Dynamic estimation of joint penetration by deep learning from weld pool image
Source abstract
Abstract
This work aims at a novel approach to estimate the root-pass penetration towards its feedback control, in which the real penetration is measured by the backside bead width. The major challenge is that it happens under the workpiece and likely cannot be directly observable. The dynamic evolution of the weld pool surface has been analysed to design an active vision method monitoring the pool surface, yet fundamentally correlated to the unobservable penetration. The designed convolutional neural network model is trained, validated, and tested for recognising the weld penetration with satisfactory accuracy.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Non-Destructive Testing Techniques · Metal and Thin Film Mechanics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Welding Research Institute and Engineering Research Center of Advanced Manufacturing Technology for Automotive Components-Ministry of Education, Beijing University of Technology, Beijing, People’s Republic of China
Institute for Sustainable Manufacturing, University of Kentucky, Lexington, KY, USA
Funding
Beijing Municipal Natural Science Foundation · National Natural Science Foundation of China
References (27)
Show source-provided references
1. 10.1016/j.rcim.2020.10197710.1016/j.rcim.2020.101977 ↗
2. 10.1049/ip-smt:1994114410.1049/ip-smt:19941144 ↗
3. 10.1109/LRA.2019.292484410.1109/LRA.2019.2924844 ↗
4. Jiao W · J Manuf Process · 2020 · 1
5. 10.1016/j.rcim.2019.05.00610.1016/j.rcim.2019.05.006 ↗
6. 10.1016/j.rcim.2015.11.00410.1016/j.rcim.2015.11.004 ↗
7. 10.1016/j.rcim.2019.05.01210.1016/j.rcim.2019.05.012 ↗
8. 10.1115/1.134971910.1115/1.1349719 ↗
9. 10.1109/TPS.2008.92713810.1109/TPS.2008.927138 ↗
10. 10.1016/j.ndteint.2008.07.00410.1016/j.ndteint.2008.07.004 ↗
11. 10.1109/AIM.1997.65292210.1109/AIM.1997.652922 ↗
12. 10.1115/1.213774710.1115/1.2137747 ↗
13. Katz JM. · Weld J · 1984 · 273
14. 10.1016/0890-6955(94)90014-010.1016/0890-6955(94)90014-0 ↗
15. 10.3390/s10060596210.3390/s100605962 ↗
16. 10.1179/174329308X30011810.1179/174329308X300118 ↗
17. Xiao Y · Weld J · 1993 · 72 · 428
18. 10.1109/28.56801110.1109/28.568011 ↗
19. 10.1016/j.jmatprotec.2018.01.03710.1016/j.jmatprotec.2018.01.037 ↗
20. Renwick RJ · Weld J · 1983
21. 10.1038/nature1453910.1038/nature14539 ↗
22. 10.1109/5.72679110.1109/5.726791 ↗
23. 10.1145/306538610.1145/3065386 ↗
24. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 3rd Int Conf Learn Represent ICLR 2015 – Conf Track Proc 2015:1–14.
25. Szegedy C · Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit · 2015 · 7 · 1
26. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, December, vol. 2016. IEEE; 2016, p. 770–778.
27. 10.1109/CEEE.2015.742823410.1109/CEEE.2015.7428234 ↗