Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network

Partial discharge (PD) classification in power cable accessories and high voltage equipment in general is essential in evaluating the severity of the damage in the insulation. In this article, the PD classification was realised as a two-fold process. Firstly, measurements taken from a high-frequency current transformer (HFCT) sensor were represented as features by means of a transformation to the classifier and secondly, the probabilistic neural network (PNN) classifier itself was capable of effectively recognising features coming from different types of discharges. The feature that was used as a fingerprint for PD characterisation was extracted from the moments of the probability density function (PDF) of the wavelet coefficients at various scales, obtained through the wavelet packets transformation. The PNN classifier was used to classify the PDs and assess the suitability of this feature vector in PD classification. Four types of artificial PDs were created in a high voltage laboratory, namely corona discharge in air, floating discharge in oil, internal discharge in oil and surface discharge in air, at different applied voltages, and were used to train the PNN algorithm. The results obtained here (97.49, 91.9, 100 and 99.8% for the corona, the floating, the internal and the surface discharges, respectively) are very encouraging for the use of PNN in PD classification with this particular feature vector. This article suggests a feature extraction and classification algorithm for PD classification, which when combined together reduced the dimensionality of the feature space to a manageable dimension, and achieved very high levels of classification.

[1]  M. Salama,et al.  SVM classification of contaminating particles in liquid dielectrics using higher order statistics of electrical and acoustic PD measurements , 2007, IEEE Transactions on Dielectrics and Electrical Insulation.

[2]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[3]  Antonello Monti,et al.  A neuro-fuzzy approach for the detection of partial discharge , 2001, IEEE Trans. Instrum. Meas..

[4]  A. Cavallini,et al.  A new methodology for the identification of PD in electrical apparatus: properties and applications , 2005, IEEE Transactions on Dielectrics and Electrical Insulation.

[5]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[6]  Magdy M. A. Salama,et al.  Neural network system using the multi-layer perceptron technique for the recognition of PD pulse shapes due to cavities and electrical trees , 1995 .

[7]  Jae-Hwan Kim,et al.  Classification of partial discharge electrical signals using wavelet transforms , 1999, Proceedings of 1999 IEEE 13th International Conference on Dielectric Liquids (ICDL'99) (Cat. No.99CH36213).

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

[9]  R. B. Murphy.  Non-Parametric Tolerance Limits , 1948 .

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

[11]  L. Hao,et al.  Comparison of support vector machine based partial discharge identification parameters , 2006, Conference Record of the 2006 IEEE International Symposium on Electrical Insulation.

[12]  Vojislav Kecman,et al.  Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models , 2001 .

[13]  Jian Jin,et al.  Denoising of partial discharge signals in wavelet packets domain , 2005 .

[14]  Magdy M. A. Salama,et al.  Fuzzy logic applied to PD pattern classification , 2000 .

[15]  Donald F. Specht,et al.  Generation of Polynomial Discriminant Functions for Pattern Recognition , 1967, IEEE Trans. Electron. Comput..

[16]  Venizelos Efthymiou,et al.  Classification of Partial Discharge Signals using Probabilistic Neural Network , 2007, 2007 IEEE International Conference on Solid Dielectrics.

[17]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[18]  T. Cacoullos.  Estimation of a multivariate density , 1966 .

[19]  I. Johnstone,et al.  Adapting to Unknown Smoothness via Wavelet Shrinkage , 1995 .

[20]  H. Ota,et al.  Application of advanced after-laying test to long-distance 275 kV XLPE cable lines , 1995 .

[21]  N. Ahmed,et al.  On-line partial discharge detection in cables , 1998 .

[22]  Roy L. Streit,et al.  Maximum likelihood training of probabilistic neural networks , 1994, IEEE Trans. Neural Networks.

[23]  L. Niemeyer,et al.  The importance of statistical characteristics of partial discharge data , 1992 .

[24]  Alexandru Isar,et al.  On the statistical decorrelation of the wavelet packet coefficients of a band-limited wide-sense stationary random process , 2007, Signal Process..

[25]  L. Hao,et al.  Identification of multiple partial discharge sources , 2008, 2008 International Conference on Condition Monitoring and Diagnosis.

[26]  Michael A. Saunders,et al.  Atomic Decomposition by Basis Pursuit , 1998, SIAM J. Sci. Comput..

[27]  P. Lewin,et al.  Comparison of on-line partial discharge detection methods for HV cable joints , 2002 .

[28]  J. Overall,et al.  Applied multivariate analysis , 1983 .

[29]  Davide Fabiani,et al.  Life model based on space-charge quantities for HVDC polymeric cables subjected to voltage-polarity inversions , 2002 .

[30]  D. W. Gross,et al.  Experience with an on-line monitoring system for 400 kV XLPE cables , 1996, Proceedings of 1996 Transmission and Distribution Conference and Exposition.

[31]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[32]  P.P. Seitz,et al.  Condition assessment of power cable accessories using advanced VHF/UHF PD detection , 2006, Conference Record of the 2006 IEEE International Symposium on Electrical Insulation.

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

[34]  A. E. Davies,et al.  Acoustic emission techniques for partial discharge detection within cable insulation , 2000 .

[35]  E. Gulski,et al.  Computer-aided measurement of partial discharges in HV equipment , 1993 .

[36]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .

[37]  T. Strehl,et al.  Practical experiences in on-site PD diagnosis tests of HV power cable accessories in service , 2006, Conference Record of the 2006 IEEE International Symposium on Electrical Insulation.

[38]  G. Montanari,et al.  Digital detection and fuzzy classification of partial discharge signals , 2002 .

[39]  Stéphane Mallat,et al.  Singularity detection and processing with wavelets , 1992, IEEE Trans. Inf. Theory.

[40]  G.C. Montanari,et al.  Insulation defect localization through partial discharge measurements and numerical classification , 2004, 2004 IEEE International Symposium on Industrial Electronics.

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

[42]  E. Gulski.  Digital analysis of partial discharges , 1995 .

[43]  Paul Lewin,et al.  Wavelet packet denoising for online partial discharge detection in cables and its application to experimental field results , 2006 .

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

[45]  P.H.F. Morshuis,et al.  Assessment of dielectric degradation by ultrawide-band PD detection , 1995 .

[46]  R. Bartnikas,et al.  Trends in partial discharge pattern classification: a survey , 2005, IEEE Transactions on Dielectrics and Electrical Insulation.

[47]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[48]  P.A. Crossley,et al.  Partial discharge pattern recognition based on 2-D wavelet transform and neural network techniques , 2002, IEEE Power Engineering Society Summer Meeting,.