Abstract
Machining is a subtractive manufacturing process where raw material is cut into a desiredshape and size. Machining has been the subject of various studies and many models of the process have been developed and improved over the years. Although the literature is rich of research and experiment results, it is noticed that many organizations are not able to use these models on their daily processes due to complexity. The aim of this study is to use machine learning to create a black box model that can predict cutting forces with respect to process parameters based on data generated using Oxley’s model with less computational cost than the analytical approach. The machine learning method used has in input layer with three neurons representing process parameters, cutting speed, axial depth of cut, and radial depth of cut, has three hidden layers with 101 neurons, and an output layer representing the cutting force and the tangential force. The validation of the artificial neural network was performed by comparing the output result of chosen input parameters with literature results. The model predicted cutting force and tangential force with high accuracy of 90% in most cases and the run time was reduced by 98%.