The present paper deals with the initial blank design of bimetallic parts obtained by deep drawing process. Normally in deep drawing, the initial blank has a simple shape and after drawing, its perimeter shape will become very complex and has considerable influences on the forming results. If the initial blank shape is designed in such a way that is formed into the desired shape after the drawing process, not only it reduces the time of trimming process, but also decreases the drawing force and the raw material needed substantially. The present paper proposes a novel approach to initial blank optimization in multilayer deep drawing. The Finite Element Method (FEM) is employed for simulating multilayer plate deep drawing process to provide training data for Artificial Neural Network (ANN). The aim of the neural network is to predict the initial blank shape for the desired final shape. The FEM results were verified through experiment.

This content is only available via PDF.
You do not currently have access to this content.