In this paper we discuss the use of the Probabilistic Neural Network (PNN) for the classification of the defects detected via the Remote Field Eddy Current (RFEC) inspection technique. The neural network is employed in order to associate each defect to one of the predefined classes. Each defect is represented by means of the phase response of the probe system. The reported results show that the proposed artificial neural network allows reliable classification results.
Classification of eddy current NDT data by Probabilistic Neural Networks / M., Angeli; P., Burrascano; E., Cardelli; Fiori, Simone; S., Resteghini. - 6:(1999), pp. 4012-4014.
Classification of eddy current NDT data by Probabilistic Neural Networks
FIORI, Simone;
1999-01-01
Abstract
In this paper we discuss the use of the Probabilistic Neural Network (PNN) for the classification of the defects detected via the Remote Field Eddy Current (RFEC) inspection technique. The neural network is employed in order to associate each defect to one of the predefined classes. Each defect is represented by means of the phase response of the probe system. The reported results show that the proposed artificial neural network allows reliable classification results.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.