Framework for Mitigation of Welding Induced Distortion through Response Surface Method and Reinforcement Learning

Welding induced distortion causes dimensional inaccuracies in parts being produced and assembly fit-up problems during manufacturing. In this study, a framework is proposed to mitigate weld distortion at the design stage. A sequential approach is adopted to optimize the welding process. In the first phase, welding process parameters are optimized through the response surface method. The effect of these parameters on the overall distortion of the welded part is observed by a simulation of the welding process. In the second phase, the weld sequence is optimized using the optimum weld parameters. A reinforcement learning-based Q-learning technique is used to select the optimum welding path by sequential observation of weld distortion at each segment being welded. The optimum process parameters and weld path sequence have been selected for 3 mm steel plates having a lap joint configuration and a 2 mm vent panel with a butt joint configuration. It is concluded that the combination of the optimum welding parameters and welding sequence yields minimum distortion. By applying this framework, a reduction of 19% is observed in overall welding induced distortion.

Automated summary

This study proposed a framework to mitigate welding-induced distortion by optimizing welding parameters and sequence at the design stage, resulting in a 19% reduction in overall welding-induced distortion.