Key words: Artificial neural network, cutting force components, hard turning, machining process.

Abstract: In this study, we develop a robust ANN technique to predict cutting force components during hard turning of an AISI 52100 steel using CBN cutting tool. The training network is performed on 20 pairs of input-output experimental dataset where cutting parameters and workpiece hardness are taken as the input dataset. Back-propagation training is performed by using Bayesian Regularization in combination with Levenberg-Marquardt algorithm. The optimal network architecture is determined after several simulations by MATLAB Neural Networks Toolbox and it is consisting of 8 neurons in hidden layer. The developed model was verified with other experimental test data not used in training; for this purpose, the maximum average MAPE value of 11.79 % was obtained for the cutting forces prediction.