Optimization of Friction Stir Welding Operation using Optimal Taguchi-based ANFIS and Genetic Algorithm

The friction stir welding (FSW) process is an effective approach to produce joints having superior quality. Unfortunately, most published investigations primarily addressed optimizing parameters boost product In the current work, FSW operation of aluminum alloy has been considered and optimized decrease specific energy (SWE) enhance jointing efficiency (JE) as well micro-hardness at welded zone (MH). parameter inputs are rotational speed (S), (f), depth penetration (D), tool title angle (T). optimal adaptive neuro-based-fuzzy inference system (ANFIS) models were utilized propose responses in terms parameters, while Taguchi method was applied optimize ANFIS operating parameters. neighborhood cultivation genetic algorithm (NCGA) employed determine best solution. obtained results indicated that values S, f, D, T 560 RPM, 90 mm/min, 0.9 mm, 2 deg, respectively. SWE decreased by 17.0%, JE MH improved 2.3% 6.4%, respectively for adequate reliably forecast response values. proposed optimization comprising orthogonal array-based ANFIS, Taguchi, NCGA could be effectively efficiently save experimental costs human efforts, predictive models, select optimum outcomes. observed findings contributed significant data responses.