Partial Discharge Pattern Recognition Based on 3D Graphs of Phase Resolved Pulse Sequence

Abstract

Partial discharge (PD) is an important phenomenon that reflects the insulation condition of electrical equipment. In order to protect the safety of power grids, it is of significance to diagnose the type of insulation defects inside the equipment accurately and early through PD pattern recognition. In this article, phase resolved pulse sequence (PRPS) graphs in 3D were constructed by the PD pulse data of the gas-insulated switchgear (GIS) acquired, then the histogram of oriented gradient (HOG) features were extracted directly from the 3D PRPS graphs, and finally the attribute selective Naïve Bayes classifier was used to recognize the discharge pattern. In addition, this method was compared with two traditional methods, i.e., the statistical method and the grayscale gradient co-occurrence matrix method, from three aspects. The result shows that 3D PRPS graphs have different morphology characteristics in vision under different defects, and the similarity among different voltages applied is higher than among different defects, so it is reasonable to use them as the basis for PD pattern recognition. The contrast indicates that the HOG method not only has the highest accuracy with the least requirement for pretreatment and training, but it also has robustness when the voltage applied changes. Consequently, this method has the universality for PD pattern recognition that is based on 3D PRPS graphs.

Partial Discharges Classification Methods in XLPE Cable: A Review

“…Compared with time-resolved features, such as TRPD, which is unsuitable for pattern recognition, the effect of signal propagation path and noise interference is quite great [64]. A classifier is difficult to develop without PRPD data because the data extracted from the PRPD can be easily used by a machine learning model.…”

Classification of Partial Discharge Images Using Deep Convolutional Neural Networks

“…In turn, supervised learning implies an algorithm's ability to recognize elements based on provided samples with the goal of recognizing new data based on training data. Supervised learning algorithms include, for example, decision trees, support vector machines (SVM), naive Bayes classifiers, k-nearest neighbors and linear regressions [7][8][9][10][11][12][13][14][15][16][17][18][19][20][34][35][36][37]. Supervised learning can be further divided into classification and regression: classification means that samples belong to two or more classes, with the goal of predicting the class of unlabeled data from the already-labeled data and thus identifying to which category an object belongs; regression is understood as predicting an attribute associated with an object.…”

A Novel Fault Diagnosis of GIS Partial Discharge Based on Improved Whale Optimization Algorithm

“…Effective extraction of feature information that can characterize different types of PD is the foundation for achieving PD identification. At present, the commonly used PD feature information extraction methods are mainly phase distribution method, including phase resolved partial discharge (PRPD) image and phase resolved pulse train (PRPS) image, which mainly extracts the spectral features of PD signals, including discharge phase, frequency, and discharge quantity to achieve the characterization of PD signals [4][5][6]. However, the method is easy to cause aliasing problem because of many sources of PD, which affects identification accuracy.…”