A Fault Diagnosis Method of Electrical Equipment Based on Infrared Thermal Image

Abstract

The invention discloses an electrical device fault diagnosis method based on infrared thermography. The method includes that collected infrared thermography images of an electrical device are input; the infrared thermography images are subjected to graying processing, and the grayed infrared thermography images of the electrical device are subjected to segmentation processing by means of an OTSU method; characteristic parameters of the segmented infrared thermography images are extracted to serve as input parameters of a GA-BP neural network and the GA-BP neural network is trained; thermal defect diagnosis is performed on the electrical device by means of the trained GA-BP neural network and a diagnosis result is output. The electrical device fault diagnosis method based on infrared thermography has the advantages that OTSU segmentation is introduced, temperature characteristics and Zernike moment parameters are extracted, fault diagnosis is performed on the electrical device through the GA-BP neural network, effects are remarkable, diagnosis processing can be performed in allusion to different electrical device thermal defects, intelligent operation of a transformer substation is facilitated, and detecting accuracy is improved.

Description

technical field [0001] The invention relates to the field of thermal defect detection of electrical equipment, in particular to a method for diagnosing electrical equipment faults based on infrared thermal images. Background technique [0002] With the rapid development of strong and smart grids, my country's requirements for power system reliability are getting higher and higher. The fault isolation of electrical equipment is extremely important to the sound power supply of the power supply area. Therefore, online monitoring and safety warning of electrical equipment are required to detect faults in time and take measures to eliminate hidden dangers. As an effective means of fault detection, infrared thermal image detection technology has been widely used. The monitoring system combined with infrared thermal image detection technology has greatly improved the fault detection level of the power system, but the current detection method still requires manual diagnosis, which ...

AI Technical Summary

Problems solved by technology

However, when the BP neural network algorithm is training data, the convergence of the neural network function is poor, and the optimization effect on the parameters is poor, while the genetic algorithm is an algorithm with strong global search ability, which can search for the global optimal solution.

Images