Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis

Akira Mita, Y. Y. Qian

研究成果: Conference contribution

抄録

Structural identification for health monitoring involves comparison of changes in structural properties or response, and it can be viewed as pattern classification problems. The fundamental idea of the pattern classification approach is to use training data to determine the classifiers to evaluate the categories of die test data. However, a very large database is required to store training data for complicated damage cases if no technique to reduce the size is used. This paper presents an approach with the purpose of using the least possible sensors. The structural damage location and damage extent are identified respectively by two different methods of pattern classification, that are, the Parzen-window method for the structural damage location firstly and the feed-forward back-propagation neural network used to identify damage extent secondly. The results of numerical simulations show that our proposed approach can indeed identify the structural damage using small number of sensors. Finally, a series of vibration experiments for the 5-story shear frame structure were performed to verify the performance of our proposed approach. The results show that for shear buildings, damage degree and extent can be successfully determined through measuring the frequency change.

元の言語English
ホスト出版物のタイトルStructural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005
ページ201-205
ページ数5
1
出版物ステータスPublished - 2006
イベント2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005 - Shenzhen, China
継続期間: 2005 11 162005 11 18

Other

Other2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005
China
Shenzhen
期間05/11/1605/11/18

Fingerprint

Damage detection
Sensitivity analysis
Pattern recognition
Sensors
Backpropagation
Structural properties
Classifiers
Health
Neural networks
Monitoring
Computer simulation
Experiments

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction

これを引用

Mita, A., & Qian, Y. Y. (2006). Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis. : Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005 (巻 1, pp. 201-205)

Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis. / Mita, Akira; Qian, Y. Y.

Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005. 巻 1 2006. p. 201-205.

研究成果: Conference contribution

Mita, A & Qian, YY 2006, Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis. : Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005. 巻. 1, pp. 201-205, 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005, Shenzhen, China, 05/11/16.
Mita A, Qian YY. Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis. : Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005. 巻 1. 2006. p. 201-205
Mita, Akira ; Qian, Y. Y. / Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis. Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005. 巻 1 2006. pp. 201-205
@inproceedings{bd63f4bbc5774747907639ce166f143d,
title = "Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis",
abstract = "Structural identification for health monitoring involves comparison of changes in structural properties or response, and it can be viewed as pattern classification problems. The fundamental idea of the pattern classification approach is to use training data to determine the classifiers to evaluate the categories of die test data. However, a very large database is required to store training data for complicated damage cases if no technique to reduce the size is used. This paper presents an approach with the purpose of using the least possible sensors. The structural damage location and damage extent are identified respectively by two different methods of pattern classification, that are, the Parzen-window method for the structural damage location firstly and the feed-forward back-propagation neural network used to identify damage extent secondly. The results of numerical simulations show that our proposed approach can indeed identify the structural damage using small number of sensors. Finally, a series of vibration experiments for the 5-story shear frame structure were performed to verify the performance of our proposed approach. The results show that for shear buildings, damage degree and extent can be successfully determined through measuring the frequency change.",
author = "Akira Mita and Qian, {Y. Y.}",
year = "2006",
language = "English",
isbn = "0415396506",
volume = "1",
pages = "201--205",
booktitle = "Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005",

}

TY - GEN

T1 - Qualitative and quantitative damage detection algorithm for structures using pattern classification and sensitivity analysis

AU - Mita, Akira

AU - Qian, Y. Y.

PY - 2006

Y1 - 2006

N2 - Structural identification for health monitoring involves comparison of changes in structural properties or response, and it can be viewed as pattern classification problems. The fundamental idea of the pattern classification approach is to use training data to determine the classifiers to evaluate the categories of die test data. However, a very large database is required to store training data for complicated damage cases if no technique to reduce the size is used. This paper presents an approach with the purpose of using the least possible sensors. The structural damage location and damage extent are identified respectively by two different methods of pattern classification, that are, the Parzen-window method for the structural damage location firstly and the feed-forward back-propagation neural network used to identify damage extent secondly. The results of numerical simulations show that our proposed approach can indeed identify the structural damage using small number of sensors. Finally, a series of vibration experiments for the 5-story shear frame structure were performed to verify the performance of our proposed approach. The results show that for shear buildings, damage degree and extent can be successfully determined through measuring the frequency change.

AB - Structural identification for health monitoring involves comparison of changes in structural properties or response, and it can be viewed as pattern classification problems. The fundamental idea of the pattern classification approach is to use training data to determine the classifiers to evaluate the categories of die test data. However, a very large database is required to store training data for complicated damage cases if no technique to reduce the size is used. This paper presents an approach with the purpose of using the least possible sensors. The structural damage location and damage extent are identified respectively by two different methods of pattern classification, that are, the Parzen-window method for the structural damage location firstly and the feed-forward back-propagation neural network used to identify damage extent secondly. The results of numerical simulations show that our proposed approach can indeed identify the structural damage using small number of sensors. Finally, a series of vibration experiments for the 5-story shear frame structure were performed to verify the performance of our proposed approach. The results show that for shear buildings, damage degree and extent can be successfully determined through measuring the frequency change.

UR - http://www.scopus.com/inward/record.url?scp=84890630628&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890630628&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84890630628

SN - 0415396506

SN - 9780415396509

VL - 1

SP - 201

EP - 205

BT - Structural Health Monitoring and Intelligent Infrastructure - Proceedings of the 2nd International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2005

ER -