Prediction and control of product quality in deep drawing process: Design and implementation of an intelligent system using knowledge technologies

Abstract

This paper aims to develop the numerical simulation model of the deep drawing process and to design the control system for product quality. First, the die set has been designed for deep drawing of an aluminium cup and its numerical simulation has been prepared by mean of ANSYS/LS-DYNA. The formability cases according to blank holder force, punch velocity, friction and die edge radius have been determined. After, the Artificial Neural Network (ANN) model of the process has been developed using an algorithm running under MATLAB and it has been trained with the results of finite element simulations. Also, the optimization software which can run together the ANN model has been developed and has been used to determine the optimum process parameters. The results of the study indicate that the optimum process parameters correspond to the good product can be determined by using together FEM simulation model and ANN model. So, formability can be improved by the control of process parameters. The attractive aspect of the study is that it proposes a quicker and a simple solution method to obtain optimum process parameters. It is expected that the use of artificial intelligence technologies will be open up new avenues for the control of the sheet metal forming process. © 2012 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.