Abstract
| Original language | English |
|---|---|
| Title of host publication | Structural Health Monitoring 2008 |
| Subtitle of host publication | Proceedings of the Fourth European Workshop |
| Publisher | Destech Pubns Inc |
| Pages | 1055-1063 |
| Number of pages | 9 |
| ISBN (Print) | 9781932078947, 1932078940 |
| DOIs | |
| Publication status | Published - 23 Jul 2008 |
Fingerprint
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
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 proceeding › Chapter (peer-reviewed)
}
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 -