Quantitative profile evaluation of natural cracks in a steam generator tube from eddy current signals

This paper reports the progress of studies in eddy current inversion in the authors' group and a novel inversion scheme that can deal with conductive cracks using eddy current signals. The novel scheme is based on artificial neural networks with its accuracy enhanced by using a shifting aperture method and signal processing techniques. A four sensor type probe is used in the eddy current testing. Several reconstruction results are introduced in this paper as validation of the proposed new scheme. The scheme is also applied to profile reconstruction of cracks which occurred in an actual steam generator tube of a pressurized water nuclear power plant. Remarkable agreement between reconstructed profiles and those obtained by destructive testing is observed. It can be concluded that the new inverse scheme is promising and will be a powerful tool for the practical applications.