Kurzfassung
Industrie 4.0 geht mit einer Vielzahl an Technologien einher, die großes Potenzial für die Elektromotorenproduktion von morgen bieten. Vor allem datengetriebene Ansätze, die sich der Methoden des maschinellen Lernens (ML) bedienen, rücken zunehmend in den Fokus. Im Rahmen dieses Beitrags wird gezeigt, wie sich die daraus ergebenden Potenziale systematisch erschließen lassen. Nach einem kurzen Überblick über bestehende ML-Ansätze in der Elektromotorenproduktion wird anhand des Referenzmodells CRISP-DM beispielhaft eine ML-basierte Qualitätsüberwachung für das Laserschweißen von Hairpins entwickelt.
Abstract
Industry 4.0 is accompanied by a multitude of technologies that offer great potential for tomorrow's electric motor production. Especially data-driven approaches such as machine learning (ML) are increasingly coming to the fore. This article shows how the resulting potentials can be tapped systematically. After a brief overview of existing ML approaches in electric motor production, an ML-based quality monitoring system for the laser welding of hairpins is developed exemplarily following the reference model CRISP-DM.
Literatur
1. Weigelt, M.; Mayr, A.; Böhm, R.; Kühl, A; Franke, J.: Quo vehis, Elektromobilität?ZWF113 (2018) 1–2, S. 59–6310.3139/104.111863Search in Google Scholar
2. Franke, J.; Risch, F.: Flexible Automatisierungstechnologien für die Produktion elektrischer Traktionsantriebe. In: Schäfer, H. (Hrsg.): Elektrische Antriebstechnologie für Hybrid- und Elektrofahrzeuge. Expert Verlag, Renningen2014, S. 377–388Search in Google Scholar
3. Wissenschaftliche Gesellschaft für Produktionstechnik e. V. (WGP): WGP-Standpunkt Industrie 4.0. WGP, Darmstadt2016Search in Google Scholar
4. Winkelhake, U.: Die digitale Transformation der Automobilindustrie. Springer-Verlag, Berlin, Heidelberg201710.1007/978-3-662-54935-3Search in Google Scholar
5. Mayr, A., et al.: Electric Motor Production 4.0 – Application Potentials of Industry 4.0 Technologies in the Manufacturing of Electric Motors. In: Proceedings of the 8th International Electric Drives Production Conference (EDPC), 2018, S. 1–13Search in Google Scholar
6. Mayr, A., et al.: Application Scenarios of Artificial Intelligence in Electric Drives Production. Procedia Manufacturing24 (2018), S. 40–4710.1016/j.promfg.2018.06.006Search in Google Scholar
7. Rebouças Filho, P. P., et al.: New Approach to Evaluate a Non-grain Oriented Electrical Steel Electromagnetic Performance Using Photomicrographic Analysis via Digital Image Processing. Journal of Materials Research and Technology (2017)Search in Google Scholar
8. Mayr, A., et al.: Potentials of Machine Learning in Electric Drives Production Using the Example of Contacting Processes and Selective Magnet Assembly. In: Proceedings of the 7th International Electric Drives Production Conference (EDPC), 2017, S. 1–810.1109/EDPC.2017.8328166Search in Google Scholar
9. Coupek, D.; Lechler, A.; Verl, A.: Cloud-Based Control Strategy: Down-stream Defect Reduction in the Production of Electric Motors. IEEE Transactions on Industry Applications53 (2017) 6, S. 5348–535310.1109/TIA.2017.2732340Search in Google Scholar
10. Machine Learning Apparatus and Method for Learning Arrangement Position of Mag-net in Rotor and Rotor Design Apparatus In-cluding Machine Learning Apparatus. U.S. Patent Application Nr. 15/277,988. 2017Search in Google Scholar
11. Kißkalt, D.; Mayr, A.; v. Lindenfels, J.; Franke, J.: Towards a Data-driven Process Monitoring for Machining Operations Using the Example of Electric Drive Production. In: Proceedings of the 8th International Electric Drives Production Conference (EDPC), 2018, S. 1–6Search in Google Scholar
12. Sun, J.; Wyss, R.; Steinecker, A.; Glocker, P.: Automated Fault Detection Using Deep Belief Networks for the Quality Inspection of Electromotors. tm – Technisches Messen81 (2014) 5, S. 255–26310.1515/teme-2014-1006Search in Google Scholar
13. Gläßel, T.; Franke, J.: Kontaktierung von Antrieben für die Elektromobilität. ZWF112 (2017) 5, S. 322–32610.3139/104.111721Search in Google Scholar
14. Fleischmann, H.; Spreng, S.; Kohl, J.; Kißkalt, D.; Franke, J.: Distributed Condition Monitoring Systems in Electric Drives Manufacturing. In: Proceedings of the 6th International Electric Drives Production Conference (EDPC), 2016, S. 52–5710.1109/EDPC.2016.7851314Search in Google Scholar
15. Weigelt, M.; Mayr, A.; Seefried, J.; Heisler, P.; Franke, J.: Conceptual Design of an Intelligent Ultrasonic Crimping Process Using Machine Learning Algorithms. Procedia Manufacturing17 (2018), S. 78–8510.1016/j.promfg.2018.10.015Search in Google Scholar
16. Gläßel, T.; Seefried, J.; Franke, J.: Challenges in the Manufacturing of Hairpin Windings and Application Opportunities of Infrared Lasers for the Contacting Process. In: Proceedinmgs of the 7th International Electric Drives Production Conference (EDPC), 2017, S. 64–70Search in Google Scholar
17. Riedel, A., et al.: Challenges of the Hairpin Technology for Production Techniques. In: Proceedings of the 21st International Conference on Electrical Machines and Systems (ICEMS), 2018, S. 2471–247610.23919/ICEMS.2018.8549105Search in Google Scholar
18. Glaessel, T., et al.: Infrared Laser Based Contacting of Bar-wound Windings in the Field of Electric Drives Production. Procedia CIRP74 (2018), S. 17–2210.1016/j.procir.2018.08.005Search in Google Scholar
19. Samuel, A. L.: Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development3 (1959) 3, S. 211–229Search in Google Scholar
20. Hastie, T.; Tibshirani, R.; Friedman, J. H.: The Elements of Statistical Learning – Data mining, Inference, and Prediction. Springer Series in Statistics, Springer-Verlag, Berlin, Heidelberg, New York2009Search in Google Scholar
21. Sutton, R. S.; Barto, A. G.: Reinforcement learning – An introduction. A Bradford book. MIT Press, Cambridge, Mass.2018Search in Google Scholar
22. Provost, F.; Fawcett, T.: Data Science für Unternehmen – Data Mining und datenanalytisches Denken praktisch anwenden. mitp Business, MITP-Verlag, Frechen2017Search in Google Scholar
23. Witten, I. H.; Frank, E.; Hall, M. A.; Pal, C.: Data Mining – Practical Machine Learning Tools and Techniques. Morgan Kaufmann Verlag, Cambridge2017Search in Google Scholar
24. Cleve, J.; Lämmel, U.: Data Mining. De Gruyter Oldenbourg Verlag, München201410.1524/9783486720341Search in Google Scholar
25. Brink, H.; Richards, J. W.; Fetherolf, M.: Real-world Machine Learning. Manning Publications Co, Shelter Island, NY2017Search in Google Scholar
26. Wierse, A.; Riedel, T.: Smart Data Analytics. Mit Hilfe von Big Data Zusammenhänge erkennen und Potentiale nutzen. De Gruyter Oldenbourg Verlag, Berlin, Boston201710.1515/9783110463958Search in Google Scholar
27. Mayr, A., et al.: Evaluation of Machine Learning for Quality Monitoring of Laser Welding Using the Example of the Contacting of Hairpin Windings. In: Proceedings of the 8th International Electric Drives Production Con-ference (EDPC), 2018, S. 1–7Search in Google Scholar
© 2019, Carl Hanser Verlag, München
