A methodological study on the use of artificial neural networks for thermal defects characterization is presented. An implementation of an algorithm called dynamic thermal tomography, by means of a tree like architecture is described. Experimental results obtained on plastic specimens, containing artificial defects, confirm the potential of the proposed data reduction procedure. The evaluation of depth, and particularly of the thickness of internal voids, proved extremely satisfactory.
APPLICATION OF NEURAL NETWORKS TO THERMOGRAPHIC DATA REDUCTION FOR NONDESTRUCTIVE EVALUATION
E GRINZATO;S MARINETTI;G MANDUCHI
1995
Abstract
A methodological study on the use of artificial neural networks for thermal defects characterization is presented. An implementation of an algorithm called dynamic thermal tomography, by means of a tree like architecture is described. Experimental results obtained on plastic specimens, containing artificial defects, confirm the potential of the proposed data reduction procedure. The evaluation of depth, and particularly of the thickness of internal voids, proved extremely satisfactory.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.