Details
| Original language | English |
|---|---|
| Title of host publication | Experimental Vibration Analysis for Civil Engineering Structures EVACES 2023 - Volume 2 |
| Editors | Maria Pina Limongelli, Pier Francesco Giordano, Carmelo Gentile, Said Quqa, Alfredo Cigada |
| Pages | 511-519 |
| Number of pages | 9 |
| ISBN (electronic) | 978-3-031-39117-0 |
| Publication status | Published - 2023 |
Publication series
| Name | Lecture Notes in Civil Engineering |
|---|---|
| Volume | 433 LNCE |
| ISSN (Print) | 2366-2557 |
| ISSN (electronic) | 2366-2565 |
Abstract
In this paper, a non-linear autoencoder trained with time-series data for unsupervised damage localization based on residuals is investigated. Due to their sensitivity regarding small changes in the time-series, autoencoder offer a powerful tool for damage detection in Structural Health Monitoring (SHM). When it comes to output-only and unsupervised SHM, data-driven models struggle to properly localize the position of small damages. In an attempt to overcome these limitations, this study is performed using selected measurement data of a lattice tower called Leibniz University Structure for Monitoring (LUMO) under ambient excitation. Considering only data sets for similar material temperatures and wind speeds, the dependencies on environmental conditions are negligible. The model is trained using acceleration time-series as the input. As an extension of the model, the residuals are evaluated using the covariance. For each input signal and each residual time-series the covariance between them is calculated. The linear correlation of the input data to the residual increases the most for the sensor closest to the structural change. It can be shown that the data-driven model is able to locate all induced damages. The study presents a novel unsupervised data-driven damage localization technique using autoencoder with time-series data and correlations of the residual to the input data. This allows a localization of damage even when the manifestation of damage is not available.
Keywords
- Autoencoder, Covariance, Unsupervised damage localization
ASJC Scopus subject areas
- Engineering(all)
- Civil and Structural Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Experimental Vibration Analysis for Civil Engineering Structures EVACES 2023 - Volume 2. ed. / Maria Pina Limongelli; Pier Francesco Giordano; Carmelo Gentile; Said Quqa; Alfredo Cigada. 2023. p. 511-519 (Lecture Notes in Civil Engineering; Vol. 433 LNCE).
Research output: Chapter in book/report/conference proceeding › Contribution to book/anthology › Research › peer review
}
TY - CHAP
T1 - Unsupervised Damage Localization Using Autoencoders with Time-Series Data
AU - Römgens, Niklas
AU - Abbassi, Abderrahim
AU - Jonscher, Clemens
AU - Grießmann, Tanja
AU - Rolfes, Raimund
N1 - The authors greatfully acknowledge the financial support provided by the Federal Ministry for Economic Affairs and Climate Action of the Federal Republic of Germany within the framework of the collaborative research project Grout-WATCH (FKZ 03SX505B).
PY - 2023
Y1 - 2023
N2 - In this paper, a non-linear autoencoder trained with time-series data for unsupervised damage localization based on residuals is investigated. Due to their sensitivity regarding small changes in the time-series, autoencoder offer a powerful tool for damage detection in Structural Health Monitoring (SHM). When it comes to output-only and unsupervised SHM, data-driven models struggle to properly localize the position of small damages. In an attempt to overcome these limitations, this study is performed using selected measurement data of a lattice tower called Leibniz University Structure for Monitoring (LUMO) under ambient excitation. Considering only data sets for similar material temperatures and wind speeds, the dependencies on environmental conditions are negligible. The model is trained using acceleration time-series as the input. As an extension of the model, the residuals are evaluated using the covariance. For each input signal and each residual time-series the covariance between them is calculated. The linear correlation of the input data to the residual increases the most for the sensor closest to the structural change. It can be shown that the data-driven model is able to locate all induced damages. The study presents a novel unsupervised data-driven damage localization technique using autoencoder with time-series data and correlations of the residual to the input data. This allows a localization of damage even when the manifestation of damage is not available.
AB - In this paper, a non-linear autoencoder trained with time-series data for unsupervised damage localization based on residuals is investigated. Due to their sensitivity regarding small changes in the time-series, autoencoder offer a powerful tool for damage detection in Structural Health Monitoring (SHM). When it comes to output-only and unsupervised SHM, data-driven models struggle to properly localize the position of small damages. In an attempt to overcome these limitations, this study is performed using selected measurement data of a lattice tower called Leibniz University Structure for Monitoring (LUMO) under ambient excitation. Considering only data sets for similar material temperatures and wind speeds, the dependencies on environmental conditions are negligible. The model is trained using acceleration time-series as the input. As an extension of the model, the residuals are evaluated using the covariance. For each input signal and each residual time-series the covariance between them is calculated. The linear correlation of the input data to the residual increases the most for the sensor closest to the structural change. It can be shown that the data-driven model is able to locate all induced damages. The study presents a novel unsupervised data-driven damage localization technique using autoencoder with time-series data and correlations of the residual to the input data. This allows a localization of damage even when the manifestation of damage is not available.
KW - Autoencoder
KW - Covariance
KW - Unsupervised damage localization
UR - http://www.scopus.com/inward/record.url?scp=85174860668&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-39117-0_52
DO - 10.1007/978-3-031-39117-0_52
M3 - Contribution to book/anthology
SN - 978-3-031-39116-3
T3 - Lecture Notes in Civil Engineering
SP - 511
EP - 519
BT - Experimental Vibration Analysis for Civil Engineering Structures EVACES 2023 - Volume 2
A2 - Limongelli, Maria Pina
A2 - Giordano, Pier Francesco
A2 - Gentile, Carmelo
A2 - Quqa, Said
A2 - Cigada, Alfredo
ER -