Multi-objective parametric appraisal of pulsed current gas tungsten arc welding process by using hybrid optimization algorithms

Recently, the pulsed current tungsten arc welding process (PC-TAW) has cemented their potential in various sorts of industrial application such as automobile, aerospace, and structural joining. However, the involvement of multiple process parameters in PC-GTAW process usually makes the process cumbersome to understand; and thereby, it is difficult to develop the mathematical model. Here, in this scientific work, the major efforts have been made to optimize multiple parameters for selected output responses through the use of evolutionary computational approaches. For this purpose, the particle swarm optimization (PSO), simulated annealing (SA) algorithm, and hybrid PSO-SA (HPSOSA) techniques have been employed and compared in terms of the quality responses for input parameters. From the soft computing modeling results, it has been observed that the HPSOSA improved the process performance and has revealed the global optimal solution within minimum interval of time. The developed models were statistically significant at 95% confidence interval. The experimental and mathematical outcomes for the welded specimens are duly supported with microscopic analyses.