PSI - Issue 62

Israel Alejandro Hernández-González et al. / Procedia Structural Integrity 62 (2024) 879–886 Hernández-González/ Structural Integrity Procedia 00 (2019) 000 – 000

886

8

was adopted. The main purpose of the modal tracking algorithm is to match the identified poles with the modal reference baseline previously reported in Table 1. To achieve this, the poles extracted after each identification are compared to the reference baseline, retaining those that meet a set of threshold criteria, including relative differences in terms of frequency of 0.10 and MAC values of 0.60. The identified time series of resonant frequencies are depicted in Fig. 5. The modal tracking approach eliminated only a limited number of residual spurious/mathematical poles, with most of the identified modes meeting the tracking thresholds. This resulted in identification success ratios exceeding 90% across all the modes. For comparison purposes, the identification results extracted by automated CoV SSI are also included, employing the same identification parameters as in the previous section. The presence of certain oscillations induced by variations in environmental conditions is noticeable, as depicted in the zoom views in Fig. 5. The proposed AI-driven BSS model showcases remarkable versatility and applicability, particularly in the context of the Méndez-Núñez Bridge. Its notable strengths lie in its ability to identify structural modes while imposing minimal computational demands and requiring limited human intervention swiftly and automatically. Acknowledgements This work has been supported by the Spanish Ministry of Science and Innovation through the research project “ BRIDGEXT - Life-extension of ageing bridges: Towards a long-term sustainable Structural Health Monitoring ” (Ref. PID2020-116644RB-I00). F. Ubertini also acknowledges support by the Italian Ministry of Education, University and Research (MIUR) through the funded proje ct of national interest “TIMING – Time evolution laws for IMproving the structural reliability evaluation of existING post- tensioned concrete deck bridges” (Protocol No. P20223Y947) and support by FABRE – “Research consortium for the evaluation and monitor ing of bridges, viaducts and other structures” (www.consorziofabre.it/en) through the project ”SAFOTEB - a reviewed safety format for structural reliability assessment of post- tensioned concrete bridges”. Any opinion expressed in the paper does not necessarily reflect the view of the funders. References Aapo, H., & Oja, E. (2000). Independent component analysis: algorithms and applications. Neural Networks , 13 (4 – 5), 411 – 430. AlHamaydeh, M., & Ghazal Aswad, N. (2022). Structural health monitoring techniques and technologies for large-scale structures: Challenges, limitations, and recommendations. Practice Periodical on Structural Design and Construction , 27 (3), 3122004. Calvi, G. M., Moratti, M., O’Reilly, G. J., Scattarreggia, N., Monteiro, R., Malomo, D., C alvi, P. M., & Pinho, R. (2019). Once upon a time in Italy: The tale of the Morandi Bridge. Structural Engineering International , 29 (2), 198 – 217. Chen, C., Carlson, D., Gan, Z., Li, C., & Carin, L. (2016). Bridging the gap between stochastic gradient MCMC and stochastic optimization. Artificial Intelligence and Statistics , 1051 – 1060. Giglioni, V., Venanzi, I., Poggioni, V., Milani, A., & Ubertini, F. (2023). Autoencoders for unsupervised real-time bridge health assessment. Computer-Aided Civil and Infrastructure Engineering , 38 (8), 959 – 974. Hao, S. (2010). I-35W bridge collapse. Journal of Bridge Engineering , 15 (5), 608 – 614. Liu, D., Bao, Y., & Li, H. (2023). Machine learning-based stochastic subspace identification method for structural modal parameters. Engineering Structures , 274 , 115178. Masciotta, M. G., & Pellegrini, D. (2022). Tracking the variation of complex mode shapes for damage quantification and localization in structural systems. Mechanical Systems and Signal Processing , 169 , 108731. McNeill, S. I., & Zimmerman, D. C. (2008). A framework for blind modal identification using joint approximate diagonalization. Mechanical Systems and Signal Processing , 22 (7), 1526 – 1548. Rosso, M. M., Aloisio, A., Cirrincione, G., & Marano, G. C. (2023). Subspace features and statistical indicators for neural network-based damage detection. Structures , 56 , 104792. Shim, H. B., Park, H. S., & others. (2023). SSI-LSTM network for adaptive operational modal analysis of building structures. Mechanical Systems and Signal Processing , 195 , 110306. Shu, J., Zhang, C., Gao, Y., & Niu, Y. (2023). A multi-task learning-based automatic blind identification procedure for operational modal analysis. Mechanical Systems and Signal Processing , 187 , 109959. Xu, Y., Brownjohn, J. M. W., & Hester, D. (2019). Enhanced sparse component analysis for operational modal identification of real-life bridge structures. Mechanical Systems and Signal Processing , 116 , 585 – 605. Yang, Y., & Nagarajaiah, S. (2013). Time-frequency blind source separation using independent component analysis for output-only modal identification of highly damped structures. Journal of Structural Engineering , 139 (10), 1780 – 1793. Zhou, W., & Chelidze, D. (2007). Blind source separation based vibration mode identification. Mechanical Systems and Signal Processing , 21 (8), 3072 – 3087.