Title: Damage detection utilising the artificial neural network methods to a benchmark structure

Authors: B.S. Wang, Y.Q. Ni, J.M. Ko

Addresses: Department of Civil Engineering, Zhejiang University, Hangzhou, 310058, China. ' Department of Civil and Structural Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China. ' Department of Civil and Structural Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China

Abstract: This paper discusses the damage identification using artificial neural network (ANN) methods for the benchmark problem set up by IASC-ASCE Task Group on Health Monitoring. A three-stage damage identification strategy for building structures is proposed. The BP network and probabilistic neural network (PNN) are employed for damage localisation and BP network for damage extent identification. Four damage patterns (patterns 1-4) in Cases 1-6 are discussed. The comparison between BP network and PNN are carried out. The results show that PNN performs better than BP network in damage localisation. The damage extent identification using back-propagation neural network (BPN) is successful even in Cases 2 and 5 and 6 in which the modelling error is quite large.

Keywords: structural health monitoring; damage detection; benchmark problems; building structures; artificial neural networks; ANNs; damage identification strategy; damage localisation; damage extent; structural damage.

DOI: 10.1504/IJSTRUCTE.2011.040782

International Journal of Structural Engineering, 2011 Vol.2 No.3, pp.229 - 242

Published online: 30 Sep 2014 *

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