities,” at - Automatisierungstechnik, vol. 69, no. 1, pp. 3–13, 08.01.2021, 2021.
  Abstract
  Advances in the domain of industrial automation systems and artificial intelligence research have brought autonomous systems into the focus of industrial automation research. However, as Hrabia et al. state, there is no common understanding of what autonomous systems are and what characterizes them: “there is still a lack of a widely accepted concept of autonomous systems or robots that contains a detailed definition according to different aspects and a clear distinction to other system concepts” 1. They conclude “the capability of adapting to the environment is strongly interconnected with autonomy”1. However, they do not derive a comprehensive definition. On the one hand, some systems are advertised as autonomous systems, although they are only highly automated systems. On the other hand, some autonomous systems are not labeled as such. In addition, a number of different properties have emerged that characterize an autonomous system as well as abilities attributed to autonomous systems. In order to provide a differentiated view on this topic, the relevant literature in the domain of industrial automation systems was investigated for this survey. The methodology of the investigation is described in Section 2. Starting with the historical development of the term autonomy, in Section 3, various definitions of autonomy are compared, and a summarizing definition is elaborated. From the definition in the narrow sense, the characteristics of industrial autonomous systems are derived (Section 3.1) and a distinction from intelligent industrial automation systems and classic automation systems is proposed (Section 3.2). Reviewing the abilities attributed to industrial autonomous systems in the literature, the abilities are categorized according to the characteristics (Section 4). In order to provide an example for the classification of systems as industrial autonomous systems based on the four derived characteristics, their manifestation is explored by three real-world examples (Section 5). Finally, Section 6 provides a conclusion and an outlook.
  BibTeX
  @article{muller2021industrial, abstract = {Advances in the domain of industrial automation systems and artificial intelligence research have brought autonomous systems into the focus of industrial automation research. However, as Hrabia et al. state, there is no common understanding of what autonomous systems are and what characterizes them: “there is still a lack of a widely accepted concept of autonomous systems or robots that contains a detailed definition according to different aspects and a clear distinction to other system concepts” [1]. They conclude “the capability of adapting to the environment is strongly interconnected with autonomy”[1]. However, they do not derive a comprehensive definition. On the one hand, some systems are advertised as autonomous systems, although they are only highly automated systems. On the other hand, some autonomous systems are not labeled as such. In addition, a number of different properties have emerged that characterize an autonomous system as well as abilities attributed to autonomous systems. In order to provide a differentiated view on this topic, the relevant literature in the domain of industrial automation systems was investigated for this survey. The methodology of the investigation is described in Section 2. Starting with the historical development of the term autonomy, in Section 3, various definitions of autonomy are compared, and a summarizing definition is elaborated. From the definition in the narrow sense, the characteristics of industrial autonomous systems are derived (Section 3.1) and a distinction from intelligent industrial automation systems and classic automation systems is proposed (Section 3.2). Reviewing the abilities attributed to industrial autonomous systems in the literature, the abilities are categorized according to the characteristics (Section 4). In order to provide an example for the classification of systems as industrial autonomous systems based on the four derived characteristics, their manifestation is explored by three real-world examples (Section 5). Finally, Section 6 provides a conclusion and an outlook.}, author = {Müller, Manuel and Müller, Timo and Talkhestani, Behrang Ashtari and Marks, Philipp and Jazdi, Nasser and Weyrich, Michael}, doi = {doi.org/10.1515/auto-2020-0131}, issn = {0178-2312}, journal = {at - Automatisierungstechnik, vol. 69, no. 1, pp. 3–13, 08.01.2021}, title = {Industrial autonomous systems: a survey on definitions, characteristics and abilities }, url = {https://www.degruyter.com/view/journals/auto/69/1/article-p3.xml}, year = 2021 }
  Link
  https://www.degruyter.com/view/journals/auto/69/1/article-p3.xml
22. D. Braun, B. Ashtari, and M. Weyrich, Integration of data and software into the Digital Twin via AML. Rainer Drath, 2021.
  Abstract
  Digital Twins and the Internet-of -Things (IoT) are going to boost many applications based on information and communication technology. A study of COOM19 indicates that the technology of a Digital Twin is about to be established in Industry. It was found that “62 percent (of companies questioned) are either in the process of establishing Digital Twin use or plans to do so”. Many authors agree that these new technologies will connect virtually everything from customers to machines and logistics. AutomationML is an important standard and relevant enabler for the creation, adaption and management of the Digital Twin. In the near future, it is expected that machines will communicate with one another, logistics and machinery will be self-controlled and all plans can be projected by simulation, which supports decision-making. From this perspective, the Digital Twin is a novel and enabling technology, which can be spread easier and faster with the use of AML. The demands of markets to release constantly market-driven innovations, compels industrial manufacturing companies to increase both the use of automated production systems and their reconfiguration during their lifecycle. Increasing product variety and shortening product life cycles require a fast and inexpensive reconfiguration of existing production systems AJS+18a. To face these challenges, one solution is to use the Digital Twins of automated manufacturing systems. The value-add of a Digital Twin for reconfiguration, promises the reconfiguration time to be reduced and thus an increase of the system availability as well as customer-specific products to be manufactured at short notice. A simulative environment using a Digital Twin enables automated systems to be quickly and easily reconfigured by a virtual test in simulation. The recommissioning and reconfiguration of the real manufacturing system therefore requires less working time, is less error prone and thereby, reducing costs. However, such savings are only worthwhile if the effort of creating the digital twin is covered by the savings from the above-mentioned benefits. It is evident that the Digital Twin should be implemented by integrated software systems, such as product lifecycle management (PLM) systems, and should also be based on standards such as AML. The implementation of AML for PLM systems combines the benefits of both and enables the managed utilization of many different tools with standardized interface and thereby helps reducing the barriers for its creation.
  BibTeX
  @book{braun2021integration, abstract = {Digital Twins and the Internet-of -Things (IoT) are going to boost many applications based on information and communication technology. A study of [COOM19] indicates that the technology of a Digital Twin is about to be established in Industry. It was found that “62 percent (of companies questioned) are either in the process of establishing Digital Twin use or plans to do so”. Many authors agree that these new technologies will connect virtually everything from customers to machines and logistics. AutomationML is an important standard and relevant enabler for the creation, adaption and management of the Digital Twin. In the near future, it is expected that machines will communicate with one another, logistics and machinery will be self-controlled and all plans can be projected by simulation, which supports decision-making. From this perspective, the Digital Twin is a novel and enabling technology, which can be spread easier and faster with the use of AML. The demands of markets to release constantly market-driven innovations, compels industrial manufacturing companies to increase both the use of automated production systems and their reconfiguration during their lifecycle. Increasing product variety and shortening product life cycles require a fast and inexpensive reconfiguration of existing production systems [AJS+18a]. To face these challenges, one solution is to use the Digital Twins of automated manufacturing systems. The value-add of a Digital Twin for reconfiguration, promises the reconfiguration time to be reduced and thus an increase of the system availability as well as customer-specific products to be manufactured at short notice. A simulative environment using a Digital Twin enables automated systems to be quickly and easily reconfigured by a virtual test in simulation. The recommissioning and reconfiguration of the real manufacturing system therefore requires less working time, is less error prone and thereby, reducing costs. However, such savings are only worthwhile if the effort of creating the digital twin is covered by the savings from the above-mentioned benefits. It is evident that the Digital Twin should be implemented by integrated software systems, such as product lifecycle management (PLM) systems, and should also be based on standards such as AML. The implementation of AML for PLM systems combines the benefits of both and enables the managed utilization of many different tools with standardized interface and thereby helps reducing the barriers for its creation.}, author = {Braun, Dominik and Ashtari, Behrang and Weyrich, Michael}, doi = {10.1515/9783110745979-031}, isbn = {978-3-11-074597-9}, journal = {AutomationML: The Industrial Cookbook, Chapter: 29, pp. 521-538, Juni 2021}, language = {English}, publisher = {Rainer Drath}, title = {Integration of data and software into the Digital Twin via AML}, url = {https://doi.org/10.1515/9783110745979-031}, year = 2021 }
  Link
  https://doi.org/10.1515/9783110745979-031
23. M. Weyrich, “Key Technologies of Automation - A Short Journey,” Problems of modeling and design automation - Festveranstaltung zum 100 jährigen Jubiläum der DonNTU (Donezker Nationale Technische Universität - G.J.-Pukhov-Institut für Simulationsprobleme in Energetik), NAW Ukraine, PROGRAMM der wissenschaftlichen Jubiläumskonferenz SIMULATION UND COMPUTER -GRAFIK, 27. Mai 2021, 2021.
  Abstract
  There has been much discussion about the future of automation in recent years. The topic of Industry 4.0 has been with us since around 2012 and has provided many impulses for the future, some of which have been implemented, are in development or research and will remain for some time to come. In this paper, we will give a glimpse at four key enablers of automation today and in the next 10 years. Fig. 1 depicts the future technologies which are based on the concept of Modularity which are going to enhance automation technology in the next decade. Apart from Modularity, the topics of Connectivity, Digital Twin and Autonomy are going to be key technologies in the coming developments and are going to determine the topic of automation over the next years.
  BibTeX
  @article{weyrich2021technologies, abstract = {There has been much discussion about the future of automation in recent years. The topic of Industry 4.0 has been with us since around 2012 and has provided many impulses for the future, some of which have been implemented, are in development or research and will remain for some time to come. In this paper, we will give a glimpse at four key enablers of automation today and in the next 10 years. Fig. 1 depicts the future technologies which are based on the concept of Modularity which are going to enhance automation technology in the next decade. Apart from Modularity, the topics of Connectivity, Digital Twin and Autonomy are going to be key technologies in the coming developments and are going to determine the topic of automation over the next years.}, author = {Weyrich, Michael}, doi = {10.31474/2074-7888-2021-1-5-12}, issn = {ISSN 2074-7888}, journal = {Problems of modeling and design automation - Festveranstaltung zum 100 jährigen Jubiläum der DonNTU (Donezker Nationale Technische Universität - G.J.-Pukhov-Institut für Simulationsprobleme in Energetik), NAW Ukraine, PROGRAMM der wissenschaftlichen Jubiläumskonferenz SIMULATION UND COMPUTER -GRAFIK, 27. Mai 2021 }, title = {Key Technologies of Automation - A Short Journey}, url = {https://archiv.ias.uni-stuttgart.de/dokumente/publikationen/2021_Problems_of_modeling_and_design_automation.pdf}, year = 2021 }
  Link
  https://archiv.ias.uni-stuttgart.de/dokumente/publikationen/2021_Problems_of_modeling_and_design_automation.pdf
24. S. Kamm, N. Jazdi, and M. Weyrich, “Knowledge Discovery in Heterogeneous and Unstructured Data of Industry 4.0 Systems: Challenges and Approaches,” in 54th CIRP Conference on Manufacturing Systems, Athen, Greece, September 2021, 2021.
  Abstract
  With the rise of the Internet of Things and Industry 4.0, the number of digital devices and their produced data increases tremendously. Due to the heterogeneity of devices, the generated data is mostly heterogeneous and unstructured. This challenges established approaches for knowledge discovery, which typically consume structured data from one source. The paper first describes aspects of data heterogeneity and their relevance for Industry 4.0 systems. Following, the upcoming challenges for different steps inside the knowledge discovery process for Industry 4.0 systems, such as for data integration and data mining, are discussed. Additionally, it mentions approaches to tackle them.
  BibTeX
  @conference{kamm2021knowledge, abstract = {With the rise of the Internet of Things and Industry 4.0, the number of digital devices and their produced data increases tremendously. Due to the heterogeneity of devices, the generated data is mostly heterogeneous and unstructured. This challenges established approaches for knowledge discovery, which typically consume structured data from one source. The paper first describes aspects of data heterogeneity and their relevance for Industry 4.0 systems. Following, the upcoming challenges for different steps inside the knowledge discovery process for Industry 4.0 systems, such as for data integration and data mining, are discussed. Additionally, it mentions approaches to tackle them.}, author = {Kamm, Simon and Jazdi, Nasser and Weyrich, Michael}, booktitle = {54th CIRP Conference on Manufacturing Systems, Athen, Greece, September 2021}, doi = {10.1016/j.procir.2021.11.164}, title = {Knowledge Discovery in Heterogeneous and Unstructured Data of Industry 4.0 Systems: Challenges and Approaches}, url = {https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Knowledge_Discovery_in_Heterogeneous_and_Unstructured_Data_of_Industry_40_Systems_Challenges_and_Approaches.pdf}, year = 2021 }
  Link
  https://www.ias.uni-stuttgart.de/dokumente/publikationen/2021_Knowledge_Discovery_in_Heterogeneous_and_Unstructured_Data_of_Industry_40_Systems_Challenges_and_Approaches.pdf
25. N. Sahlab, S. Kamm, T. Müller, N. Jazdi, and M. Weyrich, “Knowledge Graphs as Enhancers of Intelligent Digital Twins,” in 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS), May 2021, 2021.
  Abstract
  Cyber-Physical Systems, characterized by networking capabilities and digital representations, offer many promising potentials for industrial automation. In an attempt to further enrich the system's digital representation by incorporating interdisciplinary models and considering a continuous and synchronized representation of it within the cyber layer, the concept of the Digital Twin emerged, enabling system monitoring, virtual commissioning, failure diagnosis and simulations by managing the Cyber-Physical Systems data along its lifecycle. To add further intelligence into the Digital Twin, the architecture of the intelligent Digital Twin was proposed. Nevertheless, managing and relating the complex and dynamic digital models as well as the heterogeneous data of the intelligent Digital Twin present open challenges. Due to their inherent extensibility and adaptability as well as their semantic expressiveness, Knowledge Graphs are a suitable concept to overcome these challenges and enable reasoning to gain new insights. Prominent applications of Knowledge Graphs are recommendation systems and exploratory search within the semantic web. However, there seems to be a lacking yet potential applicability for Knowledge Graphs in the industrial domain. Therefore, this contribution proposes a Knowledge Graph enhanced architecture of the intelligent Digital Twin, offering capabilities, which are internal linking and referencing, knowledge completion, error detection, collective reasoning and semantic querying. Based on the proposed concept, potential application fields for Knowledge Graph enhanced intelligent Digital Twin are addressed.
  BibTeX
  @conference{sahlab2021knowledge, abstract = {Cyber-Physical Systems, characterized by networking capabilities and digital representations, offer many promising potentials for industrial automation. In an attempt to further enrich the system's digital representation by incorporating interdisciplinary models and considering a continuous and synchronized representation of it within the cyber layer, the concept of the Digital Twin emerged, enabling system monitoring, virtual commissioning, failure diagnosis and simulations by managing the Cyber-Physical Systems data along its lifecycle. To add further intelligence into the Digital Twin, the architecture of the intelligent Digital Twin was proposed. Nevertheless, managing and relating the complex and dynamic digital models as well as the heterogeneous data of the intelligent Digital Twin present open challenges. Due to their inherent extensibility and adaptability as well as their semantic expressiveness, Knowledge Graphs are a suitable concept to overcome these challenges and enable reasoning to gain new insights. Prominent applications of Knowledge Graphs are recommendation systems and exploratory search within the semantic web. However, there seems to be a lacking yet potential applicability for Knowledge Graphs in the industrial domain. Therefore, this contribution proposes a Knowledge Graph enhanced architecture of the intelligent Digital Twin, offering capabilities, which are internal linking and referencing, knowledge completion, error detection, collective reasoning and semantic querying. Based on the proposed concept, potential application fields for Knowledge Graph enhanced intelligent Digital Twin are addressed.}, author = {Sahlab, Nada and Kamm, Simon and Müller, Timo and Jazdi, Nasser and Weyrich, Michael}, booktitle = {4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS), May 2021}, doi = {10.1109/ICPS49255.2021.9468219}, title = {Knowledge Graphs as Enhancers of Intelligent Digital Twins}, url = {https://ieeexplore.ieee.org/document/9468219}, year = 2021 }
  Link
  https://ieeexplore.ieee.org/document/9468219
26. B. Maschler, T. T. H. Pham, and M. Weyrich, “Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturing,” in 54th CIRP Conference on Manufacturing Systems, Athens, Greece, Vol. 104, pp. 452-457, November 2021, 2021.
  - Abstract
  - BibTeX
  Abstract
  The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in products. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regularization strategies, which are implemented, evaluated and compared based on a real industrial metal forming dataset.
  BibTeX
  @conference{maschler2021regularizationbased, abstract = {The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in products. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regularization strategies, which are implemented, evaluated and compared based on a real industrial metal forming dataset.}, author = {Maschler, Benjamin and Pham, Thi Thu Huong and Weyrich, Michael}, booktitle = {54th CIRP Conference on Manufacturing Systems, Athens, Greece, Vol. 104, pp. 452-457, November 2021}, doi = {10.1016/j.procir.2021.11.076}, publisher = {Elsevier}, series = {Procedia CIRP}, title = {Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturing}, year = 2021 }
27. B. Maschler, S. Tatiyosyan, and M. Weyrich, “Regularization-based Continual Learning for Fault Prediction in Lithium-Ion Batteries,” in 15th CIRP Conference on Intelligent Computation and Manufacturing Engineering, July 2021, Gulf of Naples, Italy, 2021.
  - Abstract
  - BibTeX
  Abstract
  In recent years, the use of lithium-ion batteries has greatly expanded into products from many industrial sectors, e.g. cars, power tools or medical devices. An early prediction and robust understanding of battery faults could therefore greatly increase product quality in those fields. While current approaches for data-driven fault prediction provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in operational or environmental parameters. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regularization strategies, which are implemented, evaluated and compared based on a real battery wear dataset. Online elastic weight consolidation delivers the best results, but, as with all examined approaches, its performance appears to be strongly dependent on task characteristics and task sequence.
  BibTeX
  @conference{maschler2021regularizationbased, abstract = {In recent years, the use of lithium-ion batteries has greatly expanded into products from many industrial sectors, e.g. cars, power tools or medical devices. An early prediction and robust understanding of battery faults could therefore greatly increase product quality in those fields. While current approaches for data-driven fault prediction provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in operational or environmental parameters. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regularization strategies, which are implemented, evaluated and compared based on a real battery wear dataset. Online elastic weight consolidation delivers the best results, but, as with all examined approaches, its performance appears to be strongly dependent on task characteristics and task sequence. }, author = {Maschler, Benjamin and Tatiyosyan, Sophia and Weyrich, Michael}, booktitle = {15th CIRP Conference on Intelligent Computation and Manufacturing Engineering, July 2021, Gulf of Naples, Italy}, title = {Regularization-based Continual Learning for Fault Prediction in Lithium-Ion Batteries}, year = 2021 }
28. C. Ebert, M. Weyrich, B. Lindemann, and S. P. Chandrasekar, “Systematic Testing for Autonomous Driving,” ATZ elektronik, vol. 16, no. 3, pp. 26-30, 2021.
  Abstract
  Autonomous driving is the key toward ecologic and economic mobility. Robo-Test at the University of Stuttgart has created a pilot environment that uses AI-based clustering to automatically derive test scenarios and thus validate automated driving systems efficiently and effectively.
  BibTeX
  @article{ebert2021systematic, abstract = {Autonomous driving is the key toward ecologic and economic mobility. Robo-Test at the University of Stuttgart has created a pilot environment that uses AI-based clustering to automatically derive test scenarios and thus validate automated driving systems efficiently and effectively.}, author = {Ebert, Christof and Weyrich, Michael and Lindemann, Benjamin and Chandrasekar, Sarada Preethi}, journal = {ATZ elektronik, vol. 16, no. 3, pp. 26-30}, title = {Systematic Testing for Autonomous Driving}, url = {https://link.springer.com/article/10.1007/s38314-020-0575-6}, year = 2021 }
  Link
  https://link.springer.com/article/10.1007/s38314-020-0575-6
29. C. Ebert, M. Weyrich, B. Lindemann, and S. P. Chandrasekar, “Systematisches Testen für autonomes Fahren,” ATZ elektronik, vol. 16, no. 3, pp. 26-30, 2021.
  Abstract
  Autonomes Fahren ist der Schlüssel zu ökologischer und ökonomischer Mobilität. Robo-Test der Universität Stuttgart hat eine Pilotumgebung geschaffen, mit der mithilfe von KI-basierten Clustering automatisch Testszenarien abgeleitet und somit automatisierte Fahrsysteme effizient und effektiv validiert werden können.
  BibTeX
  @article{ebert202systematisches, abstract = {Autonomes Fahren ist der Schlüssel zu ökologischer und ökonomischer Mobilität. Robo-Test der Universität Stuttgart hat eine Pilotumgebung geschaffen, mit der mithilfe von KI-basierten Clustering automatisch Testszenarien abgeleitet und somit automatisierte Fahrsysteme effizient und effektiv validiert werden können.}, author = {Ebert, Christof and Weyrich, Michael and Lindemann, Benjamin and Chandrasekar, Sarada Preethi}, journal = {ATZ elektronik, vol. 16, no. 3, pp. 26-30}, title = {Systematisches Testen für autonomes Fahren}, url = {https://link.springer.com/article/10.1007/s35658-020-0573-8}, year = 2021 }
  Link
  https://link.springer.com/article/10.1007/s35658-020-0573-8
30. A. Löcklin, K. Przybysz-Herz, T. Ruppert, R. Libert, L. Jakab, N. Jazdi, and M. Weyrich, “Tailored digitization with real-time locating systems: Ultra-wideband RTLS for production and logistics,” atp magazin vol. 63, no. 3, pp. 76-83, März, 2021, 2021.
  Abstract
  We are seeing a boom in the use of real-time position data to automate and optimize tasks in the field of production and logistics. Here we consider the reasons for this, show what has already proven to be industrially viable and give an overview of six current research efforts. We show which use cases have been automated by RTLS and where RTLS could play a role to further optimize production processes or material flows in the future.
  BibTeX
  @article{locklin2021tailored, abstract = {We are seeing a boom in the use of real-time position data to automate and optimize tasks in the field of production and logistics. Here we consider the reasons for this, show what has already proven to be industrially viable and give an overview of six current research efforts. We show which use cases have been automated by RTLS and where RTLS could play a role to further optimize production processes or material flows in the future.}, author = {Löcklin, Andreas and Przybysz-Herz, Kai and Ruppert, Tamás and Libert, Robert and Jakab, László and Jazdi, Nasser and Weyrich, Michael}, doi = {10.17560/atp.v63i03.2550}, journal = {atp magazin vol. 63, no. 3, pp. 76-83, März, 2021}, title = {Tailored digitization with real-time locating systems: Ultra-wideband RTLS for production and logistics}, url = {https://doi.org/10.17560/atp.v63i03.2550 }, year = 2021 }
  Link
  https://doi.org/10.17560/atp.v63i03.2550
31. A. Löcklin, C. Kotsch, K. Krüning, M. Rentschler, C. Ebert, M. Müller, and M. Weyrich, “Testen 4.0 in der Automatisierungstechnik: Agiles modellbasiertes Testen vernetzter Systeme und Komponenten,” Automation 2021, VDI Verlag GmbH Düsseldorf, pp. 335-352, 29. und 30 June 2021, 2021.
  Abstract
  Die Flexibilisierung von Produktionsanlagen ist notwendig, um in einem volatilen Marktumfeld erfolgreich sein zu können. Durch die Bereitstellung und Pflege geeigneter Schnittstellen und Betriebsmodi, sowie dem Umbau von Anlagen, kann auf geänderte Anforderungen an die Produktion reagiert werden. Für die Realisierung derartiger hochflexibler und rekonfigurierbarer Anlagen ist ein erhöhter Engineering- und Testaufwand notwendig. Jede zusätzliche Funktion samt aller damit verbundener Abhängigkeiten müssen vor Inbetriebnahme mehrfach von Herstellern, Integratoren und Betreibern überprüft werden. Damit der resultierende erhöhte Testaufwand auch zukünftig handhabbar bleibt, werden in dieser Veröffentlichung folgende Ansätze vorgestellt, um ein effizientes und wirkungsvolles Testen im Bereich der flexiblen Produktion zu ermöglichen: Zum einen lässt sich durch eine auf Richtlinien basierende Modularisierung von Anlagen und Komponenten der Testaufwand reduzieren. Auch sorgen Agile Teams für eine verbesserte Kommunikation zwischen Entwicklungs- und Testabteilungen. Überdies ermöglicht die Anwendung von Digitalen Zwillingen einen effektiveren Informationsaustausch zwischen den Stakeholdern und Modellbasiertes Testen ermöglicht Vorteile bei der Testautomatisierung. Alle Ansätze sind jeweils eigenständig wirksam, aber zusammengenommen ergeben sich zusätzliche Synergieeffekte.
  BibTeX
  @article{locklin2021testen, abstract = {Die Flexibilisierung von Produktionsanlagen ist notwendig, um in einem volatilen Marktumfeld erfolgreich sein zu können. Durch die Bereitstellung und Pflege geeigneter Schnittstellen und Betriebsmodi, sowie dem Umbau von Anlagen, kann auf geänderte Anforderungen an die Produktion reagiert werden. Für die Realisierung derartiger hochflexibler und rekonfigurierbarer Anlagen ist ein erhöhter Engineering- und Testaufwand notwendig. Jede zusätzliche Funktion samt aller damit verbundener Abhängigkeiten müssen vor Inbetriebnahme mehrfach von Herstellern, Integratoren und Betreibern überprüft werden. Damit der resultierende erhöhte Testaufwand auch zukünftig handhabbar bleibt, werden in dieser Veröffentlichung folgende Ansätze vorgestellt, um ein effizientes und wirkungsvolles Testen im Bereich der flexiblen Produktion zu ermöglichen: Zum einen lässt sich durch eine auf Richtlinien basierende Modularisierung von Anlagen und Komponenten der Testaufwand reduzieren. Auch sorgen Agile Teams für eine verbesserte Kommunikation zwischen Entwicklungs- und Testabteilungen. Überdies ermöglicht die Anwendung von Digitalen Zwillingen einen effektiveren Informationsaustausch zwischen den Stakeholdern und Modellbasiertes Testen ermöglicht Vorteile bei der Testautomatisierung. Alle Ansätze sind jeweils eigenständig wirksam, aber zusammengenommen ergeben sich zusätzliche Synergieeffekte. }, author = {Löcklin, Andreas and Kotsch, Christoph and Krüning, Kai and Rentschler, Markus and Ebert, Christof and Müller, Manuel and Weyrich, Michael}, doi = {10.51202/9783181023921-335}, isbn = {978-3-18-092392-4}, issn = {0083-5560}, journal = {Automation 2021, VDI Verlag GmbH Düsseldorf, pp. 335-352, 29. und 30 June 2021}, title = {Testen 4.0 in der Automatisierungstechnik: Agiles modellbasiertes Testen vernetzter Systeme und Komponenten}, url = {https://doi.org/10.51202/9783181023921-335}, year = 2021 }
  Link
  https://doi.org/10.51202/9783181023921-335

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

2024

BibTeX

2023

Abstract

BibTeX

Link

BibTeX

BibTeX

BibTeX

BibTeX

Abstract

BibTeX

Link

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

Link

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

2022

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Link

Abstract

BibTeX

Link