Loading...
Loading...

Go to the content (press return)

A study of two unsupervised data driven statistical methodologies for detecting and classifying damages in structural health monitoring

Author
Tibaduiza, D.A.; Torres-Arredondo, M.A.; Mujica, L.E.; Rodellar, J.; Fritzen, C.P
Type of activity
Journal article
Journal
Mechanical systems and signal processing
Date of publication
2013-12-06
Volume
41
Number
1-2
First page
467
Last page
484
DOI
https://doi.org/10.1016/j.ymssp.2013.05.020 Open in new window
Project funding
Estructuras inteligentes: sistemas de monitorización e identificación de daños con aplicación en aeronáutica y en plantas eólicas
URL
http://www.sciencedirect.com/science/article/pii/S0888327013002793 Open in new window
Abstract
This article is concerned with the practical use of Multiway Principal Component Analysis (MPCA), Discrete Wavelet Transform (DWT), Squared Prediction Error (SPE) measures and Self-Organizing Maps (SOM) to detect and classify damages in mechanical structures. The formalism is based on a distributed piezoelectric active sensor network for the excitation and detection of structural dynamic responses. Statistical models are built using PCA when the structure is known to be healthy either directly f...
Keywords
Active ultrasonic guided-wave testing, Discrete wavelet transform, Principal component analysis, Self-organizing maps, Structural health monitoring
Group of research
CoDAlab - Control, Dynamics and Applications

Participants