Abstract
The authors have developed a torch position control system for narrow groove automatic TIG welding. This system can detect the feature point (electrode, wire, groove wall, and weld pool) positions in a weld pool image, calculate the relative positions, and move the electrode and wire to the correct positions. In order to identify the wavelength range that is less susceptible to arc light when capturing weld pool images, spectroscopic analysis was performed and a 1000-nm bandpass filter was selected. Since the brightness distribution suitable for detection differs for each feature point, weld pool images were captured with multiple exposure times. In order to accurately detect the feature points of various weld pool images, AI technology (the pose estimation model DarkPose) that can improve detection accuracy by adding training data was used. When the detection models were evaluated, it was found that the electrode, wire, and groove wall were detected with high accuracy. The torch position control system using the developed feature point detection technology was implemented. The system accurately detected the feature point positions and moved the electrode and wire to the correct position when the feature point position was misaligned. Also, the processing speed of the system was sufficient for torch position control of actual automatic TIG welding.
Similar content being viewed by others
Data Availability
The datasets generated and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Katsunori I (1980) Image processing for on-line detection of welding process (Report 1). Journal of The Japan Welding Society 49(9):609–613. https://doi.org/10.2207/qjjws1943.49.609. (in Japanese)
Takaichi K, Yoichi T, Masahiro K, Junichiro M (1989) Development of real time welding control system by using image processing. Quarterly Journal of The Japan Welding Society 7–3:363–367. https://doi.org/10.2207/qjjws.7.363. (in Japanese)
Yoshihiro F, Tsuyoshi O, Satoru A, Setsu Y, Tatsuya O, Makoto O (2012) Development of a welding monitoring system for in-process duality control of thick walled pipe. Welding in the World 56:15–25. https://doi.org/10.1007/BF03321391
Kazuki K, Yosuke O, Satoshi F, Satoru A (2020) Study on welding phenomena observation method based on arc and molten pool light emission characteristics in visible and infrared wavelength region. Quarterly Journal of The Japan Welding Society 38(2):103–113. https://doi.org/10.2207/qjjws.38.103. (in Japanese)
Akira A (2014) The visualization of arc welding phenomenon using laser illumination. Journal of The Japan Welding Society 83(8):598–601. https://doi.org/10.2207/jjws.83.598. (in Japanese)
Tsuyoshi A, Akira O, Keita O, Masatoshi H, Takayoshi Y (2018) Development of image sensor technology for automatic welding (image recognition by deep learning). Research and Development KOBE STEEL ENGINEERING REPORTS 68(2):63–66 (in Japanese)
Mobina M, Klaske VH, Ahmad A, Guy AD, Kwang MY, Amin G, Mahyar A (2022) Vision-based AL-algorithm for seam tracking and distance control of fillet welds in gas metal arc welding. Proceedings of IIW 2022 - International Conference on Welding and Joining:196–199.
Tatsuya Y (2022) Automation technology for one side welding with ceramic backing using weld pool image recognition. Proceedings of IIW 2022 Doc.XII- 2539–2022.
Kohei T, Tetsuo S, Reiko N, Yasutomo S, Taisuke W, Masakazu K, Shinya K, Masatoshi H, Mitsuo S (2022) Stabilization of welding process using Cyber-Physical System. Proceedings of IIW 2022 Doc.XII- 2537–2022.
Tetsuo S, Taisuke W, Shinya K, Yasutomo S, Masakazu K, Mitsuo S, Masatoshi H (2021) Automation of laser welding process by Cyber-Physical System (CPS) approach. Journal of The Japan Welding Society 90(1):30–35. https://doi.org/10.2207/jjws.90.30. (in Japanese)
Theo B, Issam B, Josselin D, Damien B, Cyril B (2022) Robust device for observation and classification of weld behavior. Proceedings of IIW 2022 - International Conference on Welding and Joining:223–226.
Antonio A, Pietro ML, Fabio O, Ida MC (2004) A sensing torch for on-line monitoring of the gas tungsten arc welding process of steel pipes. Meas Sci Technol 15(12):2412–2418
Sadek CAA, Diego SM, Marcelo SM (2006) Emission spectrometry evaluation in arc welding monitoring system. J Mater Process Technol 179:219–224. https://doi.org/10.1016/j.jmatprotec.2006.03.088
Jose JV, Luis RC, Adolfo C, Jose MLH, Jesus M (2022) Spectroscopic approach for the on-line monitoring of welding of tanker trucks. Appl Sci 12(10):5022. https://doi.org/10.3390/app12105022
Feng Z, Xiatian Z, Hanbin D, Mao Y, Ce Z (2019) Distribution-aware coordinate representation for human pose estimation. https://doi.org/10.48550/arXiv.1910.06278
Thong DN, Milan K (2022) A survey of top-down approaches for human pose estimation. https://doi.org/10.48550/arXiv.2202.02656
Tsung YL, Michael M, Serge B, James H, Pietro P, Deva R, Piotr D, Lawrence Z (2014) Microsoft COCO: common objects in context. Computer Vision – ECCV 2014:740–755. https://doi.org/10.1007/978-3-319-10602-1_48
Acknowledgements
The authors appreciate Tetsuo Sakai, Yasutomo Shiomi, and Taisuke Washitani of Toshiba Corporation, and Naoto Seto, Masahiro Horie, and Yoshiaki Yamasaki of Toshiba Infrastructure Systems & Solutions Corporation for their cooperation in the development of the feature point detection technology, and Yusuke Maruyama and Ryohei Tozaki of Toshiba IT & Control Systems Corporation for their help in constructing the welding torch position control system.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Amano, S., Tsujimura, Y., Ogawa, T. et al. Development of in-process welding torch position control system using AI technology. Weld World 67, 1223–1234 (2023). https://doi.org/10.1007/s40194-023-01486-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40194-023-01486-7