Gray intensity image feature extraction of partial discharge in high-voltage cross-linked polyethylene power cable joint

Abstract

SUMMARY A feature extraction method for gray intensity image of partial discharge (PD) is applied to recognize the insulating defects in high‐voltage cross‐linked polyethylene power cable joint. The method is based on a two‐directional and two‐dimensional (2‐D) maximum margin criterion (MMC). A 2‐D orthogonal projection of gray intensity image of PD was performed in horizontal and vertical directions. Projected image data were taken as discriminant vector of different gray intensity images to solve the high dimensional and small sample size of PD gray intensity image. The nearest neighbor classifier was used to classify the PD gray intensity image to recognize different insulating defects in the joint. The recongnition results of four typical insulating defects in the laboratory indicated that the extraction speed of the gray intensity image feature and recognition rate of insulating defects are superior compared with the common principal component analysis and Fisher discriminant analysis with MMC. Copyright © 2012 John Wiley & Sons, Ltd.

Statistical Study on Space Charge effects and Stage Characteristics of Needle-Plate Corona Discharge under DC Voltage

“…The statistic rules of PD parameters in this paper and others support each other in some aspects [10][11][12][13][14]. The mechanism explanations are based on the classical theories and well-founded.…”

“…Another one is considering influencing factors of discharge [6][7][8][9], such as electrode structure [6,7], air pressure [8] and air flow [9]. The rest one is studying discharge parameters characteristics, and apply them to pattern recognition and stage division of discharges [10][11][12][13][14].…”

“…In theory, through the deep analysis of discharge parameter characteristics, the space charge and electric field distribution can be reflected. While existing researches on the discharge parameters characteristics are either focused on the differences of characteristics from other discharge stages and patterns [10][11][12], or focused on the characteristic extraction [13,14]. Few researches relate the statistical rules to the space charge effect and electric field distribution.So in this paper, it is proposed to apply mathematical statistics methods and microcosmic discharge and space charge theories, to analyze space charge effect and electric field distribution on the basis of characteristic parameter rules of PD pulses.In this paper, the air discharge of needle-plate model under DC is researched.…”

“…In theory, through the deep analysis of discharge parameter characteristics, the space charge and electric field distribution can be reflected. While existing researches on the discharge parameters characteristics are either focused on the differences of characteristics from other discharge stages and patterns [10][11][12], or focused on the characteristic extraction [13,14]. Few researches relate the statistical rules to the space charge effect and electric field distribution.…”

Improving recognition accuracy of partial discharge patterns by image-oriented feature extraction and selection technique

“…On the contrary, the satisfactory recognition results can be obtained by the favorable and discriminative features with the assistance of merely simple and linear classifiers. Thus, the advanced signal processing techniques such as time-frequency representations [29][30] and image compression methods [31][32], etc. for PD features extraction are gaining popularity in recent years.…”