Modeling of underwater wet welding process based on visual and arc sensor
Abstract
Purpose
The purpose of this paper was to use visual and arc sensors to simultaneously obtain the underwater wet welding information, and a weld seam-forming model was made to predict the weld seam's geometric parameters. It is difficult to obtain a fine welding quality in underwater welding because of the intense disturbances of the water environment. To automatically control the welding quality, the weld seam-forming model should first be established. Thus, the foundation was laid for automatically controlling the underwater welding seam-forming quality.
Design/methodology/approach
Visual and arc sensors were used simultaneously to obtain the weld seam image, current and voltage information; then signal algorithms were used to process the information, and the back propagation (BP) neural network was used to model the process.
Findings
Experiment results showed that the BP neural network model could precisely predict the weld seam-forming parameters of underwater wet welding.
Originality/value
A weld seam-forming model of underwater wet welding process was made; this laid the foundation for establishing a controller for controlling the underwater wet welding process automatically.
Keywords
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant (No. 51105103), China Postdoctoral Science Foundation under Grant (No. 2012M510945), the National 863 project under Grant (No. 2008AA092901). The authors would like to thank the editor and anonymous reviewers for their careful review and constructive comments on the earlier version of this article.
Citation
Chen, B. and Feng, J. (2014), "Modeling of underwater wet welding process based on visual and arc sensor", Industrial Robot, Vol. 41 No. 3, pp. 311-317. https://doi.org/10.1108/IR-03-2014-0315
Publisher
:Emerald Group Publishing Limited
Copyright © 2014, Emerald Group Publishing Limited