Structural damage identification by neural networks and modal analysis

H. T. Zheng, S. T. Xue, Y. Y. Qian, L. Y. Xie, A. Mita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The basis for the approach to damage identification is that changes in the structure's physical properties. This paper proposes a nondestructive testing technique based on modal analysis is discussed in order to develop a new, efficient and simple damage detection method for civil structures. This paper presents a sensitivity study comparing the sensitivities of frequencies, mode shapes, and modal flexibilities. Sensitivity-based analysis for the features vectors extraction. The neural networks (NNs) are introduced in this study, the combined parameters of the "frequency change ratios (FCRs) and shifts in modal flexibilities (SMFs)" are presented as the input features of NNs in structural damage identification. It is also shown, through a simulation, that this method is verified to be practical for the location and extent of structural damage identification.

Original languageEnglish
Title of host publicationStructural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure
Pages635-639
Number of pages5
Publication statusPublished - 2003
Event1st International Conference on Structural Health Monitoring and Intelligent Infrastructure, SHMII-1'2003 - Tokyo, Japan
Duration: 2003 Nov 132003 Nov 15

Publication series

NameStructural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure
Volume1

Other

Other1st International Conference on Structural Health Monitoring and Intelligent Infrastructure, SHMII-1'2003
Country/TerritoryJapan
CityTokyo
Period03/11/1303/11/15

ASJC Scopus subject areas

  • Building and Construction
  • Architecture

Fingerprint

Dive into the research topics of 'Structural damage identification by neural networks and modal analysis'. Together they form a unique fingerprint.

Cite this