Damage detection of structures using support vector machines under various boundary conditions

Marie Shimada, Akira Mita, Maria Q. Feng

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

8 Citations (Scopus)

Abstract

Many Structural Health Monitoring (SHM) methods have been proposed for the purposes of reducing maintenance costs and/or assuring performance of civil structures. The objective of this research is to propose a damage detection system that can obtain the detailed damage information by use of the minimum number of sensors. The proposed system minimizes the possibility of incorrect judgments. Modal frequencies of a structure are used for pattern recognition in the proposed method. Changes in multiple natural frequencies can be correlated to the spatial information of the location of damaged stories. Typically only two vibration sensors, one on the roof and the other on the ground, detecting a single input and a single output for the structure are needed to determine modal frequencies. Out of many pattern recognition tools, we propose to use the Support Vector Machine (SVM). This technique has been found effective. Our previous studies demonstrated that the proposed damage detection method worked well for simple models such as shear structures and bending structures. However, real buildings have various boundary conditions at their supports. In this study, the SVM technique was applied to damage detection of structures with various boundary conditions. The feature vectors for SVMs are generated based on the model of a structure. Then locations of structural damage are detected by inputting the measured structural vibration data into the SVMs. From simulation, it was found that the influence of the change in boundary conditions on the lower modes is larger. We performed experimental studies on damage detection of power distribution poles that had overhead wires. We proposed a method for determining the boundary conditions of the poles and verified this method based on measured vibration data. We demonstrated the effectiveness of the proposed method in detecting damage in the poles.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6174 II
DOIs
Publication statusPublished - 2006
EventSmart Structures and Materials 2006 - Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems - San Diego, CA, United States
Duration: 2006 Feb 272006 Mar 2

Other

OtherSmart Structures and Materials 2006 - Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems
CountryUnited States
CitySan Diego, CA
Period06/2/2706/3/2

Fingerprint

Damage detection
Support vector machines
Boundary conditions
boundary conditions
damage
Poles
Pattern recognition
poles
Structural health monitoring
Sensors
pattern recognition
Roofs
Natural frequencies
structural vibration
vibration
Wire
structural health monitoring
roofs
sensors
maintenance

Keywords

  • Damage detection
  • Modal analysis
  • Support vector machine
  • System identification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Shimada, M., Mita, A., & Feng, M. Q. (2006). Damage detection of structures using support vector machines under various boundary conditions. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6174 II). [61742K] https://doi.org/10.1117/12.658956

Damage detection of structures using support vector machines under various boundary conditions. / Shimada, Marie; Mita, Akira; Feng, Maria Q.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6174 II 2006. 61742K.

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

Shimada, M, Mita, A & Feng, MQ 2006, Damage detection of structures using support vector machines under various boundary conditions. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6174 II, 61742K, Smart Structures and Materials 2006 - Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems, San Diego, CA, United States, 06/2/27. https://doi.org/10.1117/12.658956
Shimada M, Mita A, Feng MQ. Damage detection of structures using support vector machines under various boundary conditions. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6174 II. 2006. 61742K https://doi.org/10.1117/12.658956
Shimada, Marie ; Mita, Akira ; Feng, Maria Q. / Damage detection of structures using support vector machines under various boundary conditions. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6174 II 2006.
@inproceedings{b706cc7648754235959ea253c8b92aa2,
title = "Damage detection of structures using support vector machines under various boundary conditions",
abstract = "Many Structural Health Monitoring (SHM) methods have been proposed for the purposes of reducing maintenance costs and/or assuring performance of civil structures. The objective of this research is to propose a damage detection system that can obtain the detailed damage information by use of the minimum number of sensors. The proposed system minimizes the possibility of incorrect judgments. Modal frequencies of a structure are used for pattern recognition in the proposed method. Changes in multiple natural frequencies can be correlated to the spatial information of the location of damaged stories. Typically only two vibration sensors, one on the roof and the other on the ground, detecting a single input and a single output for the structure are needed to determine modal frequencies. Out of many pattern recognition tools, we propose to use the Support Vector Machine (SVM). This technique has been found effective. Our previous studies demonstrated that the proposed damage detection method worked well for simple models such as shear structures and bending structures. However, real buildings have various boundary conditions at their supports. In this study, the SVM technique was applied to damage detection of structures with various boundary conditions. The feature vectors for SVMs are generated based on the model of a structure. Then locations of structural damage are detected by inputting the measured structural vibration data into the SVMs. From simulation, it was found that the influence of the change in boundary conditions on the lower modes is larger. We performed experimental studies on damage detection of power distribution poles that had overhead wires. We proposed a method for determining the boundary conditions of the poles and verified this method based on measured vibration data. We demonstrated the effectiveness of the proposed method in detecting damage in the poles.",
keywords = "Damage detection, Modal analysis, Support vector machine, System identification",
author = "Marie Shimada and Akira Mita and Feng, {Maria Q.}",
year = "2006",
doi = "10.1117/12.658956",
language = "English",
isbn = "0819462276",
volume = "6174 II",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Damage detection of structures using support vector machines under various boundary conditions

AU - Shimada, Marie

AU - Mita, Akira

AU - Feng, Maria Q.

PY - 2006

Y1 - 2006

N2 - Many Structural Health Monitoring (SHM) methods have been proposed for the purposes of reducing maintenance costs and/or assuring performance of civil structures. The objective of this research is to propose a damage detection system that can obtain the detailed damage information by use of the minimum number of sensors. The proposed system minimizes the possibility of incorrect judgments. Modal frequencies of a structure are used for pattern recognition in the proposed method. Changes in multiple natural frequencies can be correlated to the spatial information of the location of damaged stories. Typically only two vibration sensors, one on the roof and the other on the ground, detecting a single input and a single output for the structure are needed to determine modal frequencies. Out of many pattern recognition tools, we propose to use the Support Vector Machine (SVM). This technique has been found effective. Our previous studies demonstrated that the proposed damage detection method worked well for simple models such as shear structures and bending structures. However, real buildings have various boundary conditions at their supports. In this study, the SVM technique was applied to damage detection of structures with various boundary conditions. The feature vectors for SVMs are generated based on the model of a structure. Then locations of structural damage are detected by inputting the measured structural vibration data into the SVMs. From simulation, it was found that the influence of the change in boundary conditions on the lower modes is larger. We performed experimental studies on damage detection of power distribution poles that had overhead wires. We proposed a method for determining the boundary conditions of the poles and verified this method based on measured vibration data. We demonstrated the effectiveness of the proposed method in detecting damage in the poles.

AB - Many Structural Health Monitoring (SHM) methods have been proposed for the purposes of reducing maintenance costs and/or assuring performance of civil structures. The objective of this research is to propose a damage detection system that can obtain the detailed damage information by use of the minimum number of sensors. The proposed system minimizes the possibility of incorrect judgments. Modal frequencies of a structure are used for pattern recognition in the proposed method. Changes in multiple natural frequencies can be correlated to the spatial information of the location of damaged stories. Typically only two vibration sensors, one on the roof and the other on the ground, detecting a single input and a single output for the structure are needed to determine modal frequencies. Out of many pattern recognition tools, we propose to use the Support Vector Machine (SVM). This technique has been found effective. Our previous studies demonstrated that the proposed damage detection method worked well for simple models such as shear structures and bending structures. However, real buildings have various boundary conditions at their supports. In this study, the SVM technique was applied to damage detection of structures with various boundary conditions. The feature vectors for SVMs are generated based on the model of a structure. Then locations of structural damage are detected by inputting the measured structural vibration data into the SVMs. From simulation, it was found that the influence of the change in boundary conditions on the lower modes is larger. We performed experimental studies on damage detection of power distribution poles that had overhead wires. We proposed a method for determining the boundary conditions of the poles and verified this method based on measured vibration data. We demonstrated the effectiveness of the proposed method in detecting damage in the poles.

KW - Damage detection

KW - Modal analysis

KW - Support vector machine

KW - System identification

UR - http://www.scopus.com/inward/record.url?scp=33745960967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745960967&partnerID=8YFLogxK

U2 - 10.1117/12.658956

DO - 10.1117/12.658956

M3 - Conference contribution

AN - SCOPUS:33745960967

SN - 0819462276

SN - 9780819462275

VL - 6174 II

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -