X-ray image classification and identification method for high-voltage strain clamp crimping defect discrimination

Abstract

The invention discloses an X-ray image classification and identification method for high-voltage strain clamp crimping defect discrimination, and the method is characterized in that the method comprises the following steps: S100, collecting a defect X-ray image of a conventional strain clamp according to classes through employing a strain clamp defect type as a classification standard; S200, establishing a deep convolution generative adversarial network model, wherein the adversarial network model comprises a generator represented by a differential function G and a discriminator represented bya differential function D; S300, training a GAN data model: firstly fixing the differential function G, and optimizing the differential function D, so that the classification accuracy of the discriminator is maximum; fixing the differential function D, and optimizing the differential function G, so that the classification accuracy of the discriminator is minimum; after loop iteration for N times,when the generated data distribution is equal to the real sample distribution, determining a target function GAN; and S400, inputting the X-ray image m of the strain clamp to be discriminated into the target function GAN in the step S300 to obtain a corresponding defect type and a corresponding probability. The method is small in training sample data, low in iteration frequency and high in discrimination accuracy.

Description

technical field [0001] The invention relates to the field of detection, in particular to the field of detection methods for physical defects of electrical equipment or components, and in particular to an X-ray image classification and recognition method for judging crimping defects of high-voltage tension clamps Background technique [0002] As an important part of power transmission, strain clamps play a vital role in the entire power grid. Once an accident occurs, a large amount of manpower, material resources, financial resources and time will need to be invested in power outage maintenance. Solving (or reducing) the impact of strain clamps has significant social significance for improving the safety, stability, and economy of the line. [0003] At present, there are mainly ultrasonic, X-ray, infrared thermal imaging and ultraviolet imaging for the detection of crimping defects of overhead line tension clamps. The crimping defects are produced in the construction of pow...

AI Technical Summary

Problems solved by technology

[0009] In order to solve the problems of long time occupation and low judgment efficiency in judging the defects of tension clamps using the existing technology, this application provides an X-ray image classification and recognition method for judging the crimping defects of high-voltage tension clamps, which is used to solve the current problems In some technologies, it is time-consuming and labor-intensive to manually judge one by one. At the same time, manual judgment needs to rely on the rich experience of the judgment personnel, so the accuracy of judgment conclusions cannot be separated from subjective factors.

Images