Prediction of thrust forces and hole diameters using artificial neural networks in drilling of AISI D2 tool steel with cemented carbide tools

Abstract

In this study, the effects of cutting speed, feed rate and different types of coating materials on thrust force and hole diameter were investigated in drilling of AISI D2 cold work tool steel. In addition, the thrust forces and hole diameters were predicted by artificial neural networks (ANN) using experimental data. Uncoated, TiN, TiAlN monolayer and TiAlN/TiN multi-layer coated cemented carbide drills with diameter of 5 mm were used in drilling experiments. The holes were drilled at different combinations of four cutting speeds (50, 55, 60, 65 m/min), two feed rates (0.063 and 0.08 mm/rev), and fixed depth of cut (7 mm). Experimental results showed that the lowest thrust forces and hole diameters were obtained with TiAlN/TiN multi-layer coated drills. After ANN training, it was found that the R2 values are very close to 1 for both training and test sets. RMSE values are smaller than 0.03, and mean error values are smaller than 5% for the test set. This case shows that ANN is a powerful method for prediction of thrust forces and hole diameters.