Socket Cable Sequencing Error Detection with Deep Learning

Yıl 2025, ERKEN GÖRÜNÜM, 1 - 1

Bahadır Elmas , Hakan Korkmaz

https://doi.org/10.2339/politeknik.1500454

Öz

The increase in product diversity and functionality in white goods and small household appliances, electrification in the automotive industry and the transition to autonomous driving have made wiring harnesses a critical component. Wiring harnesses are connected to the target unit or other wiring harnesses via sockets and provide information and energy flow. For this reason, it is critical to ensure the quality of socket assembly in terms of safety. In this study, ResNet-50 convolutional neural network with transfer learning method is used to automate the quality control inspection of cable sequencing in wiring harness production, which is performed by visual inspection of sockets by personnel. The fully connected layer of the network is removed and three fully connected layers are added. In order to train the proposed model, a camera-fixture setup connected to a computer was installed in the Tekirdağ/Çerkezköy factory of PAS South East Europe. A dataset containing 30234 images of the cable connection sequence of three sockets, which are frequently installed with this setup, was created. K-fold cross validation method was used for training the proposed model. L2 regularisation and dropout were applied to the first two layers. Adam algorithm was used to update the weights and cross entropy was used as an error measure. The test accuracy of the model is 97.25%.

Anahtar Kelimeler

Convolutional Neural Networks, Wiring Harness, Cable Sequence Error

Etik Beyan

The author(s) of this article declare that the materials and methods used in this study do not require ethical committee permission and/or legal-special permission.

Destekleyen Kurum

PAS South East Europe Sanayi ve Ticaret Limitet Şirketi Tekirdağ/Çerkezköy

Teşekkür

This study was supported by PAS South East Europe Sanayi ve Ticaret Limitet Şirketi Tekirdağ/Çerkezköy factory. We would like to thank all employees in administration, R&D and production for their support and contribution.

Derin Öğrenme ile Soket Kablo Sıralama Hata Tespiti

Öz

Beyaz eşya ve küçük ev aletlerinde ürün çeşitliliği ve işlevsellikteki artış, otomotiv endüstrisinde elektrifikasyon ve otonom sürüşe geçiş, kablo demetlerini kritik bir bileşen haline getirmiştir. Kablo demetleri, soketler aracılığıyla hedef üniteye veya diğer kablo demetlerine bağlanarak bilgi ve enerji akışını sağlar. Bu nedenle güvenlik açısından soket montaj kalitesinin sağlanması kritik önem taşımaktadır. Bu çalışmada kablo demeti üretiminde soketlerin personel tarafından göz kontrolü ile gerçekleştirilen kablo sıralaması kalite kontrol denetimini otomatikleştirmek için ResNet-50 evrişimli sinir ağı transfer öğrenme yöntemiyle kullanılmıştır. Ağın tam bağlantılı katmanı çıkarılarak üç tam bağlantılı katman eklenmiştir. Önerilen modeli eğitmek amacıyla PAS South East Europe’un Tekirdağ/Çerkezköy fabrikasında bilgisayara bağlı bir kamera-fikstür düzeneği kurulmuştur. Bu düzenekle montajı sıklıkla yapılan üç soketin kablo bağlantı sıralamasına ait 30234 adet görsel içeren bir veri seti oluşturulmuştur. Önerilen modelin eğitiminde K-kat çapraz doğrulama yöntemi kullanılmıştır. Eklenen ilk iki katmana L2 düzenlileştirmesi ve dropout uygulanmıştır. Ağırlıkları güncellemek için Adam algoritması tercih edilmiş, hata ölçüsü olarak ise çapraz entropi kullanılmıştır. Modelin test doğruluğu %97.25’tir.

Anahtar Kelimeler

Evrişimli Sinir Ağları, Kablo Demetleri, Kablo Sıralama Hatası

Etik Beyan

Bu makalenin yazarları çalışmalarında kullandıkları materyal ve yöntemlerin etik kurul izni ve/veya yasal-özel bir izin gerektirmediğini beyan ederler.

Destekleyen Kurum

PAS South East Europe Sanayi ve Ticaret Limitet Şirketi Tekirdağ/Çerkezköy

Teşekkür

Bu çalışma PAS South East Europe Sanayi ve Ticaret Limitet Şirketi Tekirdağ/Çerkezköy fabrikası tarafından desteklenmiştir. Destek ve katkılarından dolayı idari, Ar-Ge ve üretimdeki tüm çalışanlara teşekkür ederiz.

Kaynakça

• [1] Fröhlig S., Piechulek N., Friedlein M., Süß-Wolf R., Schmidt L., Nguyen M. K. H. et al. “Innovative signal and power connection solutions for alternative powertrain concepts”, 2020 10th International Electric Drives Production Conference (EDPC), Ludwigsburg, Germany, 1–7, (2020).
• [2] Nguyen H. G., Habiboglu R., Frankea J., “Enabling deep learning using synthetic data: A case study for the automotive wiring harness manufacturing”, ScienceDirect, 107: 1263-1268, (2022).
• [3] Wang H., Johansson B., “Deep Learning-Based Connector Detection for Robotized Assembly of Automotive Wire Harnesses”, 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), Auckland New Zealand, 1-8, (2023).
• [4] Nguyen H. G., Franke J., “Deep learning-based optical inspection of rigid and deformable linear objects in wiring harnesses”, ScienceDirect, 104: 1765–1770, (2021).
• [5] Trommnau J., Kühnle J., Siegert J., Inderka R., Bauernhansl T., “Overview of the State of the Art in the Production Process of Automotive Wire Harnesses, Current Research and Future Trends” ScienceDirect, 81: 387–392, (2019).
• [6] Kicki P., Bednarek M., Lembicz P., Mierzwiak G., Szymko A., Kraft M., Walas K., “Interpretable Classification of Wiring Harness Branches with Deep Neural Networks”, Sensors, 21(13): 4327, (2021).
• [7] Shrestha A., Mahmood A., “Review of Deep Learning Algorithms and Architectures”, IEEE Access, 7: 53040–53065, (2019).
• [8] Meiners M., Mayr A., Franke J., “Process curve analysis with machine learning on the example of screw fastening and press-in processes”, Procedia CIRP, 97: 166–171, (2021).
• [9] Nguyen H. G., Meiners M., Schmidt L., Franke J., “Deep learning-based automated optical inspection system for crimp connections”, 2020 10th International Electric Drives Production Conference (EDPC), Ludwigsburg Germany, 1–5, (2020).
• [10] Mayr A., Kißkalt D., Meiners M., Lutz B., Schäfer F., Seidel R. et al. “Machine Learning in Production – Potentials, Challenges and Exemplary Applications” Procedia CIRP, 86: 49–54, (2019).
• [11] Deng J., Dong W., Socher R., Li L-J., Li K., Fei-Fei L., “ImageNet: A large-scale hierarchical image database”, 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami USA, 248–255, (2009).
• [12] Ebayyeh A. A. R. M. A., Mousavi A., “A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry”, IEEE Access, 8: 183192–183271, (2020).
• [13] Parmar P., “Use of computer vision to detect tangles in tangled objects”, Image Information Processing (ICIIP-2013), Shimla India, 39–44, (2013).
• [14] Sun B., Chen F., Sasaki H., Fukuda T., “Robotic wiring harness assembly system for fault-tolerant electric connectors mating”, International Symposium on Micro-NanoMechatronics and Human Science, Nagoya Japan, 202–205, (2010).
• [15] Lee W., Cao K., “Application of Machine Vision to Inspect a Wiring Harness”. In Proceedings of the 2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS), Taipei Taiwan, 457–460, (2019).
• [16] Mohandoss R., Ganapathy V., Ramasubbu R., Rohit D., “Image processing based automatic color inspection and detection of colored wires in electric cables”, International Journal of Applied Engineering Research, 12: 611–617, (2017).
• [17] Zhou H., Li S., Lu Q., Qian J., “A Practical Solution to Deformable Linear Object Manipulation: A Case Study on Cable Harness Connection”, 2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM), Shenzhen, Chinap. 329–333, (2020).
• [18] Nguyen H. G., Meiners M., Schmidt L., Franke J., “Deep learning-based automated optical inspection system for crimp connections”, 2020 10th International Electric Drives Production Conference (EDPC), Ludwigsburg Germany,1–5, (2020).
• [19] Mou F., Wang B., Wu D., “Learning‑based cable coupling effect modeling for robotic manipulation of heavy industrial cables”, Scientific Reports, 12: 6036, (2022).
• [20] Thum G. W., Tang S. H., Ahmad S. A. et al. “Toward a Highly Accurate Classification of Underwater Cable Images via Deep Convolutional Neural Network”, Journal of Marine Science and Engineering, 8: 924, (2020).
• [21] Zheng L., Liu X., An Z., et al., “A smart assistance system for cable assembly by combining wearable augmented reality with portable visual inspection”, Virtual Reality & Intelligent Hardware, 2: 12–27, (2020).
• [22] Shi G., Jian W., “Wiring harness assembly detection system based on image processing technology”, In Proceedings of the 2011 International Conference on Electronics, Communications and Control (ICECC), Ningbo China, 2397–2400, (2011).
• [23] Salem F. M., “Recurrent Neural Networks: From Simple to Gated Architectures”, Springer, 1st edition, ISBN-13: ‎978-3030899288, Berlin, (2022).
• [24] Ackley D., Hinton G., Sejnowski T., “A Learning Algorithm for Boltzmann Machines”, Cognitive Science, 9(1):147–169, (1985).
• [25] Fischer A., Igel C., “An Introduction to Restricted Boltzmann Machines”, Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Buenos Aires Argentina, 14-16, (2012).
• [26] Al-jabery K. K., Obafemi-Ajayi T., Olbricht G. R., Wunsch II D. C., “Selected approaches to supervised learning”, Computational Learning Approaches to Data Analytics in Biomedical Applications, Academic Press, Cambridge, Massachusetts, (2019).
• [27] Zakeri A., Xia Y., Ravikumar N., Frangi A. F., “Deep learning for vision and representation learning”, Medical Image Analysis, Academic Press, (2023).
• [28] Fan J., Xu W., Wu Y., Gong Y., “Human tracking using convolutional neural networks”, IEEE Transactions on Neural Networks, 21: 1610-1623, (2010).
• [29] Toshev A., Szegedy C., “Deep -pose: Human pose estimation via deepneural networks”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1653-1660, (2014).
• [30] Jaderberg M., Vedaldi A., Zisserman A., “Deep features for text spotting”, Computer Vision-ECCV 2014, Zurich, Switzerland, 512-528, (2014).
• [31] Zhao R., Ouyang W., Li H., Wang X., “Saliency detection by multi-context deep learning”, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston USA, (2015).
• [32] Donahue J., Jia Y., Vinyals O., Hoffman J., Zhang N., Tzeng E., Darrell T., “DeCAF: A deep convolutional activation feature for generic Visual Recognition”, Proceedings of the 31st International Conference on Machine Learning, Berkeley USA, 32(1): 647-655, (2014).
• [33] Farabet C., Couprie C., Najman L., LeCun Y., “Learning hierarchical features for scene labeling”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 35: 1915-1929, (2013).
• [34] Lawrence S., Giles C. L., Tsoi A.C., Back A.D., “Face recognition: A convolutional neural-network approach”, IEEE Transactions on Neural Networks, 8:98-113, (1997).
• [35] Indolia S., Goswami A. K., Mishra S. P., Asopa P., “Conceptual Understanding of Convolutional Neural Network-A Deep Learning Approach”, Procedia Computer Science, 132: 679-688, (2018).
• [36] Yamashita R., Nishio M., Do R. K. G., Togashi K., “Convolutional neural networks: an overview and application in radiology”, Insights Imaging, 9: 611–629, (2018).
• [37] Baykal E., Doğan H., Ercin M. E., Ersoz S., Ekinci M., “Transfer learning with pre-trained deep convolutional neural networks for serous cell classification”, Multimedia Tools and Applications, 1-19, (2019).
• [38] Khan A., Rajendran P., Sidhu J. S. S., Thanigaiarasu S., Raja V., Al-Mdallal Q., “Convolutional neural network modeling and response surface analysis of compressible flow at sonic and supersonic Mach numbers”, Alexandria Engineering Journal, 65: 997-1029, (2023).
• [39] Pan S. J., Yang Q., “A survey on transfer learning”, IEEE Transactions on Knowledge and Data Engineering, 22: 1345-1359, (2010).
• [40] Chollet F., “Deep Learning with Python”, Second Edition, Manning Publications, ISBN-13: 978-1617294433, New York, (2022).
• [41] Elmas B., Türkiye'deki Kelebek Türlerinin Basamaklı Evrişimli Sinir Ağları ile Sınıflandırılması, Konya Mühendislik Bilimleri Dergisi, 9(3), 568-587, (2021).
• [42] Mathworks, https://uk.mathworks.com/help/deeplearning/gs/get-started-with-transfer-learning.html, Erişim Tarihi: 06.04.2024
• [43] He K., Zhang X., Ren S., Sun J., “Deep Residual Learning for Image Recognition”, IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas United States, 770-778, (2016).
• [44] Theckedath D., Sedamkar R. R., “Detecting Affect States Using VGG16, ResNet50 and SE‑ResNet50 Networks”, Springer Nature Computer Science, 79: 1-7, (2020).
• [45] Karadağ B., Arı A. ve Karadağ M., “Derin öğrenme modellerinin sinirsel stil aktarımı performanslarının karşılaştırılması”, Politeknik Dergisi, 24(4): 1611-1622, (2021).
• [46] Sontakke S. A., Dani R., Lohokare J., Shivagaje P., “Classification of Cardiotocography Signals using Machine Learning”, Intelligent Systems Conference, London UK, (2018).
• [47] Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R., “Dropout: A Simple Way to Prevent Neural Networks from Overfitting”, Journal of Machine Learning Research, 15:1929-1958, (2014).
• [48] Geron A., “Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems”, Second Edition, O’Reilly Publications, Californiya (2019).
• [49] Teke M., Civelek Z. ve Tümay M., “Glakom ve Katarakt Hastalığının Derin Öğrenme Modelleri ile Teşhisi”, Politeknik Dergisi, 27(5): 1813-1821, (2024).
• [50] Zeiler M. D., “ADADELTA: an adaptive learning rate method”. arXiv preprint arXiv:1212.5701, (2012). [51] Lydia A. A., Francis F. S., “Adagrad: An Optimizer for Stochastic Gradient Descent”, Internatıonal Journal of Informatıon And Computıng Scıence, 6: 599-568, (2019).
• [52] Jamin A., Humeau-Heurtier A., “(Multiscale) Cross-Entropy Methods: A Review”, Entropy, 22(1): 45, (2020).
• [53] Köroğlu B., “Cascaded Cross Entropy-Based Search Result Diversification”, Yüksek Lisans, Bilkent Üniversitesi Fen Bilimleri Enstitüsü, (2012).
• [54] Kaycı B., Demir B. E. and Demir F., “Deep learning based fault detection and diagnosis in photovoltaic system using thermal images acquired by UAV”, Politeknik Dergisi, 27(1): 91-99, (2024).
• [55] Geze R. A. ve Akbaş A. “Derin öğrenme algoritmalarını kullanarak kumaş kusurlarının tespiti ve sınıflandırılması”, Politeknik Dergisi, 27(1): 371-378, (2024).