Time-dependent reliability prediction of bridge components based on BO-LSTM and Gaussian-Copula theory

Abstract

In bridge health monitoring systems, there exists the dynamic nonlinear dependency of failure among the multiple monitoring points of bridge components. To investigate the impacts of this dynamic nonlinear dependency on the time-varying reliability indices of bridges, this study focuses on relevant research.It proposes a time-varying reliability prediction method for bridge components based on the monitoring data, a Bayesian optimization long short-term memory network (BO-LSTM) and Gaussian-Copula theory. The specific research contents are as follows: (1) Bridge monitoring data are first subjected to filtering, and based on the filtered monitoring signals, a BO-LSTM model is established to dynamically predict the extreme stresses of the existing bridge; (2) A trivariate Gaussian Copula model, which accounts for the dynamic nonlinear dependency of failure among three control monitoring points, is constructed to characterize the nonlinear dependencies among the monitoring data; (3) the validity of the proposed model and method is validated using monitoring data from the Fumin Bridge in Tianjin City of China. The above research results will provide the theoretical foundation and application for bridge reliability prediction and assessment.

Keywords

Bayesian optimization / Long short-term memory (LSTM) network / Copula theory / Time-varying reliability prediction

References

[1] Chen Y, Wang J, Xu Xet al.. Research on Forecast of Storm Surge Based on LSTM Model. Journal of Hohai University (Natural Science Edition), 2025, 53(05): 162-169

[2] Ching J, Beck JL. Bayesian analysis of the phase II structural health monitoring experimental benchmark data. J Eng Mech ASCE, 2004, 130(10): 1233-1244

[3] Dias A, Embrechts P. Dynamic copula models for multivariate high-frequency data in finance. Working Papers, 2004, 3(1): 1-14

[4] Fan X (2014) Reliability updating and Bayesian prediction of bridges based on proof loads and monitored data. Harbin: School of Civil Engineering, Harbin Institute of Technology

[5] Fan X, Liu Y, Lü D. Dynamic linear modeling of bridge monitored data and reliability prediction. Journal of Tongji University (Natural Science), 2016, 44(7): 1002-1009

[6] Fan X, Zhou H, Liu Y. Time-variant reliability analysis of bridge members based on Bayesian dynamic models and copula theory. Journal of Jilin University (Engineering Edition), 2023, 54(02): 485-493

[7] Frangopol DM, Strauss A, Kim SY. Use of monitoring extreme data for the performance prediction of structures: general approach. Eng Struct, 2008, 30: 3644-3653

[8] Goorbergh RWJVD, Genest C, Werker BJM. Bivariate option pricing using dynamic copula models. Insur Math Econ, 2003, 37(1): 101-114

[9] Habtemariam ET, Kekeba K, Martínez-Ballesteros Met al.. A Bayesian optimization-based LSTM model for wind power forecasting in the Adama District, Ethiopia. Energies, 2023, 16(5 2317

[10] Joe H (1997) Multivariate Models and Multivariate Dependence Concepts. Chapman & Hall/crc

[11] Liu H, Li X, Li Zet al.. Research on Prediction Method of Highway Tunnel Vault Settlement and Perimeter Convergence Based on Bayes-LSTM Algorithm. Chinese and foreign highways: 1–10 [2023-09-22]. Sklar A (1959) Fonctions de repartition a n dimensions et leurs marges. Pub Inst Statisr Univ Paris, 2023, 8: 229-231

[12] Liu Y (2015) System reliability analysis of bridge structures considering correlation of failure modes and proof modes. Harbin: School of Civil Engineering, Harbin Institute of Technology

[13] Liu Y, Fan X, Lü D. Time-Dependent Uncertainty Analysis of Structures Based on Copula Functions// International Conference on Vulnerability and Risk Analysis and Management, 2014, 2014: 1875-1887

[14] Liu Y, Xiao Q, Yang Get al.. Failure probability analysis of long-span bridges in service based on optimal R-Vine Gaussian Copula model. Journal of Tongji University (Natural Science Edition), 2021, 4905): 624-633

[15] Luo H, Li T, Xiong K. Bridge reliability calculation based on copula theory. J Civ Eng Manag, 2020, 37(04): 1-7

[16] Patton AJ. Modelling asymmetric exchange rate dependence. Int Econ Rev, 2006, 47(2): 527-556

[17] Qiu X. Neural networks and deep learning. J Chin Inf Process, 2020, 34(074

[18] Strauss A, Frangopol DM, Kim SY. Use of monitoring extreme data for the performance prediction of structures: bayesian updating. Eng Struct, 2008, 30: 3654-3666

[19] Yang R, Huang Y, Zhou W et al (2025) Life prediction of electromagnetic relays based on GWO-BiLSTM. Journal of Electronic Measurement and Instruments. 1–12 [2025–09–28]

[20] Zhang L, Feng D, Wu G. Dynamic vehicle load identification method based on LSTM network. Journal of Southeast University (Natural Science Edition), 2023, 5302): 187-192

[21] Zhao Q, Liu Y, Fan X. Bridge reliability assessment method considering failure nonlinear dependence based on kernel recursive adaptive filtering and generalized Nataf transformation. Struct, 2025, 79 109539

Funding

Fundamental Research Funds for the Central Universities(lzujbky-2025-05)

National Natural Science Foundation of China(51608243)

RIGHTS & PERMISSIONS

The Author(s)