Abstract
In the process of K-TIG deep penetration welding, the workpiece does not need to be bevelled; therefore, the welding method is butt welding, and the gap to be welded is very narrow (0.2~1 mm). Because of the large welding current, the welding arc light intensity is very strong. These factors cause difficulties in the K-TIG weld seam tracking process. To realize weld seam tracking in the K-TIG welding process, it is necessary to extract the keyhole entrance centre and weld centreline accurately. To reduce the interference of strong arc light in the process of K-TIG welding, the information of keyhole entrance and weld seam in the process of K-TIG welding is obtained by using a high-dynamic-range camera. An image processing algorithm based on Mask-RCNN is proposed to extract the centre of the keyhole entrance accurately. An image processing algorithm based on Hough line fitting is used to accurately identify the weld centreline in the welding image and extract the welding deviation. In welding experiments, it is verified that the welding deviation extracted by the method proposed in this paper fluctuates within ± 0.133 mm, which meets the requirements of actual K-TIG welding seam tracking.
Similar content being viewed by others
Data availability
Not applicable
References
Gao X, Mo L, Xiao Z, Chen X, Katayama S (2016) Seam tracking based on Kalman filtering of micro-gap weld using magneto-optical image. Int J Adv Manuf Technol 83:21–32. https://doi.org/10.1007/s00170-015-7560-x
Xu Y, Fang G, Chen S, Zou JJ, Ye Z (2014) Real-time image processing for vision-based weld seam tracking in robotic GMAW. Int J Adv Manuf Technol 73:1413–1425. https://doi.org/10.1007/s00170-014-5925-1
Gong Y, Dai X, Li X (2010) Structured-light based joint recognition using bottom-up and top-down combined visual processing, 2010[C]. IEEE:507–512. https://doi.org/10.1109/IASP.2010.5476064
Fan J, Jing F, Yang L, Long T, Tan M (2019) An initial point alignment method of narrow weld using laser vision sensor. Int J Adv Manuf Technol 102:201–212. https://doi.org/10.1007/s00170-018-3184-2
Xu P, Xu G, Tang X, Yao S (2008) A visual seam tracking system for robotic arc welding. Int J Adv Manuf Technol 37:70–75. https://doi.org/10.1007/s00170-007-0939-6
Kiddee P, Fang Z, Tan M (2016) An automated weld seam tracking system for thick plate using cross mark structured light. Int J Adv Manuf Technol 87:3589–3603. https://doi.org/10.1007/s00170-016-8729-7
Guo B, Shi Y, Yu G, Liang B, Wang K (2016) Weld deviation detection based on wide dynamic range vision sensor in MAG welding process. Int J Adv Manuf Technol 87:3397–3410. https://doi.org/10.1007/s00170-016-8721-2
Du R, Xu Y, Hou Z, Shu J, Chen S (2019) Strong noise image processing for vision-based seam tracking in robotic gas metal arc welding. Int J Adv Manuf Technol 101:2135–2149. https://doi.org/10.1007/s00170-018-3115-2
Shen H, Wu J, Lin T, Chen S (2008) Arc welding robot system with seam tracking and weld pool control based on passive vision. Int J Adv Manuf Technol 39:669–678. https://doi.org/10.1007/s00170-007-1257-8
Wang X, Shi Y, Yu G, Liang B, Li Y (2016) Groove-center detection in gas metal arc welding using a template-matching method. Int J Adv Manuf Technol 86:2791–2801. https://doi.org/10.1007/s00170-016-8389-7
Cui S, Shi Y, Sun K, Gu S (2018) Microstructure evolution and mechanical properties of keyhole deep penetration TIG welds of S32101 duplex stainless steel. Materials Science and Engineering A-structural Materials Properties Microstructure and Processing 709:214–222. https://doi.org/10.1016/j.msea.2017.10.051
Liu Z, Fang Y, Cui S, Luo Z, Liu W, Liu Z, Jiang Q, Yi S (2016) Stable keyhole welding process with K-TIG. J Mater Process Technol 238:65–72. https://doi.org/10.1016/j.jmatprotec.2016.07.005
Larson GW, Rushmeier H, Piatko C (1997) A visibility matching tone reproduction operator for high dynamic range scenes[J]. IEEE Trans Vis Comput Graph 3(4):291–306. https://doi.org/10.1109/2945.646233
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask R-CNN. In Proceedings of the IEEE international conference on computer vision (pp. 2961-2969). https://doi.org/10.1109/TPAMI.2018.2844175
Johnson JW. (2019) Automatic nucleus segmentation with Mask-RCNN. Science and Information Conference:399-407. https://doi.org/10.1007/978-3-030-17798-0_32
Kneis B. Face detection for crowd analysis using deep convolutional neural networks[C]. International Conference on Engineering Applications of Neural Networks, 2018: 71-80. https://doi.org/10.1007/978-3-319-98204-5_6
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Girshick R (2015) Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pp 1440–1448. https://doi.org/10.1109/ICCV.2015.169
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition, In, pp 3431–3440. https://doi.org/10.1109/TPAMI.2016.2572683
He, K., Zhang X, Ren S, & Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, Jun 26–Jul 1. https://doi.org/10.1109/CVPR.2016.90
Ahmed B, Gulliver TA, AlZahir S (2020) Image splicing detection using mask-RCNN. SIViP 14:1035–1042. https://doi.org/10.1007/s11760-020-01636-0
Zhang B, Shi Y, Gu S (2019) Narrow-seam identification and deviation detection in keyhole deep-penetration TIG welding. Int J Adv Manuf Technol 101:2051–2064. https://doi.org/10.1007/s00170-018-3089-0
Funding
This study is financially supported by the Key Research and Development Program of Guangdong Province (Grant No. 2020B090928003) and the Natural Science Foundation of Guangdong Province (Grant No. 2020A1515011050).
Author information
Authors and Affiliations
Contributions
Not applicable
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Code availability
Not applicable
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, Y., Shi, Y., Cui, Y. et al. Narrow gap deviation detection in Keyhole TIG welding using image processing method based on Mask-RCNN model. Int J Adv Manuf Technol 112, 2015–2025 (2021). https://doi.org/10.1007/s00170-020-06466-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-020-06466-5