In the field of nondestructive testing on defects identification in metallic plates, one of the most application-oriented field of research within electromagnetics, the shape reconstruction is still an open question. State-of-the-art technologies indeed enable the operator to locate the position of a defect but not its shape. The purpose of this paper is to make a contribution to the solution of this side of the problem suggesting a methodology based on soft computing approach. In particular, a novel approach is proposed to classify defects in metallic plates in terms of their depth starting from a set of experimental measurements carried out at our Lab. The problem is solved by means of asystem based on wavelets approach extracting features from thespecimen under study from the measurements and, then, implementing Support Vector MAchines in order to determine its depth. Finally, Confusion Matrices (CMs) operators have been taken into account to improve the procedure.

On the use of eddy current techniques & soft computing approach to classify defects on metallic plates

CALCAGNO, SALVATORE;MORABITO, Francesco Carlo;VERSACI, Mario
2005

Abstract

In the field of nondestructive testing on defects identification in metallic plates, one of the most application-oriented field of research within electromagnetics, the shape reconstruction is still an open question. State-of-the-art technologies indeed enable the operator to locate the position of a defect but not its shape. The purpose of this paper is to make a contribution to the solution of this side of the problem suggesting a methodology based on soft computing approach. In particular, a novel approach is proposed to classify defects in metallic plates in terms of their depth starting from a set of experimental measurements carried out at our Lab. The problem is solved by means of asystem based on wavelets approach extracting features from thespecimen under study from the measurements and, then, implementing Support Vector MAchines in order to determine its depth. Finally, Confusion Matrices (CMs) operators have been taken into account to improve the procedure.
Defect Classifying; NDT; Wavelet Transofr and Support Vector MAchines
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/20.500.12318/2384
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact