The automation of quality control in manufacturing has made great strides in recent years, in particular following new developments in machine learning, specifically deep learning, which allow to solve challenging tasks such as visual inspection or quality prediction. Yet, optimum quality control pipelines are often not obvious in specific settings, since they do not necessarily align with (supervised) machine learning tasks. In this contribution, we introduce a new automation pipeline for the quantification of wear on electrical contact pins. More specifically, we propose and test a novel pipeline which combines a deep network for image segmentation with geometric priors of the problem. This task is important for a judgement of the quality of the material and it can serve as a starting point to optimize the choices of materials based on its automated evaluation.
Die automatische Qualitätskontrolle hat in den letzten Jahren große Fortschritte gemacht. Realisiert werden konnten diese insbesondere durch neue Entwicklungen im Bereich des maschinellen Lernens (vor allem Deep Learning), die den Einsatz von qualitativ hochwertigen Modellen für anspruchsvolle Aufgaben, wie die visuelle Inspektion oder Qualitätsvorhersage, ermöglichen. Allerdings ist die Auswahl von optimalen Methoden zur Qualitätskontrolle in bestimmten Situationen nicht offensichtlich, da sie nicht notwendigerweise mit klassischen (überwachten) Aufgaben des maschinellen Lernens übereinstimmen. In diesem Beitrag stellen wir eine automatisierte Methode zur Quantifizierung von Verschleißerscheinungen an elektrischen Kontaktstiften vor. Im Einzelnen beschreiben wir die Implementierung und den Test dieser Methode, die ein tiefes neuronales Netz zur Bildsegmentierung und Kenntnisse über die Geometrie der Kontaktstifte kombiniert. Diese Lösung dieses Problems ist wichtig, um eine quantifizierbare Aussage über die Materialqualität zu treffen und so die Materialauswahl optimieren zu können.
Funding source: BMBF
Award Identifier / Grant number: 01IS18041A
Funding statement: BH acknowledges funding in the frame of the BMBF project ITS_ML, grant number 01IS18041A.
About the authors
Florian Buckermann studied Cognitive Computer Science and Intelligent Systems at Bielefeld University and received his M.Sc. in 2019. Afterwards he started his PhD at the Data Science Chair at the University of Würzburg. His main research topics are machine learning applications in industrial production processes.
Nils Klement studied physics in Bielefeld and received his MSc. in 2018. He is working on his PhD at the HARTING Technology Group. His research focuses on the electrical and mechanical behavior of contacting surfaces and their simulation.
Oliver Beyer studied computer science at the Rheinische Friedrich-Wilhelms-Universität Bonn and received his diploma in 2008. In 2013, he obtained a PhD in computer science at the Cognitive Interaction Technology Cluster of Excellence (CITEC) at Bielefeld University. Since 2013 he is part of the research and development department at the HARTING Technology Group.
Andreas Hütten studied physics in Göttingen and received his PhD in 1989. He worked in the USA at UC Berkeley and Lawrence Berkeley National Laboratory. After further positions at the Leibniz Institute for Solid State and Materials Research in Dresden and at the Institute for Nanotechnology in Karlsruhe, he accepted a professorship for experimental physics at Bielefeld University in 2007. His research focuses on magnetic nanostructures, magnetoresistive sensors, magnetocaloric materials and electron microscopy.
Barbara Hammer is a full Professor for Machine Learning at the CITEC Cluster at Bielefeld University, Germany. She received her Ph.D. in Computer Science in 1999 and her venia legendi (permission to teach) in 2003, both from the University of Osnabrueck, Germany, where she was head of an independent research group on the topic ‘Learning with Neural Methods on Structured Data’. In 2004, she accepted an offer for a professorship at Clausthal University of Technology, Germany, before moving to Bielefeld in 2010. Barbara’s research interests cover theory and algorithms in machine learning and neural networks and their application for technical systems and the life sciences, including explainability, learning with drift, nonlinear dimensionality reduction, recursive models, and learning with non-standard data. Barbara has been chairing the IEEE CIS Technical Committee on Data Mining and Big Data Analytics, the IEEE CIS Technical Committee on Neural Networks, and the IEEE CIS Distinguished Lecturer Committee. She has been elected as member of the IEEE CIS Administrative Committee and the INNS Board. She is an associate editor of the IEEE Computational Intelligence Magazine, the IEEE TNNLS, and IEEE TPAMI. Currently, large parties of her work focusses on explainable machine learning for spatial-temporal data in her role as a PI of the ERC Synergy Grant Water-Futures.
We want to thank the HARTING Technology Group and the corresponding staff for executing the necessary measurements and providing the data and labels for our experiments.
1. Zahra Riahi Samani, Jacob Antony Alappatt, Drew Parker, Abdol Aziz Ould Ismail and Ragini Verma. Qc-automator: Deep learning-based automated quality control for diffusion MR images. Frontiers in Neuroscience, 13:1456, 2019.10.3389/fnins.2019.01456Search in Google Scholar PubMed PubMed Central
2. Javier Villalba-Diez, Daniel Schmidt, Roman Gevers, Joaquín Ordieres-Meré, Martin Buchwitz and Wanja Wellbrock. Deep learning for industrial computer vision quality control in the printing industry 4.0. Sensors, 19(18), 2019.10.3390/s19183987Search in Google Scholar PubMed PubMed Central
3. Shervin Minaee, Yuri Boykov, Fatih Porikli, Antonio Plaza, Nasser Kehtarnavaz and Demetri Terzopoulos. Image segmentation using deep learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.10.1109/TPAMI.2021.3059968Search in Google Scholar PubMed
4. Sourabh Bhide, Ralf Mikut, Maria Leptin and Johannes Stegmaier. Semi-automatic generation of tight binary masks and non-convex isosurfaces for quantitative analysis of 3d biological samples. In ICIP 2020, pages 2820–2824. IEEE, 2020.10.1109/ICIP40778.2020.9190951Search in Google Scholar
5. Asifullah Khan, Anabia Sohail, Umme Zahoora and Aqsa Saeed Qureshi. A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev., 53(8):5455–5516, 2020.10.1007/s10462-020-09825-6Search in Google Scholar
6. Raghavendra Chalapathy and Sanjay Chawla. Deep learning for anomaly detection: A survey. CoRR, abs/1901.03407, 2019.10.1145/3394486.3406704Search in Google Scholar
7. Baifan Zhou, Yulia Svetashova, Seongsu Byeon, Tim Pychynski, Ralf Mikut and Evgeny Kharlamov, Predicting quality of automated welding with machine learning and semantics: A Bosch case study. In Mathieu d’Aquin, Stefan Dietze, Claudia Hauff, Edward Curry and Philippe Cudré-Mauroux, editors, CIKM’20, pages 2933–2940. ACM, 2020.10.1145/3340531.3412737Search in Google Scholar
8. Andreas Bunte, Benno Stein and Oliver Niggemann. Model-based diagnosis for cyber-physical production systems based on machine learning and residual-based diagnosis models. In AAAI 2019, pages 2727–2735. AAAI Press, 2019.10.1609/aaai.v33i01.33012727Search in Google Scholar
9. Diogo V. Carvalho, Eduardo M. Pereira and Jaime S. Cardoso. Machine learning interpretability: A survey on methods and metrics. Electronics, 8(8), 2019.10.3390/electronics8080832Search in Google Scholar
10. Aqsa Saeed Qureshi, Asifullah Khan, Nauman Shamim and Muhammad Hanif Durad. Intrusion detection using deep sparse auto-encoder and self-taught learning. Neural Comput. Appl., 32(8):3135–3147, 2020.10.1007/s00521-019-04152-6Search in Google Scholar
11. Fabio Henrique, Kiyoiti dos Santos Tanaka and Claus Aranha. Data augmentation using GANs. CoRR, abs/1904.09135, 2019.Search in Google Scholar
12. Aidan Fuller, Zhong Fan and Charles Day. Digital twin: Enabling technology, challenges and open research. CoRR, abs/1911.01276, 2019.Search in Google Scholar
13. Abhishek Dutta and Andrew Zisserman. The via annotation software for images, audio and video. Proceedings of the 27th ACM International Conference on Multimedia, 2019.10.1145/3343031.3350535Search in Google Scholar
14. Alexander Schulz, Fabian Hinder and Barbara Hammer. Deepview: Visualizing classification boundaries of deep neural networks as scatter plots using discriminative dimensionality reduction. In Christian Bessiere, editor, IJCAI 2020, pages 2305–2311. ijcai.org, 2020.10.24963/ijcai.2020/319Search in Google Scholar
15. T.W. Liskiewicz, D. Jozefczyk, K.J. Kubiak. Surface texturing for improved fretting-corrosion performance of electrical connectors. In 28th International Conference on Electric Contacts, pages 63–67, 2016.Search in Google Scholar
16. Liborio Cavaleri, Panagiotis G. Asteris, Pandora P. Psyllaki, Maria G. Douvika, Athanasia D. Skentou and Nikolaos M. Vaxevanidis. Prediction of surface treatment effects on the tribological performance of tool steels using artificial neural networks. Applied Sciences, 9(14), 2019.10.3390/app9142788Search in Google Scholar
17. Y. Meng, J. Xu, Z. Jin, Braham Prakash and Yuanzhong Hu. A review of recent advances in tribology. Friction, 8:221–300, 2020.10.1007/s40544-020-0367-2Search in Google Scholar
18. Jonathan Long, Evan Shelhamer and Trevor Darrell. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015.10.1109/CVPR.2015.7298965Search in Google Scholar
19. V. Badrinarayanan, A. Kendall and R. Cipolla. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12):2481–2495, 2017.10.1109/TPAMI.2016.2644615Search in Google Scholar PubMed
20. Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang and Jiaya Jia. Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.Search in Google Scholar
21. Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff and Hartwig Adam. Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), September 2018.10.1007/978-3-030-01234-2_49Search in Google Scholar
22. Olaf Ronneberger, Philipp Fischer and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention, 2015.10.1007/978-3-319-24574-4_28Search in Google Scholar
23. Nahian Siddique, Paheding Sidike, Colin Elkin and Vijay Devabhaktuni. U-net and its variants for medical image segmentation: theory and applications, 2020.10.1109/ACCESS.2021.3086020Search in Google Scholar
24. Diederik P. Kingma and Jimmy Ba. Adam: A Method for Stochastic Optimization. International Conference on Learning Representations, 2015.Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston