基于AR-GP模型的结构损伤识别方法

唐启智1,辛景舟1,周建庭1,付雷2,周滨枫3

振动与冲击 ›› 2021, Vol. 40 ›› Issue (9) : 102-109.

PDF(1213 KB)
PDF(1213 KB)
振动与冲击 ›› 2021, Vol. 40 ›› Issue (9) : 102-109.
论文

基于AR-GP模型的结构损伤识别方法

  • 唐启智1,辛景舟1,周建庭1,付雷2,周滨枫3
作者信息 +

Structural damage identification method based on AR-GP model

  • TANG Qizhi1, XIN Jingzhou1, ZHOU Jianting1, FU Lei2, ZHOU Binfeng3
Author information +
文章历史 +

摘要

针对传统损伤识别方法不易区分多损伤状态以及难以辨别预测结果可靠性的问题,提出了一种基于自回归(autoregressive, AR)模型和高斯过程(Gaussian process, GP)的损伤识别方法。该方法利用AR模型回归拟合结构加速度响应数据,首次引入表征损伤位置信息与损伤状态信息的参数L1L2,基于AR模型残差、系数分别建立了用于定位损伤位置和识别损伤程度的损伤敏感性特征,结合GP的分类与回归算法实现了多损伤定位及损伤程度的概率输出。通过某钢筋混凝土模型拱的数值仿真算例,验证了所提方法的有效性,并对基于AR模型残差和系数的识别结果进行了对比分析。结果表明,该方法能够识别多损伤状态,输出具有概率意义的预测结果,有助于判断结果的可靠性,并能够实现损伤预警,同时基于残差的损伤敏感性特征的识别精度与可靠度更高、抗噪性能更好,在10%噪声污染的情况下,识别结果的相对误差均值与离散系数均值仅为6.52%和0.19。

Abstract

Aiming at the problem of traditional methods for damage identification being difficult to distinguish multi-damage states and the reliability of prediction results, a method for damage identification was proposed based on autoregressive (AR) model and Gaussian process (GP).It was shown that this method uses AR model to fit acceleration response data of a structure, and for the first time, parameters L1 and L2 are  introduced to characterize the information about damage location and damage level; based on residual and coefficient of AR model, damage sensitivity features for locating damage position and identifying damage degree are established, respectively; GP’s classification algorithm is combined with its regression algorithm to realize multi-damage location and probability output of damage degree.The effectiveness of the proposed method was verified with a numerical simulation example of a reinforced concrete model arch, and the identification results based on AR model’s residual and coefficient were analyzed contrastively.The results showed that the proposed method can identify multi-damage states and output prediction results with probabilistic significance, which is helpful to judge the reliability of the results and realize damage early warning; the identification accuracy and reliability of damage sensitivity feature based on residual are higher with better anti-noise performance; in the case of 10% noise pollution, the relative error mean and discrete coefficient mean of the identification results are only 6.52% and 0.19, respectively.

关键词

自回归模型 / 高斯过程 / 多损伤定位 / 概率输出 / 预警

Key words

autoregressive (AR) model / Gaussian process (GP) / multi-damage localization / probability output / early warning

引用本文

导出引用
唐启智1,辛景舟1,周建庭1,付雷2,周滨枫3. 基于AR-GP模型的结构损伤识别方法[J]. 振动与冲击, 2021, 40(9): 102-109
TANG Qizhi1, XIN Jingzhou1, ZHOU Jianting1, FU Lei2, ZHOU Binfeng3. Structural damage identification method based on AR-GP model[J]. Journal of Vibration and Shock, 2021, 40(9): 102-109

参考文献

[1]LIU S, LIU T, ZHOU J, et al.Relationship between shear-stress distribution and resulting acoustic-emission variation along concrete joints in prefabricated girder structures [J].Engineering Structures, 2019, 196: 109319.
[2]HOELL S, OMENZETTER P.Optimal selection of autoregressive model coefficients for early damage detectability with an application to wind turbine blades [J].Mechanical Systems and Signal Processing, 2016, 70/71: 557-577.
[3]朱宏平,余璟,张俊兵.结构损伤动力检测与健康监测研究现状与展望[J].工程力学, 2011, 28(2): 1-11.
ZHU Hongping, YU Jing, ZHANG Junbing.Research status and prospect of structural damage dynamic detection and health monitoring [J].Engineering Mechanics, 2011, 28(2):1-11.
[4]张家滨, 唐催, 王磊, 等.基于频率变化率的结构刚度非均匀退化识别[J].振动、测试与诊断, 2018, 38(3): 486-493.
ZHANG Jiabing, TANG Cui, WANG Lei, et al.Identification of heterogeneous degradation of structural stiffness based on the rate of frequency change [J].Journal of Vibration, Measurement & Diagnosis, 2018, 38(3): 486-493.
[5]周宇, 狄生奎, 项长生, 等.基于柔度曲率梯度的刚架拱桥损伤识别[J].应用基础与工程科学学报, 2017, 25(6): 1211-1221.
ZHOU Yu, DI Shengkui, XIANG Changsheng, et al.Damage identification of rigid arch Bridges based on flexibility curvature gradient[J].Journal of Basic Science and Engineering, 2017, 25(6): 1211-1221.
[6]郑飞, 许金余.基于缩聚模态应变能与频率的结构损伤识别[J].工程力学, 2012, 29(7): 117-123.
ZHENG Fei, XU Jinyu.Structural damage identification based on polycondensation modal strain energy and frequency [J].Engineering Mechanics, 2012, 29(7): 117-123.
[7]杜永峰, 李万润, 李慧, 等.基于时间序列分析的结构损伤识别[J].振动与冲击, 2012,31(12):108-111.
DU Yongfeng, LI Wanrun, LI Hui, et al.Structural damage identification based on time series analysis [J].Journal of Vibration and Shock, 2012, 31(12):108-111.
[8]BUSTOS A, RUBIO H, CASTEJN C, et al.EMD-based methodology for the identification of a high-speed train running in a gear operating state [J].Sensors, 2018, 18: 763.
[9]罗德河, 郑东健, 甘声玄, 等.基于ARMAX模型的混凝土坝损伤诊断[J].武汉大学学报(工学版), 2018, 51(4): 294-298.
LUO Dehe, ZHENG Dongjian, GAN Shengxuan, et al.Damage diagnosis of concrete dam based on ARMAX model [J].Engineering Journal of Wuhan University, 2018, 51(4): 294-298.
[10]张凯玮, 付文, 银晓东, 等.基于ARMA模型的盾构隧道结构损伤识别[J].土木工程与管理学报, 2011, 35(5): 122-127.
ZAHNG Kaiwei, FU Wen, YIN Xiaodong, et al.Damage identification of shield tunnel structure based on ARMA model [J].Journal of Civil Engineering and Management, 2011, 35(5): 122-127.
[11]LYNCH J P.Linear classification of system poles for structural damage detection using piezoelectric active sensors [C]// SPIE 11th Annual International Symposium on Smart Structures and Materials.San Diego, CA,2014.
[12]NAIR K K, KIREMIDJIAN A S, LAW K H.Time series-based damage detection and localization algorithm with application to the ASCE benchmark structure [J].Journal of Sound and Vibration, 2006, 291: 349-368.
[13]DATTEO A, BUSCA G, QUATTROMANI G, et al.On the use of AR models for SHM: a global sensitivity and uncertainty analysis framework [J].Reliability Engineering and System Safety, 2018, 170: 99-115.
[14]朱军华, 余岭.基于时间序列分析与高阶统计矩的结构损伤检测[J].东南大学学报(自然科学版), 2012, 42(1):137-143.
ZHU Junhua, YU Ling.Structural damage detection based on time series analysis and high order statistical moments [J].Journal of Southeast University (Natural Science Edition), 2012, 42(1):137-143.
[15]李雪松, 马宏伟, 林逸洲.基于卷积神经网络的结构损伤识别[J].振动与冲击, 2019, 38(2):159-167.
LI Xuesong, MA Hongwei, LIN Yizhou.Structural damage identification based on convolution neural network [J].Journal of Vibration and Shock, 2019, 38(2):159-167.
[16]孙艳丽, 杨娜, 张正涛, 等.基于核主元分析和支持向量机的结构损伤识别研究[J].应用基础与工程科学学报, 2018, 26(4):888-900.
SUN Yanli, YANG Na, ZHANG Zhengtao, et al.Structural damage identification based on kernel principal component analysis and support vector machine [J].Journal of Basic Science and Engineering, 2018, 26(4):888-900.
[17]SAWANT M M, BHURCHANDI K.Hierarchical facial age estimation using Gaussian process regression [J].IEEE Access, 2019(1): 1.
[18]舒坚, 刘满兰, 尚亚青, 等.基于高斯过程回归的链路质量预测模型[J].通信学报, 2018, 39(7): 148-156.
SHU Jian, LIU Manlan, SHANG Yaqing, et al.Link quality prediction model based on Gaussian process regression [J].Journal on Communications, 2018, 39(7): 148-156.
[19]朱彬, 裴华富, 杨庆.基于高斯过程回归的响应面法及边坡可靠度分析[J].岩土工程学报, 2019, 41(7): 209-212.
ZHU Bin, PEI Huafu, YANG Qing.Response surface method and slope reliability analysis based on Gaussian process regression [J].Chinese Journal of Geotechnical Engineering, 2019, 41(7): 209-212.
[20]程虎, 李微, 郭文平, 等.基于高斯过程回归的距离选通成像系统工作参数的在线优化[J].光学学报, 2019, 39(4): 1-8.
CHENG Hu, LI Wei, GUO Wenping, et al.On-line optimization of operating parameters of distance gate imaging system based on Gaussian process regression [J].Acta Optica Sinica, 2019, 39(4): 1-8.
[21]陈丽江.基于ADF检验的中国出口集装箱班轮运价随机特性研究[J].武汉理工大学学报(社会科学版), 2013, 26(1): 15-20.
CHEN Lijiang.Study on stochastic characteristics of freight rates of China’s export container liner based on ADF test [J].Journal of Wuhan University of Technology (Social Science Edition), 2013, 26(1): 15-20.
[22]CHUDIK A, PESARAN M H.Common correlated effects estimation of heterogeneous dynamic panel data models with weakly exogenous regressors [J].Journal of Econometrics, 2013, 188(2):393-420.
[23]王继新, 翟新婷, 毕野虹天, 等.基于AIC-K-means的载荷分段混合分布估计[J].吉林大学学报(工学版), 2018, 48(4): 1092-1098.
WANG Jixin, ZHAI Xinting, BIYE Hongtian, et al.Estimation of load piecewise mixed distribution based on AIC-K-means [J].Journal of Jilin University (Engineering and Technology Edition), 2018, 48(4): 1092-1098.
[24]ARLOT S, CELISSE A.A survey of cross validation procedures for model selection [J].Statistics Surveys, 2010, 4:40-79.
[25]何志昆, 刘光斌, 赵曦晶, 等.高斯过程回归方法综述[J].控制与决策, 2013, 28(8): 1121-1129.
HE Zhikun, LIU Guangbin, ZHAO Xijing, et al.A review of gaussian process regression methods [J].Control and Decision, 2013, 28(8): 1121-1129.
[26]尹金良, 朱永利, 俞国勤, 等.基于高斯过程分类器的变压器故障诊断[J].电工技术学报, 2013, 28(1): 158-164.
YIN Jinliang, ZHU Yongli, YU Guoqin, et al.Transformer fault diagnosis based on gaussian process classifier [J].Transactions of China Electrotechnical Society, 2013, 28(1): 158-164.
[27]DIAO Y, MEN X, SUN Z, et al.Structural damage identification based on the transmissibility function and support vector machine [J].Shock and Vibration, 2018,2018: 4892428.

PDF(1213 KB)

493

Accesses

0

Citation

Detail

段落导航
相关文章

/