Eddy current defect characterization using neural networks : Materials evaluation, Vol. 48, No. 3, pp. 342–347 (Mar. 1990)

Abstract

This paper proposes the use of neural networks for interpreting signals from eddy current probes used in nondestructive testing (NDT). Classification results obtained by implementing a multilayered neural network using the back-propagation algorithm are presented. The merits of this approach as well as a comparison with traditional techniques for the classification of signals are also discussed