Optimization of Process Parameter in High-Speed Milling AA6061 Using SVR and NSGA-II

Obtaining optimal machining conditions to increase machining efficiency in the milling process is a difficult mission. This paper presents an experimental study and optimization of the machining parameters for the AA6061 in the high-speed milling process in this context. Material removal rate (MMR), tool wear rate (TWR), and surface roughness were the performance parameters measured in the experiments (Ra). The four variables studied were cutting speed, feed, depth of cut, and cutting time. The Support Vector Machine (SVM) technique is used to predict MRR, TWR, and Ra. Three error metrics were used to evaluate the model’s performance: Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAE), and Coefficient of Determination (R2). As a result, the SVR models’ predictions for MRR, TWR, and Ra were correct. Three machine learning (ML) models and the NSGA-II algorithm were used to perform multiobjective optimization of the high-speed milling process. Fifty Pareto solutions were discovered in cases of high MRR, low VB, and low Ra. For high-speed milling AA6061, optimal machining parameter values are suggested.