Multi Objective Optimization of Weld Bead Geometry Parameters of Pulsed Current Micro Plasma Arc Welded Inconel 625 Using Enhanced Non-dominated Sorting Genetic Algorithm

Abstract

Pulsed Current Plasma Arc Welding (PCPAW) is one of the most widely used welding processes in sheet metal manufacturing industry. In any fusion arc welding process, the weld bead geometry plays an important role in determining the mechanical properties of the weld and hence, quality of the weld. Moreover, the geometry of weld bead involves several simultaneously multiple quality characteristics such as front width, back width, front height and back height, which must be closely monitored, controlled and optimized. The present study is focused on the multi-objective optimization of performance parameters of weld bead geometry of PCMPAW welded Inconel 625 sheets. The enhanced elitist non-dominated sorting genetic algorithm (NSGA-II) is used to solve this multi-objective problem. A mathematical predictive model for each of the weld bead parameters was developed using Response Surface Method (RSM) based Central Composite Design (CCD) design matrix. Further, an enhanced NSGA-II algorithm is used to optimize the models developed by RSM. Experiments are carried out to validate the results obtained from RSM and enhanced NSGA-II.