Damage identification and simulation of structure based on RBF network

Author

Jianwei, Zhang ; Yina, Zhang

Author_Institution

North China Univ. of Water Conservancy & Electr. Power, Zhengzhou, China

fYear

2010

fDate

26-28 June 2010

Firstpage

1608

Lastpage

1610

Abstract

RBF neural network is presented to identify and locate the crack damage of concrete structures in this paper. A cantilever is analyzed by finite element method, and the damage indices of the perfect structure and damaged structure are gained. Then RBF neural network is used to analyze the single damage and multi-damage quantification and damage location. Numerical simulation results show that RBF neural network method can make a better diagnosis for single and multiple damage identification. This method has certain guiding sense to damage identification in actual structures.

Keywords

cantilevers; condition monitoring; crack detection; finite element analysis; radial basis function networks; structural engineering; RBF neural network; cantilever; concrete structures; crack damage; damage identification; damage location; finite element method; multidamage quantification; structure simulation; Artificial neural networks; Civil engineering; Frequency; Kernel; Multi-layer neural network; Neural networks; Pattern recognition; Radial basis function networks; Rivers; Water conservation; RBF neural network; damage identification; simulation analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechanic Automation and Control Engineering (MACE), 2010 International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-7737-1

Type

conf

DOI

10.1109/MACE.2010.5535986

Filename

5535986