Optimum design based on mathematical model and neural network to predict weld parameters for fillet joints

The welding process variables of welding current, arc voltage, welding speed, gas flow rate, and offset distance, which influence weld bead shape, are coupled with each other but not directly connected with weld bead shape individually. Therefore, it is very difficult and time consuming to determine the welding process variables necessary to obtain the desired weld bead shape. Mathematical modeling in conjunction with many experiments must be used to predict the magnitude of weld bead shape. Even though experimental results are reliable, prediction is difficult because of the coupling characteristics. In this study, the 2 n−1 fractional factorial design method was used to investigate the effect of welding process variables on fillet joint shape. Finally, a neural network based on the backpropagation algorithm and an optimum design based on mathematical modeling were implemented to estimate the weld parameters for the desired fillet joint shape. Mathematical modeling based on multiple nonlinear regression analysis was used for modeling the gas metal arc welding (GMAW) parameters of the fillet joint. It was shown that the neural network and optimum design for estimating the weld parameters could be effectively implemented, which resulted in little error percentage difference between the estimated and experimental results.