Substation equipment thermal fault diagnosis method and system

Abstract

The invention relates to a substation equipment thermal fault diagnosis method and system. The method comprises the following steps: preprocessing an infrared image; determining a corresponding temperature matrix according to the preprocessed infrared image; performing coarse segmentation of a power transformation equipment target and a background on the preprocessed infrared image by adopting a K-means clustering algorithm; combining difference information obtained by detecting a target edge through a Prewitt operator with a Chan-Vese model, and determining an improved Chan-Vese model; taking the infrared image subjected to coarse segmentation as an initial segmentation condition of the model, performing fine segmentation of the power transformation equipment target and the background on the infrared image subjected to coarse segmentation by using the model, and determining a target position to be diagnosed; determining the temperature of the target position according to the target position and a temperature matrix; and diagnosing the thermal fault of the substation equipment according to the temperature of the target position. The accuracy of thermal fault diagnosis of the substation equipment can be improved.

Description

technical field [0001] The invention relates to the field of thermal fault diagnosis of substation equipment, in particular to a thermal fault diagnosis method and system for substation equipment. Background technique [0002] With the gradual increase in the demand for electric energy in national production and life, the scale of the power grid is also expanding. The addition of infrared diagnostic technology has greatly improved the efficiency of fault diagnosis of substation equipment. However, the use of infrared imaging to diagnose faults in substation equipment has problems such as large scene interference. . Extracting the Region of Interest (ROI) in the infrared image first, and then performing fault diagnosis can effectively reduce the problem of large scene interference and facilitate the promotion of infrared fault diagnosis of substation equipment. [0003] Among them, the methods for infrared fault diagnosis of substation equipment in the prior art are as follo...

AI Technical Summary

Problems solved by technology

Its advantage lies in the high accuracy of feature extraction and fault diagnosis, but this method is difficult to extract complex features, and feature selection is difficult, so the generalization ability of the model is difficult to guarantee

Images