Grid-based partial discharge signal clustering analysis method

Abstract

The invention belongs to the field of power electrical equipment partial discharge signal monitoring, and provides a grid-based partial discharge signal clustering analysis method, relates to a data mining technology and a digital signal processing technology. The method comprises the following steps: firstly, acquiring an original partial discharge signal through an acquisition system to obtain an effective signal characteristic quantity; performing normalization processing on the original effective characteristic quantity through preprocessing; dividing grid units by utilizing the attributes of the data set; mapping the data into a grid through a certain index relation; estimating the local density of the grid by using the advantages of a Gaussian kernel function; self-deciding the clustering number and the clustering center point in the form of a decision diagram by using the idea of relative distance; distributing non-clustering center data according to the clustering center point; and finally, marking noise points and outliers according to the relative distance. The grid-based partial discharge signal clustering analysis method provided by the invention has a series of advantages of easy thought realization, easy integration, short development period, high real-time performance, less clustering result human intervention and the like.

Description

technical field [0001] The invention relates to a detection and analysis method for the partial discharge signal state of electric power equipment, and relates to the fields of data mining technology, digital signal processing technology and the like. Background technique [0002] As a characterization of insulator defects, partial discharge is helpful for proper maintenance and replacement of high-voltage electrical equipment after detecting its existence and content. However, different discharge types have different causes, discharge intensity and discharge duration. In a complex environment, there are often a variety of partial discharge source signals and noises, which increases the difficulty of identifying the type of partial discharge, and sometimes even relies on subjective experience to judge the type of discharge. It is difficult to make a correct judgment in complex situations, and it may even be misjudged as other discharge types, so that the maintenance work ca...

AI Technical Summary

Problems solved by technology

However, conventional clustering methods cannot meet the automation and intelligence requirements of partial discharge detection.

Images