基于DBO-LSTM模型的桥梁环境温度及其效应预测方法研究
A Hybrid DBO-LSTM Model for Predicting Bridge Ambient Temperature and Its Thermal Response
针对传统健康监测系统数据处理复杂及有限元方法在桥梁环境温度效应预测中存在的计算量大、实时性差等问题,提出一种基于蜣螂优化算法(DBO)优化长短期记忆网络(LSTM)超参数的混合模型(DBO-LSTM),用于桥梁环境温度及温度效应的预测。该方法通过DBO算法对LSTM的隐藏层节点数、初始学习率及L2正则化系数三项关键超参数进行全局优化,提升了模型在长序列非线性特征学习过程中的预测精度和稳定性。基于成绵立交主线桥为期一年的温度与温度效应监测数据,对环境温度、伸缩缝位移、主梁梁底应变和墩顶偏位等多项指标进行预测实验,结果显示所建模型在各类预测项中均表现出良好的拟合能力和趋势捕捉能力。决定系数R²最低为0.966,最高达0.995,平均绝对百分比误差(MAPE)在0.02至0.38之间,预测值与实测值在数值及趋势上高度一致。
To address the limitations of traditional bridge health monitoring systems and finite element methods, such as heavy computational demands and poor real-time performance, a hybrid prediction model based on Dung Beetle Optimization and Long Short-Term Memory networks (DBO-LSTM) is proposed for forecasting bridge ambient temperature and temperature-induced effects.The model utilizes the DBO algorithm to optimize three critical hyperparameters of the LSTM network: the number of hidden units, initial learning rate, and L2 regularization coefficient.This optimization enhances the model's ability to learn complex nonlinear dependencies in long-term monitoring data.Using one year of real-time monitoring data from the Chengmian Interchange mainline bridge, the model was applied to predict multiple indicators, including ambient temperature, expansion joint displacement, bottom beam strain, and pier top displacement.The results demonstrate high predictive performance, with coefficients of determination (R²) ranging from 0.966 to 0.995 and mean absolute percentage errors (MAPE) between 0.02 and 0.38.The predicted values closely match the actual measurements in both magnitude and trend.
| [1] |
占玉林,斯睿哲,臧亚美.混凝土桥梁耐久性2020年度研究进展[J].土木与环境工程学报(中英文),2021,43(S1):100-106. |
| [2] |
Zhan Yulin,Si Ruizhe,Zang Yamei.Research progress in durability of concrete bridges in 2020[J].Journal of Civil and Environmental Engineering (Chinese and English),2021,43(S1):100-106.(in Chinese) |
| [3] |
廖聿宸,张坤,杜孟林,基于长期监测的开口截面组合梁斜拉桥温度场分析[J].东南大学学报(自然科学版),2023,53(6):1080-1090. |
| [4] |
Liao Yuchen,Zhang Kun,Du Menglin,et al.Temperature field analysis of cable-stayed bridge with composite girders of open sections based on long-term monitoring[J].Journal of Southeast University (Natural Science Edition),2023,53(6):1080-1090.(in Chinese) |
| [5] |
周云,危俊杰,李剑,基于InSAR技术的大跨桥梁温度变形监测研究[J].湖南大学学报(自然科学版),2024,51(3):39-50. |
| [6] |
Zhou Yun,Wei Junjie,Li Jian,et al.Monitoring of temperature deformation of long-span bridges based on InSAR technology[J].Journal of Hunan University (Natural Science Edition),2024,51(3):39-50.(in Chinese) |
| [7] |
卫俊岭,王浩,茅建校,混凝土连续箱梁桥温度场数值模拟及实测验证[J].东南大学学报(自然科学版),2021,51(3):378-383. |
| [8] |
Wei Junling,Wang Hao,Mao Jianxiao,et al.Numerical simulation and field verification of temperature field in continuous concrete box girder bridges[J].Journal of Southeast University (Natural Science Edition),2021,51(3):378-383.(in Chinese) |
| [9] |
张玉平,李思阳,李传习,基于气象参数的钢箱梁竖向温度梯度模式[J].公路交通科技,2025,42(1):147-155. |
| [10] |
Zhang Yuping,Li Siyang,Li Chuanxi,et al.Vertical temperature gradient pattern of steel box girders based on meteorological parameters[J].Highway and Transportation Technology,2025,42(1):147-155.(in Chinese) |
| [11] |
胡安庆,邓长军,任东华,某立交匝道桥墩梁“抵触”病害长期监测分析[J].公路,2021,66(10):118-124. |
| [12] |
Hu Anqing,Deng Changjun,Ren Donghua,et al.Long-term monitoring and analysis of pier-girder “conflict” damage in a ramp bridge of an interchange[J].Highway,2021,66(10):118-124.(in Chinese) |
| [13] |
郭桥,梁柱,沈国栋,基于知识图谱及机器学习的桥梁病害智能诊断方法[J].公路,2023,68(10):329-334. |
| [14] |
Guo Qiao,Liang Zhu,Shen Guodong,et al.Intelligent diagnosis method for bridge diseases based on knowledge graph and machine learning[J].Highway,2023,68(10):329-334.(in Chinese) |
| [15] |
朱颖,郭辉,孙大奇,运营期公铁两用悬索桥温度效应研究[J].铁道学报,2024,46(6):156-166. |
| [16] |
Zhu Ying,Guo Hui,Sun Daqi,et al.Study on temperature effects of highway-railway suspension bridges during operation period[J].Journal of the China Railway Society,2024,46(6):156-166.(in Chinese) |
| [17] |
郭风俊.基于ANSYS的不平衡日照混凝土箱梁温度场分布研究[J].西安建筑科技大学学报(自然科学版),2020,52(2):207-212. |
| [18] |
Guo Fengjun.Study on temperature field distribution of concrete box girders under uneven solar radiation based on ANSYS[J].Journal of Xi'an University of Architecture & Technology (Natural Science Edition),2020,52(2):207-212.(in Chinese) |
| [19] |
陈鹏,郭佳,张俊豪,整体式T梁桥温度荷载效应可靠性概率评价[J].公路交通科技,2023,40(6):140-147. |
| [20] |
Chen Peng,Guo Jia,Zhang Junhao,et al.Probabilistic reliability assessment of temperature load effects in integral T-beam bridges[J].Highway and Transportation Technology,2023,40(6):140-147.(in Chinese) |
| [21] |
刘扬,向胜涛,王达.基于BP-LSTM混合模型的钢-混组合桥面系空间温度场及温度效应实时评估及预测[J].土木工程学报,2021,54(11):57-70,78. |
| [22] |
Liu Yang,Xiang Shengtao,Wang Da.Real-time assessment and prediction of spatial temperature field and temperature effect of steel-concrete composite bridge deck system based on BP-LSTM hybrid model[J].China Civil Engineering Journal,2021,54(11):57-70,78.(in Chinese) |
| [23] |
惠迎新,孙晓荣,王红雨,大跨变截面混凝土箱梁施工期温度效应研究[J].公路交通科技,2023,40(1):98-105. |
| [24] |
Hui Yingxin,Sun Xiaorong,Wang Hongyu,et al.Study on temperature effects during construction of long-span variable-section concrete box girders[J].Highway and Transportation Technology,2023,40(1):98-105.(in Chinese) |
| [25] |
聂华伟,应江虹,邓捷.基于Bi-LSTM模型的桥梁健康监测挠度预测方法[J].公路,2024,69(10):213-219. |
| [26] |
Nie Huawei,Ying Jianghong,Deng Jie.Deflection prediction method for bridge health monitoring based on Bi-LSTM model[J].Highway,2024,69(10):213-219.(in Chinese) |
| [27] |
方佳畅,黄天立,李苗,基于迁移学习和Bi-LSTM神经网络的桥梁温度-应变映射建模方法[J].振动与冲击,2023,42(12):126-134,186. |
| [28] |
Fang Jiachang,Huang Tianli,Li Miao,et al.Bridge temperature-strain mapping modeling method based on transfer learning and Bi-LSTM neural network[J].Journal of Vibration and Shock,2023,42(12):126-134,186.(in Chinese) |
| [29] |
Yue Z,Ding Y,Zhao H,et al.Mechanics-guided optimization of an LSTM network for real-time modeling of temperature-induced deflection of a cable-stayed bridge[J].Engineering Structures,2022,252:113619. |
| [30] |
黄孝彬,王永凯.基于改进蜣螂优化算法的电站NOx排放预测[J].科学技术与工程,2024,24(23):9929-9936. |
| [31] |
Huang Xiaobin,Wang Yongkai.Prediction of power plant NOx emissions based on improved dung beetle optimization algorithm[J].Science Technology and Engineering,2024,24(23):9929-9936.(in Chinese) |
| [32] |
Xue J,Shen B.Dung beetle optimizer:A new meta-heuristic algorithm for global optimization[J].The Journal of Supercomputing,2023,79(7):7305-7336. |
| [33] |
Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780. |
四川交投科研联合项目(HT-GLQ2024-0055)
/
| 〈 |
|
〉 |