论文信息 - Application of Probabilistic Neural Networks to Eddy Current Non Destructive Test Problems

Application of Probabilistic Neural Networks to Eddy Current Non Destructive Test Problems

The aim of this paper is to propose the use of elliptical basis function probabilistic neural networks in automatic defects classification. The aim of classification is to assign a new pattern to a class, on the basis of already classified patterns. In eddy current based inspection, the patterns are sequences of complex voltages whose shape depends on the kind of defect affecting the conductive object under test.

[1] Simone G. O. Fiori,et al. Blind signal processing by the adaptive activation function neurons , 2000, Neural Networks.

[2] Donald F. Specht,et al. Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification , 1990, IEEE Trans. Neural Networks.

[3] Simone G. O. Fiori,et al. Non-destructive test by the Hopfield network , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[4] Jan Sikora,et al. Neural network approach to crack identification , 1998 .

[5] T. R. Schmidt. The remote field eddy current inspection technique , 1984 .

[6] Lalita Udpa,et al. Developments in gas pipeline inspection technology , 1996 .

[7] Pietro Burrascano,et al. Learning vector quantization for the probabilistic neural network , 1991, IEEE Trans. Neural Networks.

[8] Mohamad T. Musavi,et al. A minimum error neural network (MNN) , 1993, Neural Networks.

[9] Steffen Gutjahr,et al. Elliptical Basis Function Networks for Classification Tasks , 1997, ICANN.

[10] Donald F. Specht,et al. Probabilistic neural networks , 1990, Neural Networks.

[11] Rodney R. Saldanha,et al. Inverse problem methodology and finite elements in the identification of cracks, sources, materials, and their geometry in inaccessible locations , 1991 .