Maximizing efficiency in C45 steel machining: an integrated AI-based approach to coated insert optimization

Abstract Machining involves the subtraction of the material from the sample workpiece to achieve the desired shape or surface. This versatile method is capable of producing a wide range of parts, varying from simple to intricate profiles. Coating materials are increasingly being utilized in tool inserts in the production industry owing to their superior thermal properties and wear resistance. The shielding of hard coatings, with thicknesses of only a few microns, enhances performance and durability. In this study, machining of C45 steel using distinct coated inserts was explored. The experimental trials employed PVD and CVD methods for coated tungsten carbide (WC) tools/inserts and PVD-coated cermet tools/inserts with different machining parameters. Performance metrics, such as the surface finish and reliability of the tool, were considered for the evaluation. The average tool life variation between the PVD-coated cermet and PVD-coated WC was 178.86%, and 30.11% between the PVD-coated cermet and CVD-coated WC at 1 mm DOC. ANOVA was performed using Response Surface Methodology to explore the influence of input parameters on output. The results indicate that the depth of machining and spindle speed significantly influence Ra, whereas spindle speed and type of tool insert have a considerable impact on the life span of the tool. The developed mathematical model for the prediction of tool life and Ra indicates its potential for performance forecasting during C45 steel machining. Grey relation analysis was employed to optimize the process parameters. Optimal results were achieved with a spindle speed of 400 m/min, 0.5 mm depth of cut, and cermet tool inserts. PVD-coated WC inserts performed better. ANFIS was applied for the prediction and optimization of the machining parameters.