Since the dimension of combined feature set for partial discharge (PD) pattern recognition is higher, the corresponding sample size increases, as does the required amount of storage space and calculation, and there are features with less category-related characteristics in the feature parameters, which may contain redundant information between them. To solve the problem of higher feature dimension and complicated classification model required for the identification of partial discharge insulation defect type in this paper. Random forest sequential forward selection method based on variance analysis (RF-VA) is proposed for the optimal subset selection. This method is improved in two aspects. Firstly, a method based on variance analysis is proposed, which measures feature differences between categories, and obtains a modified arrangement displacement scheme to guide rearrangement of the order of values taken on data sample out of bag. Secondly, the sequence forward search method used to do feature selection could get iteration evaluation results, which solves randomness to determine the size of feature subset and instability of the results existing in the original algorithm. The results show RF-VA can obtain a better subset of features. It is feasible to reduce the dimension of partial discharge characteristic set, and effectively improve the identification rate of partial discharge defect type.

Identification of insulation defects in gas insulated metal-enclosed switchgear (GIS) is important for partial discharge (PD) evaluation. This article proposes a polar coordinate pattern approach to characterize the different kinds of defect types. These defect types include floating electrodes, a fixed protrusion on the enclosure, surface contamination on the spacer, metallic prominence on the high voltage electrode, a void in the insulator, and free metal particles on the enclosure. First, the physical models for the insulation defects in the established GIS model are designed. Second, the phase resolved pulse sequence (PRPS) data sets are obtained using ultra-high frequency (UHF) measurement. Then, the polar coordinate patterns are proposed to characterize the defects. Nine discharge parameters combined with the parameters based on quadrant statistical theory constitute the input feature vector to identify the PD types. The experimental results show that these new parameters could produce a clear, quantitative description of the characteristics of the defect types and could be used to distinguish between the different kinds of defect types.

This paper presents an experiment to study the partial discharge (PD) characteristics and development process of the physical models of general insulation defects in gas-insulated switchgear (GIS). Four types of typical artificial insulation defects are designed to imitate the insulation faults in an actual GIS. The experiment PD data are obtained from a 220-kV GIS equipment using ultrahigh-frequency (UHF) PD measurement. The PD data obtained by UHF detection are stored as phase-resolved pulse sequence (PRPS) data. Then, the multiple PD patterns, such as PRPS analysis pattern, phase-resolved PD pattern, and Δu pattern, can be calculated from the PRPS data sets. On the basis of the present experimental research, the multiple PD patterns can be used to classify different PD defects and evaluate the stage of PD development process comprehensively of each typical defect.