Review on multi-information acquisition, defect prediction and quality control of aluminum alloy GTAW process

The gas tungsten arc welding (GTAW) is a classic traditional welding method for aluminum alloys. However, the strong reflection of the welding area illuminated by arc light and the weld pool surface of aluminum alloy work piece determines the difficulty of making the visual sensor disturbed and sensitive during the welding process. The high sensitivity of aluminum alloys to heat input is the difficulty in determining the real-time and stability control of heat input adjustment. Online defect detection in aluminum alloy welding is significantly more difficult compared to materials like low-carbon steel. This paper focuses on intelligent technology in GTAW for aluminum alloys, specifically highlighting multi-information acquisition, defect prediction and quality control of weld formation, penetration state, and pore generation. Firstly, the paper reviews and discusses the development and application of multi-information sensing technology in aluminum alloy GTAW. Subsequently, different modeling methods for defect prediction related to penetration, weld formation, and porosity defects are sum-marized and compared. Additionally, the application of intelligent control methods in the aluminum alloy welding process is categorized. Finally, existing scientific and technical issues and further research directions are proposed.