Classification of damage using time series analysis and statistical pattern recognition

O. R. De Lautour, P. Omenzetter

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

1 Citation (Scopus)

Abstract

The application of time series analysis methods to Structural Health Monitoring (SHM) is a relatively novel and emerging technique. Time series methods are inherently suited to SHM where data is sampled regularly and over a long period of time. This study focuses on the application of statistical pattern recognition techniques to classify damage based on analysis of the time series model coefficients. Autoregressive (AR) models were used to analyse time histories from a structure in both healthy and damaged states. The coefficients of these models were selected as damage sensitive features. Principal Component Analysis (PCA) was used to reduce the dimensionality of the features. Two statistical pattern recognition techniques, Nearest Neighbour (NN) and Learning Vector Quantisation (LVQ) were used to classify damage into states. The results showed that NN classifiers performed well however, improvements could be made using LVQ. The method was applied to a 3-storey bookshelf structure.
Original languageEnglish
Title of host publicationStructural Health Monitoring 2008
Subtitle of host publicationProceedings of the Fourth European Workshop
PublisherDestech Pubns Inc
Pages1055-1063
Number of pages9
ISBN (Print)9781932078947, 1932078940
DOIs
Publication statusPublished - 23 Jul 2008

Fingerprint

Time series analysis
Pattern recognition
Structural health monitoring
Vector quantization
Time series
Principal component analysis
Classifiers

Keywords

  • health
  • pattern recognition
  • principal component analysis
  • structural health monitoring
  • structures (built objects)
  • time series
  • auto-regressive models
  • damage-sensitive features
  • learning vector quantisation
  • nearest neighbours
  • principal components
  • series analysis
  • statistical pattern recognition
  • structural healths
  • time history
  • time series methods
  • time series models
  • time series analysis

Cite this

De Lautour, O. R., & Omenzetter, P. (2008). Classification of damage using time series analysis and statistical pattern recognition. In Structural Health Monitoring 2008: Proceedings of the Fourth European Workshop (pp. 1055-1063). Destech Pubns Inc. https://doi.org/10.13140/2.1.4377.2482

Classification of damage using time series analysis and statistical pattern recognition. / De Lautour, O. R.; Omenzetter, P.

Structural Health Monitoring 2008: Proceedings of the Fourth European Workshop. Destech Pubns Inc, 2008. p. 1055-1063.

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

De Lautour, OR & Omenzetter, P 2008, Classification of damage using time series analysis and statistical pattern recognition. in Structural Health Monitoring 2008: Proceedings of the Fourth European Workshop. Destech Pubns Inc, pp. 1055-1063. https://doi.org/10.13140/2.1.4377.2482
De Lautour OR, Omenzetter P. Classification of damage using time series analysis and statistical pattern recognition. In Structural Health Monitoring 2008: Proceedings of the Fourth European Workshop. Destech Pubns Inc. 2008. p. 1055-1063 https://doi.org/10.13140/2.1.4377.2482
De Lautour, O. R. ; Omenzetter, P. / Classification of damage using time series analysis and statistical pattern recognition. Structural Health Monitoring 2008: Proceedings of the Fourth European Workshop. Destech Pubns Inc, 2008. pp. 1055-1063
@inbook{9ef7850747b84bd7a55fc3c306a901b1,
title = "Classification of damage using time series analysis and statistical pattern recognition",
abstract = "The application of time series analysis methods to Structural Health Monitoring (SHM) is a relatively novel and emerging technique. Time series methods are inherently suited to SHM where data is sampled regularly and over a long period of time. This study focuses on the application of statistical pattern recognition techniques to classify damage based on analysis of the time series model coefficients. Autoregressive (AR) models were used to analyse time histories from a structure in both healthy and damaged states. The coefficients of these models were selected as damage sensitive features. Principal Component Analysis (PCA) was used to reduce the dimensionality of the features. Two statistical pattern recognition techniques, Nearest Neighbour (NN) and Learning Vector Quantisation (LVQ) were used to classify damage into states. The results showed that NN classifiers performed well however, improvements could be made using LVQ. The method was applied to a 3-storey bookshelf structure.",
keywords = "health, pattern recognition, principal component analysis, structural health monitoring, structures (built objects), time series, auto-regressive models, damage-sensitive features, learning vector quantisation, nearest neighbours, principal components, series analysis, statistical pattern recognition, structural healths, time history, time series methods, time series models, time series analysis",
author = "{De Lautour}, {O. R.} and P. Omenzetter",
year = "2008",
month = "7",
day = "23",
doi = "10.13140/2.1.4377.2482",
language = "English",
isbn = "9781932078947",
pages = "1055--1063",
booktitle = "Structural Health Monitoring 2008",
publisher = "Destech Pubns Inc",

}

TY - CHAP

T1 - Classification of damage using time series analysis and statistical pattern recognition

AU - De Lautour, O. R.

AU - Omenzetter, P.

PY - 2008/7/23

Y1 - 2008/7/23

N2 - The application of time series analysis methods to Structural Health Monitoring (SHM) is a relatively novel and emerging technique. Time series methods are inherently suited to SHM where data is sampled regularly and over a long period of time. This study focuses on the application of statistical pattern recognition techniques to classify damage based on analysis of the time series model coefficients. Autoregressive (AR) models were used to analyse time histories from a structure in both healthy and damaged states. The coefficients of these models were selected as damage sensitive features. Principal Component Analysis (PCA) was used to reduce the dimensionality of the features. Two statistical pattern recognition techniques, Nearest Neighbour (NN) and Learning Vector Quantisation (LVQ) were used to classify damage into states. The results showed that NN classifiers performed well however, improvements could be made using LVQ. The method was applied to a 3-storey bookshelf structure.

AB - The application of time series analysis methods to Structural Health Monitoring (SHM) is a relatively novel and emerging technique. Time series methods are inherently suited to SHM where data is sampled regularly and over a long period of time. This study focuses on the application of statistical pattern recognition techniques to classify damage based on analysis of the time series model coefficients. Autoregressive (AR) models were used to analyse time histories from a structure in both healthy and damaged states. The coefficients of these models were selected as damage sensitive features. Principal Component Analysis (PCA) was used to reduce the dimensionality of the features. Two statistical pattern recognition techniques, Nearest Neighbour (NN) and Learning Vector Quantisation (LVQ) were used to classify damage into states. The results showed that NN classifiers performed well however, improvements could be made using LVQ. The method was applied to a 3-storey bookshelf structure.

KW - health

KW - pattern recognition

KW - principal component analysis

KW - structural health monitoring

KW - structures (built objects)

KW - time series

KW - auto-regressive models

KW - damage-sensitive features

KW - learning vector quantisation

KW - nearest neighbours

KW - principal components

KW - series analysis

KW - statistical pattern recognition

KW - structural healths

KW - time history

KW - time series methods

KW - time series models

KW - time series analysis

UR - http://www.scopus.com/inward/record.url?scp=62949152958&partnerID=8YFLogxK

U2 - 10.13140/2.1.4377.2482

DO - 10.13140/2.1.4377.2482

M3 - Chapter (peer-reviewed)

SN - 9781932078947

SN - 1932078940

SP - 1055

EP - 1063

BT - Structural Health Monitoring 2008

PB - Destech Pubns Inc

ER -