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

Abstract

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