ART 2 - an unsupervised neural network for PD pattern recognition and classification

This paper introduces a method of classifying partial discharges of unknown origin. The innovative trend of using Artificial Neural Network (ANN) towards classification of Partial Discharge (PD) patterns is cogent and discernible. The Adaptive Resonance Theory (ART), a type of neural network which is suitable for PD pattern recognition is explained here. To ensure the suitability and reliability of chosen network for PD pattern recognition, the network is tested with the well known Iris plant database and alphabet character for recognition & classification. Further more the network is trained with various combinations off–q–n distributions of PD patterns and tested. It is shown that the ART 2 network is able to classify the PD patterns. The paper ends with analyzing the efficacy of multifarious features selected in the measurement space. Also the validation of input features is done using ‘Hold-One-Out’ method and partial set training technique q 2005 Elsevier Ltd. All rights reserved.

[1]  H.-G. Kranz,et al.  Fundamentals in computer aided PD processing, PD pattern recognition and automated diagnosis in GIS , 2000 .

[2]  H. Kranz,et al.  Partial discharge diagnosis using statistical optimization on a PC-based system , 1992 .

[3]  H.-G. Kranz.  Diagnosis of partial discharge signals using neural networks and minimum distance classification , 1993 .

[4]  B. T. Phung,et al.  Development of computer-based measurements and their application to PD pattern analysis , 1995 .

[5]  E. Gulski,et al.  Pattern analysis of partial discharges in SF/sub 6/ GIS , 1998 .

[6]  R. J. Brunt,et al.  Stochastic properties of partial-discharge phenomena , 1991 .

[7]  M. Salama,et al.  PD pattern recognition with neural networks using the multilayer perceptron technique , 1993 .

[8]  Bernd Freisleben,et al.  PD source identification with novel discharge parameters using counterpropagation neural networks , 1997 .

[9]  M.T.C. Fang,et al.  PD classification by a modular neural network based on task decomposition , 1996 .

[10]  Meijer,et al.  Pattern Analysis of Partial Discharges in SFG CIS , 2004 .

[11]  Kai Gao,et al.  PD pattern recognition for stator bar models with six kinds of characteristic vectors using BP network , 2002 .

[12]  A. Pedersen,et al.  The theory and measurement of partial discharge transients , 1991 .

[13]  R. Candela,et al.  PD recognition by means of statistical and fractal parameters and a neural network , 2000 .

[14]  Magdy M. A. Salama,et al.  Discrimination between PD pulse shapes using different neural network paradigms , 1994 .

[15]  E. Gulski,et al.  Computer-aided recognition of discharge sources , 1992 .

[16]  Magdy M. A. Salama,et al.  Determination of neural-network topology for partial discharge pulse pattern recognition , 2002, IEEE Trans. Neural Networks.

[17]  E. Gulski,et al.  Neural networks as a tool for recognition of partial discharges , 1993 .

[18]  C. Cachin,et al.  PD recognition with knowledge-based preprocessing and neural networks , 1995 .

[19]  L. Satish,et al.  Artificial neural networks for recognition of 3-d partial discharge patterns , 1994 .

[20]  E. Gulski,et al.  The use of fractal features for recognition of 3-D discharge patterns , 1995 .