A Bayesian dynamic linear model (BDLM) framework for data modeling and forecasting is proposed to evaluate the performance of an operational cable-stayed bridge, that is, Ting Kau Bridge in Hong Kong, by using SHM strain field data acquired. One of the major challenges in dealing with the existing in-service bridge under extreme typhoon loads is to forecast structural behavior using the typhoon response exhibiting non-stationarity, large data fluctuations and strong randomness. The first attempt for SHM data modeling during extreme events, that is, typhoons, using BDLM framework, was conducted in this study. The data from multiple sensors are analyzed for one-step, multi-step ahead forecasting and missing data imputation. The overall bridge behavior is incorporated into a forecasting model by superposition of forecasting results of trend (representing the structural baseline response), periodic component (response component evolving regularly over time), and autoregressive component (time-dependent error) through BDLM algorithm. The results demonstrate that the BDLM framework yielded more accurate calculations compared with Gaussian process and Variational Heteroscedasticity Gaussian Process methods with respect to one-step ahead forecasting for strain data under typhoons. Multi-step ahead forecasting was successfully carried out both for non-typhoon and typhoon responses within an acceptable precision range. The correlation between periodic component and temperature was also investigated. Regarding missing data imputation, BLDM algorithm can generate robust results due to making full use of the monitoring data both before and after the missing segments.
GuoYKareemANiY, et al.Performance evaluation of Canton tower under winds based on full-scale data. J Wind Eng Ind Aerodyn2012; 104: 116–128.
2.
LiSYiJ. Monitoring of dynamic behaviour of super-tall buildings during typhoons. Struct Infrastruct Eng2016; 12(3): 289–311.
3.
SuJZXiaYZhuLD, et al.Typhoon- and temperature-induced quasi-static responses of a supertall structure. Eng Structures2017; 143: 91–100.
4.
WanHPNiYQ. Bayesian multi-task learning methodology for reconstruction of structural health monitoring data. Struct Health Monit2019; 18(4): 1282–1309.
5.
YangYNagarajaiahS. Harnessing data structure for recovery of randomly missing structural vibration responses time history: Sparse representation versus low-rank structure. Mech Syst Signal Process2016; 74: 165–182.
6.
ChenZLiHBaoY. Analyzing and modeling inter-sensor relationships for strain monitoring data and missing data imputation: a copula and functional data-analytic approach. Struct Health Monit2019; 18(4): 1168–1188.
7.
KuokSCYuenKV. Model-free data reconstruction of structural response and excitation via sequential broad learning. Mech Syst Signal Process2016; 141: 106738.
8.
ParkGInmanDJ. Structural health monitoring using piezoelectric impedance measurements. Phil Trans R Soc A : Math Phys Eng Sci2007; 365(1851): 373–392.
9.
BernalDZontaDPozziM. ARX residuals in damage detection. Struct Control Health Monit2012; 19(4): 535–547.
10.
BornnLFarrarCRParkG, et al.Structural health monitoring with autoregressive support vector machines. J Vibration Acoust2009; 131(2): 021004.
11.
WanHPNiYQ. Bayesian modeling approach for forecast of structural stress response using structural health monitoring data. J Struct Eng2018; 144(9): 04018130.
12.
RenPChenXSunL, et al.Incremental Bayesian matrix/tensor learning for structural monitoring data imputation and response forecasting. Mech Syst Signal Process2021; 158: 107734.
13.
XuYL. SHM-based fatigue damage prognosis for long-span cable-supported bridges under multiple dynamic loadings. In: Proceeding of 8th International Conference on Bridge Maintenance, Safety and Management (IABMAS), Foz do Iguacu, Brazil, 26–30 June 2016, 2016, pp. 129–142.
14.
ZhangRChenZChenS, et al.Deep long short-term memory networks for nonlinear structural seismic response prediction. Comput Structures2019; 220: 55–68.
15.
ZhangRLiuYSunH. Physics-informed multi-LTSM networks for metamodeling of nonlinear structures. Comp Methods Appl Mech Eng2020; 369: 113226.
16.
MylonasCAbdallahIChatziE. Deep unsupervised learning for condition monitoring and prediction of high dimensional data with application on windfarm SCADA data. Model Validat Uncertain Quantificat2020; 3: 189–196.
17.
LiMX. Recognition method of non-stationary mechanical vibration signal based on convolution neural network. In: 5th International Conference on Smart Grid and Electrical Automation (ICSGEA), Zhangjiajie, China, 13–14 June 2020, 2020, pp. 217–221.
18.
ZhangYLWangYCLuoGM. A new optimization algorithm for non-stationary time series prediction based on recurrent neural networks. Future Generat Comp Syst Intern J Escience2020; 102: 738–745.
19.
ChengXTXuKSunJ, et al.Adaptive grouping sparse Bayesian learning for channel estimation in non-stationary uplink massive MIMO systems. IEEE Trans Wireless Commun2019; 18(8): 4184–4198.
20.
DingSWangL. A sparse bayesian learning based scheme for multi-movement recognition using sEMG. Australas Phys Eng Sci Med2016; 39(1): 59–69.
21.
Lázaro-GredillaMMichalisK. Variational heteroscedastic Gaussian process regression. In: Appearing in Proceedings of the 28th International Conference on Machine Learning, Bellevue, WA, USA, 28 June–2 July 2011, 2011.
22.
KouPLiangDGaoL, et al.Probabilistic electricity price forecasting with variational heteroscedastic Gaussian process and active learning. Energ Convers Manag2015; 89: 298–308.
23.
WangQANiYQ. Measurement and forecasting of high-speed rail track slab deformation under uncertain SHM data using variational heteroscedastic gaussian process. Sensors2019; 19(15): 3311.
24.
BaiQLiuZXHanJJ, et al.Application of wavelet transform in stochastic loading characteristics analysis. In: International Conference on Advanced Engineering Materials and Architecture Science. ICAEMAS, Hohhot, China, 26-27 July 2014, pp. 662–665.
25.
ZhangRHHuLQFanW, et al.Application of wavelet transform with tunable Q-factor to analysis of non-stationary harmonics. In: International Conference on Mechanical Engineering and Instrumentation (ICMEI), Brisbane, Australia, 31 December 2013-2 January 2014, pp. 182–186.
26.
SolhjellIK. Bayesian Forecasting and Dynamic Models Applied to Strain Data from the Göta River Bridge. Oslo, Norway: University of Oslo, 2009.
27.
GouletJA. Bayesian dynamic linear models for structural health monitoring. Struct Control Health Monit2017; 24(12): 1–18.
28.
GouletJAKooK. Empirical validation of Bayesian dynamic linear models in the context of structural health monitoring. J Bridge Eng2017; 23(2): 05017017.
29.
NguyenLHGouletJA. Anomaly detection with the Switching Kalman Filter for structural health monitoring. Struct Control Health Monit2018; 25: e2136.
30.
WangYW. Bayesian-Based Methodology for Progressive Structural Health Evaluation and Prediction by Use of Monitoring Data. Hong Kong: The Hong Kong Polytechnic University, 2017.
31.
SantosASantosRSilvaM, et al.A global expectation-maximization approach based on memetic algorithm for vibration-based structural damage detection. IEEE Trans Instrument Meas2017; 66(4): 661–670.
32.
YeXWDingYWanHP. Statistical evaluation of wind properties based on long-term monitoring data. J Civil Struct Health Monit2020; 10(5): 987–1000.
33.
Avendano-ValenciaLDChatziEN. Multivariate GP-VAR models for robust structural identification under operational variability. Probabilistic Eng Mech2020; 60: 103035.
34.
FanXP. Bridge extreme stress prediction based on Bayesian dynamic linear models and non-uniform sampling. Struct Health Monit2017; 16: 253–261.
35.
LiuYXiaoQFanX. Cubic function-based Bayesian dynamic linear prediction approach of bridge extreme stress. Adv Mater Sci Eng2017; 2017: 7460378.
36.
MaZYunCBShenYB, et al.Bayesian forecasting approach for structure response prediction and load effect separation of a revolving auditorium. Smart Structures Syst2019; 24(4): 507–524.
37.
WangYWNiYQ. Bayesian dynamic forecasting of structural strain response using structural health monitoring data. Struct Control Health Monit2020; 27(8): e2575.
38.
WestMHarrisonJ. Bayesian Forecasting and Dynamic Models. New York: Springer, 1997.
39.
NguyenLHGaudotIKhazaeliS, et al.A kernel-based method for modeling non-harmonic periodic phenomena in Bayesian dynamic linear models. Front Built Environ2019; 5: 8.
40.
WangHZhangYMMaoJX, et al.Modeling and forecasting of temperature-induced strain of a long-span bridge using an improved Bayesian dynamic linear model. Eng Structures2019; 192: 220–232.
41.
MenzeraOMoffataAMMeiringbW, et al.Random errors in carbon and water vapor fluxes assessed with Gaussian Processes. Agric For Meteorol2013; 178–179: 161–172.
