UM
Design of artificial neural networks for structural health monitoring
Lam H.F.2; Yuen K.V.1
2003-12-01
Source PublicationStructural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure
Volume1
Pages611-618
AbstractThis paper addresses the problem of structural health monitoring (damage detection) based on the pattern matching approach utilizing dynamic data. Artificial Neural Networks (ANNs) are employed as tools for matching the "damage patterns" for the purpose of detecting the damage location and the corresponding damage extent. This paper concentrates on the design of ANNs, which is usually neglected or only slightly addressed in the literature. It is very clear that the selection of the class of feedforward ANN models, that is to decide the number of hidden layers and the number of nodes in each hidden layer, has significant effect on both the training of ANNs and the performance of the trained ANNs. In this paper, an ANN class selection method, which follows the Bayesian probabilistic approach, is proposed. A five-story building example is used to demonstrate the proposed methodology. © 2003 Swets & Zeitlinger, Lisse.
URLView the original
Language英語
Fulltext Access
Document TypeConference paper
CollectionUniversity of Macau
Affiliation1.Universidade de Macau
2.City University of Hong Kong
Recommended Citation
GB/T 7714
Lam H.F.,Yuen K.V.. Design of artificial neural networks for structural health monitoring[C],2003:611-618.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Lam H.F.]'s Articles
[Yuen K.V.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lam H.F.]'s Articles
[Yuen K.V.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lam H.F.]'s Articles
[Yuen K.V.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.