Multi-objective Optimization for Surface Roughness, Cutting Force, and Material Removal Rate During Turning 4340 Alloy Steel by Using Support Machine Vector and NSGA-III

The focus of this research paper is to optimize the process parameters for turning AISI 4340 alloy steel, with the objective functions of achieving a simultaneous minimum of surface roughness (Ra) and cutting force (Fc) and maximum material removal rate (MRR) under the cutting parameter constraints of cutting speed, tool nose radius, feed rate, and depth of cut. In order to achieve this, a combination of Support Vector Machine regression (SVR) algorithms and a Non-Dominated Sorting Genetic Algorithm (NSGA-III) is utilized to determine the optimal solution. First, the SVR model is applied to predict Ra, Fc, and MRR using the GridSearchCV algorithm to search for the best hyperparameters. Then, the NSGA-III is implemented to obtain the optimal solutions, while SVRs are objective functions. Results indicate that Ra ranges between 0.973 and 1.711 µm, while the cutting force ranges between 1.978 and 31.279 kgf, and MRR ranges between 1.679 and 16.192 cm3/min for the fifty Pareto solutions. Finally, experimental validations are conducted to confirm predictive results.