Composite insulator defect diagnosis method based on U-net segmentation

Abstract

The invention relates to a composite insulator defect diagnosis method based on U-net segmentation. The method comprises the following steps: S1, constructing a training sample set; S2, based on a U-net segmentation algorithm, establishing a composite insulator infrared image segmentation model, and performing training based on the training sample set; S3, inputting an image to be detected into the trained infrared image segmentation model of the composite insulator to obtain a binary image, and finding out a corresponding central axis of the composite insulator according to the binary image; S4, on the basis of the central axis of the composite insulator, obtaining the temperature data of the central axis of the composite insulator by combining the image temperature data matrix; and S5, judging the defect type of the composite insulator through the central axis temperature curve of the composite insulator based on the heating characteristics of different defect types of the composite insulator. According to the method, the overall heating characteristics of the composite insulator can be rapidly and effectively extracted, and the defects are accurately diagnosed and classified.

Description

technical field [0001] The invention relates to the field of high-voltage composite insulator defect detection, in particular to a composite insulator defect diagnosis method based on U-net segmentation. Background technique [0002] Composite insulators play the role of mechanical fixation and electrical insulation in UHV transmission systems due to their light weight, high mechanical strength, and superior performance in anti-pollution flashover. However, in actual operation, composite insulators will gradually deteriorate due to the joint action of electrical, mechanical and external environments, resulting in different degrees of heating. Infrared thermography, as a portable and efficient detection method without power failure and high accuracy, plays an important role in the defect detection of composite insulators. However, the current defect detection method is only to import infrared images one by one into the analysis software of the thermal imager to obtain the ov...

AI Technical Summary

Problems solved by technology

However, the current defect detection method is only to import infrared images one by one into the analysis software of the thermal imager to obtain the overall temperature distribution characteristics of the insulator by artificially drawing lines. The detection efficiency is slow, and it is greatly affected by human subjective factors. Requirements for Efficiency and Accuracy of Insulator Infrared Inspection

Images