Application of artificial intelligence for the prediction of undercut in photochemical machining

Abstract

This paper presents the application of an artificial neural network (ANN) for the prediction of undercut in the photochemical machining (PCM) process. The etching time, etching temperature and etching concentration were used as inputs to the ANN model. A full factorial design of experiments (DoE) approach was used to conduct the experiments. A feed forward backpropagation network (FFBPN) was used to predict the undercut. The various neural network architectures were considered by changing the number of neurons in the hidden layer. A FFBPN with eight neurons in the hidden layer has been selected as the optimum network. The results show that the model can be used to predict the undercut in PCM in response to machining parameters.