Share Email Print
cover

Proceedings Paper

Classification of eddy current signals using fuzzy logic and neural networks
Author(s): Hartmut Ewald; Michael Stieper
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The nondestructive eddy current methods are commonly used for automated defect inspection to detect cracks in materials which are used in cars, power and aircraft industries. The eddy current signal from a infinitely long crack can be classified with the help of the fuzzy logic and the neural network techniques. A rule based fuzzy logic classification guarantees better results than fuzzy-cluster- means algorithm, because the classification results can be increased in this case step by step. By using the neural network for the classification of the crack signals it is very important to have a good 'learning pattern.' The advantage of time-delay networks in this application is the fact that the network can 'learn' the eddy-current time signal; a signal preprocessing is not necessary.

Paper Details

Date Published: 14 November 1996
PDF: 10 pages
Proc. SPIE 2947, Nondestructive Evaluation of Utilities and Pipelines, (14 November 1996); doi: 10.1117/12.259171
Show Author Affiliations
Hartmut Ewald, Hochschule Wismar (Germany)
Michael Stieper, Hochschule Wismar (Germany)


Published in SPIE Proceedings Vol. 2947:
Nondestructive Evaluation of Utilities and Pipelines
Martin Prager; Richard M. Tilley, Editor(s)

© SPIE. Terms of Use
Back to Top