Wrinkling Prediction in Deep Drawing by Using Response Surface Methodology and Artificial Neural Network

Abstract

SummaryThe objective of this study is to predict influences of tooling parameters such as die and punch radius, blank holder force and friction coefficient between the die and the blank surfaces in a deep drawing process on the wrinkling height in aluminium AA5754 by using the response surface methodology (RSM) and an artificial neural network (ANN). The 3D finite element method (FEM), i.e. the Abaqus software, is employed to model the deep drawing process. In order to investigate the accuracy of this model, the results are compared with experimental results. The data derived from the FEM are used for modelling the RSM and training an ANN. Finally, the RSM and ANN outputs are compared so as to select the best model. The results of the two methods are promising and it is found that the ANN results are more accurate than the RSM results.

Comparison of Artificial Neural Network Model and Response Surface Methodology for Springback Prediction

“…The artificial neural networks are one of the most suitable meta-models to solve metal forming problems [9]. ANN are biologically derived from neural process of the human brain and they have a parallelly distributed structure with a high number of neurons and connections.…”