Laser welding monitoring techniques based on optical diagnosis and artificial intelligence: a review

Abstract

Laser welding is an efficient and precise joining method widely used in various industries. Real-time monitoring of the welding process is important for improving the quality of the weld products. This study provides an overview of the optical diagnostics of the laser welding process. The common welding defects and their formation mechanisms are described, starting with an introduction to the principles of laser welding. Optical signal sources are divided into radiated and external active lights, and different monitoring systems are summarized and classified. Also, the applications of artificial intelligence techniques in data processing, weld defect prediction and classification, and adaptive welding control are summarized. Finally, future research and challenges in real-time laser welding monitoring technology based on optical diagnostics are discussed. This study demonstrated that optical diagnostic techniques could acquire substantial information about the laser welding process and help identify welding defects.

Keywords

Laser welding / Real-time monitoring / Welding defect / Optical diagnosis / Artificial intelligence / Engineering / Manufacturing Engineering

Funding

National Natural Science Foundation of China(52275317)

Natural Science Foundation of Guangdong Province(2023A1515012172)

Guangzhou Municipal Special Fund Project for Scientific and Technological Innovation and Development(2023B03J1326)

RIGHTS & PERMISSIONS

Shanghai University and Periodicals Agency of Shanghai University and Springer-Verlag GmbH Germany, part of Springer Nature