环境因素变化可能会掩盖损伤引起的结构动力特性变化，导致传统基于振动的损伤识别方法失效。为解决这一问题，本文提出了一种将变分模态分解（Variational Mode Decomposition，VMD）、主成分分析（Principal Component Analysis，PCA）和高斯过程回归（Gaussian Process Regression，GPR）相融合的结构损伤识别方法。首先，利用VMD算法对频率数据进行预处理，得到分离季节性环境模式后的第1本征模态数据（IMF1）；其次，采用PCA方法对IMF1数据进行分析，计算PCA残差的欧式距离；然后，以IMF1数据和相对应的PCA残差欧式距离为输入和输出，采用GPR模型学习输入-输出之间的计算规则；最后，利用训练好的GPR模型来预测剩余部分IMF1数据的PCA欧式距离，计算预测值与真实值之间的预测残差，并采用统计控制图进行损伤预警。实验室木桥和Z24桥的监测数据验证了该方法的有效性。
Abstract
The influence of the changing environments on dynamic feature may completely mask the dynamic feature changes caused by damage, making vibration-based methods challenging to effectively detect structural damage. To address this issue, this paper proposes a structural damage detection method based on the Variational Mode Decomposition (VMD), Principal Component Analysis (PCA) and Gaussian Process Regression (GPR). First, the VMD algorithm is used to preprocess the frequency signal to obtain the IMF1 after separating the seasonal environmental patterns; Secondly, the PCA method is used to analyze the IMF1 and calculate the Euclidean distance of the PCA residual; Then, the IMF1 signal and the corresponding PCA residual Euclidean distance are used as input and output, and the GPR model is used to learn the calculation rules between input and output; Finally, the trained GPR model is used to predict the PCA Euclidean distance of the remaining IMF1, the prediction residual between the predicted value and the true value is calculated, and statistical control chart is used for damage warning. Monitoring data from a laboratory wooden bridge and the Z24 bridge are used to verify the effectiveness of this method.
关键词
损伤识别 /
环境变化 /
变分模态分解 /
主成分分析 /
高斯过程回归
{{custom_keyword}} /
Key words
damage identification /
environmental variations /
variational mode decomposition /
principal component analysis /
gaussian process regression
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 周毅，孙利民，谢谟文. 运营环境作用对跨海大桥模态频率的影响研究[J]. 工程力学，2018, 35(S1): 34-39.
ZHOU Yi, SUN Li-min, XIE Mo-wen. Influence of operational and environmental actions on modal frequencies of a sea-crossing bridge [J]. Engineering Mechanics, 2018, 35(S1): 34-39.
[2] Wang Z, Yang D H, YI T H, et al. Eliminating environmental and operational effects on structural modal frequency: A comprehensive review [J]. Structural Control and Health Monitoring, 2022, e3073.
[3] 夏樟华，林友勤，张景杭，等. 环境温度对连续箱梁刚构桥相对小波熵指标的影响研究[J]. 振动与冲击，2017, 36(1): 207-214.
XIA Zhang-hua, LIN You-qin, ZHANG Jin-hang, et al. Influences of environmental temperature on relative wavelet entropy index for continuous rigid-frame bridges with box sections [J]. Journal of vibration and shock, 2017, 36(1): 207-214.
[4] Moser P, Moaveni B. Environmental effects on the identified natural frequencies of the Dowling Hall Footbridge [J]. Mechanical Systems and Signal Processing, 2011, 25(7): 2336-2357.
[5] Peeters B, De Roeck G. One‐year monitoring of the Z24‐Bridge: environmental effects versus damage events [J]. Earthquake Engineering and Structural Dynamics, 2001, 30(2): 149-171.
[6] Zhang Y-M, Wang H, Bai Y, et al. Switching Bayesian dynamic linear model for condition assessment of bridge expansion joints using structural health monitoring data [J]. Mechanical Systems and Signal Processing, 2021, 160: 107879.
[7] Ceravolo R, Coletta G, Miraglia G, et al. Statistical correlation between environmental time series and data from long-term monitoring of buildings [J]. Mechanical Systems and Signal Processing, 2021, 152: 107460.
[8] Yan A-M, Kerschen G, De Boe P, et al. Structural damage diagnosis under varying environmental conditions—part I: a linear analysis [J]. Mechanical Systems and Signal Processing, 2005, 19(4): 847-864.
[9] Deraemaeker A, Worden K. A comparison of linear approaches to filter out environmental effects in structural health monitoring [J]. Mechanical Systems and Signal Processing, 2018, 105: 1-15.
[10] 刁延松, 任红. 基于AR模型和因子分析的结构损伤预警研究[J]. 振动与冲击，2014, 33(18): 115-119.
DIAO Yan-song, REN Hong. Structural damage early warning based on AR model and factor analysis [J]. Journal of vibration and shock, 2014, 33(18): 115-119.
[11] Tomé E S, Pimentel M, Figueiras J. Damage detection under environmental and operational effects using cointegration analysis–application to experimental data from a cable-stayed bridge [J]. Mechanical Systems and Signal Processing, 2020, 135: 106386.
[12] Yan A M, Kerschen G, De Boe P, et al. Structural damage diagnosis under varying environmental conditions - part II: local PCA for non-linear cases [J]. Mechanical Systems and Signal Processing, 2005, 19(4): 865-880.
[13] Reynders E, Wursten G, De Roeck G. Output-only structural health monitoring in changing environmental conditions by means of nonlinear system identification [J]. Structural Health Monitoring-an International Journal, 2014, 13(1): 82-93.
[14] 郑泓，段忠东. 考虑非线性环境因素影响的结构损伤预警方法研究[J]. 振动工程学报，2021, 34(6): 1101-1111.
ZHENG Hong，DUAN Zhong-dong. Structural damage alert with consideration of the nonlinear environmental effects [J]. Journal of vibration engineering, 2021, 34(6): 1101-1111.
[15] 李东升，黄杰忠，李宏男. 环境变化下基于核典型相关分析与协整的损伤识别方法[J]. 中国公路学报，2019, 32(11): 71-82.
LI Dong-sheng, HUANG Jie-zhong, LI Hong-nan. Structural Damage Identification Based on Kernel Canonical Correlation Analysis and Cointegration under Changing Environments [J]. China Journal of Highway and Transport, 2019, 32(11): 71-82.
[16] 黄海宾，臧敬刚. 变运营环境下基于混合主成分分析的结构损伤识别方法[J]. 重庆交通大学学报(自然科学版)， 2022, 41(7): 51-58.
HUANG Hai-bin, ZANG Jing-gang. Structural damage identification method based on mixed principal component analysis under changing operational environment [J]. Journal Of Chongqing Jiaotong University (Natural Science), 2022, 41(7): 51-58.
[17] Mousavi M, Gandomi A H. Prediction error of Johansen cointegration residuals for structural health monitoring [J]. Mechanical Systems and Signal Processing, 2021, 160: 107847.
[18] 丁承君，冯玉伯，王曼娜. 基于变分模态分解与深度卷积神经网络的滚动轴承故障诊断[J]. 振动与冲击，2021, 40(2): 287-96.
DING Cheng-jun, FENG Yu-bo, WANG Man-na. Rolling bearing fault diagnosis using variational mode decomposition and deep convolutional neural network [J]. Journal of vibration and shock, 2021, 40(2): 287-96.
[19] Peng Z, Li J, Hao H. Structural damage detection via phase space based manifold learning under changing environmental and operational conditions [J]. Engineering Structures, 2022, 263: 114420.
[20] 赵荣荣，赵忠盖，刘飞. 基于k-近邻互信息的发酵过程高斯过程回归建模[J]. 化工学报，2019, 70(12): 4741-4748.
ZHAO Rongrong, ZHAO Zhonggai, LIU Fei. Gaussian process regression modeling of fermentation process based on k-nearest neighbor mutual information [J]. Journal of Chemical Industry and Engineering, 2019, 70(12): 4741-4748.
[21] Mousavi M, Gandomi A H. Structural health monitoring under environmental and operational variations using MCD prediction error [J]. Journal of Sound and Vibration, 2021, 512: 116370.
[22] Kullaa J. Eliminating environmental or operational influences in structural health monitoring using the missing data analysis [J]. Journal of Intelligent Material Systems and Structures, 2009, 20(11): 1381-1390.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2717 KB)
