Time-Varying Identification Model for Crack Monitoring Data from Concrete Dams Based on Support Vector Regression and the Bayesian Framework

被引:18
作者
Chen, Bo [1 ,2 ,3 ,4 ]
Wu, Zhongru [1 ,3 ,4 ]
Liang, Jiachen [1 ,3 ,4 ]
Dou, Yanhong [4 ]
机构
[1] Hohai Univ, State Key Lab Hydrol Water Resources & Hydraul En, Nanjing 210098, Jiangsu, Peoples R China
[2] Minist Water Resources, Key Lab Earth Rock Dam Failure Mech & Safety Cont, Nanjing 210029, Jiangsu, Peoples R China
[3] Hohai Univ, Natl Engn Res Ctr Water Resources Efficient Utili, Nanjing 210098, Jiangsu, Peoples R China
[4] Hohai Univ, Coll Water Conservancy & Hydropower Engn, Nanjing 210098, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
FRACTURE PARAMETERS; ABNORMALITY; PROPAGATION; DIAGNOSIS; KERNEL;
D O I
10.1155/2017/5450297
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The modeling of cracks and identification of dam behavior changes are difficult issues in dam health monitoring research. In this paper, a time-varying identification model for crack monitoring data is built using support vector regression (SVR) and the Bayesian evidence framework (BEF). First, the SVR method is adopted for better modeling of the nonlinear relationship between the crack opening displacement (COD) and its influencing factors. Second, the BEF approach is applied to determine the optimal SVR modeling parameters, including the penalty coefficient, the loss coefficient, and the width coefficient of the radial kernel function, under the principle that the prediction errors between the monitored and the model forecasted values are as small as possible. Then, considering the predicted COD, the historical maximum COD, and the time-dependent component, forewarning criteria are proposed for identifying the time-varying behavior of cracks and the degree of abnormality of dam health. Finally, an example of modeling and forewarning analysis is presented using two monitoring subsequences from a real structural crack in the Chencun concrete arch-gravity dam. The findings indicate that the proposed time-varying model can provide predicted results that are more accurately nonlinearity fitted and is suitable for use in evaluating the behavior of cracks in dams.
引用
收藏
页数:11
相关论文
共 41 条
[1]   Lagrangian support vector regression via unconstrained convex minimization [J].
Balasundaram, S. ;
Gupta, Deepak ;
Kapil .
NEURAL NETWORKS, 2014, 51 :67-79
[2]   Study on crack propagation of adhesively bonded DCB for aluminum foam using energy release rate [J].
Bang, Hyejin ;
Lee, Sang-kyo ;
Cho, Chongdu ;
Cho, Jae Ung .
JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2015, 29 (01) :45-50
[3]   Abnormality monitoring model of cracks in concrete dams [J].
Bao TengFei ;
Qin Dong ;
Zhou XiWu ;
Wu GuiFen .
SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2011, 54 (07) :1914-1922
[4]   Concrete pavement monitoring with PPP-BOTDA distributed strain and crack sensors [J].
Bao, Yi ;
Tang, Fujian ;
Chen, Yizheng ;
Meng, Weina ;
Huang, Ying ;
Chen, Genda .
SMART STRUCTURES AND SYSTEMS, 2016, 18 (03) :405-423
[5]  
Bishop CM, 1995, Neural Networks for Pattern Recognition
[6]   On the modelling of nonlinear dynamic systems using support vector neural networks [J].
Chan, WC ;
Chan, CW ;
Cheung, KC ;
Harris, CJ .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2001, 14 (02) :105-113
[7]   Cracking analysis of arch dams by 3D boundary element method [J].
Feng, LM ;
Pekau, OA ;
Zhang, CH .
JOURNAL OF STRUCTURAL ENGINEERING-ASCE, 1996, 122 (06) :691-699
[8]   Crack Modeling for Structural Health Monitoring [J].
Friswell, M. I. ;
Penny, J. E. T. .
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2002, 1 (02) :139-148
[9]   Support vector regression for black-box system identification [J].
Gretton, A ;
Doucet, A ;
Herbrich, R ;
Rayner, PJW ;
Schölkopf, B .
2001 IEEE WORKSHOP ON STATISTICAL SIGNAL PROCESSING PROCEEDINGS, 2001, :341-344
[10]   Study on Semi-Parametric Statistical Model of Safety Monitoring of Cracks in Concrete Dams [J].
Gu, Chongshi ;
Qin, Dong ;
Li, Zhanchao ;
Zheng, Xueqin .
MATHEMATICAL PROBLEMS IN ENGINEERING, 2013, 2013