Local damage assessment of a building using Support Vector Machine

H. Hagiwara, Akira Mita

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

Abstract

A damage detection method utilizing the Support Vector Machine (SVM) is proposed. The SVM is a powerful pattern recognition tool applicable to complicated classification problems. Modal frequencies of a structure are used for pattern recognition in the proposed method. Typically, only two vibration sensors detecting a single input and a single output for a structural system can easily determine modal frequencies. For training SVMs the relationship between changes normalised by original modal frequencies, before suffering any damage, is utilized. The SVM trained for single damage was also found to be effective for detecting damage in multiple stories. The SVM based damage assessment is able to identify damage qualitatively as well as quantitatively.

Original languageEnglish
Title of host publicationAdvances in Earthquake Engineering
EditorsG. Latini, C.A. Brebbia
Pages235-244
Number of pages10
Volume13
Publication statusPublished - 2003
EventFourth International Conference on Earthquake Resistant Engineering Structures, ERES IV - Ancona, Italy
Duration: 2003 Sep 222003 Sep 24

Other

OtherFourth International Conference on Earthquake Resistant Engineering Structures, ERES IV
CountryItaly
CityAncona
Period03/9/2203/9/24

Fingerprint

Support vector machines
Pattern recognition
Damage detection
Sensors

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hagiwara, H., & Mita, A. (2003). Local damage assessment of a building using Support Vector Machine. In G. Latini, & C. A. Brebbia (Eds.), Advances in Earthquake Engineering (Vol. 13, pp. 235-244)

Local damage assessment of a building using Support Vector Machine. / Hagiwara, H.; Mita, Akira.

Advances in Earthquake Engineering. ed. / G. Latini; C.A. Brebbia. Vol. 13 2003. p. 235-244.

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

Hagiwara, H & Mita, A 2003, Local damage assessment of a building using Support Vector Machine. in G Latini & CA Brebbia (eds), Advances in Earthquake Engineering. vol. 13, pp. 235-244, Fourth International Conference on Earthquake Resistant Engineering Structures, ERES IV, Ancona, Italy, 03/9/22.
Hagiwara H, Mita A. Local damage assessment of a building using Support Vector Machine. In Latini G, Brebbia CA, editors, Advances in Earthquake Engineering. Vol. 13. 2003. p. 235-244
Hagiwara, H. ; Mita, Akira. / Local damage assessment of a building using Support Vector Machine. Advances in Earthquake Engineering. editor / G. Latini ; C.A. Brebbia. Vol. 13 2003. pp. 235-244
@inproceedings{35cfe0a90f924947a62245ee510a15fe,
title = "Local damage assessment of a building using Support Vector Machine",
abstract = "A damage detection method utilizing the Support Vector Machine (SVM) is proposed. The SVM is a powerful pattern recognition tool applicable to complicated classification problems. Modal frequencies of a structure are used for pattern recognition in the proposed method. Typically, only two vibration sensors detecting a single input and a single output for a structural system can easily determine modal frequencies. For training SVMs the relationship between changes normalised by original modal frequencies, before suffering any damage, is utilized. The SVM trained for single damage was also found to be effective for detecting damage in multiple stories. The SVM based damage assessment is able to identify damage qualitatively as well as quantitatively.",
author = "H. Hagiwara and Akira Mita",
year = "2003",
language = "English",
volume = "13",
pages = "235--244",
editor = "G. Latini and C.A. Brebbia",
booktitle = "Advances in Earthquake Engineering",

}

TY - GEN

T1 - Local damage assessment of a building using Support Vector Machine

AU - Hagiwara, H.

AU - Mita, Akira

PY - 2003

Y1 - 2003

N2 - A damage detection method utilizing the Support Vector Machine (SVM) is proposed. The SVM is a powerful pattern recognition tool applicable to complicated classification problems. Modal frequencies of a structure are used for pattern recognition in the proposed method. Typically, only two vibration sensors detecting a single input and a single output for a structural system can easily determine modal frequencies. For training SVMs the relationship between changes normalised by original modal frequencies, before suffering any damage, is utilized. The SVM trained for single damage was also found to be effective for detecting damage in multiple stories. The SVM based damage assessment is able to identify damage qualitatively as well as quantitatively.

AB - A damage detection method utilizing the Support Vector Machine (SVM) is proposed. The SVM is a powerful pattern recognition tool applicable to complicated classification problems. Modal frequencies of a structure are used for pattern recognition in the proposed method. Typically, only two vibration sensors detecting a single input and a single output for a structural system can easily determine modal frequencies. For training SVMs the relationship between changes normalised by original modal frequencies, before suffering any damage, is utilized. The SVM trained for single damage was also found to be effective for detecting damage in multiple stories. The SVM based damage assessment is able to identify damage qualitatively as well as quantitatively.

UR - http://www.scopus.com/inward/record.url?scp=2942650382&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942650382&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:2942650382

VL - 13

SP - 235

EP - 244

BT - Advances in Earthquake Engineering

A2 - Latini, G.

A2 - Brebbia, C.A.

ER -