Indirect structural health monitoring of a simplified laboratory-scale bridge model

Fernando Cerda, Siheng Chen, Jacobo Bielak, James H. Garrett, Piervincenzo Rizzo, Jelena Kovacevic

Research output: Contribution to journalArticle

Abstract

An indirect approach is explored for structural health bridge monitoring allowing for wide, yet cost-effective, bridge stock coverage. The detection capability of the approach is tested in a laboratory setting for three different reversible proxy types of damage scenarios: changes in the support conditions (rotational restraint), additional damping, and an added mass at the midspan. A set of frequency features is used in conjunction with a support vector machine classifier on data measured from a passing vehicle at the wheel and suspension levels, and directly from the bridge structure for comparison. For each type of damage, four levels of severity were explored. The results show that for each damage type, the classification accuracy based on data measured from the passing vehicle is, on average, as good as or better than the classification accuracy based on data measured from the bridge. Classification accuracy showed a steady trend for low (1-1.75 m/s) and high vehicle speeds (2-2.75 m/s), with a decrease of about 7% for the latter. These results show promise towards a highly mobile structural health bridge monitoring system for wide and cost-effective bridge stock coverage.

Original languageEnglish (US)
Pages (from-to)849-868
Number of pages20
JournalSmart Structures and Systems
Volume13
Issue number5
DOIs
StatePublished - Jan 1 2014

Fingerprint

Structural health monitoring
Health
Monitoring
Support vector machines
Costs
Wheels
Classifiers
Damping

Keywords

  • Classification
  • Damage detection
  • Indirect SHM
  • Laboratory experiment

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Indirect structural health monitoring of a simplified laboratory-scale bridge model. / Cerda, Fernando; Chen, Siheng; Bielak, Jacobo; Garrett, James H.; Rizzo, Piervincenzo; Kovacevic, Jelena.

In: Smart Structures and Systems, Vol. 13, No. 5, 01.01.2014, p. 849-868.

Research output: Contribution to journalArticle

Cerda, Fernando ; Chen, Siheng ; Bielak, Jacobo ; Garrett, James H. ; Rizzo, Piervincenzo ; Kovacevic, Jelena. / Indirect structural health monitoring of a simplified laboratory-scale bridge model. In: Smart Structures and Systems. 2014 ; Vol. 13, No. 5. pp. 849-868.
@article{12e8c46ff10942ab8d76f1af557b8622,
title = "Indirect structural health monitoring of a simplified laboratory-scale bridge model",
abstract = "An indirect approach is explored for structural health bridge monitoring allowing for wide, yet cost-effective, bridge stock coverage. The detection capability of the approach is tested in a laboratory setting for three different reversible proxy types of damage scenarios: changes in the support conditions (rotational restraint), additional damping, and an added mass at the midspan. A set of frequency features is used in conjunction with a support vector machine classifier on data measured from a passing vehicle at the wheel and suspension levels, and directly from the bridge structure for comparison. For each type of damage, four levels of severity were explored. The results show that for each damage type, the classification accuracy based on data measured from the passing vehicle is, on average, as good as or better than the classification accuracy based on data measured from the bridge. Classification accuracy showed a steady trend for low (1-1.75 m/s) and high vehicle speeds (2-2.75 m/s), with a decrease of about 7{\%} for the latter. These results show promise towards a highly mobile structural health bridge monitoring system for wide and cost-effective bridge stock coverage.",
keywords = "Classification, Damage detection, Indirect SHM, Laboratory experiment",
author = "Fernando Cerda and Siheng Chen and Jacobo Bielak and Garrett, {James H.} and Piervincenzo Rizzo and Jelena Kovacevic",
year = "2014",
month = "1",
day = "1",
doi = "10.12989/sss.2014.13.5.849",
language = "English (US)",
volume = "13",
pages = "849--868",
journal = "Smart Structures and Systems",
issn = "1738-1584",
publisher = "Techno Press",
number = "5",

}

TY - JOUR

T1 - Indirect structural health monitoring of a simplified laboratory-scale bridge model

AU - Cerda, Fernando

AU - Chen, Siheng

AU - Bielak, Jacobo

AU - Garrett, James H.

AU - Rizzo, Piervincenzo

AU - Kovacevic, Jelena

PY - 2014/1/1

Y1 - 2014/1/1

N2 - An indirect approach is explored for structural health bridge monitoring allowing for wide, yet cost-effective, bridge stock coverage. The detection capability of the approach is tested in a laboratory setting for three different reversible proxy types of damage scenarios: changes in the support conditions (rotational restraint), additional damping, and an added mass at the midspan. A set of frequency features is used in conjunction with a support vector machine classifier on data measured from a passing vehicle at the wheel and suspension levels, and directly from the bridge structure for comparison. For each type of damage, four levels of severity were explored. The results show that for each damage type, the classification accuracy based on data measured from the passing vehicle is, on average, as good as or better than the classification accuracy based on data measured from the bridge. Classification accuracy showed a steady trend for low (1-1.75 m/s) and high vehicle speeds (2-2.75 m/s), with a decrease of about 7% for the latter. These results show promise towards a highly mobile structural health bridge monitoring system for wide and cost-effective bridge stock coverage.

AB - An indirect approach is explored for structural health bridge monitoring allowing for wide, yet cost-effective, bridge stock coverage. The detection capability of the approach is tested in a laboratory setting for three different reversible proxy types of damage scenarios: changes in the support conditions (rotational restraint), additional damping, and an added mass at the midspan. A set of frequency features is used in conjunction with a support vector machine classifier on data measured from a passing vehicle at the wheel and suspension levels, and directly from the bridge structure for comparison. For each type of damage, four levels of severity were explored. The results show that for each damage type, the classification accuracy based on data measured from the passing vehicle is, on average, as good as or better than the classification accuracy based on data measured from the bridge. Classification accuracy showed a steady trend for low (1-1.75 m/s) and high vehicle speeds (2-2.75 m/s), with a decrease of about 7% for the latter. These results show promise towards a highly mobile structural health bridge monitoring system for wide and cost-effective bridge stock coverage.

KW - Classification

KW - Damage detection

KW - Indirect SHM

KW - Laboratory experiment

UR - http://www.scopus.com/inward/record.url?scp=84901813670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901813670&partnerID=8YFLogxK

U2 - 10.12989/sss.2014.13.5.849

DO - 10.12989/sss.2014.13.5.849

M3 - Article

AN - SCOPUS:84901813670

VL - 13

SP - 849

EP - 868

JO - Smart Structures and Systems

JF - Smart Structures and Systems

SN - 1738-1584

IS - 5

ER -