Optimization of friction stir welding process using NSGA-II and DEMO

摘要: In welding processes, the selection of optimal process parameter settings is very important to achieve best weld qualities. this work, neuro-multi-objective evolutionary algorithms (EAs) are proposed optimize parameters in friction stir process. Artificial neural network (ANN) models developed for simulation correlation between and mechanical properties using back-propagation algorithm. The qualities joint, such as ultimate tensile strength, yield stress, elongation, bending angle hardness nugget zone, considered. order those quality characteristics, two multi-objective EAs that non-dominated sorting genetic algorithm II differential evolution coupled with ANN models. end, multi-criteria decision-making method which technique preference by similarity ideal solution applied on Pareto front extract solutions. Comparisons conducted results obtained from techniques, confirmation experiments performed verify simulated results.