PSI - Issue 84

Elisa Tomassini et al. / Procedia Structural Integrity 84 (2026) 288–295

295

models to accurately reproduce the dynamic response of complex bridge structures with a level of computational efficiency that is compatible with continuous monitoring applications. By replacing high-fidelity finite element models with fast-to-evaluate surrogate models, the approach enables rapid damage identification while preserving high predictive accuracy on both modal frequencies and mode shapes. The transferability of the surrogate modeling strategy was assessed on two real-world bridges. A surrogate model was initially trained for the source structure using an extensive numerical dataset, while the surrogate for the target bridge was efficiently obtained through fine-tuning using a significantly reduced number of simulations. Despite the limited training data for the target structure, the transferred model achieved excellent agreement with numerical references, confirming the effectiveness of knowledge transfer between structurally similar assets. Overall, the proposed methodology establishes a scalable and transferable SHM paradigm that supports efficient deployment across bridge networks by exploiting shared structural knowledge. By reducing data requirements and computational costs while maintaining high accuracy, the framework provides a practical pathway toward network level monitoring and damage assessment in increasingly instrumented infrastructure systems. Acknowledgements The authors gratefully acknowledge ANAS S.p.A. for providing access to monitoring data and technical documentation related to the source bridge. This study was 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 2021–2026 research program. Any opinion expressed in this paper does not necessarily reflect the views of the funders. References Andreose F., Borlenghi P., Chellini G., Faleschini F., Garcìa-Macìas E., Gentile C., Lepori L., Mariani F., Mannella P., Pellegrino C., Ruccolo A., Salvatore W., Tomassini E., Ubertini F., Venanzi I., Zanini M.A. Management of road bridge networks in Italy by means of integrated SHM systems (2024) Procedia Structural Integrity, 64, pp. 40–47. American Society of Civil Engineers (ASCE). 2025 Report Card for America’s Infrastructures, 2025. Bull, L., Gardner, P., Gosliga, J., Rogers, T., Dervilis, N., Cross, E., Papatheou, E., Maguire, A., Campos, C., Worden, K. Foundations of population-based SHM, Part I: Homogeneous populations and forms, Mech. Syst. Signal Process. 148 (2021) 107145. Cuerva Navas, S., Köhler, J., Liljefors, F., Ptacek, L., Wessels, J., Darò, P., Abspoel-Bukman, L. Actual and future context of transport infrastructure monitoring and maintenance (D1.1 IM-SAFE), IM-SAFE Consortium, 2021. García-Macías, E., Hernández-González, I.A., Tomassini, E., Ubertini, F. Leveraging artificial intelligence to unlock next-generation SHM software: Advanced feature extraction and damage identification, Int. J. Bridg. Eng. Manag. Res. 2 (1) (2025) 21425007. Gardner, P., Bull, L., Gosliga, J., Dervilis, N., Worden, K. Foundations of population-based SHM, Part III: Heterogeneous populations – mapping and transfer, Mech. Syst. Signal Process. 149 (2021) 107147.http://dx.doi.org/10.1016/j.ymssp.2020.107142 Gkoumas, K., Marques Dos Santos, F., Van Balen, M., Tsakalidis, A., Ortega Hortelano, A., Grosso, M., Haq, A., Pekar, F. Research and Innovation in Bridge Maintenance, Inspection and Monitoring, Publications Office of the European Union, 2019. Gosliga, J., Gardner, P., Bull, L., Dervilis, N., Worden, K. Foundations of population-based SHM, Part II: Heterogeneous populations – graphs, networks, and communities, Mech. Syst. Signal Process. 148 (2021) 107146. López-Cuervo, A.S., García-Macías, E., Castro-Triguero, R., Chiachío, J. OSP-SAP: A MATLAB graphical user interface for optimal sensor placement using SAP2000 (2025) SoftwareX, 31, art. no. 102216. Magalhães F., Cunha A. Caetano. Dynamic monitoring of a long span arch bridge. Engineering Structures, 30:3034–3044, 11 2008. Rai, A., Ierimonti, L., Giglioni, V., Tomassini, E., Ubertini, F., Venanzi, I. A multivariate autoencoder-based anomaly detection for post earthquake diagnosis of masonry structures using long-term accelerometer and ambient temperature recordings (2026) Journal of Building Engineering, 117, art. no. 114784. Tan, J.S., Elbaz, K., Wang, Z.F., Shen, J.S., Chen, J. Lessons learnt from bridge collapse: A view of sustainable management, Sustainability 12 (3) (2020). Tomassini, E., Centofanti, G., Chellini, G., García-Macías, E., Lepori, L., Mannella, P., Salvatore, W., Ubertini, F. Key findings from long-term operational modal analysis of a landmark steel arch bridge in Italy, Structures 82 (2025) 110436. Tomassini, E., García-Macías, E., Venanzi, I., Ubertini, F. ML-Driven Operational Modal Analysis of Road Bridges: Preliminary Results, in: Lecture Notes in Civil Engineering 514 LNCE, 2024, pp. 589–599. X. Jian, Y. Xia, G. Duth´e, K. Bacsa, W. Liu, and E. Chatzi. Using graph neural networks and frequency domain data for automated operational modal analysis of populations of structures. Data-Centric Engineering, 6:e45, 2025.