Enhanced features in principal component analysis with spatial and temporal windows for damage identification

Principal component analysis (PCA) methods have been widely applied to damage identification in the long-term structural health monitoring (SHM) of infrastructure. Usually, the first few eigenvector components derived by PCA methods are treated as damage-sensitive features. In this paper, the effective method of double-window PCA (DWPCA) and novel features are proposed for better damage identification performance. In the proposed method, spatial and temporal windows are introduced to the traditional PCA method. The spatial windows are applied to group damage-sensitive sensors and exclude those sensors insensitive to damage, while the temporal window is applied to better discriminate eigenvectors between the damaged and healthy states. In addition, the length and directional angle of the eigenvector variation between the healthy and damaged states are used as the damage-sensitive features, instead of the components of the eigenvector variation used in previous studies. Numerical simulations based on a large-scale bridge reveal that the proposed features are successful in identifying the damage located far from sensors due to the use of both spatial and temporal windows as well as the length of the eigenvector variation. In addition, compared to the previous PCA and moving PCA methods, the novel features have higher sensitivity and resolution in damage identification.

[1]  Ian F. C. Smith,et al.  Evaluating two model-free data interpretation methods for measurements that are influenced by temperature , 2011, Adv. Eng. Informatics.

[2]  Sami F. Masri,et al.  Finite Element Model Updating Using Evolutionary Strategy for Damage Detection , 2011, Comput. Aided Civ. Infrastructure Eng..

[3]  Samir Khatir,et al.  Inverse problem for dynamic structural health monitoring based on slime mould algorithm , 2021, Engineering with Computers.

[4]  Chen Yang,et al.  Damage detection using modal frequency curve and squared residual wavelet coefficients-based damage indicator , 2017 .

[5]  Jung-Ryul Lee,et al.  Structural health monitoring for a wind turbine system: a review of damage detection methods , 2008 .

[6]  Ge Zhang,et al.  Principal Component Analysis Method with Space and Time Windows for Damage Detection , 2019, Sensors.

[7]  José Rodellar,et al.  Data-driven multivariate algorithms for damage detection and identification: Evaluation and comparison , 2014 .

[8]  Bijan Samali,et al.  Damage identification in civil engineering structures utilizing PCA‐compressed residual frequency response functions and neural network ensembles , 2011 .

[9]  Ratneshwar Jha,et al.  Wavelet spectral finite element for modeling guided wave propagation and damage detection in stiffened composite panels , 2016 .

[10]  George K. Atia,et al.  Performance-based structural health monitoring through an innovative hybrid data interpretation framework , 2015 .

[11]  Ian F. C. Smith,et al.  Methodologies for model-free data interpretation of civil engineering structures , 2010 .

[12]  James H. Garrett,et al.  Exploration and evaluation of AR, MPCA and KL anomaly detection techniques to embankment dam piezometer data , 2015, Adv. Eng. Informatics.

[13]  Luis Eduardo Mujica,et al.  Damage classification in structural health monitoring using principal component analysis and self‐organizing maps , 2013 .

[14]  A. Rama Mohan Rao,et al.  Nonlinear identification of structures using ambient vibration data , 2015 .

[15]  Abbas Karamodin,et al.  A novel anomaly detection method based on adaptive Mahalanobis-squared distance and one-class kNN rule for structural health monitoring under environmental effects , 2020 .

[16]  B. F. Spencer,et al.  A Test Method for Damage Diagnosis of Suspension Bridge Suspender Cables , 2015, Comput. Aided Civ. Infrastructure Eng..

[17]  H. Tran-Ngoc,et al.  Finite element model updating of a multispan bridge with a hybrid metaheuristic search algorithm using experimental data from wireless triaxial sensors , 2021, Engineering with Computers.

[18]  Ge Zhang,et al.  Analysis of structural responses of bridges based on long-term structural health monitoring , 2018 .

[19]  Mustafa Gul,et al.  An integrated approach for structural health monitoring using an in-house built fiber optic system and non-parametric data analysis , 2014 .

[20]  Hassan Sarmadi,et al.  Energy-based damage localization under ambient vibration and non-stationary signals by ensemble empirical mode decomposition and Mahalanobis-squared distance , 2019 .

[21]  Yi-Zhou Lin,et al.  Structural Damage Detection with Automatic Feature‐Extraction through Deep Learning , 2017, Comput. Aided Civ. Infrastructure Eng..

[22]  Takehisa Yairi,et al.  A review on the application of deep learning in system health management , 2018, Mechanical Systems and Signal Processing.

[23]  Burcu Gunes,et al.  International Journal of Physical Sciences Structural Health Monitoring and Damage Assessment Part I: a Critical Review of Approaches and Methods , 2011 .

[24]  Ian F. C. Smith,et al.  Model-free data interpretation for continuous monitoring of complex structures , 2008, Adv. Eng. Informatics.

[25]  A. Rama Mohan Rao,et al.  Damage diagnostic technique for structural health monitoring using POD and self adaptive differential evolution algorithm , 2012 .

[26]  Gaëtan Kerschen,et al.  Distortion function and clustering for local linear models , 2005 .

[27]  Zhishen Wu,et al.  Vibration‐Based Damage Localization in Flexural Structures Using Normalized Modal Macrostrain Techniques from Limited Measurements , 2011, Comput. Aided Civ. Infrastructure Eng..

[28]  PosenatoDaniele,et al.  Model-free data interpretation for continuous monitoring of complex structures , 2008 .

[29]  Chun Zhang,et al.  Damage identification in bridge structures subject to moving vehicle based on extended Kalman filter with l1-norm regularization , 2020, Inverse Problems in Science and Engineering.

[30]  Wai Lok Woo,et al.  Impact Damage Detection and Identification Using Eddy Current Pulsed Thermography Through Integration of PCA and ICA , 2014, IEEE Sensors Journal.

[31]  Naresh G. Jaiswal,et al.  Investigation on Selection of Optimal Mother Wavelet in Mode Shape based Damage Detection Exercise , 2017 .

[32]  K Lakshmi,et al.  Output-only damage localization technique using time series model , 2018, Sādhanā.

[33]  Ian F. C. Smith,et al.  Combined Model-Free Data-Interpretation Methodologies for Damage Detection during Continuous Monitoring of Structures , 2013, J. Comput. Civ. Eng..

[34]  H. Van Brussel,et al.  On feature extraction for condition monitoring using time series analysis and distance techniques , 1999 .

[35]  Jean-Claude Golinval,et al.  Null subspace-based damage detection of structures using vibration measurements , 2006 .