TY - JOUR
T1 - Dynamic-based damage identification using neural network ensembles and damage index method
AU - Dackermann, Ulrike
AU - Li, Jianchun
AU - Samali, Bijan
PY - 2010
Y1 - 2010
N2 - This paper presents a vibration-based damage identification method that utilises a "damage fingerprint" of a structure in combination with Principal Component Analysis (PCA) and neural network techniques to identify defects. The Damage Index (DI) method is used to extract unique damage patterns from a damaged beam structure with the undamaged structure as baseline. PCA is applied to reduce the effect of measurement noise and optimise neural network training. PCA-compressed DI values are, then, used as inputs for a hierarchy of neural network ensembles to estimate locations and severities of various damage cases. The developed method is verified by a laboratory structure and numerical simulations in which measurement noise is taken into account with different levels of white Gaussian noise added. The damage identification results obtained from the neural network ensembles show that the presented method is capable of overcoming problems inherent in the conventional DI method. Issues associated with field testing conditions are successfully dealt with for numerical and the experimental simulations. Moreover, it is shown that the neural network ensemble produces results that are more accurate than any of the outcomes of the individual neural networks.
AB - This paper presents a vibration-based damage identification method that utilises a "damage fingerprint" of a structure in combination with Principal Component Analysis (PCA) and neural network techniques to identify defects. The Damage Index (DI) method is used to extract unique damage patterns from a damaged beam structure with the undamaged structure as baseline. PCA is applied to reduce the effect of measurement noise and optimise neural network training. PCA-compressed DI values are, then, used as inputs for a hierarchy of neural network ensembles to estimate locations and severities of various damage cases. The developed method is verified by a laboratory structure and numerical simulations in which measurement noise is taken into account with different levels of white Gaussian noise added. The damage identification results obtained from the neural network ensembles show that the presented method is capable of overcoming problems inherent in the conventional DI method. Issues associated with field testing conditions are successfully dealt with for numerical and the experimental simulations. Moreover, it is shown that the neural network ensemble produces results that are more accurate than any of the outcomes of the individual neural networks.
UR - http://handle.uws.edu.au:8081/1959.7/535804
UR - http://search.ebscohost.com/login.aspx?direct=true&db=a9h&AN=55773201&site=ehost-live&scope=site
M3 - Article
SN - 1369-4332
VL - 13
SP - 1001
EP - 1016
JO - Advances in Structural Engineering
JF - Advances in Structural Engineering
IS - 6
ER -