Prediction of surface roughness in CNC face milling using neural networks and Taguchi's design of experiments

In this paper, a neural network modeling approach is presented for the prediction of surface roughness (R-a) in CNC face milling. The data used for the training and checking of the networks' performance derived from experiments conducted on a CNC milling machine according to the principles of Taguchi design of experiments (DoE) method. The factors considered in the experiment were the depth of cut, the feed rate per tooth, the cutting speed, the engagement and wear of the cutting tool, the use of cutting fluid and the three components of the cutting force. Using feedforward artificial neural networks (ANNs) trained with the Levenberg-Marquardt algorithm, the most influential of the factors were determined, again using DoE principles, and a 5 x 3 x 1 ANN based on them was able to predict the surface roughness with a mean squared error equal to 1.86% and to be consistent throughout the entire range of values. (C) 2002 Elsevier Science Ltd. All rights reserved.