A New Approach to Evaluate Defects in Metallic Plates Based on Computing with Words and Fuzzy Entropy

摘要

Eddy-Current Techniques for non-destructive testing and evaluation of conducting material are one of the most known application oriented field in electromagnetics research. According to the Italian PRIN Project (proj. 2009TCLKNF_002), the Authors, in this work, propose a novel approach based on soft computing domain to characterize defects in metallic plates in terms of depth and shape starting from a set of experimental measurements. The problem is solved by means of a classification system based on computation with words and fuzzy entropy extracting information on the specimen under test from the measurements carried out in Non Destructive Tests Laboratory of "Mediterranea " University. Whereas, fuzzy entropy minimization module is based on traditional fuzzy inference system due to intrinsic characteristics of data the main advantage of the proposed approach is the introduction of computation with words in order to improve the data characterization.