Analysis of seismic damage using time series models and Artificial Neural Networks

O.R. De Lautour, P. Omenzetter

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

Abstract

In the past decade research into SHM systems has received much attention. One of the emerging and promising approaches is the use of time series analysis. This study develops a method for the assessment of earthquake-induced damage in buildings utilising Autoregressive (AR) time series models and Artificial Neural Networks (ANNs). AR models were applied to the computer simulated seismic response of a linear, lumped mass model of a 3-storey building under different damage conditions. Damage was simulated by a reduction in lateral stiffness at each storey. The AR coefficients were considered to be damage sensitive features of the building's response. ANNs were trained to recognize changes in the patterns of the AR coefficients caused by damage and hence identify and quantify the level of damage at each storey.
Original languageEnglish
Title of host publicationProgress in Mechanics of Structures and Materials
Subtitle of host publicationProceedings of the 19th Australasian Conference on the Mechanics of Structures and Materials, ACMSM19
PublisherTaylor & Francis
Pages889-894
Number of pages6
ISBN (Print)9780415426923
Publication statusPublished - 30 Dec 2006

Fingerprint

Time series
Neural networks
Time series analysis
Seismic response
Earthquakes
Stiffness

Cite this

De Lautour, O. R., & Omenzetter, P. (2006). Analysis of seismic damage using time series models and Artificial Neural Networks. In Progress in Mechanics of Structures and Materials: Proceedings of the 19th Australasian Conference on the Mechanics of Structures and Materials, ACMSM19 (pp. 889-894). Taylor & Francis.

Analysis of seismic damage using time series models and Artificial Neural Networks. / De Lautour, O.R.; Omenzetter, P.

Progress in Mechanics of Structures and Materials: Proceedings of the 19th Australasian Conference on the Mechanics of Structures and Materials, ACMSM19. Taylor & Francis, 2006. p. 889-894.

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

De Lautour, OR & Omenzetter, P 2006, Analysis of seismic damage using time series models and Artificial Neural Networks. in Progress in Mechanics of Structures and Materials: Proceedings of the 19th Australasian Conference on the Mechanics of Structures and Materials, ACMSM19. Taylor & Francis, pp. 889-894.
De Lautour OR, Omenzetter P. Analysis of seismic damage using time series models and Artificial Neural Networks. In Progress in Mechanics of Structures and Materials: Proceedings of the 19th Australasian Conference on the Mechanics of Structures and Materials, ACMSM19. Taylor & Francis. 2006. p. 889-894
De Lautour, O.R. ; Omenzetter, P. / Analysis of seismic damage using time series models and Artificial Neural Networks. Progress in Mechanics of Structures and Materials: Proceedings of the 19th Australasian Conference on the Mechanics of Structures and Materials, ACMSM19. Taylor & Francis, 2006. pp. 889-894
@inbook{cf65853c95c94c8895f5b3b999c106ac,
title = "Analysis of seismic damage using time series models and Artificial Neural Networks",
abstract = "In the past decade research into SHM systems has received much attention. One of the emerging and promising approaches is the use of time series analysis. This study develops a method for the assessment of earthquake-induced damage in buildings utilising Autoregressive (AR) time series models and Artificial Neural Networks (ANNs). AR models were applied to the computer simulated seismic response of a linear, lumped mass model of a 3-storey building under different damage conditions. Damage was simulated by a reduction in lateral stiffness at each storey. The AR coefficients were considered to be damage sensitive features of the building's response. ANNs were trained to recognize changes in the patterns of the AR coefficients caused by damage and hence identify and quantify the level of damage at each storey.",
author = "{De Lautour}, O.R. and P. Omenzetter",
year = "2006",
month = "12",
day = "30",
language = "English",
isbn = "9780415426923",
pages = "889--894",
booktitle = "Progress in Mechanics of Structures and Materials",
publisher = "Taylor & Francis",

}

TY - CHAP

T1 - Analysis of seismic damage using time series models and Artificial Neural Networks

AU - De Lautour, O.R.

AU - Omenzetter, P.

PY - 2006/12/30

Y1 - 2006/12/30

N2 - In the past decade research into SHM systems has received much attention. One of the emerging and promising approaches is the use of time series analysis. This study develops a method for the assessment of earthquake-induced damage in buildings utilising Autoregressive (AR) time series models and Artificial Neural Networks (ANNs). AR models were applied to the computer simulated seismic response of a linear, lumped mass model of a 3-storey building under different damage conditions. Damage was simulated by a reduction in lateral stiffness at each storey. The AR coefficients were considered to be damage sensitive features of the building's response. ANNs were trained to recognize changes in the patterns of the AR coefficients caused by damage and hence identify and quantify the level of damage at each storey.

AB - In the past decade research into SHM systems has received much attention. One of the emerging and promising approaches is the use of time series analysis. This study develops a method for the assessment of earthquake-induced damage in buildings utilising Autoregressive (AR) time series models and Artificial Neural Networks (ANNs). AR models were applied to the computer simulated seismic response of a linear, lumped mass model of a 3-storey building under different damage conditions. Damage was simulated by a reduction in lateral stiffness at each storey. The AR coefficients were considered to be damage sensitive features of the building's response. ANNs were trained to recognize changes in the patterns of the AR coefficients caused by damage and hence identify and quantify the level of damage at each storey.

UR - http://www.scopus.com/inward/record.url?scp=84857214782&partnerID=8YFLogxK

M3 - Chapter (peer-reviewed)

SN - 9780415426923

SP - 889

EP - 894

BT - Progress in Mechanics of Structures and Materials

PB - Taylor & Francis

ER -