Intelligent Prediction of Machine Tool Performance in Micro Turning Using Textured Inserts

Intelligent machine tools can adapt to modifications in the machining environment while performing operations. An intelligent prediction of machine tool condition is an essential aspect in the manufacturing sector of Industry 4.0. Micro components of titanium alloys have huge applications in aerospace, optical and biomedical industries. In this study, machine learning (ML) based models are developed to forecast the performance of a micro-turning machine tool while working with plain and variously patterned textured micro inserts. The micro-turning experiments are performed on Ti6Al4V alloy and the cutting force, surface roughness and tool flank wear are measured for every machining pass. Supervised ML models are trained in order to predict the cutting force, flank wear and surface roughness with cutting parameters and the type of cutting inserts. In the comparison of developed ML models, Extreme Gradient Boost (XGBoost) performs best in prediction with the accuracy of 98.53% and runs in 40.67 milliseconds.