Methodology of preform design considering workability in metal forming by the artificial neural network and Taguchi method

This study describes a new method of preform design in multi-stage metal forming processes considering workability limited by ductile fracture. The finite element simulation combined with ductile fracture criterion has been carried out in order to predict ductile fracture. The artificial neural network (ANN) using Taguchi method has been implemented for minimizing objective functions relevant to the forming process. The combinations of design parameters used in finite element simulation are selected by an orthogonal array in a statistical design of experiments. The orthogonal array and the results of simulation are used as training data of ANN. A cold heading process is taken as an example of designing a preform which does not form any fracture in the finished product. The results of analysis to validate the proposed design method are presented. (C) 1998 Elsevier Science S.A. All rights reserved.