A Study on Prediction of the Optimal Process Parameters for GMA Root-pass welding in Pipeline

Conventionally, welding processes are highly labor-intensive and need skilled operators. Compared to plate welding process, pipe welding process imposes higher skill requirement on operators and sound welds which guaranteed to be repeatable from weld to weld because of the harsh environment and intense process disturbance. Also, the automated arc welding process becomes important for productivity, quality and cost-efficiency. Even if many welding parameters, such as the arc current, welding voltage and weld speed, can affect the result of weldability, most of the automated welding system cannot handle so many welding parameters online to adapt the change of conditions during the weld process. Therefore, a suitable control algorithm to get a good weld quality in the pipe welding process must be developedThe objective of this study is focused on developing an automatic control algorithm not only to improve the productivity, quality and efficiency of the STT (Surface Tension Transfer) welding process, but also to select the optimal welding conditions for root-pass welding. This algorithm should be able to adjust the optimal welding parameters to ensure the welding quality and overcome the process variability, fluctuation and disturbance.