A Mathematical Model for Wire Cut Electrical Discharge Machine Parameters Using Artificial Neural Network

Abstract

Unconventional machining process finds heavy application in aerospace, automobile and in production industries where accuracy is most needed. This process is chosen over other traditional methods because of the advent of composite and high strength materials, multifaceted parts and also because of its elevated precision. Regularly in unconventional machines, trial and error method is used to fix the values of process parameters. An algorithm incorporating Artificial Neural Network (ANN) is proposed to create mathematical model functionally relating process parameters and operating parameters of a wire cut electric discharge machine (WEDM) and copper is the work piece. This is accomplished by training a learning algorithm of feed forward neural network with back propagation. The required data used for training and testing the ANN is obtained by conducting trial runs in wire cut electric discharge machine. Proposed algorithm paves reduction in time for fixing the values for the process parameters and thus reduces the production time along with reduction in cost of machining processes and thereby increases the production as well as the efficiency. The programs for training and testing the neural network are developed, using matlab 7.0.1 package.