An Integrated Ga-Taguchi Model for Parametric Optimization of Submerged Arc Welding Process

An optimization method influenced by biological evolution, a genetic algorithm (GA) is controlled by variables like mutation rate, crossover fraction, and population size. An integrated GA-Taguchi approach is used in this study to determine the ideal GA control settings for the SAW process. Following the optimization of these GA parameters, the SAW process parameters are further optimized using the same GA. A semi-automatic submerged arc welding setup is used for the experimental work. Weld bead width and weld bead hardness are taken into consideration as the output responses, and welding current, arc voltage, and welding speed are chosen as input variables. The objective function for GA optimization is created by combining regression models created for both output responses using a weighted-sum method. The ideal GA parameters, as determined by the suggested integrated methodology, are a mutation rate of 0.05, a crossover fraction of 0.7, and a population size of 100. The findings show that optimizing SAW parameters with the tuned GA performs better than optimizing with non-optimized GA parameters.