Support vector machines for automated modelling of nonlinear structures using health monitoring results

Abstract Structural health monitoring (SHM) is backwards analysis of past to current state of damage, but cannot create a structure-specific nonlinear model for forward analysis of future response and damage. This paper aims to develop an automated modelling approach to translate proven hysteresis loop analysis (HLA) SHM results into nonlinear foundation models for response forecasting in subsequent events, particularly for steel structures with post-yielding behaviors. Support vector machine (SVM) is employed to identify the proposed nonlinear baseline model. Stiffness features are extracted from HLA to train the SVM model incorporating the constraints of SHM identification. A proof-of-concept case study validates the ability of the proposed method to accurately identify 12 model parameters with average error of 2.8% for a nonlinear numerical structure in the presence of 10% RMS measurement noise. Experimental validation from a full-scale 3-storey real building shows the predicted nonlinear responses match the measured response well with cross correlation coefficients Rcoeff = 0.94, 0.92 and 0.89 for the first, second and third floor, respectively. In addition, the predicted stiffness changes also match the SHM results very well with errors less than 2.1%. Finally, and most importantly, the identified model is able to predict the response of 2 further events with average of correlation coefficient Rcoeff = 0.91 and average error of 1.9% for stiffness changes across all cases. The overall results validate the ability of the created predictive model to accurately capture the essential dynamics and structural degradation, as well as predicting future possible response and risk.

[1]  John B. Mander,et al.  Incremental dynamic analysis applied to seismic financial risk assessment of bridges , 2007 .

[2]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[3]  Cong Zhou,et al.  Physical Parameter Identification of Structural Systems with Hysteretic Pinching , 2015, Comput. Aided Civ. Infrastructure Eng..

[4]  Y. Wen.  Method for Random Vibration of Hysteretic Systems , 1976 .

[5]  Chih-Jen Lin,et al.  Working Set Selection Using Second Order Information for Training Support Vector Machines , 2005, J. Mach. Learn. Res..

[6]  Keith Worden,et al.  IDENTIFICATION OF HYSTERETIC SYSTEMS USING THE DIFFERENTIAL EVOLUTION ALGORITHM , 2001 .

[7]  J. Suykens.  Nonlinear modelling and support vector machines , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[8]  Andrew W. Smyth,et al.  Real-time parameter estimation for degrading and pinching hysteretic models , 2008 .

[9]  John B. Mander,et al.  A simple LMS‐based approach to the structural health monitoring benchmark problem , 2005 .

[10]  Jiuchao Feng,et al.  Real-time nonlinear structural system identification via iterated unscented Kalman filter , 2012 .

[11]  Cong Zhou,et al.  Comparing model-based adaptive LMS filters and a model-free hysteresis loop analysis method for structural health monitoring , 2017 .

[12]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[13]  J. Weston,et al.  Support Vector Machine Solvers , 2007 .

[14]  J. G. Chase,et al.  LMS-based approach to structural health monitoring of nonlinear hysteretic structures , 2011 .

[15]  Mohammed Ismail,et al.  The Hysteresis Bouc-Wen Model, a Survey , 2009 .

[16]  Dimitrios Vamvatsikos,et al.  Incremental dynamic analysis , 2002 .

[17]  Cong Zhou,et al.  Degradation evaluation of lateral story stiffness using HLA-based deep learning networks , 2019, Adv. Eng. Informatics.

[18]  H. Zhang,et al.  Parameter Analysis of the Differential Model of Hysteresis , 2004 .

[19]  Chu-Kia Wang,et al.  Reinforced Concrete Design , 1965 .

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

[21]  Y. K. Wen,et al.  Stochastic Equivalent Linearization for Hysteretic, Degrading, Multistory Strutctures , 1980 .

[22]  Sang Whan Han,et al.  Approximate incremental dynamic analysis using the modal pushover analysis procedure , 2006 .

[23]  Zhang Yigong,et al.  Nonlinear structural identification using extended kalman filter , 1994 .

[24]  José Rodellar,et al.  Dynamic properties of the hysteretic Bouc-Wen model , 2007, Syst. Control. Lett..

[25]  Mohammad Noori,et al.  Random Vibration of Degrading, Pinching Systems , 1985 .

[26]  Li Zhou,et al.  An adaptive extended Kalman filter for structural damage identification , 2006 .

[27]  Richard W. Longman,et al.  On‐line identification of non‐linear hysteretic structural systems using a variable trace approach , 2001 .

[28]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[29]  Yongmin Yang,et al.  Parameter identification of inelastic structures under dynamic loads , 2002 .

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

[31]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[32]  Andrew W. Smyth,et al.  Application of the unscented Kalman filter for real‐time nonlinear structural system identification , 2007 .

[33]  Yi-Qing Ni,et al.  IDENTIFICATION OF NON-LINEAR HYSTERETIC ISOLATORS FROM PERIODIC VIBRATION TESTS , 1998 .

[34]  V. K. Koumousis,et al.  A Bouc–Wen model compatible with plasticity postulates , 2009 .

[35]  George A. F. Seber,et al.  Linear regression analysis , 1977 .

[36]  S. Sathiya Keerthi,et al.  Evaluation of simple performance measures for tuning SVM hyperparameters , 2003, Neurocomputing.

[37]  Sergio M. Savaresi,et al.  Identification of semi-physical and black-box non-linear models: the case of MR-dampers for vehicles control , 2005, Autom..

[38]  Cong Zhou,et al.  Damage assessment by stiffness identification for a full-scale three-story steel moment resisting frame building subjected to a sequence of earthquake excitations , 2017, Bulletin of Earthquake Engineering.

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

[40]  Bernhard Schölkopf,et al.  Comparing support vector machines with Gaussian kernels to radial basis function classifiers , 1997, IEEE Trans. Signal Process..