Die-Face Compensation for Hot Bending of U-Shaped Part Based on RBF Neural Network

Yu Zhang; Wei Wang; Zhi Guo An

doi:10.4028/www.scientific.net/AMR.510.196

Paper Titles

Research on the Memory Cutting Model of Shearer
p.170

Screen-Printing-Based Fabrication of Silver Patterns on Polyimide Substrate
p.176

Linear Stability Analysis of Space Compressive Structure of the Inverted-V Combinatorial Jib
p.182

Study on the Uncertain Problem for Project-Based Remanufacturing Systems
p.191

Die-Face Compensation for Hot Bending of U-Shaped Part Based on RBF Neural Network
p.196

Simulation of the 45t Converter Tilting Torque
p.200

Heat Conduction Equation Finite Volume Method to Achieve on MATLAB
p.205

Driving Dynamic Analysis and Motion Control for Biped-Imitating Walking Mechanism
p.211

Design on Cutting Die of Connection Plate
p.218

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 510Die-Face Compensation for Hot Bending of U-Shaped...

Die-Face Compensation for Hot Bending of U-Shaped Part Based on RBF Neural Network

Abstract:

Aimed at the shrinkage and deformation of U-shape part in cooling process after hot forming, the RBF model is established to predict the deformation and direct the die modification. The main factors influencing deformation were set as the design variables and the sample data were obtained using Latin Hypercube Sampling. From the FEM simulation results based on these samples, the deformation was taken as the response.The forecasting value of RBF model is compared with that of FEM. The error is smaller than 1.78% and the RBF predicting model has enough precision. At last, the compensation of deformation on the die-face was made based on the displacement vector of node during the cooling process and the forecasting deformation by using RBF model. The results show that the dimension error of the U-shape part produced by the modified die is lower than 0.3% and the accuracy can meet the production requirement.

You might also be interested in these eBooks

Machinery, Materials Science and Engineering Applications, MMSE2012

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 510)

Pages:

196-199

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.510.196

Citation:

Cite this paper

Online since:

April 2012

Authors:

Yu Zhang, Wei Wang, Zhi Guo An

Keywords:

Finite Element Analysis (FEA), Hot Bending, RBF Neural Network, Shrinkage Deformation

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] ZHANG Yu, ZHOU Jie. Thermo-Coupled Analysis of Arc-Bending of the Steel Plate of Medium Thickness and Determination of the Curve Equation for the Die Shape [J]. Die & mould industry, 2005, 7: 17-21.

Google Scholar

[2] LI Junchao, ZHANG Xu, HU Jianbiao. Springback Prediction of Truncated Cone Formed by Incremental Forming Based on Numerical Simulation and Neural Network [J]. Hot working technology, 2010, Vol. 39, No. 19: 114-117.

Google Scholar

[3] ZHOU Jie, YI Zhonghua, YANG Desen, etc. Research on Springback Quality of U-shaped Steel Sheet Part with High-strength Based on Controllable Drawbead [J]. Hot working technology, 2010, Vol. 39, No. 1: 67-70.

Google Scholar

[4] MENG Ling-qi, WANG Hai-long, XU Ru-song, etc. Temperature Decrease Model of Medium-Plate Mill Based on RBF Neural Network [J]. Journal of Iron and Steel Research, 2008, Vol20, No. 6: 27-31.

Google Scholar

[5] ZHU Shuxian, ZHANG Renjie. Comparison with BP and RBF neural network used in face recognition [J]. Chinese Journal of Scientific Instrument, 2007, Vol. 28, No. 2 : 375-379.

Google Scholar