Cable defect detection method and device and storage medium

By constructing and analyzing the joint discharge spectrum and extracting and fusing the time and frequency domain feature information, the problem of low accuracy in cable defect detection in the prior art is solved, and a higher accuracy in defect recognition is achieved.

CN119715596AActive Publication Date: 2025-03-28GUANGDONG POWER GRID CO LTD +1
9 Cites 0 Cited by

Patent Information

Application Number
CN202411922206.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-25
Publication Date
2025-03-28
Estimated Expiration
2044-12-25

AI Technical Summary

Technical Problem

In the prior art, when detecting cable defects, the amount of information in the spectrum characteristics is small, resulting in a lower accuracy in identifying cable defects.

Method used

By collecting time-domain reflected signals, frequency-domain reflected signals and original discharge spectrograms, a joint discharge spectrogram is constructed, feature information in the time-domain and frequency domains are extracted, the joint discharge spectrogram is mapped to the double-spectral space, and the correlation between feature information and double-spectral features is calculated. If the correlation is less than or equal to the preset threshold, the double-spectral features and feature information are fused into the fingerprint data of the cable, and the defect type of the cable is identified based on the fingerprint data.

Benefits of technology

The amount of information about the feature is improved, the accuracy of fingerprint data is improved, and thus the accuracy of identifying defect types is improved.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a defect detection method and device for a cable and a storage medium. The method comprises the steps that a time domain reflection signal, a frequency domain reflection signal and an original discharge spectrogram of the cable are collected; constructing a combined discharge spectrogram according to the time domain reflection signal, the frequency domain reflection signal and the original discharge spectrogram; extracting feature information on a time domain and a frequency domain from the combined discharge spectrogram; mapping the combined discharge spectrogram to a bispectrum space to obtain bispectrum features; calculating the correlation between the feature information and the bispectrum features; if the correlation is smaller than or equal to a preset threshold value, fusing the bispectrum features and the feature information into fingerprint data of the cable; and identifying the defect type of the cable according to the fingerprint data. According to the embodiment of the invention, the combined discharge spectrogram is constructed for the information of the cable on the time domain, the frequency domain and the spectrogram at the first level, and the features are extracted from the time frequency and the high dimension at the secondary level, so that the information amount of the features can be effectively increased, the accuracy of the fingerprint data is improved, and the accuracy of identifying the defect type is improved.
Need to check novelty before this filing date? Find Prior Art