Fuzzy computation for classifying defects in metallic plates

Abstract

Eddy Current Techniques (ECT) for Non-Destructive Testing and Evaluation (NDT/NDE) of conducting materials is one of the most application-oriented field of research within electromagnetics. In this work, a novel approach is proposed to classify defects in metallic plates in terms of their depth starting from a set of experimental measurements. The problem is solved by means of a system based on wavelets approach applied to extract relevant information on the specimen under test directly from the reading and, then, by implementing Fuzzy Inference Systems in order to determine its depth. Finally, Shannon Fuzzy Entropy as well as Subsethood operators have been taken into account to improve the classification methodology.