Vibration-based damage detection using online learning algorithm for output-only structural health monitoring

Damage-sensitive features such as natural frequencies are widely used for structural health monitoring; however, they are also influenced by the environmental condition. To address the environmental effect, principal component analysis is widely used. Before performing principal component analysis, the training data should be defined for the normal condition (baseline model) under environmental variability. It is worth noting that the natural change of the normal condition may exist due to an intrinsic behavior of the structural system. Without accounting for the natural change of the normal condition, numerous false alarms occur. However, the natural change of the normal condition cannot be known in advance. Although the description of the normal condition has a significant influence on the monitoring performance, it has received much less attention. To capture the natural change of the normal condition and detect the damage simultaneously, an adaptive statistical process monitoring using online learning algorithm is proposed for output-only structural health monitoring. The novelty aspect of the proposed method is the adaptive learning capability by moving the window of the recent samples (from normal condition) to update the baseline model. In this way, the baseline model can reflect the natural change of the normal condition in environmental variability. To handle both change rate of the normal condition and non-linear dependency of the damage-sensitive features, a variable moving window strategy is also proposed. The variable moving window strategy is the block-wise linearization method using k-means clustering based on Linde–Buzo–Gray algorithm and Bayesian information criterion. The proposed method and two existing methods (static linear principal component analysis and incremental linear principal component analysis) were applied to a full-scale bridge structure, which was artificially damaged at the end of the long-term monitoring. Among the three methods, the proposed method is the only successful method to deal with the non-linear dependency among features and detect the structural damage timely.

[1]  D.D.L. Chung,et al.  Structural health monitoring by electrical resistance measurement , 2001 .

[2]  Chandler Davis.  The rotation of eigenvectors by a perturbation , 1963 .

[3]  Age K. Smilde,et al.  Principal Component Analysis , 2003, Encyclopedia of Machine Learning.

[4]  D. K. Watson,et al.  Seasonal variation in material properties of a flexible pavement , 1997 .

[5]  Zhang Yi,et al.  A New Incremental PCA Algorithm With Application to Visual Learning and Recognition , 2009, Neural Processing Letters.

[6]  Keith Worden,et al.  Long-term stability of normal condition data for novelty detection , 2000, Smart Structures.

[7]  Pasi Fränti,et al.  Knee Point Detection in BIC for Detecting the Number of Clusters , 2008, ACIVS.

[8]  Stefano Marsili-Libelli,et al.  Adaptive data-derived anomaly detection in the activated sludge process of a large-scale wastewater treatment plant , 2016, Eng. Appl. Artif. Intell..

[9]  Bogdan Gabrys,et al.  Review of adaptation mechanisms for data-driven soft sensors , 2011, Comput. Chem. Eng..

[10]  G. De Roeck,et al.  DESCRIPTION OF Z24 BENCHMARK , 2003 .

[11]  Gaëtan Kerschen,et al.  Structural damage diagnosis under varying environmental conditions—Part I: A linear analysis , 2005 .

[12]  A. Raftery,et al.  Model-based Gaussian and non-Gaussian clustering , 1993 .

[13]  Ieee Yuan.  A Dimensionality Reduction Framework for Detection of Multiscale Structure in Heterogeneous Networks , 2012 .

[14]  Chonghun Han,et al.  Robust Recursive Principal Component Analysis Modeling for Adaptive Monitoring , 2006 .

[15]  G. De Roeck,et al.  Z24 bridge damage detection tests , 1999 .

[16]  Xiao Bin He,et al.  Variable MWPCA for Adaptive Process Monitoring , 2008 .

[17]  Yozo Fujino,et al.  Bridge monitoring in Japan: the needs and strategies , 2011 .

[18]  Hashem Shariatmadar,et al.  An unsupervised learning approach by novel damage indices in structural health monitoring for damage localization and quantification , 2018 .

[19]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[20]  Edwin Reynders,et al.  Output-only structural health monitoring in changing environmental conditions by means of nonlinear system identification , 2014 .

[21]  Guido De Roeck,et al.  REFERENCE-BASED STOCHASTIC SUBSPACE IDENTIFICATION FOR OUTPUT-ONLY MODAL ANALYSIS , 1999 .

[22]  Luis Eduardo Mujica,et al.  Q-statistic and T2-statistic PCA-based measures for damage assessment in structures , 2011 .

[23]  W. Kahan,et al.  The Rotation of Eigenvectors by a Perturbation. III , 1970 .

[24]  In-Beum Lee,et al.  Adaptive multivariate statistical process control for monitoring time-varying processes , 2006 .

[25]  Jyh-Cheng Jeng,et al.  Adaptive process monitoring using efficient recursive PCA and moving window PCA algorithms , 2010 .

[26]  Guido De Roeck,et al.  One-year monitoring of the Z24-Bridge : environmental effects versus damage events , 2001 .

[27]  Babak Moaveni,et al.  Environmental effects on the identified natural frequencies of the Dowling Hall Footbridge , 2011 .

[28]  Hoon Sohn,et al.  Damage diagnosis under environmental and operational variations using unsupervised support vector machine , 2009 .

[29]  John F. MacGregor,et al.  Multivariate SPC charts for monitoring batch processes , 1995 .

[30]  Victor Giurgiutiu,et al.  Electro-Mechanical Impedance Method for Crack Detection in Thin Plates , 2001 .

[31]  David A. Nix,et al.  Vibration–based structural damage identification , 2001, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[32]  Daniel T. Larose,et al.  Data Mining and Predictive Analytics , 2015 .

[33]  Hyung-Jo Jung,et al.  Adaptive reference updating for vibration-based structural health monitoring under varying environmental conditions , 2015 .

[34]  Gaëtan Kerschen,et al.  Structural damage diagnosis under varying environmental conditions - Part II: local PCA for non-linear cases , 2005 .

[35]  Issam Dagher,et al.  Face recognition using IPCA-ICA algorithm , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Mia Hubert,et al.  Parameter selection guidelines for adaptive PCA‐based control charts , 2016 .

[37]  R. A. van den Berg,et al.  Centering, scaling, and transformations: improving the biological information content of metabolomics data , 2006, BMC Genomics.

[38]  Mia Hubert,et al.  Overview of PCA-Based Statistical Process-Monitoring Methods for Time-Dependent, High-Dimensional Data , 2015 .

[39]  Lirong Xia,et al.  Process monitoring based on improved recursive PCA methods by adaptive extracting principal components , 2013 .

[40]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[41]  Charles R. Farrar,et al.  The fundamental axioms of structural health monitoring , 2007, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[42]  Young-Jin Cha,et al.  Unsupervised novelty detection–based structural damage localization using a density peaks-based fast clustering algorithm , 2018 .

[43]  G. Irwin,et al.  Process monitoring approach using fast moving window PCA , 2005 .