Title: Application of neural networks in complex forging die design

Authors: Lianjun Cheng, Guoqun Zhao, Junna Cheng, Xinhai Zhao

Addresses: School of Materials Science and Engineering, Shandong University, Jinan 250061, China. ' School of Materials Science and Engineering, Shandong University, Jinan 250061, China. ' College of Information Science and Engineering, Ocean University of China, Qingdao 266100, China. ' School of Materials Science and Engineering, Shandong University, Jinan 250061, China

Abstract: In this paper, a Back Propagation (BP) neural network was proposed for forging die design of automobile steering knuckles. It was used to predict the appropriate die cavity geometry data by training from sample data of practically successful cases according to the correlations between various factors that influence the forging process. In particular, a Radial Basis Function (RBF) neural network was also developed to compare its prediction accuracy with that of the BP neural network. The results show that the neural network is suitable for actual forging die design as long as the number of learning samples is enough.

Keywords: forging die design; radial basis function neural networks; back propagation neural networks; automobile industry; automotive steering knuckles; die cavity geometry; prediction accuracy.

DOI: 10.1504/IJMPT.2010.032102

International Journal of Materials and Product Technology, 2010 Vol.38 No.2/3, pp.237 - 247

Available online: 10 Mar 2010 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article