Method and system for recognition of GIS ultrahigh frequency partial discharge signal

Abstract

The invention provides a method and system for recognition of a GIS ultrahigh frequency partial discharge signal. The method for recognition of the GIS ultrahigh frequency partial discharge signal comprises the following steps of (1) carrying out preprocessing on the GIS ultrahigh frequency partial discharge signal to obtain a three-dimensional spectrogram, (2) carrying out projection on the three-dimensional spectrogram to form a two-dimensional spectrogram, respectively extracting discharge characteristic parameters which describe shape difference of the two-dimensional spectrogram, and discharge characteristic parameters which describe difference between a positive semi-circle outline and a negative semi-circle outline of the two-dimensional spectrogram to obtain a sample to be detected, and (3) carrying out defect recognition on the sample to be detected according to an ABC-BP model which is built in advance. The method for recognition of the GIS ultrahigh frequency partial discharge signal can carry out rapid convergence to obtain the global optimum, and improves efficiency and accuracy of fault recognition of GIS partial discharge.

Description

technical field [0001] The invention relates to the technical field of electrical equipment insulation detection, in particular to a GIS UHF partial discharge signal identification method and a GIS UHF partial discharge signal identification system. Background technique [0002] In recent years, with the development of urban power grid construction, the number of GIS (Gas Insulated Substation, closed combined electrical appliances) substations has been increasing, and the probability of GIS equipment failure has also increased. As one of the most important equipment in substations, GIS , is widely used in the field of high-voltage power transmission because of its high reliability and small footprint. However, once a failure occurs, the maintenance time will be long, and the impact and loss will be great. Therefore, it is particularly important to be able to detect and judge the type of failure before GIS fails, and it will help us take timely measures to prevent problems be...

AI Technical Summary

Problems solved by technology

In the selection of various characteristic parameters, there is no better method to determine which characteristic parameters can effectively identify the type of partial discharge in GIS. Various mixed characteristics have been proposed, but there is no strong theoretical basis; and in various classification algorithms Among them, BP (Back Propagation) neural network is the most widely used, but BP neural network has problems such as sensitivity to initial weight threshold, slow convergence, long training time, easy to fall into local minimum, etc., and its reliability and accuracy are low.

Images