Paper Titles
Damage Identification of a Mechanical Structure with a Non-Minimum Phase Based on Singular Value Decomposition
p.119
Wavelet Transform Domain Filter and Its Application in Incipient Fault Prognosis
p.127
Classification Using Radial Basis Function Networks with Uncertain Weights
p.135
Comparison of Different Methods of Ritz Vectors Extraction
p.143
Considerations for Practical Neural Network Application to a Damage Detection Problem
p.151
Impact Load Identification Based on Local Measurements
p.159
Extracting Gear Fault Features Using Maximal Bispectrum
p.167
Data Mining for Fault Diagnosis and Machine Learning for Rotating Machinery
p.175
Vibration Based Modal Parameters Identification and Wear Fault Diagnosis Using Laplace Wavelet
p.183

Considerations for Practical Neural Network Application to a Damage Detection Problem

Article Preview

Abstract:

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.

You might also be interested in these eBooks
Damage Assessment of Structures VI View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 293-294)

Pages:

151-158

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.293-294.151

Citation:

Cite this paper

Online since:

September 2005

Authors:

Gareth Pierce, Keith Worden, Graeme Manson

Keywords:

Damage Detection, Generalisation, Neural Network (NN), Regularisation, Thresholding

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2005 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

References

[1] R.P. Lippmann: IEEE Communications Magazine, 47, (11), (1989), pp.47-64.

Google Scholar

[2] G. P Zhang: IEEE Trans Systems, Man and Cybernetics-Part C: Applications and Reviews, 30 (4), (2000), pp.451-462.

Google Scholar

[3] P.J.G. Lisboa: Neural Networks 15, (2002), pp.11-39.

Google Scholar

[4] V.L. Berardi, B.E. Patuwo, and M.Y. Hu: Decision Support Systems 38, (2004), pp.233-246.

Google Scholar

[5] M.F. Augusteijn and B.A. Folkert: International Journal of Remote Sensing 23(14), (2002), pp.2891-2902.

Google Scholar

[6] A. Masnata and M. Sunseri: NDT&E International, 29 (2), (1996), pp.97-93.

Google Scholar

[7] G. Manson, K. Worden, and D. Allman: Journal of Sound and Vibration 259(2), (2003a), pp.345-363.

Google Scholar

[8] G. Manson, K. Worden, and D. Allman: Journal of Sound and Vibration 259(2), (2003b), pp.365-385.

Google Scholar

[9] S. Dreiseitl and L. Ohno-Machado: Journal of Biomedical Informatics 35, (2002), p.352359.

Google Scholar

[10] S. Haykin: Neural Networks, a Comprehensive Foundation (2nd edition), Prentice Hall (1999).

Google Scholar

[11] G. Schwarzer, W. Vach, and M. Schumacher: Statistics in Medicine 19, (2000), pp.541-561.

Google Scholar

[12] C.M. Bishop: Neural Networks for Pattern Recognition, Oxford University Press (1995).

Google Scholar

[13] I.T. Nabney: Netlab-Algorithms for Pattern Recognition, Springer-Verlag (2002).

Google Scholar

[14] D.J.C. MacKay: Information Theory, Inference, and Learning Algorithms, Cambridge University Press (2003).

Google Scholar