PSI - Issue 77

ScienceDirect Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia 00 (2026) 000 – 000 Available online at www.sciencedirect.com ScienceDirect Structural Integrity Procedia 00 (2026) 000 – 000 Available online at www.sciencedirect.com Procedia Structural Integrity 77 (2026) 152–160

www.elsevier.com/locate/procedia

www.elsevier.com/locate/procedia

© 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers Data-driven structural health monitoring (SHM) systems are designed to assess the structural health conditions and to detect any potential damage, ensuring both structural safety and functionality. These systems rely on machine learning-based methods to process and analyze structural response data. The key step of these methods is damage sensitive feature extraction. Signal processing techniques, statistical modeling and neural networks were widely used in this step. However, these techniques presents limitations as information loss and computational complexity. Additionally, machine learning methods that use these techniques are supervised, which make them impractical because of damage and undamaged labels lack. To overcome these limitations, an unsupervised deep learning method based on spatio- temporel graph neural network is proposed in this paper. The method doesn’t require any preprocessing step to extract damage sensitive features. It integrates three key steps: First, Dynamic Time Warping (DTW) is used to construct a graph that captures the interactions among sensor measurements by assessing similarities between signals data. Second, a hybrid neural network architecture combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) layers is established to automatically capture the spatio-temporal dependencies from the historical sensor data of the undamaged structure. This combination enables accurate forecasting of expected sensor responses under normal conditions. Finally, the model prediction errors are analyzed to identify potential damage under unknown conditions; significant deviations between predicted and actual sensor data suggest damage presence. To quantify these deviations, the Kolmogorov – Smirnov test is employed, measuring the differences between the error distributions for undamaged and damaged scenarios. The proposed method is applied Data-driven structural health monitoring (SHM) systems are designed to assess the structural health conditions and to detect any potential damage, ensuring both structural safety and functionality. These systems rely on machine learning-based methods to process and analyze structural response data. The key step of these methods is damage sensitive feature extraction. Signal processing techniques, statistical modeling and neural networks were widely used in this step. However, these techniques presents limitations as information loss and computational complexity. Additionally, machine learning methods that use these techniques are supervised, which make them impractical because of damage and undamaged labels lack. To overcome these limitations, an unsupervised deep learning method based on spatio- temporel graph neural network is proposed in this paper. The method doesn’t require any preprocessing step to extract damage sensitive features. It integrates three key steps: First, Dynamic Time Warping (DTW) is used to construct a graph that captures the interactions among sensor measurements by assessing similarities between signals data. Second, a hybrid neural network architecture combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) layers is established to automatically capture the spatio-temporal dependencies from the historical sensor data of the undamaged structure. This combination enables accurate forecasting of expected sensor responses under normal conditions. Finally, the model prediction errors are analyzed to identify potential damage under unknown conditions; significant deviations between predicted and actual sensor data suggest damage presence. To quantify these deviations, the Kolmogorov – Smirnov test is employed, measuring the differences between the error distributions for undamaged and damaged scenarios. The proposed method is applied International Conference on Structural Integrity Spatio-temporal graph neural network for damage detection and global structural condition assessment Douaa BENHADDOUCHE a, *, Vincent BARRA b , Alaa CHATEAUNEUF c a Clermont Auvergne university, Institut Pascal, LIMOS, CIDECO, 1 Rue de la Chebarde, 63178 Aubière, France b Clermont Auvergne university, CNRS, Mines de Saint-Etienne, LIMOS, 1, rue de la Chebarde, 63178 Aubière, France c CIDECO, 28 Place Henri Dunant, 63001 Clermont-Ferrand, France International Conference on Structural Integrity Spatio-temporal graph neural network for damage detection and global structural condition assessment Douaa BENHADDOUCHE a, *, Vincent BARRA b , Alaa CHATEAUNEUF c a Clermont Auvergne university, Institut Pascal, LIMOS, CIDECO, 1 Rue de la Chebarde, 63178 Aubière, France b Clermont Auvergne university, CNRS, Mines de Saint-Etienne, LIMOS, 1, rue de la Chebarde, 63178 Aubière, France c CIDECO, 28 Place Henri Dunant, 63001 Clermont-Ferrand, France Abstract Abstract

* Corresponding author. Tel.: +334 73 40 50 08. E-mail address: douaa.benhaddouche@doctorant.uca.fr

* Corresponding author. Tel.: +334 73 40 50 08. E-mail address: douaa.benhaddouche@doctorant.uca.fr

2452-3216 © 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers 10.1016/j.prostr.2026.01.021 2452-3216 © 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers 2452-3216 © 2026 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of ICSI organizers