Research Article
BibTex RIS Cite

Evaluation Of The Resistance Spot Welding Process With KNN and CART Machine Learning Techniques

Year 2023, , 132 - 145, 15.12.2023
https://doi.org/10.53448/akuumubd.1302120

Abstract

Spot welding, a type of resistance welding, is a welding application widely used in the production area and it is a common method for joining metal sheets. The spot-welding process is widely used in many production areas, especially in the automotive industry, radiator, and wire mesh production. Spot welding in car production lines is mainly performed by robotic applications. Industry 4.0 and digital transformation trends have led to unprecedented data growth. Nowadays, the manufacturing industry benefits from the power of machine learning and data science algorithms to monitor production processes and make predictions for quality, maintenance, and production optimization. Applying machine learning algorithms reduces the duration and cost of experiments. This study aims to confirm whether the spot welding, applied by robotic arms, is within the ideal spot-welding norms, in real production area. The ideal parameter norms were evaluated by using KNN and CART machine learning algorithms. To use real production data, this study was executed in the body production assembly line, which is selected as the pilot area, at TOFAŞ factory. The data set used in this research consists of the welding parameters of the current year, 2023. By running machine learning algorithms on the dataset, the performance evaluation of each algorithm was examined and the most appropriate estimation method was determined. In the experiments, the best F1-Score value was obtained by the CART model with 93%.

Thanks

Thanks to Adem Şener, who provided significant support during the data collection process and assisted in machine communication. Thanks to Tofaş Turkish Automobile Factory Inc. for granting permission to access their data sources.

References

  • Ahmed, F., Jannat, N.-E., Schmidt, D. and Kim, K.-Y., 2021. Data-driven cyber-physical system framework for connected resistance spot welding weldability certification. Robotics and Computer Integrated Manufacturing, 67.
  • Akgül, K., 2017. Modeling the Relationship Between Welding Electrode Types, Sheet Thicknesses, and Welding Force in the Automotive Sector. Master's Thesis, Gebze Technical University, Institute of Natural Sciences, Gebze.
  • Ambroziak, A., Korzeniowski, M. and Kustroń, P. Investigations of spot welds quality based on ultrasonic techniques. Institute of Production Engineering and Automation, Wroclaw University of Technology, Wrocław.
  • Gavidel, S.Z., Lu, S. and Rickli, J.L., 2019. Performance analysis and comparison of machine learning algorithms for predicting nugget width of resistance spot welding joints. The International Journal of Advanced Manufacturing Technology, 105(9), 3779–3796.
  • Kas, Z. and Das, M., 2019. Adaptive Control of Resistance Spot Welding Based on a Dynamic Resistance Model. Mathematical and Computational Applications, 24(4), 86.
  • Küçükvardar, M. and Aslan, A., 2021. Analysis of the Economic, Technological, Social, and Ethical Effects of Digitalization via International Reports. Intermedia International e-journal, 8(14), 21-38.
  • Selova, L. and Aydın, H., 2019. Investigation of Welding Parameters in Triple Sheet Resistance Spot Welding. Master's thesis, Uludağ University, Institute of Science, Bursa, 72.
  • Smith, J., 2015. Gini Coefficient and Income Inequality. Journal of Economics, 30(2), 45-60.
  • Wei, D., Li, D., Zheng, Y. and Wang, D., 2022. Online quality inspection of resistance spot welding for automotive production lines. Journal of Manufacturing Systems, 63(7), 354-369.
  • Xing, B., Xiao, Y., Qin, Q. and Cui, H., 2018. Quality assessment of resistance spot welding process based The International Journal of Advanced Manufacturing Technology, 94, 327–339.
  • Zhang, H., Hou, Y., Zhang, J. and Qi, X., 2014. A new method for nondestructive quality evaluation of the resistance spot welding based on the radar chart method and the decision tree classifier. The International Journal of Advanced Manufacturing Technology, 78(5-8).
  • Zhou, B., 2021. Machine Learning Methods for Product Quality Monitoring in Electric Resistance Welding ,Dissertation. Karlsruhe Institute of Technology (KIT), Faculty of Mechanical Engineering, 218.
  • Zhou, B., Pychynski, T., Reischl, M. and Mikut, R., 2018. Comparison of Machine Learning Approaches for Time-series-based Quality Monitoring of Resistance Spot Welding (RSW).

Dirençli Punta Kaynağı Prosesinin KNN ve CART Makine Öğrenimi Teknikleri ile Değerlendirilmesi

Year 2023, , 132 - 145, 15.12.2023
https://doi.org/10.53448/akuumubd.1302120

Abstract

Bir çeşit direnç kaynağı olan punta kaynağı, metal sac birleştirme işleminde kullanılan ve üretim alanında yaygın olarak bulunan bir kaynak uygulamasıdır. Punta kaynak prosesi otomotiv endüstrisi başta olmak üzere, radyatör ve tel örgü üretimi gibi birçok üretim alanında yaygın olarak kullanılır. Araç üretim bantlarında punta kaynağı ağırlıklı olarak robotik uygulamalarla gerçekleştirilmektedir. Endüstri 4.0 ve dijital dönüşüm trendleri benzeri görülmemiş bir veri büyümesine yol açmıştır. Günümüz imalat sektöründe kalite, bakım ve üretim süreçlerinin izlenmesi, tahmini ve optimizasyonu konularında makine öğrenimi ve veri bilimi algoritmalarının gücünden yararlanılmaktadır. Makine öğrenimi algoritmalarının uygulanması deneylerin süresini kısaltmanın yanı sıra deneysel maliyeti de azaltmaktadır. Bu çalışma, gerçek üretim sahasında robotik kollarla uygulanan punta kaynağının izlenerek, kaynak argümanlarının ideal punta normları içerisinde olup olmadığının tespitini amaçlamaktadır. İdeal parametre normları değerlendirilirken KNN (K-En Yakın Komşu) ve CART (Sınıflandırma ve Regresyon Ağacı) makine öğrenimi algoritmaları kullanılmıştır. Çalışma üretimdeki gerçek verileri kullanabilmek için TOFAŞ fabrikasında yapılmıştır ve pilot hat olarak gövde üretim montaj hattı seçilmiştir. Araştırmada kullanılan veri seti 2023 yılı güncel kaynak parametrelerinden oluşmaktadır. Veri kümesi üzerinde makine öğrenimi algoritmaları çalıştırılarak her bir algoritmanın başarım değerlendirmesine bakılmış ve en uygun tahminleme yöntemi belirlenmiştir. Yapılan deneylerde en iyi F1-Skor değeri %93 ile CART modeli tarafından elde edilmiştir.

References

  • Ahmed, F., Jannat, N.-E., Schmidt, D. and Kim, K.-Y., 2021. Data-driven cyber-physical system framework for connected resistance spot welding weldability certification. Robotics and Computer Integrated Manufacturing, 67.
  • Akgül, K., 2017. Modeling the Relationship Between Welding Electrode Types, Sheet Thicknesses, and Welding Force in the Automotive Sector. Master's Thesis, Gebze Technical University, Institute of Natural Sciences, Gebze.
  • Ambroziak, A., Korzeniowski, M. and Kustroń, P. Investigations of spot welds quality based on ultrasonic techniques. Institute of Production Engineering and Automation, Wroclaw University of Technology, Wrocław.
  • Gavidel, S.Z., Lu, S. and Rickli, J.L., 2019. Performance analysis and comparison of machine learning algorithms for predicting nugget width of resistance spot welding joints. The International Journal of Advanced Manufacturing Technology, 105(9), 3779–3796.
  • Kas, Z. and Das, M., 2019. Adaptive Control of Resistance Spot Welding Based on a Dynamic Resistance Model. Mathematical and Computational Applications, 24(4), 86.
  • Küçükvardar, M. and Aslan, A., 2021. Analysis of the Economic, Technological, Social, and Ethical Effects of Digitalization via International Reports. Intermedia International e-journal, 8(14), 21-38.
  • Selova, L. and Aydın, H., 2019. Investigation of Welding Parameters in Triple Sheet Resistance Spot Welding. Master's thesis, Uludağ University, Institute of Science, Bursa, 72.
  • Smith, J., 2015. Gini Coefficient and Income Inequality. Journal of Economics, 30(2), 45-60.
  • Wei, D., Li, D., Zheng, Y. and Wang, D., 2022. Online quality inspection of resistance spot welding for automotive production lines. Journal of Manufacturing Systems, 63(7), 354-369.
  • Xing, B., Xiao, Y., Qin, Q. and Cui, H., 2018. Quality assessment of resistance spot welding process based The International Journal of Advanced Manufacturing Technology, 94, 327–339.
  • Zhang, H., Hou, Y., Zhang, J. and Qi, X., 2014. A new method for nondestructive quality evaluation of the resistance spot welding based on the radar chart method and the decision tree classifier. The International Journal of Advanced Manufacturing Technology, 78(5-8).
  • Zhou, B., 2021. Machine Learning Methods for Product Quality Monitoring in Electric Resistance Welding ,Dissertation. Karlsruhe Institute of Technology (KIT), Faculty of Mechanical Engineering, 218.
  • Zhou, B., Pychynski, T., Reischl, M. and Mikut, R., 2018. Comparison of Machine Learning Approaches for Time-series-based Quality Monitoring of Resistance Spot Welding (RSW).
There are 13 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Sena Pekşin 0000-0003-2537-890X

Soydan Serttaş 0000-0001-8887-8675

Early Pub Date December 3, 2023
Publication Date December 15, 2023
Submission Date May 25, 2023
Published in Issue Year 2023

Cite

APA Pekşin, S., & Serttaş, S. (2023). Evaluation Of The Resistance Spot Welding Process With KNN and CART Machine Learning Techniques. International Journal of Engineering Technology and Applied Science, 6(2), 132-145. https://doi.org/10.53448/akuumubd.1302120