Simulation of Tool Life for Ceramic with Negative Rake Angle Using Neural Network

The current work presents the simulation of tool life in high speed Hard Turning (HSHT) of AISI 4340 hardened steel using artificial neural networks. An experimental investigation was carried out using ceramic cutting tools, composed approximately of Al2O3 (70%) and TiC (30%) on AISI 4340 heat treated to a hardness of 60 HRC. A new model was adjusted to predict tool life for different values of cutting speed, feed rate, depth of cut and rake angle. The model was built by using the neural network. A set of experimental data was obtained in the following design boundary: cutting speeds (175-325 m/min), feed rate (0.075-0.125 m/rev), negative rake angle (0 to -12) and depth of cut of (0.1-0.15) mm. The experiments were planned and implemented using Box Behnken design (BBD) of Response Surface Methodology (RSM) with four input factors at three levels. The neural network model was built by using MATLAB. The results indicate that even with the complexity of developing a model, the neural network technique is found to be adequate in predicting and simulating the tool life.