Optimization of machining parameters in CNC turning is essential for achieving high product quality, improved productivity, and reduced manufacturing cost. Traditional trial-and-error methods are time-consuming and often fail to capture the complex relationships between process variables and performance characteristics. In this study, a combined statistical and machine learning–based approach is proposed to optimize CNC turning parameters. Cutting speed, feed rate, and depth of cut are selected as input variables, while surface roughness, material removal rate, and tool wear are considered as response parameters. Design of Experiments (DoE) and Analysis of Variance (ANOVA) are employed to identify significant machining factors and their interactions. Further, machine learning models such as Artificial Neural Networks and Support Vector Regression are developed to predict machining performance with high accuracy. The optimized parameter set obtained from the proposed hybrid approach demonstrates significant improvement in surface finish and productivity compared to conventional methods. The results confirm that integrating statistical techniques with machine learning provides a robust and reliable framework for intelligent machining optimization in modern manufacturing environments.
Gujar A (Sat,) studied this question.