A Fuzzy Inference-neural Network Control of Dynamic Process of Weld Bead Width in Pulse TIG Welding

A fuzzy inference-artificial neural network control approach to the dynamic process of welding current-top bead width in the pulse TIG welding is presented in this paper. Using artificial neural networks for modelling the process, the design of the fuzzy control system is simulated so that the difficulties of modelling and control of the pulse TIG welding in classic control methods are avoided. The results of experiment on the pulse TIG welding process show that the fuzzy inference-neural network control scheme presented in this paper is effective.