A novel bridge structure damage diagnosis algorithm based on post-nonlinear ICA and statistical pattern recognition

Haitao Xiao, Sheng Lou, Harutoshi Ogai

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Monitoring the health of bridges and diagnosing the damage is vital for government and related institutions in Japan because of frequent earthquakes and the oceanic climate. This paper develops a bridge structure health monitoring system (BSHM), which includes data acquisition and analysis. A two-stage structure damage detection algorithm based on post-nonlinear independent component analysis (ICA) and statistical pattern recognition is proposed to analyze the acquired data and evaluate the health of bridges. First, an improved post-nonlinear ICA algorithm is proposed for denoising, and a data-sample matching based data normalization scheme to reduce the effect of varying environmental and operational condition. Thereafter, fast Fourier transform (FFT) is used to detect the damage. Based on the first stage, a statistical pattern recognition damage detection algorithm, including a new damage sensitive index D<inf>SPR</inf>, is proposed to determine the severity and location(s) of damage. In addition to the algorithm, this paper presents several simulations and experiments, including a detection experiment that applies artificial damage to a real bridge to show that our design choices are indeed effective.

Original languageEnglish
Pages (from-to)287-300
Number of pages14
JournalIEEJ Transactions on Electrical and Electronic Engineering
Volume10
Issue number3
DOIs
Publication statusPublished - 2015 May 1

Fingerprint

Independent component analysis
Pattern recognition
Damage detection
Health
Monitoring
Fast Fourier transforms
Data acquisition
Earthquakes
Experiments

Keywords

  • Bridge diagnosis
  • Geometric linearization
  • Independent component analysis
  • Statistical pattern recognition
  • System design
  • Wireless sensor networks

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{c69f8a5856074634931fcafcf5a6f23b,
title = "A novel bridge structure damage diagnosis algorithm based on post-nonlinear ICA and statistical pattern recognition",
abstract = "Monitoring the health of bridges and diagnosing the damage is vital for government and related institutions in Japan because of frequent earthquakes and the oceanic climate. This paper develops a bridge structure health monitoring system (BSHM), which includes data acquisition and analysis. A two-stage structure damage detection algorithm based on post-nonlinear independent component analysis (ICA) and statistical pattern recognition is proposed to analyze the acquired data and evaluate the health of bridges. First, an improved post-nonlinear ICA algorithm is proposed for denoising, and a data-sample matching based data normalization scheme to reduce the effect of varying environmental and operational condition. Thereafter, fast Fourier transform (FFT) is used to detect the damage. Based on the first stage, a statistical pattern recognition damage detection algorithm, including a new damage sensitive index DSPR, is proposed to determine the severity and location(s) of damage. In addition to the algorithm, this paper presents several simulations and experiments, including a detection experiment that applies artificial damage to a real bridge to show that our design choices are indeed effective.",
keywords = "Bridge diagnosis, Geometric linearization, Independent component analysis, Statistical pattern recognition, System design, Wireless sensor networks",
author = "Haitao Xiao and Sheng Lou and Harutoshi Ogai",
year = "2015",
month = "5",
day = "1",
doi = "10.1002/tee.22085",
language = "English",
volume = "10",
pages = "287--300",
journal = "IEEJ Transactions on Electrical and Electronic Engineering",
issn = "1931-4973",
publisher = "John Wiley and Sons Inc.",
number = "3",

}

TY - JOUR

T1 - A novel bridge structure damage diagnosis algorithm based on post-nonlinear ICA and statistical pattern recognition

AU - Xiao, Haitao

AU - Lou, Sheng

AU - Ogai, Harutoshi

PY - 2015/5/1

Y1 - 2015/5/1

N2 - Monitoring the health of bridges and diagnosing the damage is vital for government and related institutions in Japan because of frequent earthquakes and the oceanic climate. This paper develops a bridge structure health monitoring system (BSHM), which includes data acquisition and analysis. A two-stage structure damage detection algorithm based on post-nonlinear independent component analysis (ICA) and statistical pattern recognition is proposed to analyze the acquired data and evaluate the health of bridges. First, an improved post-nonlinear ICA algorithm is proposed for denoising, and a data-sample matching based data normalization scheme to reduce the effect of varying environmental and operational condition. Thereafter, fast Fourier transform (FFT) is used to detect the damage. Based on the first stage, a statistical pattern recognition damage detection algorithm, including a new damage sensitive index DSPR, is proposed to determine the severity and location(s) of damage. In addition to the algorithm, this paper presents several simulations and experiments, including a detection experiment that applies artificial damage to a real bridge to show that our design choices are indeed effective.

AB - Monitoring the health of bridges and diagnosing the damage is vital for government and related institutions in Japan because of frequent earthquakes and the oceanic climate. This paper develops a bridge structure health monitoring system (BSHM), which includes data acquisition and analysis. A two-stage structure damage detection algorithm based on post-nonlinear independent component analysis (ICA) and statistical pattern recognition is proposed to analyze the acquired data and evaluate the health of bridges. First, an improved post-nonlinear ICA algorithm is proposed for denoising, and a data-sample matching based data normalization scheme to reduce the effect of varying environmental and operational condition. Thereafter, fast Fourier transform (FFT) is used to detect the damage. Based on the first stage, a statistical pattern recognition damage detection algorithm, including a new damage sensitive index DSPR, is proposed to determine the severity and location(s) of damage. In addition to the algorithm, this paper presents several simulations and experiments, including a detection experiment that applies artificial damage to a real bridge to show that our design choices are indeed effective.

KW - Bridge diagnosis

KW - Geometric linearization

KW - Independent component analysis

KW - Statistical pattern recognition

KW - System design

KW - Wireless sensor networks

UR - http://www.scopus.com/inward/record.url?scp=84927697602&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927697602&partnerID=8YFLogxK

U2 - 10.1002/tee.22085

DO - 10.1002/tee.22085

M3 - Article

AN - SCOPUS:84927697602

VL - 10

SP - 287

EP - 300

JO - IEEJ Transactions on Electrical and Electronic Engineering

JF - IEEJ Transactions on Electrical and Electronic Engineering

SN - 1931-4973

IS - 3

ER -