Modeling and optimization of WEDM of monel 400 alloy using ANFIS and snake optimizer: A comparative study

Abstract

The exploration of the prediction of wired electro-discharge machining parameters is becoming progressively more crucial in order to choose the ideal parameters for making products with impeccable designs. The objective of this work is to develop an augmented adaptive neuro-fuzzy inference system (ANFIS) model by encrypting the snake optimizer for estimating the surface roughness, material removal rate, and residual stress of Monel 400 alloy in wire electric discharge machining (WEDM). The performance of the indicated augmented model called ANFIS-SO was evaluated using 64 trials of WEDM experimental data. As a means of emphasizing the performance of the presented model, estimation results were compared to those from existing models, which included integration of ANFIS and beetle antennae search capabilities, reptile search algorithms, and COOT algorithms. The ANFIS-SO model showed excellent performance based on the statistical benchmarks tested for the developed models. The model achieved RMSE of 0.0793, 0.2781, and 16.3286 with performance errors of 0.3203, 1.9687, and 1112.529 along with an accuracy of 99%, 98%, and 95% for surface roughness, MRR, and residual stress, respectively, which are extremely more accurate than the ANFIS, ANFIS-BAS, ANFIS-RSA, and ANFIS-COOT. As a result of these findings, it is evident that the developed ANFIS-SO model might be used with reliability when designing future model forecasting approaches for optimizing machining parameters. Therefore, it is discovered that using ANFIS-SO is an innovative method for determining WEDM machining parameters which are very promising.