Performance Investigation of Coated Carbide Tools in Milling Procedures

Abstract

The optimization of the manufacturing conditions in milling processes composes a crucial task for enhancing machining efficiency and extending the tool’s lifespan. This study presents an investigation of the cutting tool’s performance under varying machining parameters via the generation of an experimental dataset that was obtained through laboratory-controlled milling operations. Based on this dataset, artificial intelligence (AI) models, including artificial neural network (ANN), k-nearest neighbors (KNN), and support vector regression (SVR), were developed in order to predict the tool’s life as a function of the milling conditions. Additionally, finite element method (FEM) simulations were conducted to estimate tool wear and analyze the manufacturing process at a numerical level. In particular, FE models were utilized to compute the milling forces and the corresponding developed stress fields, as well as to assess the cutting tool’s performance based on certain machining variables. Furthermore, a comparative analysis between AI-driven forecasts and FEM simulations was performed to evaluate their effectiveness and reliability. The findings provide insights into the advantages and limitations of both methodologies, guiding the optimization of coated carbide tool performance. The outcomes of this study contribute to the advancement of predictive modeling in machining processes, offering a data-driven approach for improved tool wear assessment.