Application of Back Propagation Algorithm in Optimization of Weave Friction Stir Welding—A Study

Modern engineering applications require the amalgamation of unlike materials for achieving specific thermal, electrical, and physical properties. Aluminium alloys are quite often employ fusion or solid-state processes to join with copper. However, fusion welding of dissimilar materials results in defects such as porosity and the formation of brittle particles. Friction Stir Welding (FSW) is energy efficient, environment friendly process used for joining dissimilar metals. Hence, an attempt is made to join aluminium alloy (AA6061-T6) and pure copper. In this article, the effect of tool pin offset, eccentric weave tool path, and the addition of graphene nano-platelets was studied and compared with the conventional FSW. The effect of pin offset compared to the conventional pin position helped in obtaining a good weld strength due to the large volume of material transportation of base materials and better stirring effect. The novel eccentric weave motion of the tool was useful for obtaining enhanced joint property due to higher holding time, adequate heat input, and uniform mixing during the joining process. A back propagation network (BPN) was utilized in arriving at the optimal process parameters.