Defect Identification by Eddy Current Inspection Data Classification Through Probabilistic Neural Networks with Elliptical Kernels

* This work was partially supported by the Italian MURST. AbstractThe aim of this paper is to present a novel technique for defect identification by neural networks based on the classification of remote field effect eddy current (RFEC) data. We consider a kind of neural network that does not require a long training and is particularly well suited for fast classification, the Probabilistic Neural Network (PNN). Then we introduce the concept of elliptical kernels for PNN and show how these structures can be used for defect identification. Finally, experimental results are presented that illustrate how PNN can achieve 100% correct classification with a very small amount of available measures.