Objective Accurate prediction of deflection variation holds significant importance for bridge operation and maintenance. The complex and nonlinear dynamic characteristics of bridge deflection consistently challenge traditional prediction models, as hysteresis in the deflection response and interference from irregular waveforms in historical monitoring data reduce prediction accuracy. This study proposes a deflection separation-prediction model for bridges by integrating wavelet optimization and long short-term memory networks to capture multi-scale features of deflection signals and account for external influences. Methods Firstly, an Internet of Things monitoring system was employed to investigate the deflection behavior of in-service bridges. Focusing on the Xiongshang High-speed Railway Bridge over the Daguang Expressway, sensors installed on the structure were utilized to record variations in deflection, dynamic load, and temperature. Secondly, given the decoupling of different deflection components across multiple time scales, a wavelet-based optimization approach was applied to decompose historical monitoring data into trend deflection generated by prestress loss and noise deflection induced by external influences such as temperature and dynamic loads. Thirdly, based on the decomposed deflection components and the associated external factors, two LSTM-based time series prediction models were developed, including a multi-factor model for noise deflection and a single-factor model for trend deflection. Vehicle load, temperature, and noise deflection served as the inputs for the noise model, while trend deflection was used as the sole input for the trend model. Separate predictions were conducted, and the final cumulative bridge deflection was obtained by summing both predicted components based on the principle of time series superposition. Traditional models were adopted for comparison across short-term, medium-term, and long-term periods to evaluate prediction accuracy. Prediction performance was assessed using three metrics: correlation coefficient (R), root mean square error (ERMS), and mean absolute error (EMA). Fourthly, a comparative analysis was performed between the proposed model and the single LSTM prediction model to demonstrate the necessity of the combined model for forecasting bridge deflection. Fifthly, in order to verify the necessity of incorporating external factors, the proposed model was compared to a time series model including a single external factor and another excluding external influences, emphasizing differences in prediction accuracy. Sixthly, the maximal information coefficient was introduced to identify the dominant factors affecting noise deflection by analyzing its correlation with temperature and dynamic load. Results and Discussions 1) Comparison of the prediction results for short-term, medium-term, and long-term periods with the BP neural network and LSSVM models showed that the prediction accuracy for all three models remained similar in the short and medium periods. However, in the long-term deflection prediction, the DWT‒LSTM-based bridge deflection separation model achieved the highest accuracy and demonstrated stronger generalization ability, with correlation coefficients of 0.86 and 0.77, ERMS of 2.18 and 2.20 mm, and mean absolute errors (EMA) of 2.05 and 1.91 mm. In contrast, the LSSVM model produced ERMS values of 2.82 and 3.52 mm, with EMA values of 2.45 and 3.13 mm. The BP neural network produced ERMS values of 3.06 and 3.53 mm, with EMA values of 2.89 and 3.24 mm. Compared to the LSSVM model, the DWT‒LSTM deflection separation model reduced ERMS by 22.70% and 37.50% and reduced EMA by 39.26% and 38.98%. Compared to the BP neural network, the DWT‒LSTM deflection separation model reduced ERMS by 28.76% and 37.68% and reduced EMA by 29.07% and 41.05%. 2) Compared to the DWT‒LSTM deflection separation model, the prediction accuracy decreased when the single LSTM model was used. The ERMS reached 3.74 mm, and the EMA reached 3.45 mm. These relatively large deviations indicated that this model had limited suitability for bridge deflection prediction. 3) Compared to the time series models that considered only temperature, only vehicle load, or excluded external factors, the model that excluded external factors exhibited the lowest prediction accuracy, with ERMS of 3.91 mm and EMA of 3.38 mm. Among the models that considered a single external factor, the time series model that considered load showed higher prediction accuracy, with ERMS of 2.81 mm and EMA of 2.65 mm, outperforming the temperature-only model, which had ERMS of 2.97 mm and EMA of 2.83 mm. In contrast, the DWT‒LSTM deflection separation model achieved the highest accuracy, with ERMS of only 2.18 mm and EMA of only 2.05 mm. 4) Analysis of the dominant factors that influenced noise deflection using the Maximal Information Coefficient (MIC) showed correlation coefficients of 0.35 for temperature and 0.51 for load, indicating that vehicle load has a greater impact on noise deflection than temperature. Conclusions This study presents a DWT‒LSTM-based bridge deflection separation prediction model that is suitable for predicting long-term deflection variation patterns. Compared to traditional prediction models, the proposed model shows higher accuracy, reduced errors, and improved capability in addressing time-lag effects, providing a new approach and method for long-term bridge deflection prediction.
LiHui, BaoYuequan, LiShunlong,et al.Data science and engineering for structural health monitoring[J].Engineering Mechanics,2015,32(8):1‒7. doi:10.6052/j.issn.1000-4750.2014.08.st11
ChenShuyang, XuLinrong, CaoLulai.Prediction of subsidenceof high-speed railway considering regional subsidence using dynamic neural network method[J].Journal of the China Railway Society,2015,37(5):83‒87. doi:10.3969/j.issn.1001-8360.2015.05.014
Editoral Department of China Journal of Highway and Transport.Review on China's bridge engineering research:2021[J].China Journal of Highway and Transport,2021,34(2):1‒97. doi:10.1111/sdi.12950
ZhuSiyu, YangMengxue, XiangTianyu,et al.Advanced time-series prediction of bridge long-term deflection using the learning models[J].Structures,2024,67:106967. doi:10.1016/j.istruc.2024.106967
[8]
JuHanwen, ShiHuaiyuan, ShenWeicheng,et al.An accurate and low-cost vehicle-induced deflection prediction framework for long-span bridges using deep learning and monitoring data[J].Engineering Structures,2024,310:118094. doi:10.1016/j.engstruct.2024.118094
[9]
YueZixiang, DingYouliang, ZhaoHanwei.Deep learning-based minute-scale digital prediction model of temperature-induced deflection of a cable-stayed bridge:Case study[J].Journal of Bridge Engineering,2021,26(6):05021004. doi:10.1061/(asce)be.1943-5592.0001716
[10]
WangManya, DingYouliang, ZhaoHanwei.Digital prediction model of temperature-induced deflection for cable-stayed bridges based on learning of response-only data[J].Journal of Civil Structural Health Monitoring,2022,12(3):629‒645. doi:10.1007/s13349-022-00570-8
[11]
WangXudong, MiaoChangqing, WangXiaoming.Prediction analysis of deflection in the construction of composite box-girder bridge with corrugated steel webs based on MEC‒BP neural networks[J].Structures,2021,32:691‒700. doi:10.1016/j.istruc.2021.03.011
[12]
Van LeM, NguyenD D, HaH,et al.Ensemble soft computing models for prediction of deflection of steel-concrete composite bridges[J].Arabian Journal for Science and Engineering,2024,49(4):5505‒5515. doi:10.1007/s13369-023-08474-5
[13]
KumarS, PatelK A, ChaudharyS,et al.Rapid prediction of long-term deflections in steel-concrete composite bridges through a neural network model[J].International Journal of Steel Structures,2021,21(2):590‒603. doi:10.1007/s13296-021-00458-1
[14]
ZongZhouhong, ZhongRumian, ZhengPeijuan,et al.Damage and safety prognosis of bridge structures based on structural health monitoring:Progress and challenges[J].China Journal of Highway and Transport,2014,27(12):46‒57. doi:JournalArticle/5b435873c095d716a4c7388c
ChenGuoliang, LinXungen, YueQing,et al.Study on separation and forecast of long-term deflection based on time series analysis[J].Journal of Tongji University(Natural Science),2016,44(6):962‒968. doi:10.11908/j.issn.0253-374x.2016.06.021
LiShuangjiang, XinJingzhou, JiangYan,et al.Temperature-induced deflection separation based on bridge deflection data using the TVFEMD-PE-KLD method[J].Journal of Civil Structural Health Monitoring,2023,13(2):781‒797. doi:10.1007/s13349-023-00679-4
[19]
XinJingzhou, JiangYan, ZhouJianting,et al.Bridge deformation prediction based on SHM data using improved VMD and conditional KDE[J].Engineering Structures,2022,261:114285. doi:10.1016/j.engstruct.2022.114285
[20]
ZhengQiuyi, ZhouGuangdong, LiuDingkun.Method of modeling temperature‒displacement correlation for long-span arch bridges based on long short-term memory neural networks[J].Engineering Mechanics,2021,38(4):68‒79.
DengYang, JuHanwen, ZhaiWenqiang,et al.Correlation model of deflection,vehicle load,and temperature for in-service bridge using deep learning and structural health monitoring[J].Structural Control and Health Monitoring,2022,29(12):e3113. doi:10.1002/stc.3113
[23]
WangShuhong, ZhuBaoqiang.Time series prediction for ground settlement in portal section of mountain tunnels[J].Chinese Journal of Geotechnical Engineering,2021,43(5):813‒821. doi:10.11779/CJGE202105004
TadesseZ, PatelK A, ChaudharyS,et al.Neural networks for prediction of deflection in composite bridges[J].Journal of Constructional Steel Research,2012,68(1):138‒149. doi:10.1016/j.jcsr.2011.08.003
[26]
FaridmehrI, ShariqM, PlevrisV,et al.Novel hybrid informational model for predicting the creep and shrinkage deflection of reinforced concrete beams containing GGBFS[J].Neural Computing and Applications,2022,34(15):13107‒13123. doi:10.1007/s00521-022-07150-3
[27]
XiaoXinhui, WangZepeng, ZhangHaiping,et al.A novel method of bridge deflection prediction using probabilistic deep learning and measured data[J].Sensors,2024,24(21):6863. doi:10.3390/s24216863
[28]
QianJiangu, WuAnhai, JiJun,et al.Prediction for nonlinear time series of geotechnical engineering based on wavelet-optimized LSTM‒ARMA model[J].Journal of Tongji University(Natural Science),2021,49(8):1107‒1115.
LiTao, ShuJiajun, WangYanlong,et al.Horizontal deformation prediction of deep foundation pit support piles based on decomposition methods model[J].Rock and Soil Mechanics,2024,45():496‒506.
JuHanwen, DengYang, LiAiqun.Correlation model of deflection‒temperature‒vehicle load monitoring data for bridge structures[J].Journal of Vibration and Shock,2023,42(6):79‒89.
LekomtsevA, KeykhosraviA, MoghaddamM B,et al.On the prediction of filtration volume of drilling fluids containing different types of nanoparticles by ELM and PSO-LSSVM based models[J].Petroleum,2022,8(3):424‒435. doi:10.1016/j.petlm.2021.04.002
[35]
WangChunsheng, HeWenlong, ZhangWenting,et al.Static system reliability analysis of cable-stayed bridge based on improved BP neural network[J].Journal of Traffic and Transportation Engineering,2024,24(5):86‒100.
TanDongmei, GuoTai, GanQinlin.Separation of temperature effect in monitored deflection of bridges based on VMD‒SVD[J].Bridge Construction,2023,53(3):87‒94.
XiaoXinhui, LiuXian, ZhangHaiping,et al.Research on deflection prediction and early warning method of suspension bridge girder based on CNN‒LSTM‒GD[J].Vibration and impact, 2025,44(14):84‒94.
ReshefD N, ReshefY A, FinucaneH K,et al.Detecting novel associations in large data sets[J].Science,2011,334(6062):1518‒1524. doi:10.1126/science.1205438
[42]
MeiShengqi, LiuXiaodong, WangXingju,et al.Prediction of high strength concrete creep based on parametric MIC analysis and machine learning algorithm[J].Journal of Jilin University(Engineering and Technology Edition),2025,55(5):1595‒1603.
TangLibin, NaS.Comparison of machine learning methods for ground settlement prediction with different tunneling datasets[J].Journal of Rock Mechanics and Geotechnical Engineering,2021,13(6):1274‒1289. doi:10.1016/j.jrmge.2021.08.006