Bridge deflection was regarded as a critical indicator that reflected structural deformation and bearing performance, and its accurate prediction was considered essential for structural safety assessment and maintenance decision-making. Traditional inspection methods, which rely heavily on manual inspection, were insufficient for real-time health assessment. The integration of modern sensing technologies and intelligent algorithms has become a prominent research focus in structural health monitoring. A hybrid deflection prediction model was proposed based on real-time data collected from bridge structural health monitoring sensors, including deflection, temperature, and other key parameters. Outliers were identified and removed using the isolation forest algorithm. The time convolutional network (TCN) was employed for its time-series modeling capability, the long short-term memory (LSTM) network was used for capturing long-term dependencies, and the Attention mechanism was integrated for adaptive feature selection. A TCN-LSTM-Attention hybrid model was proposed to predict bridge deflection. To optimize the model’s performance, the whale optimization algorithm was used for hyperparameter tuning. The results demonstrate that the TCN-LSTM-Attention model performs excellently across various evaluation metrics, with an R2 of 0.97 and an RMSE of 0.206 6. Compared to the TCN and LSTM models, it improves R2 by 5.24% and 3.78%, and reduces RMSE by 5.47% and 4.21%, respectively. Notably, the model exhibits strong robustness and accuracy, especially in long-term predictions scenarios. This work provides an effective and intelligent approach to bridge deflection prediction and offers valuable support for condition-based maintenance planning.
相关学者在桥梁挠度预测方面做了大量研究,早期的桥梁健康监测多依赖于传统的统计方法,如回归分析、时间序列分析等[4]。Deng等[5]基于在役桥梁挠度、车辆荷载和温度等因素构建了相关性模型,有效预测了极端条件下桥梁挠度和结构健康度。Lee等[6]将有限元分析和实际测量数据相结合,为预应力混凝土桥梁开发了一种贝叶斯预测方法。陈国良等[7]基于时间序列分析建立了自回归差分移动平均模型(autoregressive integrated moving average model, ARIMA)模型,对桥梁结构变形趋势进行预测。然而,传统方法在面对复杂的非线性关系时表现较差,难以应对大规模、高维度的复杂数据[8],机器学习方法逐渐成为桥梁健康监测领域的重要手段,学者们基于支持向量机、决策树、随机森林等算法开发了多种桥梁健康预测模型[9]。Almohammedi等[10]结合美国州际公路与运输官员协会(American Association of State Highway and Transportation Officials, AASHTO)规定提出了预应力混凝土梁的增强拱度和挠度估算方法。Qu等[11]基于新的贝叶斯动态差分模型和非平稳数据构建了一种实时桥梁挠度预测模型,为桥梁挠度提供了实时监测能力。
近年来,深度学习技术逐步引起桥梁健康监测领域的广泛关注。Wang等[12]基于思维进化计算(mind evolutionary computation, MEC)算法与反向传播(back propagation, BP)算法构建MEC-BP神经网络实现了波纹钢腹板组合箱梁桥的挠度预测。周宇等[13]通过结合桥梁挠度等静动态响应特征提出一种基于曲率变化的简支梁检测方法,通过信号分解与建模实现了结构损伤定位。Liu等[14]使用BP和径向基函数神经网络(radial basis function neural network, RBF)预测刚架连续梁桥挠度,为基于有限元分析结果预测较长时期的挠度值提供了见解。Xiao等[15]使用概率深度学习和测量数据进行桥梁挠度预测,通过结合卷积神经网络(convolutional neural networks, CNN)、长短期记忆网络(long short-term memory, LSTM)和概率密度估计层,以预测随机交通荷载和环境温度影响下的挠度。聂华伟等[16]基于挠度、应力和温度的关系,进一步构建了双向长短期记忆(bi-directional long short-term memory, Bi-LSTM)模型实现挠度预测,综合效果明显好于门控循环单元(gate recurrent unit, GRU)、LSTM、ARIMA等模型。郭永刚等[17]综合变分模态分解(variational mode decomposition, VMD)、完全集成经验模态分解与自适应噪声(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)和粒子群算法(particle swarm optimization, PSO)构建了CEEMDAN-VMD-PSO-LSTM模型对桥梁挠度进行预测,通过对原始时间序列模态分解,大大提升了模型的预测精度。顾思思等[18]基于毫米波雷达监测的桥梁挠度数据建立了CNN-GRU组合模型,发现预测精度显著高于传统的LSTM模型。鞠翰文等[19]综合桥梁挠度、车载和温度关系,基于GRU模型实现了挠度的短期和中长期预测。
XuWencheng, WangMiao. Research on data separation technology for bridge dynamic deflection monitoring based on millimeter-wave radar[J]. Highway, 2024, 69(11): 144-155.
ChuXi, ZhouZhixiang, DuanXin, et al. A monitoring method for continuous line-shape of bridge structure[J]. Journal of Highway and Transportation Research and Development, 2023, 40(11): 157-163, 171.
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.
TanDongmei, GuoTai, GanQinlin. Separation of temperature effect in monitored deflection of bridges based on VMD-SVD[J]. Bridge Construction, 2023, 53(3): 87-94.
[9]
DengY, JuH, ZhaiW, 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): 3113.
[10]
LeeJ, LeeK, SimS, et al. Bayesian prediction of pre-stressed concrete bridge deflection using finite element analysis[J]. Sensors, 2019, 19(22): 4956.
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.
QiXingjun, SunXufa, WangShanshan, et al. Bridge modal deflection prediction method based on additional mass block[J]. Journal of Vibration and Shock, 2022, 41(19): 104-113.
XiongChen, CenChengyu, ZhouHaijun, et al. Study on deflection measurement of simply supported girder bridges based on laser-position sensitive detectors[J]. Engineering Mechanics, 2025, 42(1): 223-232.
[17]
AlmohammediA, DangC, MurrayC, et al. Enhanced camber and deflection estimation for AASHTO prestressed concrete girders[J]. PCI Journal, 2022, 67(6): 35-50.
[18]
QuG, SongM, SunL. Real-time bridge deflection prediction based on a novel Bayesian dynamic difference model and nonstationary data[J]. Journal of Bridge Engineering, 2024, 29(9): 04024064.
[19]
WangX, MiaoC, WangX. 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.
ZhouYu, LiuRunzhou, DiShengkui, et al. Deflection influence line identification and damage diagnosis method of beam bridge under moving vehicle loading[J]. Science Technology and Engineering, 2024, 24(9): 3834-3843.
[22]
LiuJ, WuH, SunQ. Research on the prediction of rigid frame-continuous girder bridge deflection usingBP and RBF neural networks[J]. Stavební Obzor-Civil Engineering Journal, 2023, 32(2): 257-270.
[23]
XiaoX, WangZ, ZhangH, et al. A novel method of bridge deflection prediction using probabilistic deep learning and measured data[J]. Sensors, 2024, 24(21): 6863.
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.