Assessment of quality predictions achieved with machine learning using established measurement process capability procedures in manufacturing
-
Sebastian Schorr
Sebastian Schorr studied Industrial Engineering at RWTH Aachen University and Tsinghua University and received his Master of Science degrees in 2017. From 2018 until 2021 he did his PhD at Saarland University in cooperation with Bosch Rexroth AG. Since 2021 he is working at Bosch Rexroth AG as an engineer for machine learning and quality management.
,
Dirk Bähre
Dirk Bähre studied mechanical engineering and completed his PhD in the field of cutting technologies at the Technical University of Kaiserslautern 1994. After holding management positions in research at the TU Kaiserslautern and in process development at a large automotive supplier, he is holding the Chair of Production Engineering at Saarland University since 2008. Since 2021, he is a scientific director at the Centre for Mechatronics and Automation Technology ZeMA in Saarbrücken. He researches and teaches in the field of manufacturing techniques for industrial applications. His research focus is on precise machining technologies, the analysis of machining effects on material properties and resource efficiency as well as sustainability in production.
Andreas Schütze received his diploma in physics from RWTH Aachen in 1990 and his doctorate in Applied Physics from Justus-Liebig-Universität in Gießen in 1994 with a thesis on microsensors and sensor systems for the detection of reducing and oxidizing gases. From 1994 until 1998 he worked for VDI/VDE-IT, Teltow, Germany, mainly in the fields of microsystems technology. From 1998 until 2000 he was professor for Sensors and Microsystem Technology at the University of Applied Sciences in Krefeld, Germany. Since April 2000 he is professor for Measurement Technology in the Department Systems Engineering at Saarland University, Saarbrücken, Germany and head of the Laboratory for Measurement Technology (LMT). His research interests include smart gas sensor systems as well as data engineering methods for industrial applications.
Abstract
The increasing amount of available process data from machining and other manufacturing processes together with machine learning methods provide new possibilities for quality control and condition monitoring. A prediction of the workpiece quality in an early machining stage can be used to alter current quality control strategies and could lead to savings in terms of time, cost and resources. However, most methods are tested under controlled lab conditions and few implementations in real manufacturing processes have been reported yet. The main reason for this slow uptake of this promising technology is the need to prove the capability of a machine learning method for quality prediction before it can be applied in serial production and supplement current quality control methods. This article introduces and compares approaches from the fields of machine learning and quality management in order to assess predictions. The comparison and adaption of the two approaches is carried out for an industrial use case at Bosch Rexroth AG where the diameter and the roundness of bores are predicted with machine learning based on process data.
Zusammenfassung
Die zunehmende Verfügbarkeit von Prozessdaten aus Fertigungsprozessen und die Zugänglichkeit zu Methoden des maschinellen Lernens eröffnet neue Möglichkeiten für die Qualitätskontrolle und die Zustandsüberwachung. Die Prognose der Qualität eines Werkstückes in einem frühen Bearbeitungsstadium kann zur Änderung der bisherigen Qualitätskontrollstrategien führen und zudem Einsparungen in Bezug auf Zeit, Kosten und Ressourcen hervorbringen. Die meisten Prognosemodelle werden zumeist ausschließlich unter kontrollierten Laborbedingungen getestet, sodass bisher nur wenige Implementierungen in reale Fertigungsprozesse erfolgten. Der Hauptgrund für diese langsame Integration dieser vielversprechenden Technologie in die Serienfertigung sowie die Ergänzung der bisherigen Qualitätskontrollstrategien ist die Notwendigkeit, die Fähigkeit einer Methode des maschinellen Lernens zur Qualitätsprognose nachzuweisen. Dieser Artikel stellt jeweils einen Ansatz aus den Bereichen maschinellen Lernens und Qualitätsmanagement vor, um die Genauigkeit einer Qualitätsprognose zu bewerten. Die Implementierung der beiden Ansätze erfolgt für einen industriellen Anwendungsfall bei der Bosch Rexroth AG, bei dem der Durchmesser und die Rundheit von Bohrungen mithilfe von maschinellem Lernen auf der Basis von Prozessdaten prognostiziert werden.
About the authors
Sebastian Schorr studied Industrial Engineering at RWTH Aachen University and Tsinghua University and received his Master of Science degrees in 2017. From 2018 until 2021 he did his PhD at Saarland University in cooperation with Bosch Rexroth AG. Since 2021 he is working at Bosch Rexroth AG as an engineer for machine learning and quality management.
Dirk Bähre studied mechanical engineering and completed his PhD in the field of cutting technologies at the Technical University of Kaiserslautern 1994. After holding management positions in research at the TU Kaiserslautern and in process development at a large automotive supplier, he is holding the Chair of Production Engineering at Saarland University since 2008. Since 2021, he is a scientific director at the Centre for Mechatronics and Automation Technology ZeMA in Saarbrücken. He researches and teaches in the field of manufacturing techniques for industrial applications. His research focus is on precise machining technologies, the analysis of machining effects on material properties and resource efficiency as well as sustainability in production.
Andreas Schütze received his diploma in physics from RWTH Aachen in 1990 and his doctorate in Applied Physics from Justus-Liebig-Universität in Gießen in 1994 with a thesis on microsensors and sensor systems for the detection of reducing and oxidizing gases. From 1994 until 1998 he worked for VDI/VDE-IT, Teltow, Germany, mainly in the fields of microsystems technology. From 1998 until 2000 he was professor for Sensors and Microsystem Technology at the University of Applied Sciences in Krefeld, Germany. Since April 2000 he is professor for Measurement Technology in the Department Systems Engineering at Saarland University, Saarbrücken, Germany and head of the Laboratory for Measurement Technology (LMT). His research interests include smart gas sensor systems as well as data engineering methods for industrial applications.
References
1. A. Schütze, N. Helwig, T. Schneider, “Sensors 4.0 – smart sensors and measurement technology enable Industry 4.0,” J. Sens. Sens. Syst. 7, 2018, 359–371, doi: 10.5194/jsss-7-359-2018.Search in Google Scholar
2. B. Denkena, M. Dittrich, F. Uhlich, “Self-optimizing cutting process using learning process models,” Procedia Technology 26, 2016, 221–226, doi: 10.1016/j.protcy.2016.08.030.Search in Google Scholar
3. D. Weichert, P. Link, A. Stol, S. Rüping, S. Ihlenfeldt, S. Wrobel, “A review of machine learning for the optimization of production processes,” The International Journal of Advanced Manufacturing Technology 104, 2019, 1889–1902, doi: 10.1007/s00170-019-03988-5.Search in Google Scholar
4. L. Wang, X. V. Wang, “Condition Monitoring for Predictive Maintenance,” in: “Cloud-Based Cyber-Physical Systems in Manufacturing,” Springer, Cham, 2017, 163–192, doi: 10.1007/978-3-319-67693-7_7.Search in Google Scholar
5. T. Schneider, S. Klein, A. Schütze, “Machine learning in industrial measurement technology for detection of known and unknown faults of equipment and sensors,” tm – Technisches Messen 86 (11), 2019, 706–718, doi: 10.1515/teme-2019-0086.Search in Google Scholar
6. S. Eichstädt, B. Ludwig, “Metrology for heterogeneous sensor networks in the IoT,” tm – Technisches Messen 86 (11), 2019, 623–629, doi: 10.1515/teme-2019-0073.Search in Google Scholar
7. S. Schorr, M. Möller, J. Heib, D. Bähre, “Quality Prediction of Drilled and Reamed Bores Based on Torque Measurements and the Machine Learning Method of Random Forest,” Procedia Manufacturing 48, 2020, 894–901, doi: 10.1016/j.promfg.2020.05.127.Search in Google Scholar
8. T. Pfeifer, Quality Management. Strategies, Methods, Techniques, 3rd edition. Hanser, München, 2002.10.3139/9783446224025Search in Google Scholar
9. S. Schorr, M. Möller, J. Heib, D. Bähre, “In-process Quality Control of Drilled and Reamed Bores using NC-Internal Signals and Machine Learning Method,” Procedia CIRP 93, 2020, 1328–1333, doi: 10.1016/j.procir.2020.03.020.Search in Google Scholar
10. S. Schorr, M. Möller, J. Heib, D. Bähre, “Comparison of Machine Learning Methods for Quality Prediction of Drilled and Reamed Bores Based on NC-Internal Signals,” Procedia CIRP 101, 2021, 77–80, doi: 10.1016/j.procir.2020.09.190.Search in Google Scholar
11. S. Schorr, “Prozessparallele Prognose der Werkstückqualität mithilfe von NC-internen Daten und maschinellem Lernen”, PhD thesis, Saarland University, 2021, doi: 10.22028/D291-34543.Search in Google Scholar
12. O. Sagi, L. Rokach, “Ensemble learning: A survey,” WIREs Data Mining and Knowledge Discovery 8 (4), 2018, doi: 10.1002/widm.1249.Search in Google Scholar
13. C. Schaffer, “Selecting a classification method by cross-validation,” Machine Learning 13, 1993, 135–143, doi: 10.1007/BF00993106.Search in Google Scholar
14. J. Cleve, U. Lämmel, Data mining, De Gruyter Studium, Berlin, 2016.10.1515/9783110456776Search in Google Scholar
15. C. P. Keferstein, M. Marxer, C. Bach, Fertigungsmesstechnik. Alles zu Messunsicherheit, konventioneller Messtechnik und Multisensorik, 9. Auflage. Springer Vieweg, Wiesbaden, 2017.Search in Google Scholar
16. Joint Committee for Guides in Metrology, “JCGM 100: Evaluation of measurement data – Guide to the expression of uncertainty in measurement,” JCGM100:2008, 2008. Available online: https://www.bipm.org/en/committees/jc/jcgm/publications.Search in Google Scholar
17. German Association of the Automotive Industry (VDA), “Quality Management in the Automotive Industry, Measurement and inspection processes, capability, planning and management”, 3rd edition, vol. 5, 2021.Search in Google Scholar
18. AIAG Core Tools, “Measurement Systems Analysis (MSA),” 4th edition, 2010.Search in Google Scholar
19. J. Tilsch, “Quality Management in the Bosch Group, 10. Capability of Measurement and Test Processes,” 2019, available online.Search in Google Scholar
20. E. Dietrich, Messmanagementsystem/Prüfmittelmanagement. in: T. Pfeifer, R. Schmitt, Masing Handbuch Qualitätsmanagement, 6. Auflage. Hanser, München 2014, 714–729.10.3139/9783446439924.031Search in Google Scholar
21. J. Tilsch, “Quality Management in the Bosch Group, 9. Machine and Process Capability,” 5th edition, 2019, available online.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Editorial
- Measurement systems and sensors with cognitive features
- Beiträge
- The digital transformation and novel calibration approaches
- Comparison of different ML methods concerning prediction quality, domain adaptation and robustness
- Assessment of quality predictions achieved with machine learning using established measurement process capability procedures in manufacturing
- Cognitive sensor systems for NDE 4.0: Technology, AI embedding, validation and qualification
- GAN-regularized augmentation strategy for spectral datasets
- Automatic multimodal sensor calibration of the UNICARagil vehicles
Articles in the same Issue
- Frontmatter
- Editorial
- Measurement systems and sensors with cognitive features
- Beiträge
- The digital transformation and novel calibration approaches
- Comparison of different ML methods concerning prediction quality, domain adaptation and robustness
- Assessment of quality predictions achieved with machine learning using established measurement process capability procedures in manufacturing
- Cognitive sensor systems for NDE 4.0: Technology, AI embedding, validation and qualification
- GAN-regularized augmentation strategy for spectral datasets
- Automatic multimodal sensor calibration of the UNICARagil vehicles
