Ultra-high frequency partial discharge detection graph characteristic parameter extracting method and abnormal detection method

Abstract

The invention discloses an ultra-high frequency partial discharge detection graph characteristic parameter extracting method and an abnormal detection method. The ultra-high frequency partial discharge detection graph characteristic parameter extracting method comprises the steps that the values and coordinates of all data points on an ultra-high frequency partial discharge detection graph are extracted, and the ultra-high frequency partial discharge detection graph is converted into a PRPD data matrix; 2 for the PRPD data matrix, a statistical method is used to extract the characteristics ofa partial discharge pattern, and a feature vector is constructed to characterize the statistical distribution characteristics of the graph to serve as the classification basis for a partial dischargecategory. Characteristic parameters can be directly extracted from the unstructured partial discharge graph, and can be further used for subsequent abnormal partial discharge detection and identification based on the characteristic parameters. The method has a high practical value.

Description

technical field [0001] The invention belongs to the field of image data processing, and in particular relates to a method for extracting characteristic parameters of a UHF partial discharge detection map and an abnormality detection method. Background technique [0002] With the continuous growth of power demand, the power system has continuously improved the economic and reliability requirements of power equipment. As a kind of power equipment with the characteristics of small footprint, high operation reliability, flexible configuration, simple maintenance and long maintenance cycle, the closed gas insulated combined electrical apparatus GIS (Gas Insulated Substation) is characterized by its technological advancement and life The economy of cycle cost is widely used in high-voltage power transmission and transformation systems such as urban power supply, power plants, and large industrial and mining enterprises. Due to its structural characteristics, GIS equipment has hig...

AI Technical Summary

Problems solved by technology

[0004] Existing stored partial discharge data mostly exist in the form of maps, but the formats of maps produced by various manufacturers are inconsistent, and it is difficult to obtain the original discharge data corresponding to the maps

In the past, most of the detection methods for partial discharge signals of power equipment were based on the obtained partial discharge data, and could not directly realize the detection and discrimination from the on-site detection of partial discharge maps to the detection and identification of abnormal partial discharge defects.

Images