Prediction of Tool Life when End Milling of Ti6Al4V Alloy Using Hybrid Learning System

Tool life significantly affects the machining cost and productivity. A wide number of techniques have been applied to modelling metal cutting processes. Techniques of artificial intelligence are new soft computing methods which suit solutions of nonlinear and complex problems such as metal cutting processes. The current study is concerned with the application of an adaptive neuro-fuzzy inference system (ANFIS). This ANFIS model is developed to predict tool life when end milling of Ti6Al4V alloy with coated (PVD) and uncoated cutting tools are under dry cutting conditions. By carrying out training and testing the ANFIS models, the current study employed real experimental results, and based on such results, a selection of the best model was conducted based on the mean absolute percentage error (%). For the modelling process, the study adopted a generalised bell shape membership function, and there was a change in its number from 2 to 5. The findings revealed that ANFIS is capable of modelling tool life in end milling process, and that there was good matching obtained between experimental and predicted results.