Autonomous Operation Planning in the Machining of difficult-to-cut Materials

Since difficult-to-cut materials are very expensive, their machinability data are very scarce. This paper describes autonomous operation planning that can optimize cutting operation with little machining experience. Adaptive prediction in the operation planning can predict machining processes by analysis and neural network. It can also identify the parameters used for the prediction to minimize the prediction error in few cutting operations. As a result, adaptive prediction gives us knowledge of machining without several cutting tests. It is shown that autonomous operation planning considering tool wear and cutting force is effective in the machining of Inconel X750.