A pattern recognition technique for structural identification using observed vibration signals: Nonlinear case studies

This and the companion article summarize linear and nonlinear structural identification (SI) methods using a pattern recognition technique, support vector regression (SVR). Signal processing plays a key role in the SI field, because observed data are often incomplete and contaminated by noise. Support vector regression (SVR) is a novel data processing technique that is superior in terms of its robustness, thus it has the potential to be applied for accurate and efficient structural identification. Three SVR-based methods employing the autoregression moving average (ARMA) time series, the high-order AR model, and the sub-structuring strategy are presented for linear structural parameter identification using observed vibration data. The SVR coefficient selection and incremental training algorithm have also been presented. Numerical evaluations demonstrate that the SVR-based methods identify structural parameters accurately. A five-floor structure shaking table test has also been conducted, and the observed data are used to verify experimentally the novel SVR technique for linear structural identification.

[1]  Y. Wen.  Approximate Method for Nonlinear Random Vibration , 1975 .

[2]  Giuseppe Lacidogna,et al.  In situ damage assessment and nonlinear modelling of a historical masonry tower , 2005 .

[3]  R. Bouc.  Forced Vibration of Mechanical Systems with Hysteresis , 1967 .

[4]  Jian Zhang.  Advanced signal processing technique for structural health monitoring , 2006 .

[5]  P. Ibáñez,et al.  Identification of dynamic parameters of linear and non-linear structural models from experimental data , 1973 .

[6]  Jann N. Yang,et al.  On-line identification of non-linear hysteretic structures using an adaptive tracking technique , 2004 .

[7]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[8]  Y. Sherif,et al.  Optimization by pattern search , 1994 .

[9]  N. Huang,et al.  System identification of linear structures based on Hilbert–Huang spectral analysis. Part 1: normal modes , 2003 .

[10]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[11]  C. Loh,et al.  A three-stage identification approach for hysteretic systems , 1993 .

[12]  A. McQuarrie,et al.  Regression and Time Series Model Selection , 1998 .

[13]  Wilfried B. Krätzig,et al.  Structural damage and life-time estimates by nonlinear FE simulation , 2005 .

[14]  Xinqun Zhu,et al.  Structural damage detection from wavelet packet sensitivity , 2005 .

[15]  Yi-Qing Ni,et al.  Multi-stage identification scheme for detecting damage in cable-stayed Kap Shui Mun Bridge , 2002 .

[16]  Alex H. Barbat,et al.  Equivalent linearization of the Bouc-Wen hysteretic model , 2000 .

[17]  F. Bakhtiari-Nejad,et al.  A structural damage detection method using static noisy data , 2005 .

[18]  Chan Ghee Koh,et al.  Substructural and progressive structural identification methods , 2003 .

[19]  John B. Mander,et al.  Parameter identification for degrading and pinched hysteretic structural concrete systems , 1997 .

[20]  W. T. Yeung,et al.  Damage detection in bridges using neural networks for pattern recognition of vibration signatures , 2005 .

[21]  James Theiler,et al.  Accurate On-line Support Vector Regression , 2003, Neural Computation.

[22]  Zucchini,et al.  An Introduction to Model Selection. , 2000, Journal of mathematical psychology.

[23]  Luis E. Suarez,et al.  Applications of wavelet transforms to damage detection in frame structures , 2004 .

[24]  Luis Alvarez-Icaza,et al.  LuGre friction model for a magnetorheological damper , 2005 .

[25]  Vikram Pakrashi,et al.  Structural damage detection and calibration using a wavelet-kurtosis technique , 2007 .

[26]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[27]  Yong-Lin Pi,et al.  Modal Identification of Vibrating Structures Using ARMA Model , 1989 .

[28]  Kai Qi,et al.  Adaptive H ∞ Filter: Its Application to Structural Identification , 1998 .

[29]  Sami F. Masri,et al.  Modeling and control of an electrorheological device for structural control applications , 1995 .

[30]  G. Kitagawa.  Monte Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models , 1996 .

[31]  G. De Roeck,et al.  System identification of mechanical structures by a high-order multivariate autoregressive model , 1997 .

[32]  Sami F. Masri,et al.  A Nonparametric Identification Technique for Nonlinear Dynamic Problems , 1979 .

[33]  Chung Bang Yun,et al.  Substructural identification using neural networks , 2000 .

[34]  Jinkoo Kim,et al.  Estimation of the modal mass of a structure with a tuned-mass damper using H-infinity optimal model reduction , 2006 .

[35]  Hani G. Melhem,et al.  Damage detection of structures by wavelet analysis , 2004 .

[36]  Mohamed Maalej,et al.  Adaptive magnitude spectrum algorithm for Hilbert–Huang transform based frequency identification , 2008 .

[37]  W. Ko,et al.  Identification of modal parameters from measured output data using vector backward autoregressive model , 2002 .

[38]  C. Loh,et al.  SYSTEM IDENTIFICATION OF FEI-TSUI ARCH DAM FROM FORCED VIBRATION AND SEISMIC RESPONSE DATA , 2000 .

[39]  Yi-Qing Ni,et al.  Correlating modal properties with temperature using long-term monitoring data and support vector machine technique , 2005 .