Intelligent methodology for sensing, modeling and control of pulsed GTAW: Part I - Bead-on-plate welding

This study addresses intelligent techniques for Fulfilling quality control of bead-on-plate welding. A new visual double-sided sensing system capable of imaging the weld pool topside and backside simultaneously in a frame was provided to determine the weld pool geometry parameters. The imaging princ iple was analyzed with spectrum distribution, in which the weld pool was il luminated by are light emission to receive a clear image under base current . Double-sided size parameters describing weld pool geometry were defined a nd determined in real time with the developed image processing algorithm. T he influences of welding parameters such as pulse duty ratio and travel spe ed on weld bead geometry were identified by step response. Based on the ana lysis, a neural network model of the dynamic process was established for pr edicting the backside width with the welding parameters and topside size pa rameters. The simulation results indicated the accuracy of the model, and t he characteristics of the welding process were analyzed carefully. Aiming a t the bead-on-plate pulsed GTAW process, conventional and intelligent contr ol methods of single input and single output were investigated, and the neu ron self-learning PSD control was verified with better performance for prac tical application through comparisons.