A.B Besya - M. Sc. of Mech. Eng.Mechanical Engineering Department,Sharif University of Technology, Tehran, Iran
A.R Fathi - Phd Student

A new technique for prediction of initial blank shape in deep drawing process is proposed in this paper using the neural network. A three layer neural network is used and a back propagation algorithm is employed to train the network. Training data is obtained from the slip line field method. Trained network is simulated for an arbitrary flange shape. The simulated result is compared with the result of slip line field method and shows good agreement. The advantage of using neural network over numerical computation is in the saving in time and efforts required for blank shape planning.

Deep drawing, Initial blank, Neural network