Feasibility of Using Adaptive Learning Networks for Eddy Current Signal Analysis

摘要

Unambiguous discrimination and accurate sizing between simulated pits and cracks have been obtained via Adaptive Learning Network (ALN) flaw-classification and ALN flaw-size models for both single and multiple frequency eddy current data. In terms of sizing flaws, fie error rates were 2.4 percent for pits and 3.6 percent for cracks.nEddy current signal responses were generated, recorded, and digitized from several simulated pits and cracks in sample nuclear reactor steam generator tubing. These responses were parameterized to measure the in-phase and quadrature signal and power components. The accuracy of ALN flaw classifiers and ALN flaw-size models, which were synthesized from these parameters, was independent of the presence of tube-support plates over the flaw region.