桥梁数据异常诊断方法在伸缩缝监测中的应用
|
摘要
针对由桥梁结构损伤和监测系统传感器故障引起的桥梁数据异常诊断问题,提出了一种基于主成分分析和超球面一类支持向量机的桥梁数据异常诊断方法。首先,对原始信号进行预处理和小波阈值去噪,然后,统计信号的时域、频域及自回归模型系数特征,利用主成分分析进行特征提取获得重要特征,最后,利用超球面一类支持向量机进行异常模式识别。通过江阴大桥伸缩缝相关监测数据表明,该方法可以较好识别和伸缩缝相关的数据异常,防止监测系统误报漏报的发生。
The bridge data novelty diagnosis generated by the bridge structure damage or sensor fault,is a challenging problem for researchers in structural health monitoring area.A novel method has proposed which is based on a principal component analysis and hyperspherical one-class support vector machine toward the problem.Firstly,the original signal is pre-processed and denoised by wavelet threshold.Secondly,for the filtered signal,the statistical features in time domain,frequency domain and the autoregressive coefficients are used to construct its feature vector.Finally,the main feature vector generated from principal component analysis is presented to the hyperspherical one-class support vector machine for examination.The method is demonstrated on the monitoring data of an expansion joint in the Jiangyin bridge.It shows the accuracy and efficiency of the method for the identification of abnormal data.
The bridge data novelty diagnosis generated by the bridge structure damage or sensor fault,is a challenging problem for researchers in structural health monitoring area.A novel method has proposed which is based on a principal component analysis and hyperspherical one-class support vector machine toward the problem.Firstly,the original signal is pre-processed and denoised by wavelet threshold.Secondly,for the filtered signal,the statistical features in time domain,frequency domain and the autoregressive coefficients are used to construct its feature vector.Finally,the main feature vector generated from principal component analysis is presented to the hyperspherical one-class support vector machine for examination.The method is demonstrated on the monitoring data of an expansion joint in the Jiangyin bridge.It shows the accuracy and efficiency of the method for the identification of abnormal data.
引文
[1]袁万成,崔飞,张启伟.桥梁健康监测与状态评估的研究现状与发展[J].同济大学学报,1999,27(2):184-188.
[2]Zimmerman D C,Kaouk M.Eigenstructureassignment approach for structural damage detection[J].AIAA Journal,1992,30(12):1848-1855.
[3]Fritzen C P,Jennewein D,Kiefer T.Damagedetection based on model updating methods[J].Mechanical Systems and Signal Process,1998,12(1):163-186.
[4]王兆辉,樊可清,李霆.系统辨识在桥梁状态监测中的应用[J].中南公路工程,2006,31(3):159-163.
[5]Pandey A K,Biswas M,Samman M M.Damagedetection from changes in curvature mode shapes[J].Journal of Sound and Vibration,1991,45(2):321-332.
[6]Topole K G,Stubbs N.Non-destructive damageevaluation of a structure from limited modalparameters[J].Earthquake Engineering&Structural Dynamics,1995,24(11):1427-1436.
[7]Sun Z,Chang C C.Structural damage assessmentbased on wavelet packet transform[J].Journal ofStructure Engineering,2002,128(10):1354-1361.
[8]Zhang Q W.Statistical damage identification forbridge using ambient vibration data[J].Computers&Structures,2007,85:476-485.
[9]滕龙,曾储惠.模式识别技术在桥路状态评估与安全监测中的应用[J].中国铁道科学,2005,26(4):47-51.
[10]张启伟.桥梁健康监测中的损伤特征提取与异常诊断[J].同济大学学报,2003,31(3):258-262.
[11]Jolliffe I T.Principal component analysis[M].2ndEdition.[S.l.]:Springer Serires in Statistics,2002.
[12]Scholkopf B,Platt J C,Shawe-Taylor J.Estimatingthe support of a high-dimensional distribution[J].Neural Computation,2001,13(7):1443-1471.
[13]Tax D,Duin R P.Support vector domain description[J].Pattern Recognition Letters,1999,20(11/13):1191-1199.
[14]张宇峰,朱仕村,姚蓓,等.苏通大桥在汶川地震作用下的结构动力响应分析[C]//大跨经桥梁结构损伤预警及状态评估技术研讨会论文集.南京,中国:[s.n.],2010,10:272-281.
[15]Niu Gang,Widodo A,Son J D,et al.Decision-levelfusion based on wavelet decomposition for inductionmotor fault diagnosis using transient current signal[J].Expert Systems with Application,2008(35):918-928.
[16]Niu Gang,Lee S S,Yang B S,et al.Decision fusionsystem for fault diagnosis of elevator tractionmachine[J].Journal of Mechanical Science andTechnology,2008,22:85-95.
[17]Marple Jr S L.Digital spectral analysis withapplications[M].Prentice Hall:Englewood Cliffs,1987.
[18]冯爱民,刘学军,孙廷凯.嵌入数据结构信息的单类支持向量机及其线性规划算法[J].中山大学学报,2009,48(6):10-17.
[2]Zimmerman D C,Kaouk M.Eigenstructureassignment approach for structural damage detection[J].AIAA Journal,1992,30(12):1848-1855.
[3]Fritzen C P,Jennewein D,Kiefer T.Damagedetection based on model updating methods[J].Mechanical Systems and Signal Process,1998,12(1):163-186.
[4]王兆辉,樊可清,李霆.系统辨识在桥梁状态监测中的应用[J].中南公路工程,2006,31(3):159-163.
[5]Pandey A K,Biswas M,Samman M M.Damagedetection from changes in curvature mode shapes[J].Journal of Sound and Vibration,1991,45(2):321-332.
[6]Topole K G,Stubbs N.Non-destructive damageevaluation of a structure from limited modalparameters[J].Earthquake Engineering&Structural Dynamics,1995,24(11):1427-1436.
[7]Sun Z,Chang C C.Structural damage assessmentbased on wavelet packet transform[J].Journal ofStructure Engineering,2002,128(10):1354-1361.
[8]Zhang Q W.Statistical damage identification forbridge using ambient vibration data[J].Computers&Structures,2007,85:476-485.
[9]滕龙,曾储惠.模式识别技术在桥路状态评估与安全监测中的应用[J].中国铁道科学,2005,26(4):47-51.
[10]张启伟.桥梁健康监测中的损伤特征提取与异常诊断[J].同济大学学报,2003,31(3):258-262.
[11]Jolliffe I T.Principal component analysis[M].2ndEdition.[S.l.]:Springer Serires in Statistics,2002.
[12]Scholkopf B,Platt J C,Shawe-Taylor J.Estimatingthe support of a high-dimensional distribution[J].Neural Computation,2001,13(7):1443-1471.
[13]Tax D,Duin R P.Support vector domain description[J].Pattern Recognition Letters,1999,20(11/13):1191-1199.
[14]张宇峰,朱仕村,姚蓓,等.苏通大桥在汶川地震作用下的结构动力响应分析[C]//大跨经桥梁结构损伤预警及状态评估技术研讨会论文集.南京,中国:[s.n.],2010,10:272-281.
[15]Niu Gang,Widodo A,Son J D,et al.Decision-levelfusion based on wavelet decomposition for inductionmotor fault diagnosis using transient current signal[J].Expert Systems with Application,2008(35):918-928.
[16]Niu Gang,Lee S S,Yang B S,et al.Decision fusionsystem for fault diagnosis of elevator tractionmachine[J].Journal of Mechanical Science andTechnology,2008,22:85-95.
[17]Marple Jr S L.Digital spectral analysis withapplications[M].Prentice Hall:Englewood Cliffs,1987.
[18]冯爱民,刘学军,孙廷凯.嵌入数据结构信息的单类支持向量机及其线性规划算法[J].中山大学学报,2009,48(6):10-17.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心