Structural damage identification by neural networks and modal analysis

H. T. Zheng, S. T. Xue, Y. Y. Qian, L. Y. Xie, Akira 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
Volume1
Publication statusPublished - 2003
Event1st International Conference on Structural Health Monitoring and Intelligent Infrastructure, SHMII-1'2003 - Tokyo, Japan
Duration: 2003 Nov 132003 Nov 15

Other

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

Fingerprint

Modal analysis
Electric network analysis
Neural networks
Damage detection
Nondestructive examination
Physical properties

ASJC Scopus subject areas

  • Building and Construction
  • Architecture

Cite this

Zheng, H. T., Xue, S. T., Qian, Y. Y., Xie, L. Y., & Mita, A. (2003). Structural damage identification by neural networks and modal analysis. In Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure (Vol. 1, pp. 635-639)

Structural damage identification by neural networks and modal analysis. / Zheng, H. T.; Xue, S. T.; Qian, Y. Y.; Xie, L. Y.; Mita, Akira.

Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure. Vol. 1 2003. p. 635-639.

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

Zheng, HT, Xue, ST, Qian, YY, Xie, LY & Mita, A 2003, Structural damage identification by neural networks and modal analysis. in Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure. vol. 1, pp. 635-639, 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure, SHMII-1'2003, Tokyo, Japan, 03/11/13.
Zheng HT, Xue ST, Qian YY, Xie LY, Mita A. Structural damage identification by neural networks and modal analysis. In Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure. Vol. 1. 2003. p. 635-639
Zheng, H. T. ; Xue, S. T. ; Qian, Y. Y. ; Xie, L. Y. ; Mita, Akira. / Structural damage identification by neural networks and modal analysis. Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure. Vol. 1 2003. pp. 635-639
@inproceedings{ae3b2c9a8f2441dc9ba675fbe6ebc990,
title = "Structural damage identification by neural networks and modal analysis",
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.",
author = "Zheng, {H. T.} and Xue, {S. T.} and Qian, {Y. Y.} and Xie, {L. Y.} and Akira Mita",
year = "2003",
language = "English",
isbn = "9058096483",
volume = "1",
pages = "635--639",
booktitle = "Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 1st International Conference on Structural Health Monitoring and Intelligent Infrastructure",

}

TY - GEN

T1 - Structural damage identification by neural networks and modal analysis

AU - Zheng, H. T.

AU - Xue, S. T.

AU - Qian, Y. Y.

AU - Xie, L. Y.

AU - Mita, Akira

PY - 2003

Y1 - 2003

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84857709130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857709130&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9058096483

SN - 9789058096487

VL - 1

SP - 635

EP - 639

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

ER -