Modelling of abrasive flow machining process: a neural network approach

A simple neural network model for abrasive flow machining process has been established. The effects of machining parameters on material removal rate a nd surface finish have been experimentally analysed. Based on this analysis , model inputs and outputs were chosen and off-line model training using ba ck-propagation algorithm was carried out. Simulation results confirm the fe asibility of this approach and show a good agreement with experimental and theoretical results for a wide range of machining conditions. Learning coul d remarkably be enhanced by training the network with noise injected inputs . (C) 1999 Published by Elsevier Science S.A. All rights reserved.