APPLICATION OF ARTIFICIAL INTELLIGENCE TECHNIQUES FOR DEFECT PREVENTION AND QUALITY CONTROL IN ARC WELDING PROCESSES: A COMPREHENSIVE REVIEW

Year 2024, Volume: 10 Issue: 2, 179 - 206, 30.12.2024

Turgay Tugay Bilgin , Musa Selman Kunduracı , Ahmet Metin , Merve Doğru , Erdal Nayir

https://doi.org/10.51477/mejs.1497277

Abstract

This study presents a comprehensive review of research applying artificial intelligence (AI) techniques to prevent defects in arc welding processes. Arc welding is essential across various industries, but numerous issues can arise, impacting weld quality and production efficiency. The review systematically analyzes relevant studies published since 2018, focusing on three key aspects: datasets used, methodologies and approaches adopted, and performance metrics reported. The findings reveal significant adoption of both machine learning and deep learning techniques, with the choice depending on factors like input data nature, welding process dynamics, and computational requirements. Deep learning models, particularly convolutional neural networks (CNNs) and long short-term memory (LSTM) networks, have demonstrated superior performance in image-based defect detection and time-series analysis for quality prediction. However, traditional machine learning algorithms have also been utilized, often coupled with dimensionality reduction or feature selection techniques. The review highlights the diverse range of performance metrics employed, such as accuracy, precision, recall, F1-score, mean squared error (MSE), and root mean squared error (RMSE). Metric selection depends on the specific task (classification or regression) and the desired trade-off between different performance aspects. While many studies reported promising results with accuracy rates frequently exceeding 90%, challenges remain in real-world industrial settings due to factors like noise, occlusions, and rapidly changing welding conditions. This review serves as a comprehensive guide for researchers and practitioners in AI-assisted defect prevention and quality control for arc welding processes, highlighting current trends, methodologies, and future research directions.

Keywords

Arc Welding, Deep Learning, Machine Learning, Welding Defect Prevention

Project Number

TUBITAK 1711 Yapay Zeka Ekosistem Çağrısı, Proje Adı: "Robotlu MIG/MAG Kaynak Proseslerinde Yapay Zekâ Destekli Hata Önleyici ve Tahminleyici Akıllı Üretim Sistemi Geliştirme" Proje No: 3227006

References

• K. Weman and G. Lindén, MIG welding guide. Woodhead Publishing, 2006.
• J. Norrish, Advanced Welding Processes. Institute of physics Publishing, 1992.
• “What is MIG/MAG Welding?” [Online]. Available: https://www.fronius.com/en/welding-technology/world-of-welding/mig-mag-welding
• D. Young, “MIG Welding Transfer Methods - A.E.D. Motorsport Products,” A.E.D. Motorsport Products. [Online]. Available: https://www.aedmetals.com/news/mig-welding-transfer-methods
• Miller, “MIG Welding: Setting the Correct Parameters,” Miller.
• S. C. A. Alfaro and P. Drews, “Intelligent Systems for Welding Process Automation,” J. of the Braz. Soc. of Mech. Sci. & Eng., vol. XXVIII, no. 1, pp. 25–29, 2006.
• Unimig, “Troubleshooting Your Weld – The 12 Most Common Problems & How to Fix Them,” Unimig.
• R. Singh, Arc welding processes handbook. John Wiley & Sons, 2021.
• A. B. Short, “Gas tungsten arc welding of α + β titanium alloys: A review,” Materials Science and Technology, vol. 25, no. 3, pp. 309–324, Mar. 2009, doi: 10.1179/174328408X389463.
• K. Weman, Welding processes handbook. Elsevier, 2011.
• L. F. Jeffus, H. V Johnson, and A. Lesnewich, Welding: principles and applications. Delmar Publishers New York, 1999.
• P. Kah, R. Suoranta, and J. Martikainen, “Advanced gas metal arc welding processes,” The International Journal of Advanced Manufacturing Technology, vol. 67, pp. 655–674, 2013.
• F. Khoshnaw, I. Krivtsun, and V. Korzhyk, “Arc welding methods,” in Welding of Metallic Materials, Elsevier, 2023, pp. 37–71.
• T. Chen et al., “Xgboost: extreme gradient boosting,” R package version 0.4-2, vol. 1, no. 4, pp. 1–4, 2015.
• T. M. Mitchell and T. M. Mitchell, Machine learning, vol. 1, no. 9. McGraw-hill New York, 1997.
• L. Breiman, “Random forests,” Mach Learn, vol. 45, no. 1, pp. 5–32, 2001.
• B. Yegnanarayana, Artificial neural networks. PHI Learning Pvt. Ltd., 2009.
• J.-S. Jang, “ANFIS: adaptive-network-based fuzzy inference system,” IEEE Trans Syst Man Cybern, vol. 23, no. 3, pp. 665–685, 1993.
• R. Hecht-Nielsen, “Theory of the backpropagation neural network,” in Neural networks for perception, Elsevier, 1992, pp. 65–93.
• E. Eze and J. Eze, “ARTIFICIAL INTELLIGENCE SUPPORT FOR 5G/6G-ENABLED INTERNET OF VEHICLES NETWORKS: AN OVERVIEW.” [Online]. Available: https://www.itu.int/en/journal/j-fet/Pages/default.aspx
• K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” Mar. 2017, [Online]. Available: http://arxiv.org/abs/1703.06870
• K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” Dec. 2015, [Online]. Available: http://arxiv.org/abs/1512.03385
• L. R. Medsker and L. C. Jain, “Recurrent neural networks,” Design and Applications, vol. 5, pp. 64–67, 2001.
• S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput, vol. 9, no. 8, pp. 1735–1780, 1997.
• I. Goodfellow et al., “Generative adversarial networks,” Commun ACM, vol. 63, no. 11, pp. 139–144, 2020, doi: 10.1145/3422622.
• Y. Zheng, Z. Xu, and X. Wang, “The fusion of deep learning and fuzzy systems: A state-of-the-art survey,” IEEE Transactions on Fuzzy Systems, vol. 30, no. 8, pp. 2783–2799, 2021.
• K. Asif, L. Zhang, S. Derrible, J. E. Indacochea, D. Ozevin, and B. Ziebart, “Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs,” J Intell Manuf, vol. 33, no. 3, pp. 881–895, Mar. 2022, doi: 10.1007/s10845-020-01667-x.
• G. Chen, B. Sheng, R. Luo, and P. Jia, “A parallel strategy for predicting the quality of welded joints in automotive bodies based on machine learning,” J Manuf Syst, vol. 62, pp. 636–649, Jan. 2022, doi: 10.1016/j.jmsy.2022.01.011.
• S. Shin, C. Jin, J. Yu, and S. Rhee, “Real-time detection of weld defects for automated welding process base on deep neural network,” Metals (Basel), vol. 10, no. 3, Mar. 2020, doi: 10.3390/met10030389.
• L. Liu, H. Chen, and S. Chen, “Quality analysis of CMT lap welding based on welding electronic parameters and welding sound,” J Manuf Process, vol. 74, pp. 1–13, Feb. 2022, doi: 10.1016/j.jmapro.2021.11.055.
• K. Meyer and V. Mahalec, “Anomaly detection methods for infrequent failures in resistive steel welding,” J Manuf Process, vol. 75, pp. 497–513, Mar. 2022, doi: 10.1016/j.jmapro.2021.12.003.
• P. Jirapipattanaporn and W. Lawanont, “Development of Anomaly Detection Model for Welding Classification Using Arc Sound,” in KST 2022 - 2022 14th International Conference on Knowledge and Smart Technology, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 57–62. doi: 10.1109/KST53302.2022.9729058.
• S. F. Laving, “Gas Metal Arc Welding Defect Detection using Sound signals,” Master Thesis, Seljuk University Institute of Science, Konya, 2019.
• D. Bacioiu, G. Melton, M. Papaelias, and R. Shaw, “Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning,” NDT and E International, vol. 107, Oct. 2019, doi: 10.1016/j.ndteint.2019.102139.
• C. El Hachem, G. Perrot, L. Painvin, J. B. Ernst-Desmulier, and R. Couturier, “Welding Seam Classification in the Automotive Industry using Deep Learning Algorithms,” in Proceedings - 2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2021, Institute of Electrical and Electronics Engineers Inc., Jul. 2021, pp. 235–240. doi: 10.1109/IAICT52856.2021.9532569.
• H. Guo, L. Lin, Y. Lv, J. Liu, and C. Tong, “Machine Learning for Determining Key Parameters in Welding Process of Underground Engineering Equipment,” in Proceedings of 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 33–41. doi: 10.1109/SDPC52933.2021.9563365.
• J. Lin, J. Lu, J. Xu, and D. Li, “Welding quality analysis and prediction based on deep learning,” in Proceedings - 2021 4th World Conference on Mechanical Engineering and Intelligent Manufacturing, WCMEIM 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 173–177. doi: 10.1109/WCMEIM54377.2021.00045.
• X. Ma, S. Pan, Y. Li, C. Feng, and A. Wang, “Intelligent welding robot system based on deep learning,” Proceedings - 2019 Chinese Automation Congress, CAC 2019, pp. 2944–2949, 2019, doi: 10.1109/CAC48633.2019.8997310.
• X. Jin, L. Lv, C. Chen, F. Yang, and T. Chen, “A New Welding Seam Recognition Methodology Based on Deep Learning Model MRCNN,” in 2020 7th International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2020, Institute of Electrical and Electronics Engineers Inc., Nov. 2020, pp. 767–771. doi: 10.1109/ICCSS52145.2020.9336927.
• C. El Hachem, “Automation of quality control and reduction of non-compliance using machine learning techniques at Faurecia Clean Mobility.” [Online]. Available: https://theses.hal.science/tel-03775370
• M. A. Kesse, “Artificial intelligence: A modern approach to increasing productivity and improving weld quality in TIG welding,” Doctoral Thesis, Lappeenranta-Lahti University of Technology LUT, Lappeenranta, 2021.
• E. A. Gyasi, P. Kah, H. Wu, and M. A. Kesse, “Modeling of an artificial intelligence system to predict structural integrity in robotic GMAW of UHSS fillet welded joints,” International Journal of Advanced Manufacturing Technology, vol. 93, no. 1–4, pp. 1139–1155, Oct. 2017, doi: 10.1007/s00170-017-0554-0.
• H. S. Nogay and T. C. Akinci, “Classification of operation cases in electric arc welding wachine by using deep convolutional neural networks,” Neural Comput Appl, vol. 33, no. 12, pp. 6657–6670, Jun. 2021, doi: 10.1007/s00521-020-05436-y.
• J. Wang et al., “On-line defect recognition of MIG lap welding for stainless steel sheet based on weld image and CMT voltage: Feature fusion and attention weights visualization,” J Manuf Process, vol. 108, pp. 430–444, Dec. 2023, doi: 10.1016/j.jmapro.2023.10.081.
• A. El Houd, C. El Hachem, and L. Painvin, “Deep Learning Model Explainability for Inspection Accuracy Improvement in the Automotive Industry,” Oct. 2021, [Online]. Available: http://arxiv.org/abs/2110.03384
• B. S. G. Pernambuco, C. R. Steffens, J. R. Pereira, A. V. Werhli, R. Z. Azzolin, and E. Da Silva Diaz Estrada, “Online sound based arc-welding defect detection using artificial neural networks,” in Proceedings - 2019 Latin American Robotics Symposium, 2019 Brazilian Symposium on Robotics and 2019 Workshop on Robotics in Education, LARS/SBR/WRE 2019, Institute of Electrical and Electronics Engineers Inc., Oct. 2019, pp. 263–268. doi: 10.1109/LARS-SBR-WRE48964.2019.00053.
• R. Wang, H. Wang, Z. He, J. Zhu, and H. Zuo, “WeldNet: a lightweight deep learning model for welding defect recognition,” Welding in the World, 2024, doi: 10.1007/s40194-024-01759-9.
• S. Li, J. Gao, E. Zhou, Q. Pan, and X. Wang, “Deep learning‐based fusion hole state recognition and width extraction for thin plate TIG welding,” Welding in the World, vol. 66, no. 7, pp. 1329–1347, Jul. 2022, doi: 10.1007/s40194-022-01287-4.
• Y. Wang, J. Han, J. Lu, L. Bai, and Z. Zhao, “TIG stainless steel molten pool contour detection and weld width prediction based on Res-Seg,” Metals (Basel), vol. 10, no. 11, pp. 1–15, Nov. 2020, doi: 10.3390/met10111495.
• X. Zhang, S. Zhao, and M. Wang, “Deep Learning-Based Defects Detection in Keyhole TIG Welding with Enhanced Vision,” Materials, vol. 17, no. 15, Aug. 2024, doi: 10.3390/ma17153871.
• C. Xia, Z. Pan, Z. Fei, S. Zhang, and H. Li, “Vision based defects detection for Keyhole TIG welding using deep learning T with visual explanation,” J Manuf Process, vol. 56, pp. 845–855, Aug. 2020, doi: 10.1016/j.jmapro.2020.05.033.
• Y. Liu, Y. Zhou, S. Wen, and C. Tang, “A strategy on selecting performance metrics for classifier evaluation,” International Journal of Mobile Computing and Multimedia Communications (IJMCMC), vol. 6, no. 4, pp. 20–35, 2014.