Condition transfer between prestressed bridges using structural state translation for structural health monitoring

Abstract

Implementing Structural Health Monitoring (SHM) systems with extensive sensing layouts on all civil structures is obviously expensive and unfeasible. Thus, estimating the state (condition) of dissimilar civil structures based on the information collected from other structures is regarded as a useful and essential way. For this purpose, Structural State Translation (SST) has been recently proposed to predict the response data of civil structures based on the information acquired from a dissimilar structure. This study uses the SST methodology to translate the state of one bridge (Bridge #1) to a new state based on the knowledge acquired from a structurally dissimilar bridge (Bridge #2). Specifically, the Domain-Generalized Cycle-Generative (DGCG) model is trained in the Domain Generalization learning approach on two distinct data domains obtained from Bridge #1; the bridges have two different conditions: State-H and State-D. Then, the model is used to generalize and transfer the knowledge on Bridge #1 to Bridge #2. In doing so, DGCG translates the state of Bridge #2 to the state that the model has learned after being trained. In one scenario, Bridge #2’s State-H is translated to State-D; in another scenario, Bridge #2’s State-D is translated to State-H. The translated bridge states are then compared with the real ones via modal identifiers and mean magnitude-squared coherence (MMSC), showing that the translated states are remarkably similar to the real ones. For instance, the modes of the translated and real bridge states are similar, with the maximum frequency difference of 1.12% and the minimum correlation of 0.923 in Modal Assurance Criterion values, as well as the minimum of 0.947 in Average MMSC values. In conclusion, this study demonstrates that SST is a promising methodology for research with data scarcity and population-based structural health monitoring (PBSHM). In addition, a critical discussion about the methodology adopted in this study is also offered to address some related concerns.

Keywords

Structural state translation / Structural health monitoring / Domain generalization / Population-based structural health monitoring / Generative adversarial networks

References

[1] Albuquerque, I., Monteiro, J., Darvishi, M., et al. (2019). Generalizing to unseen domains via distribution matching. arXiv

[2] Avci, O., Abdeljaber, O., Kiranyaz, S., Inman, D. (2017). Structural damage detection in real time: implementation of 1D convolutional neural networks for SHM applications. In: C. Niezrecki (Ed.), Structural Health Monitoring & Damage Detection, vol 7. Conference Proceedings of the Society for Experimental Mechanics Series. Springer: Cham. https://doi.org/10.1007/978-3-319-54109-9_6

[3] Ben-David, J, Blitzer, J., Crammer, K., Pereira F. (2007). Analysis of representations for domain adaptation. in NIPS 19.

[4] G. Blanchard, G. Lee, C. Scott (2011) Generalizing from several related classification tasks to a new unlabeled sample. in NeurIPS

[5] Catbas, F.N., Ciloglu, S.K., Hasancebi, O., Aktan, A.E. (2002). Fleet Strategies for Condition Assessment and Its Application for Re-qualification of Pennsylvania’s Aged T-beam Bridges. Paper No. 02-3890. In Proceedings of the 80th Annual Meeting of Transportation Research Board, TRB, Washington DC

[6] CatbasF, CilogluS, AktanA. Strategies for load rating of infrastructure populations: A case study on T-beam bridges. Structure and Infrastructure Engineering, 2005, 1: 221-238

[7] CatbasFN, GokceHB, GulM. Practical approach for estimating distribution factor for load rating: Demonstration on reinforced concrete T-beam bridges. Journal of Bridge Engineering, 2012, 17: 652-661

[8] CatbasFN, LuleciF, ZakariaM, et al.. Extended reality (XR) for condition assessment of civil engineering structures: A literature review. Sensors, 2022, 22: 9560

[9] CatbasFN, MalekzadehM. A machine learning-based algorithm for processing massive data collected from the mechanical components of movable bridges. Automation in Construction, 2016, 72: 269-278

[10] DebeesM, LuleciF, CatbasFN. Effect of structural repairs on the load rating and reliability of a prestressed concrete bridge. Advances in Bridge Engineering, 2023, 4: 8

[11] de Bézenac, E., Ayed, I., Gallinari, P. (2019). Optimal unsupervised domain translation. arXiv.

[12] Delo, G., Bunce, A., Cross, E.J., et al. (2023). When is a bridge not an aeroplane? Part II: A Population of Real Structures. pp 965–974

[13] Deshmukh, A.A., Lei, Y., Sharma, S., et al. (2019). A genealization error boundfor multi-class domain generalization. arXiv

[14] DongC, BasS, DebeesM, et al.. Bridge load testing for identifying live load distribution load rating serviceability and dynamic response. Frontiers in Built Environment, 2020

[15] Gosliga J, Gardner P, Bull LA, et al (2021a) Towards population-based structural health monitoring, Part III: Graphs, Networks and Communities. (pp 255–267)

[16] Gosliga)J, GardnerPA, BullLA, et al.. Foundations of Population-based SHM, Part II: Heterogeneous populations—Graphs, networks, and communities. Mechanical Systems and Signal Processing, 2021, 148: 107144

[17] GosligaJ, HesterD, WordenK, BunceA. On Population-based structural health monitoring for bridges. Mechanical Systems and Signal Processing, 2022, 173: 108919

[18] Von Haza-Radlitz, G. C, K. P, et al. (2000). Information Technology Issues In Fleet Health Monitoring. In: Paper Invited for Workshop on Present and Future of Health Monitoring, Bauhaus University, Aedificatio Publishers, D-79104 Freiburg, 2000. pp 173–190

[19] Heusel, M., Ramsauer, H., Unterthiner, T., et al. (2017). GANs trained by a two time-scale update rule converge to a local nash equilibrium, 31st Conference on Neural Information Processing Systems (NIPS2017), LongBeach: CA, USA

[20] Hu, W., Li, M., Ju, X. (2021). Improved cycleGAN for image-to-image translation

[21] Li, Y., Gong, M., Tian, X., et al. (2018). Domain generalization via conditional invariant representation

[22] Lu, W., Wang, J., Li, H., et al. (2022). Domain-invariant feature exploration for domain generalization

[23] Luleci F, Catbas FN (2022) Structural state translation: Condition transfer between civil structures using domain-generalization for structural health monitoring.

[24] Luleci, F., AlGadi, A., Debees, M., et al. (2022a). Investigation of Comparative Analysis of a Multi-Span Prestressed Concrete Highway Bridge. In: Bridge Safety, Maintenance, Management, Life-Cycle, Resilience and Sustainability. CRC Press, London, pp 1433–1437

[25] LuleciF, AvciO, CatbasFN. Improved undamaged-to-damaged acceleration response translation for structural health monitoring. Engineering Applications of Artificial Intelligence, 2023

[26] LuleciF, CatbasFN, AvciO. Generative adversarial networks for labeled acceleration data augmentation for structural damage detection. Journal of Civil Structural Healgth Monitoring, 2021

[27] LuleciF, CatbasFN, AvciO. A literature review: Generative adversarial networks for civil structural health monitoring. Frontiers in Built Environment, 2022

[28] LuleciF, CatbasFN, AvciO. CycleGAN for undamaged-to-damaged domain translation for structural health monitoring and damage detection. Mechanical Systems and Signal Processing, 2023

[29] MalekzadehM, AtiaG, CatbasFN. Performance-based structural health monitoring through an innovative hybrid data interpretation framework. Journal of Civil Structural Healgth Monitoring, 2015, 5: 287-305

[30] Muandet, K., Balduzzi, D., Scholkopf, B. (2013). Domain generalization via invariant feature representation. in ICML

[31] van OverscheeP, de MoorB. Subspace algorithms for the stochastic identification problem. Automatica, 1993, 29: 649-660

[32] Shen, Z., Liu, J., He, Y., et al. (2021). Towards out-of-distribution generalization: a survey. arXiv

[33] WickramarachchiCT, PooleJ, CrossEJ, WordenK. On aspects of geometry in SHM and population-based SHM, 2022 Cham Springer 67-77

[34] WordenK, BullLA, GardnerP, et al.. A brief introduction to recent developments in population-based structural health monitoring. Frontiers in Built Environment, 2020

[35] Yang, J., Zhou, K., Li, Y., Liu, Z. (2021a). Generalized out-of-distribution detection: A survey. arXiv

[36] YangKD, BelyaevaA, VenkatachalapathyS, et al.. Multi-domain translation between single-cell imaging and sequencing data using autoencoders. Nature Communications, 2021, 12: 31

[37] Ye, H., Xie, C., Cai, T., et al. (2021). Towards a theoretical framework of out-of-distribution generalization. arXiv

[38] Zhou, K., Liu, Z., Qiao, Y., et al. (2021). Domain Generalization: A survey. https://doi.org/10.1109/TPAMI.2022.3195549

[39] Zhu, J.-Y., Park, T., Isola, P., Efros, A.A. (2017) Unpaired image-to-image translationusing cycle-consistent adversarial networks. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2242-2251. https://doi.org/10.1109/ICCV.2017.244

[40] ZhuangY, QinJ, ChenB, et al.. Data loss reconstruction method for a bridge weigh-in-motion system using generative adversarial networks. Sensors, 2022, 22: 858

Funding

Division of Civil, Mechanical and Manufacturing Innovation(1463493); National Academy of Engineering(IDEA Project 222); National Aeronautics and Space Administration(80NSSC20K0326)