Universiti Teknologi Malaysia Institutional Repository

A comparison of artificial neural network learning algorithms for vibration-based damage detection

Goh, Lyn Dee and Bakhary, Norhisham and Abd. Rahman, Azlan and Ahmad, Baderul Hisham (2011) A comparison of artificial neural network learning algorithms for vibration-based damage detection. In: Advances in Structures. Trans Tech Publications, Switzerland, pp. 2756-2760. ISBN 978-087849206-0

Full text not available from this repository.

Official URL: http://dx.doi.org/10.4028/www.scientific.net/AMR.1...


This paper investigates the performance of Artificial Neural Network (ANN) learning algorithms for vibration-based damage detection. The capabilities of six different learning algorithms in detecting damage are studied and their performances are compared. The algorithms are Levenberg-Marquardt (LM), Resilient Backpropagation (RP), Scaled Conjugate Gradient (SCG), Conjugate Gradient with Powell-Beale Restarts (CGB), Polak-Ribiere Conjugate Gradient (CGP) and Fletcher-Reeves Conjugate Gradient (CGF) algorithms. The performances of these algorithms are assessed based on their generalisation capability in relating the vibration parameters (frequencies and mode shapes) with damage locations and severities under various numbers of input and output variables. The results show that Levenberg-Marquardt algorithm provides the best generalisation performance.

Item Type:Book Section
Additional Information:2011 International Conference on Structures and Building Materials
Uncontrolled Keywords:damage detection, learning algorithm, neural network (NN)
Subjects:T Technology > TA Engineering (General). Civil engineering (General)
Divisions:Civil Engineering
ID Code:24159
Deposited By: Liza Porijo
Deposited On:25 Jun 2012 03:42
Last Modified:10 Oct 2017 04:39

Repository Staff Only: item control page