Key points are not available for this paper at this time.
The present article examines the effects of machining parameters on machined surfaces to determine optimum turning parameters for AISI-316 under dry machining environment. L 27 -OA with different levels of Cutting Speed (CS), Feed Rate (FR) and Depth-of-Cut (DOC) is used for experimentation. Surface Roughness (R a ) and Material Removal Rate (MRR) are considered as the response parameters. Among three Machine Learning (ML) models viz. Support Vector Regression (SVR), Gaussian Process Regression (GPR) and Gradient Boosting Regression (GBR), GBR yielded the best results, with significantly higher R 2 scores and lower RMSE values. An integration of GBR-PSO algorithms is used to determine 50 sets of, Pareto solutions and desirability analysis rendered the most suitable input parameter values as 111.66 m/min for CS, 0.15 mm/rev for FR and 1.23 mm DOC. At validation stage, R a and MRR predicted by ML have a nominal difference of 15.19% and 0.115% compared to measured values.
Dewangan et al. (Wed,) studied this question.