Three-way analysis of Structural Health Monitoring data

Structural Health Monitoring aims to identify damages in engineering structures by monitoring changes in their vibration response. Unsupervised learning algorithms can be used to obtain a model of the undamaged condition and detect which samples are not in agreement with it. However, in real structures with a sensor network configuration, the number of candidate features usually becomes large. Therefore, complexity increases and it is necessary to perform feature selection and/or dimensionality reduction. We propose to exploit the three-way structure of data and apply a true multi-way data analysis algorithm: parallel factor analysis. A simple model is obtained and used to train accurate novelty detectors. The methods are tested both with real and simulated structural data to assess that three-way analysis can be successfully used in structural health monitoring.

[1]  Jaakko Hollmén,et al.  Novelty Detection in Projected Spaces for Structural Health Monitoring , 2010, IDA.

[2]  Michel Verleysen,et al.  Multivariate statistics process control for dimensionality reduction in structural assessment , 2008 .

[3]  S. Huffel,et al.  Neonatal seizure localization using PARAFAC decomposition , 2009, Clinical Neurophysiology.

[4]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

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

[6]  Liqing Zhang,et al.  Noninvasive BCIs: Multiway Signal-Processing Array Decompositions , 2008, Computer.

[7]  J. Leeuw,et al.  Principal component analysis of three-mode data by means of alternating least squares algorithms , 1980 .

[8]  Rasmus Bro,et al.  Multi-way Analysis with Applications in the Chemical Sciences , 2004 .

[9]  Rasmus Bro,et al.  The N-way Toolbox for MATLAB , 2000 .

[10]  Bülent Yener,et al.  Unsupervised Multiway Data Analysis: A Literature Survey , 2009, IEEE Transactions on Knowledge and Data Engineering.

[11]  Keith Worden,et al.  An introduction to structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[12]  Charles R. Farrar,et al.  Damage detection in building joints by statistical analysis , 2000 .

[13]  K. Worden,et al.  The application of machine learning to structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[14]  D. Adams,et al.  Transmissibility as a Differential Indicator of Structural Damage , 2002 .

[15]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[16]  Andrzej Cichocki,et al.  Nonnegative Matrix and Tensor Factorization T , 2007 .

[17]  Jaakko Hollmén,et al.  Feature Extraction and Selection from Vibration Measurements for Structural Health Monitoring , 2009, IDA.