Considerations for Practical Neural Network Application to a Damage Detection Problem

Abstract:

Article Preview

The application of a multilayer perceptron (MLP) neural network to a damage location problem on a GNAT aircraft wing is considered. The problems associated with effective network training and evaluation are discussed, focussing on ensuring good generalisation performance of the network to the classification of new data. Both conventional Maximum Likelihood and Bayesian Evidence based training techniques are considered and a simple thresholding technique is presented to aid in the rejection of poorly regularised network structures. Examples are presented for an artificial simple 2 class problem (drawn from a Gaussian distribution) and a real 9 class problem on the GNAT aircraft wing.

Info:

Periodical:

Key Engineering Materials (Volumes 293-294)

Edited by:

W.M. Ostachowicz, J.M. Dulieu-Barton, K.M. Holford, M. Krawczuk and A. Zak

Pages:

151-158

DOI:

10.4028/www.scientific.net/KEM.293-294.151

Citation:

G. Pierce et al., "Considerations for Practical Neural Network Application to a Damage Detection Problem ", Key Engineering Materials, Vols. 293-294, pp. 151-158, 2005

Online since:

September 2005

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.