Investigation of friction stir welding tool parameters using FEM and neural network

Abstract

The welding tool geometry plays a critical role in acquiring desired microstructures and the heat-affected zones, and consequently improving the strength of the joint in friction stir welding. In this study, a friction stir welding process with different tool pin and shoulder diameter was numerically modeled. A thermomechanically coupled, 3D FEM analysis was used to investigate the effect of tool pin and shoulder diameter on welding force, material flow, thermal, and strain distributions in AA5083 aluminum alloy. Then, an artificial neural network model was employed to model the correlation between the tool parameters (pin and shoulder diameter) and heat-affected zone, thermal, and strain value in the weld zone.