Feature extraction of partial discharge gray-scale images for identification based on multifractal spectrum using fluorescence fiber sensor

Abstract. This document proposes the utilization of partial discharge (PD) optical signals from a fluorescence optical sensor system for constructing φ-u-n charts and gray-scale images. The fractal characteristics cannot fully characterize the PD gray-scale images, which reduce the PD pattern recognition rates. Multifractal spectrum is used for analyzing the characteristics of gray-scale images, and a new probability calculation method is proposed for computing the multifractal spectrogram of these images. By conducting a series of experiments, the multifractal spectrum is proven effective in describing the variations in the geometric characteristics of the gray-scale images. The main physical features of the multifractal spectrum are extracted and used as pattern recognition features. The backpropagation neural network with an improved conjugate gradient algorithm is used as a classifier in identifying the different PD types, which achieves recognition rates that are >87%. The multifractal spectrum improves the accuracy of the PD pattern recognition unlike other pattern recognition features, such as the box-counting dimension and the information dimension.

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

[2]  Jian Yang,et al.  Two-dimensional discriminant transform for face recognition , 2005, Pattern Recognit..

[3]  Jian Li,et al.  Partial discharge image recognition using a new group of features , 2006, IEEE Transactions on Dielectrics and Electrical Insulation.

[4]  Yilu Liu,et al.  Position location of partial discharges in power transformers using fiber acoustic sensor arrays , 2006 .

[5]  J. Xiao-dong,et al.  Study of multi-fractal spectrum of sol-gel hydrophobic anti-reflective SiO 2 coating after laser-conditioning , 2007 .

[6]  A. Schnettler,et al.  Determination of a failure probability prognosis based on PD - diagnostics in gis , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[7]  T. Czaszejko,et al.  Conditions of discharge-free operation of XLPE insulated power cable systems , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[8]  Hakan Cevikalp,et al.  Two-dimensional subspace classifiers for face recognition , 2009, Neurocomputing.

[9]  Orlando Frazão,et al.  Extrinsic and intrinsic fiber optic interferometric sensors for acoustic detection in high-voltage environments , 2009 .

[10]  Jaihie Kim,et al.  Fake-fingerprint detection using multiple static features , 2009 .

[11]  Ju Tang,et al.  Feature extraction and recognition of UHF partial discharge signals in GIS based on dual‐tree complex wavelet transform , 2009 .

[12]  Venizelos Efthymiou,et al.  Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network , 2010 .

[13]  M Istad,et al.  Thirty-Six Years of Service Experience with a National Population of Gas-Insulated Substations , 2010, IEEE Transactions on Power Delivery.

[14]  Jian Li,et al.  Oil-paper aging evaluation by fuzzy clustering and factor analysis to statistical parameters of partial discharges , 2010, IEEE Transactions on Dielectrics and Electrical Insulation.

[15]  Shigemitsu Okabe,et al.  Aging effect on insulation reliability evaluation with weibull distribution for oil-immersed transformers , 2010, IEEE Transactions on Dielectrics and Electrical Insulation.

[16]  S. Gopal,et al.  Robust Heteroscedastic Probabilistic Neural Network for multiple source partial discharge pattern recognition - Significance of outliers on classification capability , 2011, Expert Syst. Appl..

[17]  On Robustness of Multi Fractal Spectrum to Geometric Transformations and Illumination , 2011 .

[18]  Zhengjun Liu,et al.  Target recognition for small samples of ladar range image using classifier ensembles , 2012 .

[19]  Fu-Hsien Chen,et al.  Partial discharge pattern recognition of power cable joints using extension method with fractal feature enhancement , 2012, Expert Syst. Appl..

[20]  Hung-Cheng Chen,et al.  Partial discharge identification system for high-voltage power transformers using fractal feature-based extension method , 2013 .

[21]  B. Phung,et al.  Spectral features for the classification of partial discharge signals from selected insulation defect models , 2013 .

[22]  Subrata Biswas,et al.  An approach based on rough set theory for identification of single and multiple partial discharge source , 2013 .

[23]  Alexey Lyubushin,et al.  Discrimination of earthquakes and explosions using multi-fractal singularity spectrums properties , 2013, Journal of Seismology.

[24]  Xiaopeng Zhang,et al.  Object shape classification and scene shape representation for three-dimensional laser scanned outdoor data , 2013 .