Hybrid Approach for Supervised Machine Learning Algorithms to Identify Damage in Bridges
Publication: Journal of Bridge Engineering
Volume 29, Issue 8
Abstract
In bridges, monitoring data usually correspond to normal operational and environmental conditions, resulting in a lack of damage-related data. For this reason, machine learning algorithms for damage detection are typically unsupervised. Conversely, numerical models are employable as surrogates for extreme events rarely encountered during the existence of a bridge and for common damage scenarios, enabling the training of supervised machine learning algorithms. In this paper, hybrid data obtained by integrating monitoring and numerical observations from the Z-24 Bridge benchmark are used for training supervised machine learning algorithms to classify damage. Special attention is dedicated to the numerical model that, while being simple enough to be used on thousands of runs, must capture the complex nonlinear behavior that typifies damaged conditions. A model updating technique is used for the preliminary calibration of the finite-element model. Numerical data are generated in a probabilistic manner starting from the initial finite-element model, assuming the Gaussian distribution of the uncertain parameters. Three undamaged scenarios and three damaged scenarios are modeled. Subsequently, several supervised learning classifiers are trained with the same hybrid database and a comparative summary of their effectiveness is presented. The paper introduces a novel soft classification method that accounts for the overlapping of observations belonging to different structural conditions in the feature space. This study proves that data generated from probabilistic-based finite-element models can be used for structural health monitoring and damage identification in the context of bridges, therefore providing a hybrid supervised approach that can be easily applied in practice.
Practical Applications
Because bridges are one-of-a-kind, expensive structures, considerable efforts are made to ensure they remain in service for as long as possible. Consequently, monitoring systems are being installed on more and more bridges. However, monitoring data are usually related to healthy states of the structure rather than damage occurrences. Therefore, digital replicas can be employed to simulate damage scenarios that may occur in the lifespan of a bridge. Hybrid data can be obtained by blending monitoring data with simulated data from the same bridge. This paper illustrates the construction of such a hybrid database, which covers a wide range of possible scenarios for a well-known bridge benchmark. This hybrid database is then used to train machine learning algorithms to distinguish between various changes in the dynamic behavior of the bridge as a way to evaluate the condition of the structure and identify damage. In practice, the hybrid approach can be implemented on monitored bridges to raise flags when flaws are detected, to localize and evaluate the severity of damage, and even to make a prognosis on the remaining life of the bridge.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data, models, or codes that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The authors thank Computers and Structures Inc. for the license of CSi Bridge used to generate the numerical models of the Z-24 Bridge and the Fundação para a Ciência e a Tecnologia for providing financial support through project UIDB/04625/2020. This research was partially supported by project 38 PFE in the frame of the PDI-PFE-CDI 2021 program.
References
Barthorpe, R. 2010. “On model- and data-based approaches to structural health monitoring.” Ph.D. thesis, Dept. of Mechanical Engineering, Univ. of Sheffield.
Bishop, C. M. 2006. Pattern recognition and machine learning. New York: Springer.
Buckley, T., B. Ghosh, and V. Pakrashi. 2023. “A feature extraction & selection benchmark for structural health monitoring.” Struct. Health Monit. 22 (3): 2082–2127. https://doi.org/10.1177/14759217221111141.
Bud, M. A., I. Moldovan, L. Radu, M. Nedelcu, and E. Figueiredo. 2022. “Reliability of probabilistic numerical data for training machine learning algorithms to detect damage in bridges.” Struct. Control Health Monit. 29 (7): 1–24. https://doi.org/10.1002/stc.2950.
CSI (Computers & Structures Inc.). 2016. CSI analysis reference manual for SAP2000, ETABS, SAFE and CSiBridge. Berkeley, CA: CSI.
Fernandez-Navamuel, A., D. Zamora-Sánchez, Á. J. Omella, D. Pardo, D. Garcia-Sanchez, and F. Magalhães. 2022. “Supervised deep learning with finite element simulations for damage identification in bridges.” Eng. Struct. 257 (February): 114016. https://doi.org/10.1016/j.engstruct.2022.114016.
Figueiredo, E., and J. Brownjohn. 2022. “Three decades of statistical pattern recognition paradigm for SHM of bridges.” Struct. Health Monit. 21: 3018–3054. https://doi.org/10.1177/14759217221075241.
Figueiredo, E., and E. Cross. 2013. “Linear approaches to modeling nonlinearities in long-term monitoring of bridges.” J. Civ. Struct. Health Monit. 3 (3): 187–194. https://doi.org/10.1007/s13349-013-0038-3.
Figueiredo, E., I. Moldovan, and M. B. Marques. 2013. Condition assessment of bridges: Past, present and future—A complementary approach. Lisbon, Portugal: Univ. Catolica Editora.
Figueiredo, E., I. Moldovan, A. Santos, P. Campos, and J. C. W. A. Costa. 2019. “Finite element–based machine-learning approach to detect damage in bridges under operational and environmental variations.” J. Bridge Eng. 24 (7): 04019061. https://doi.org/10.1061/(asce)be.1943-5592.0001432.
Figueiredo, E., M. Omori Yano, S. da Silva, I. Moldovan, and M. Adrian Bud. 2023. “Transfer learning to enhance the damage detection performance in bridges when using numerical models.” J. Bridge Eng. 28 (1): 04022134. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001979.
Figueiredo, E., G. Park, C. R. Farrar, K. Worden, and J. Figueiras. 2011. “Machine learning algorithms for damage detection under operational and environmental variability.” Struct. Health Monit. 10 (6): 559–572. https://doi.org/10.1177/1475921710388971.
Freund, Y., and R. E. Schapire. 1997. “A decision-theoretic generalization of on-line learning and an application to boosting.” J. Comput. Syst. Sci. 55 (1): 119–139. https://doi.org/10.1006/jcss.1997.1504.
Friedman, J., T. Hastie, and R. Tibshirani. 2000. “Additive logistic regression: A statistical view of boosting (with discussion and a rejoinder by the authors).” Ann. Stat. 28: 337–407. https://doi.org/10.1214/aos/1016218223.
Giagopoulos, D., A. Arailopoulos, V. Dertimanis, C. Papadimitriou, E. Chatzi, and K. Grompanopoulos. 2019. “Structural health monitoring and fatigue damage estimation using vibration measurements and finite element model updating.” Struct. Health Monit. 18 (4): 1189–1206. https://doi.org/10.1177/1475921718790188.
Hastie, T., R. Tibshirani, and J. Friedman. 2009. The elements of statistical learning. New York: Springer.
Krämer, C. 1999. Brite EuRam projects SIMCES, task A1 and A2: Long term monitoring and bridge test. Technical Rep. 168’349/21. Dübendorf, Switzerland: Swiss Federal Laboratories for Materials Testing and Research (EMPA).
Manning, C. D., P. Raghavan, and H. Schütze. 2008. Introduction to information retrieval. Cambridge, UK: Cambridge University Press.
Mirzaee, A., R. Abbasnia, and M. Shayanfar. 2015. “A comparative study on sensitivity-based damage detection methods in bridges.” Shock Vib. 2015: 120630. https://doi.org/10.1155/2015/120630.
Peeters, B., and G. De Roeck. 1999. “Reference based stochastic subspace identification for output-only modal analysis.” Mech. Syst. Sig. Process. 13 (6): 855–878. https://doi.org/10.1006/mssp.1999.1249.
Peeters, B., and G. De Roeck. 2001. “One-year monitoring of the Z24-bridge: Environmental effects versus damage events.” Earthquake Eng. Struct. Dyn. 30: 149–171.https://doi.org/<149::AID-EQE1>3.0.CO;2-Z.
Reynders, E., G. Wursten, and G. De Roeck. 2014. “Output-only structural health monitoring in changing environmental conditions by means of nonlinear system identification.” Struct. Health Monit. 13 (1): 82–93. https://doi.org/10.1177/1475921713502836.
Rytter, A. 1993. “Vibrational based inspection of civil engineering structures.” Ph.D. thesis, Dept. of Building Technology and Structural Engineering, Aalborg Univ.
Santos, A., E. Figueiredo, M. F. M. Silva, C. S. Sales, and J. C. W. A. Costa. 2016. “Machine learning algorithms for damage detection: Kernel-based approaches.” J. Sound Vib. 363: 584–599. https://doi.org/10.1016/j.jsv.2015.11.008.
Schapire, R. E., Y. Freund, P. Bartlett, and S. Lee. 1998. “Boosting the margin: A new explanation for the effectiveness of voting methods.” Ann. Stat. 26 (5): 1651–1686.
Seventekidis, P., and D. Giagopoulos. 2021. “A combined finite element and hierarchical deep learning approach for structural health monitoring: Test on a pin-joint composite truss structure.” Mech. Syst. Sig. Process. 157: 107735. https://doi.org/10.1016/j.ymssp.2021.107735.
The MathWorks Inc. 2022. MATLAB version 9.13.0.2080170 (R2022b). Natick, MA: The MathWorks Inc.
Zhang, Z., and C. Sun. 2021. “Structural damage identification via physics-guided machine learning: A methodology integrating pattern recognition with finite element model updating.” Struct. Health Monit. 20 (4): 1675–1688. https://doi.org/10.1177/1475921720927488.
Information & Authors
Information
Published In
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Jun 25, 2023
Accepted: Mar 8, 2024
Published online: Jun 4, 2024
Published in print: Aug 1, 2024
Discussion open until: Nov 4, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.