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 -