Empirical and Neural Network Modelling of Tool Wear Development in the Machining of Nickel Base Superalloys

Tool wear measurement data from turning of Inconel 718 aircraft engine components were processed by conventional interpolation and neural network based methods, aiming at the on-line prediction of tool wear development. A four-constant empirical model was derived to predict flank wear as a function of cutting time and cutting speed. These results were compared with those obtained from the application of a supervised neural network paradigm for flank wear forecasting.