运营状态下桥梁结构挠度、车载和温度的相关性复杂，高精度的车载、温度与挠度相关性模型对桥梁结构健康监测具有重要意义。为此，提出了基于门控循环单元(gated recurrent unit ,GRU)神经网络的桥梁挠度监测数据建模方法。为解决车辆荷载监测数据在时域内离散分布的问题，提出了基于挠度影响线的车载影响参数计算方法；在此基础上建立了基于GRU神经网络的车载影响参数、环境温度和桥梁挠度相关性模型。以一座悬索桥为例，分别建立了短时段、中长时段的相关性模型，考察了相关性模型对加劲梁挠度的预测能力，并利用相关性模型提出了一种温度和车载挠度分量的分离方法。悬索桥实例研究表明，短时段相关性模型的挠度预测值与实时监测数据基本吻合，而中长时段相关性模型则对一定时间窗口内的挠度极值具有精确的预测能力；采用相关性模型计算得到的温度与车载挠度分量与小波分解结果具有良好的一致性。
Abstract
The correlation between vehicle load, environmental temperature, and deflection of in-service bridge structures is complex. A high-precision correlation model between vehicle load, temperature, and deflection is important to bridge structural health monitoring. This study proposed a modeling method of bridge deflection monitoring data based on gated recurrent unit (GRU) neural network. The calculation method of vehicle load influence parameter was developed based on deflection influence line to solve the problem of time-domain discrete distribution of vehicle load monitoring data. On this basis, the correlation model of vehicle load influence parameter, temperature and bridge deflection based on GRU neural network was established. Taking a suspension as the example, the short-term, medium-term, and long-term correlation models were established. The prediction ability of stiffening girder deflection was investigated. A new separation method of temperature- and vehicle-induce deflection components was presented by using the correlation model. The suspension bridge case-study reveals that the predicted deflection based on the short-term correlation model is basically consistent with real-time deflection monitoring data. The medium- and long-term correlation models can accurately predict the deflection extremes in a certain time window. The temperature- and vehicle-induce deflection components separated by using the correlation model have favorable consistency with wavelet decomposition results.
关键词
结构健康监测 /
GRU神经网络 /
相关性模型 /
挠度 /
车辆荷载 /
环境温度
{{custom_keyword}} /
Key words
structural health monitoring /
gated recurrent unit(GRU)neural network /
correlation model /
deflection /
vehicle load /
environmental temperature
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李 勇，闫维明，陈彦江. 基于倾角测试的桥梁变形实时监测研究[J]. 振动与冲击，2013，32(05)：65-69.
LI Yong, YAN Wei-ming, CHEN Yan-jiang. Bridge deflection real-time monitoring based on inclined angle measurement [J]. Journal of vibration and shock, 2013, 32(05): 65-69.
[2] Deng Y，Li A Q，Chen S R，et al. Serviceability assessment for long-span suspension bridge based on deflection measurements[J]. Structural Control and Health Monitoring, 2018, 25(11): e2254.
[3] Feng D M，Feng M Q. Computer vision for SHM of civil infrastructure: from dynamic response measurement to damage detection-a review[J]. Engineering Structures, 2018, 156: 105-117.
[4] 杨 红，孙 卓，刘夏平，等. 基于多最小二乘支持向量机的桥梁温度挠度效应的分离[J]. 振动与冲击，2014，33(01)：71-76+88.
YANG Hong, SUN Zhuo, LIU Xia-ping. Separation of bridge temperature deflection effect based on M-LS-SVM [J]. Journal of vibration and shock, 2014, 33(01): 71-76+88.
[5] 谭冬梅，姚 欢，陈方望，等. 基于温度挠度识别斜拉桥拉索损伤的研究[J]. 振动与冲击，2021，40(23)：166-174.
TAN Dong-mei, YAO Huan, CHEN Fang-wang. Identification of cable damage for cable-stayed bridge based on temperature deflection [J]. Journal of vibration and shock, 2021, 40(23): 166-174.
[6] 黄 腾，孙泽信，李桂华，等. 大跨度预应混凝土箱梁桥的挠度监测与预测[J]. 工程勘察，2009，37(5)：60-63+84.
HUANG Teng, SUN Ze-xin, LI Gui-hua, et al. Deflection monitoring and forecasting of long span prestressed concrete continuous box beams [J]. Geotechnical Investigation and Surveying, 2009, 37(05): 60-63+84.
[7] 李雪莲. 温度与斜拉桥跨中挠度的关联性分析[J]. 城市道桥与防洪，2013，27(12)：66-69.
LI Xue-lian. Analysis on correlation of temperature and mid-span deflection cable-stayed bridge [J]. Urban Roads Bridges and Flood Control, 2013(12): 66-69.
[8] Liu Y，Deng Y，Cai C S. Deflection monitoring and assessment for a suspension bridge using a connected pipe system: a case study in China[J]. Structural Control and Health Monitoring, 2015, 22(12): 1408-1425.
[9] Mao J X，Wang H，Spencer B F. Toward data anomaly detection for automated structural health monitoring: exploiting generative adversarial nets and autoencoders[J]. Structural Health Monitoring, 2021, 20(4): 1609-1626.
[10] 刘小玲，黄 侨，任 远，等. 大跨度钢斜拉桥主梁监测挠度的评估与预警[J]. 湖南大学学报(自然科学版)，2016，43(09)：98-104.
LIU Xiao-ling, HUANG Qiao, REN Yuan, et al. Assessment and early warning on the monitoring girder deflection of the long-span steel cable-stayed bridge [J]. Journal of Hunan University (Natural Sciences), 2016, 43(09): 98-104.
[11] 祝青鑫，王 浩，茅建校，等. 基于ANFIS的环境激励下桥梁结构应变响应预测分析[J]. 中国公路学报，2019，32(11)：62-70+117.
ZHU Qing-xin, WANG Hao, MAO Jian-xiao, et al. Prediction of strain response of bridges under ambient excitation based on adaptive network-based fuzzy inference system [J]. China Journal of Highway and Transport, 2019, 32(11): 62-70+117.
[12] Xu X，Ren Y，Huang Q，et al. Thermal response separation for bridge long term monitoring systems using multi resolution wavelet based methodologies[J]. Journal of Civil Structural Health Monitoring, 2020, 10: 527-541.
[13] 李 苗，任伟新，胡异丁，等. 基于解析模态分解法的桥梁动态应变监测数据温度影响的分离[J]. 振动与冲击，2012，31(21)：6-10.
LI Miao, REN Wei-xin, HU Yi-ding, et al. Separating temperature effect from dynamic strain measurements of a bridge based on analytical mode decomposition method [J]. Journal of Vibration and Shock, 2012, 31(21): 6-10.
[14] 郑彩红，申 强，邓思勉，等. 基于优化VMD 的悬索桥挠度温度效应分离方法[J]. 公路交通科技，2021，38(6)：88-96.
ZHENG Cai-hong, SHEN Qiang, DENG Si-mian, et al. A method for separating temperature effect on deflection of suspension bridge based on optimized VMD [J]. Journal of Highway and Transportation Research and Development, 2021, 38(6): 88-96.
[15] 刘 纲，邵毅敏，黄宗明，等. 长期监测中结构温度效应分离的一种新方法[J]. 工程力学，2010，27(3)：55-061.
LIU Gang, SHAO Yi-min, HUANG Zong-ming, et al. A new method to separate temperature effect from long-term structural health monitoring data [J]. Engineering Mechanics, 2010, 27(3):55-061.
[16] 李 明，钟继卫，严 凤. 结构温度与悬索桥主梁挠度的关联性分析[J]. 振动与冲击，2018，37(11)：237-244.
LI Ming, ZHONG Ji-wei, YAN Feng. Correlation analysis between structure temperature and deflection of a suspension bridge girder [J]. Journal of Vibration and Shock, 2018, 37(11): 237-244.
[17] Yang D H，Yi T H，Li H N，et al. Correlation-based estimation method for cable-stayed bridge girder deflection variability under thermal action[J]. Journal of Performance of Constructed Facilities, 2018, 32(5): 04018070.
[18] Zhou G D，Yi T H，Chen B，et al. Modeling deformation induced by thermal loading using long-term bridge monitoring data[J]. Journal of Performance of Constructed Facilities, 2018, 32(3): 04018011.
[19] 郑秋怡，周广东，刘定坤. 基于长短时记忆神经网络的大跨拱桥温度-位移相关模型建立方法[J]. 工程力学，2021，38(04)：68-79.
ZHENG Qiu-yi, ZHOU Guang-dong, LIU Ding-kun. Method of modeling temperature-displacement correlation for long-span arch bridges based on long short-term memory neural networks [J]. Engineering Mechanics, 2021, 38(04): 68-79.
[20] Yue Z X，Ding Y L，Zhao H W. 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.
[21] 沈月千，黄 腾，陈喜凤，等. 逐步回归分析在桥梁挠度变形预测中的应用[J]. 工程勘察，2012，40(07)：79-83.
SHEN Yue-qian, HUANG Teng, CHEN Xi-feng, et al. The applications of stepwise regression analysis for prediction of bridge deflection [J]. Geotechnical investigation and surveying, 2012, 40(07): 79-83.
[22] 袁阳光，黄平明，韩万水，等. 基于可靠度理论的中小跨径桥梁卡车载重限值研究[J]. 工程力学，2017，34(08)：161-170.
YUAN Yang-guang, HUANG Ping-ming, HAN Wan-shui, et al. Reliability based research on truck-load limitation of medium-small-span bridges [J]. Engineering Mechanics, 2017, 34(08): 161-170.
[23] Chen J L，Jing H J，Chang Y H，et al. Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process[J]. Reliability Engineering and System Safety, 2019, 185: 372-382.
[24] 姚德臣，李博阳，刘恒畅，等. 基于注意力GRU算法的滚动轴承剩余寿命预测[J]. 振动与冲击，2021，40(17)：116-123.
YAO De-chen, LI Bo-yang, LIU Heng-chang, et al. Residual life prediction of rolling bearing based on attention GRU algorithm [J]. Journal of Vibration and Shock, 2021, 40(17): 116-123.
[25] 孟子尧，谷 雪，梁艳春，等. 深度神经架构搜索综述[J]. 计算机研究与发展，2021，58(01)：22-33.
MENG Zi-yao, GU Xue, LIANG Yan-chun, et al. Deep neural architecture search: a survey [J]. Journal of Computer Research and Development, 2021, 58(01): 22-33.
[26] Li S W，Li S C，Laima S，et al. Data-driven modeling of bridge buffeting in the time domain using long short-term memory network based on structural health monitoring[J]. Struct Control and Health Monitoring, 2021, 28(8): e2772.
[27] Zhao H W，Ding Y L，Li A Q，et al. Digital modeling on the nonlinear mapping between multi-source monitoring data of in-service bridges[J]. Struct Control and Health Monitoring, 2020, 27: e2618.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(3069 KB)
