The predictive model for machinability of 304 stainless steel

This paper presents an effort to develop a predictive model for machinability of 304 stainless steel. The artificial neural network (ANN) theory was used in this model to predict surface roughness of the workpiece, the cutting force and the tool life. It is shown that the errors of the surface roughness, the cutting force and the tool life are 4.4, 5.3 and 4.2%, respectively. Then the genetic algorithm and the ANN were incorporated to find the optimum cutting conditions for the maximum metal removal rate under the constraints of the expected surface roughness, and the expected surface roughness associated with the tool life. The optimum cutting conditions to be found in this model are cutting speed, feed and depth of cut. By comparing the predicted values with the experimental data, it is seen that this model is useful and convenient to determine the cutting parameters. It is recommended that this preliminarily developed model can be expanded to be a more comprehensive one in the metal machining process by adding other controlling parameters. (C) 2001 Elsevier Science B.V. All rights reserved.