Research on Stamping Spring-Back Prediction for Car Body Panel Based on BP Neural Network

Abstract:

On the basis of orthogonal test analysis of variance, BP neural network is used to forecast quantitatively the stamping spring-back of front panel of a car body, namely the engine hood, under the conditions of different stamping parameters. Firstly, BP neural network prediction model is established and sample training is done in Matlab. Then, the spring-back prediction using BP neural network and the result of spring-back simulation using Dynaform is compared to verify the precision and stability of the prediction model. Lastly, modification is made to the BP neural network according to practical stamping parameters and an efficient BP neural network model is established. Using this model, stamping spring-back prediction for the front panel of a car body is made. The spring-back prediction could then be used for spring-back compensation in the mould design of the front panel.

• Periodical: Advanced Materials Research (Volumes 97-101)
• Pages: 250-254
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.97-101.250
• Online since: March 2010
• Authors: Xin Jian Zhou
• Keywords: BP Neural Network (BPNN), Car Body Panel, Springback, Stamping

References

[1] Zhigang Mao, Peiyu Zhu, Weijian Xu et al: Die and Mold Technology Vol. (6)(2004), p.7(in Chinese).

[2] Zhiyuan Mei: Stamping Forming Simulation and Spring-back Prediction of the Auto-body Panel (Thesis of master degree, East China Jiaotong University, China 2007) (in Chinese).

[3] Xiaoan Li, Xiaoji Zhang: Introduction to �eural �etwork and �eural Computer(Xian Northwestern Polytechnical University Press, China 1994) (in Chinese).

[4] Feisi Technological Product R&D Center: �eural �etwork Theory and MATLAB7 Implementation(Publishing House of Electronics Industry, China 2006) (in Chinese).

[5] Shuntian Lou, Yangzhu Shi: Matlab Based System Analysis and Design-�eural �etwork( Xidian University Press, Chnia 1999) (in Chinese).