PSI - Issue 64

Marco Pirrò et al. / Procedia Structural Integrity 64 (2024) 661–668 Author name / Structural Integrity Procedia 00 (2019) 000–000

668

8

R 2

Ch1 0.07 0.02

Ch2 0.08 0.06

Ch3 0.08 0.06

Ch4 0.06 0.02

Relative humidity Surface temperature

5. Conclusions

The paper proposes a vibration-based anomaly detection procedure using autoencoders, in which the training of a single autoencoder is done by using simultaneously the dynamic measurements from all the sensors as input of the network. If the structural condition and the EOV are similar to those of the training period, the autoencoder will reconstruct the input measurements with good approximation. Conversely, in presence of structural anomalies, the AE model will not be able to reconstruct the input measurements with good approximation: within this context, the Mean Absolute Error (MAE) computed between the input data and the reconstructed output is expected to increase as soon as the structural condition departs from the normal condition, leading to possible alarms. The proposed methodology is validated on a 14-month monitoring of KW51 railway bridge: since the monitoring period includes accelerations before and after a structural retrofitting that interested the bridge for almost 4 months, the proposed methodology is able to: (a) account for normal EOVs (i.e., normal temperature, humidity and train passages) and (b) detect structural changes due to retrofitting. Acknowledgements / Data availability statement The measurements of the KW51 bridge were published in (Maes and Lombaert 2021) and are available online (https://doi.org/10.5281 /zenodo.3745914). References Bao, Y., Li, H., 2021. Machine learning paradigm for structural health monitoring. Structural Health Monitoring, 20(4): 1353-1372. Borlenghi, P., Gentile, C., Pirrò, M., 2023. Continuous dynamic monitoring and automated Modal Identification of an arch bridge. In: Rizzo, P., Milazzo, A. (Ed.). European Workshop on Structural Health Monitoring, Springer, Cham. Farrar, C., Worden, K., 2007. An introduction to structural health monitoring. Philosophical Transactions of the Royal Society A 365(1851), 303–315. Federal Highway Administration, 2008. Status of the Nation’s highways, bridges and transit: conditions and performance – Report to Congress, Technical Report, U.S. Department of Transportation, 2008. Finotti, R., Barbosa, F., Cury, A., Pimentel, R., 2021. Numerical and experimental evaluation of structural changes using sparse Auto-Encoders and SVM applied to dynamic responses. Applied Sciences 11, 11965. Finotti, R., Gentile, C., Barbosa, F., Cury, A., 2022. Structural novelty detection based on sparse Autoencoders and control charts. Structural Engineering and Mechanics 81(5), 647–664. Giglioni, V., Venanzi, I., Poggioni, V., Milani, A., Ubertini, F., 2022. Autoencoders for unsupervised real-time bridge health assessment. Computer-Aided Civil and Infrastructure Engineering 00, 1–16. Goodfellow, I., Bengio, Y., Courville, A., 2016. Deep Learning. MIT Press, USA. Kingmaand, D., Ba, J., 2015. Adam: A method for stochastic optimization. In: Proc. 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA. Maes, K., Lombaert, G., 2021. Monitoring railway bridge KW51 before, during, and after retrofitting. ASCE Journal of Bridge Engineering 26, 04721001. Magalhães, F., Cunha, À., Caetano, E., 2012. Vibration based structural health monitoring of an arch bridge: from automated OMA to damage detection. Mechanical Systems and Signal Processing 28, 212–228. Pathirage, C., Li, J., Li, L., Hao, H., Liu, W., 2018. Application of deep autoencoder model for structural condition monitoring. Journal of Systems Engineering and Electronics 29(4), 873–880. Peeters, B., De Roeck, G., 2001. One-year monitoring of the Z24-bridge: environmental effects versus damage events. Earthquake Engineering & Structural Dynamics 30, 149–171. Wang, Z., Cha, Y., 2021. Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage. Structural Health Monitoring 20(1), 406–425. Worden, K., Manson, G., 2007. The application of machine learning to structural health monitoring. Philosophical Transactions of the Royal Society A 365(1851), 515–537.