Diagnosis of edge condition based on force measurement during milling of composites

The present paper presents comparative results of the forecasting of a cutting tool wear with the application of different methods of diagnostic deduction based on the measurement of cutting force components. The research was carried out during the milling of the Duralcan F3S.10S aluminum-ceramic composite. Prediction of the tool wear was based on one variable, two variables regression, Multilayer Perceptron (MLP) and Radial Basis Function (RBF) neural networks. Forecasting the condition of the cutting tool on the basis of cutting forces has yielded very satisfactory results.