Intelligent Recognition of Laser Welding Deviation Based on Improved Neural Networks
Abstract
Laser welding technology has become one of the most commonly used high-precision welding methods in the field of modern industrial manufacturing, but there are deviations in the laser welding process, such as uneven weld seams and positional shifts, etc., which will directly affect the quality and performance of the welded joints. Therefore, accurately identifying and timely correcting these laser welding deviations is crucial to ensure welding quality and improve productivity. The aim of this study is to realize the intelligent identification of laser welding deviations based on an improved neural network approach.
References
[1] Yan Hui. Intelligent identification and loading gantry device for raw material packaging boxes in the laser welding assembly line of
battery cell modules [J]. Packaging Engineering, 2022, 43 (19): 262-267.
[2] Gao Xiangdong, Mo Ling, You Deyong, et al. RBF neural network prediction algorithm for weld seam deviation [J]. Journal of
Welding, 2012,33 (04): 1-4+113.
[3] Gao Xiangdong, Mo Ling, Zhong Xungao et al. Infrared detection method for tracking deviation of high-power fiber laser welding
seam [J]. Acta Physica Sinica, 2011, 60 (08): 743-750.
[4] Cheng Huixiang, Ma Yan-E, Li Xinwei. Laser welding deviation based on improved neural network intelligent identification study
[J]. Journal of laser, and 2021 (12) : 165-169.
[5] LI Z Z. Research on identification of weld deviation and welding torch height based on two-axis robot dual-line laser sensing [D].
Nanchang University,2013.
