GIS partial discharge type identification method based on GK fuzzy clustering

Abstract

The present invention discloses a GIS partial discharge type identification method based on GK fuzzy clustering. The method is characterized by comprising the steps of S01, constructing a GIS partial discharge gray scale image according to the acquired data; S02, extracting the fractal features of the GIS partial discharge gray scale image, namely a box dimension and an information dimension; S03, processing the fractal feature data further by a GK fuzzy clustering algorithm, isolating a GIS site interference signal; S04, designing a GIS partial discharge mode recognizer based on a least squares support vector machine classification algorithm; S05, identifying the GIS partial discharge type. By a GK fuzzy clustering method, the GIS site interference signal is isolated, thereby improving the accuracy of extracting the fractal features of the partial discharge signal. Meanwhile, by identifying the GIS partial discharge type by the least squares support vector machine classification algorithm, the correctness and rapidity of the discharge type identification are improved.

Description

technical field [0001] The invention relates to a GIS partial discharge type identification method based on GK fuzzy clustering. Background technique [0002] Gas insulated switchgear (GIS, also known as SF6 fully enclosed switchgear) has the characteristics of small footprint, high operational reliability, and convenient maintenance, and has been widely used in power systems. However, GIS faults caused by defects left in the manufacturing or installation process occur from time to time, and the internal fault types are mostly insulation faults, which mainly include four types: corona discharge, suspended solid discharge, insulator surface defects discharge and free particle discharge. When a fault occurs, partial discharges are generated by the defect distortion electric field. Therefore, judging the potential faults of GIS through partial discharge detection is of great significance to grasp the insulation status of GIS and guide its maintenance, and the type identificat...

AI Technical Summary

Problems solved by technology

However, in the current literature, the extraction of fractal features of GIS partial discharge signals does not consider the influence of GIS field interference on fractal features. Inaccurate problem of fractal feature extraction

[0004] In terms of partial discharge pattern recognition, the current literature regards the artificial neural network with good adaptive ability, robust performance and nonlinear mapping ability as the classifier of GIS partial discharge pattern. Problems such as minimum value and under-learning and over-learning may have a certain impact on the correctness of the recognition results

Images