Defect recognition of cold rolled plate shape based on RBF-BP neural network

Author

Li, Xiaohua ; Zhang, Junjie

Author_Institution

Inst. of Electron. & Inf. Eng., Univ. of Sci. & Technol., Anshan, China

fYear

2012

fDate

6-8 July 2012

Firstpage

496

Lastpage

500

Abstract

By means of the analysis for the defect pattern of plate shape, a shape defect recognition method for cold rolled strips is proposed based on RBF-BP neural network in this paper. The memberships relative to six basic patterns of common plate shape defects are identified. This method syncretizes the advantages of RBF and BP neural network. There are very fast approaching speed and high precision of network recognition. The simulation of the proposed method is done, and the simulation results are compared with the results of the recognition method by using BP neural network. The results show that the recognition method proposed in this paper gives better effect than the one making use of single network. And it is more suitable for real-time shape control.

Keywords

backpropagation; cold rolling; mechanical engineering computing; pattern recognition; plates (structures); radial basis function networks; strips; RBF BP neural network; cold rolled plate shape; cold rolled strips; common plate shape defects; defect pattern; network recognition; real time shape control; shape defect recognition; Automation; Intelligent control; Materials processing; Neural networks; Pattern recognition; Shape; Shape control; combinational RBF-BP neural network; pattern recognition; plate shape defects;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation (WCICA), 2012 10th World Congress on

Conference_Location

Beijing

Print_ISBN

978-1-4673-1397-1

Type

conf

DOI

10.1109/WCICA.2012.6357926

Filename

6357926