PSI - Issue 62

Valentina Giglioni et al. / Procedia Structural Integrity 62 (2024) 887–894 Giglioni et al. / Structural Integrity Procedia 00 (2019) 000–000

894

8

spans may be affected by similar defects, the possibility to detect damage across spans using a restricted amount of labels represents an interesting solution accordingly. To investigate TL in the field of PBSHM, the analyses are carried out in a mock-up bridge, representative of post tensioned continuous concrete bridges as well as continuous steel-concrete bridges, that is subjected to a wide monitoring campaign, including damage simulations and various environmental conditions. Results demonstrate an effective transfer when the same stiffness reduction is applied to two different spans; nevertheless, it should be noted that the removal of temperature effects could improve anomaly detection performance and facilitate knowledge transfer. A second aspect that may be worth further exploring is the choice of damage-sensitive features. In fact, the small damage-induced variations of natural frequencies on the lateral span suggest that specific local features should be defined, especially for SHM applications to post-tensioned concrete bridges for which cable stiffness reduction may be challenging to detect. Acknowledgements This study was supported by the Italian Ministry of Education, University and Research (MIUR) via the funded project of national interest “TIMING – Time evolution laws for IMproving the structural reliability evaluation of existING post-tensioned concrete deck bridges” (Protocol No. P20223Y947). The study was also partially supported by FABRE – “Research consortium for the evaluation and monitoring of bridges, viaducts and other structures” (www.consorziofabre.it/en) within the activities of the FABRE-ANAS 2021-2024 research program and by the University of Perugia via the funded projects “AIDMIX-Artificial Intelligence for Decision making: Methods for Interpretability and eXplainability” within the program “Fondo Ricerca di Ateneo, 2021” and “MiRA: Mixed Reality and AI Methodologies for Immersive Robotics” within the program "Fondo Ricerca di Ateneo, 2023". Any opinion expressed in the paper does not necessarily reflect the view of the funder. This research made use of the test facilities at The Laboratory for Verification and Validation (LVV) situated at The University of Sheffield and was funded by the EPSRC as part of the ROSEHIPS project (grant number EP/W005816/1). References Betti, R., 2013. Monitoring technologies for bridge management. Structure and Infrastructure Engineering 9, 1299. He, Z., Li, W., Salehi, H., Zhang, H., Zhou, H., Jiao, P., 2022. Integrated structural health monitoring in bridge engineering 136, 104168. Worden, K., Bull, L.A., Gardner, P., Gosliga, J., Rogers, T.J., Cross, E.J., Papatheou, E., Lin, W., Dervilis, N., 2020. A brief introduction to recent developments in population-based structural health monitoring. Frontiers in Built Environment 6, 146. Bull, L. A., Gardner, P.A., Gosliga, J., Rogers, T.J., Cross, E.J., Papatheou, E., Maguire, A.E., Campos, C., Worden, K., 2021. Foundations of population-based SHM, Part I: Homogeneous populations and forms. Mechanical Systems and Signal Processing 148, 107141. Gardner, P., Bull, L. A., Gosliga, J, Dervilis, N., Worden, K., 2021. Foundations of population-based SHM, Part III: Heterogeneous populations– Mapping and transfer. Mechanical Systems and Signal Processing 149, 107142. Yano, M.O., Figueiredo, E., Da Silva, S., Cury, A., 2023. Foundations and applicability of transfer learning for structural health monitoring of bridges. Mechanical Systems and Signal Processing 204, 110766. Gardner, P., Bull, L.A., Dervilis, N., Worden, K., 2022. Domain-adapted Gaussian mixture models for population-based structural health monitoring. Journal of Civil Structural Health Monitoring 12(6), 1343-1353. Giglioni, V., Poole, J., Venanzi, I., Ubertini, F., Worden, K. A Domain Adaptation Approach to Damage Classification with an Application to Bridge Monitoring. Available at SSRN: https://ssrn.com/abstract=4545602 or http://dx.doi.org/10.2139/ssrn.4545602. Giglioni, V., Poole, J., Mills, R., Dervilis, N., Venanzi, I., Ubertini, F., Worden, K. A comprehensive dataset for a population of experimental bridges under changing environmental conditions for PBSHM. To appear in the proceedings of IMAC-XLII 2024. Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., He, Q., 2020. A comprehensive survey on transfer learning, IEEE 2020, 43-76. Pan, S. J., Yang, Q., 2009. A survey on transfer learning, IEEE Transactions on Knowledge and Data Engineering, 22, 1345-1359. Poole, J., Gardner, P., Dervilis, N., Bull, L., Worden, K., 2023. On statistic alignment for domain adaptation in structural health monitoring. Structural Health Monitoring 22(3), 1581-1600. García-Macías, E., Ubertini, F., 2020. Mova/moss: Two integrated software solutions for comprehensive structural health monitoring of structures. Mechanical Systems and Signal Processing 143, 106830.