Autonomous turning operation planning with adaptive prediction of tool wear and surface roughness

Abstract Small-sized batch jobs with large product diversification require intelligent machine tools to optimize cutting conditions by adapting to the cutting tools, work materials, and machine tools. Proposed is autonomous operation planning, which optimizes machining operations for each machine tool using adaptive prediction of processes. Machining processes are predicted and optimizes more accurately using the adapting parameters of the governing equations, used for analytical prediction, and/or weight parameters of neural networks through learning of machining results. When considering tool wear and surface roughness simultaneously, machining operations are optimizes to minimize cost by predicting flank wear analytically based on metalcutting theory and by predicting surface roughness with a neural network.