A method for predicting the combined probability of failure of a dirty insulator

By combining the probabilistic prediction method of ultraviolet pulse and infrared temperature characteristics, the accuracy and comprehensiveness of fault prediction for polluted insulators in the existing technology are solved, and more accurate fault probability prediction is achieved.

CN115902535BActive Publication Date: 2026-05-29STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO +2
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO
Filing Date
2022-10-24
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies for predicting faults in polluted insulators suffer from narrow prediction ranges and imperfect models, failing to accurately reflect the fault evolution process.

Method used

A joint probability prediction method based on ultraviolet pulse and infrared temperature features is adopted. By acquiring ultraviolet pulse waveforms and infrared thermograms, feature distributions are obtained using Hibert transform and image processing. Combined with histogram nonparametric estimation method, threshold and probability density distribution are determined, and joint probability is calculated for fault prediction.

Benefits of technology

It improves the accuracy and comprehensiveness of fault prediction for polluted insulators, better characterizes the insulator condition, and achieves more accurate fault probability prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115902535B_ABST
    Figure CN115902535B_ABST
Patent Text Reader

Abstract

The present application relates to a kind of based on the joint probability prediction method of dirty insulator failure of ultraviolet pulse and infrared temperature feature, comprising: S1, the ultraviolet pulse waveform and infrared thermogram of dirty insulator obtained by experiment are obtained, based on Hibert transformation envelope line is obtained, based on image processing method the temperature distribution of infrared thermogram;S2, respectively determine the probability density distribution of ultraviolet pulse envelope line and the probability density distribution of infrared temperature using sample statistical method and histogram nonparametric estimation method;S3, based on the indication effect of ultraviolet pulse envelope line and infrared temperature feature to insulator failure, determine the threshold value of the ultraviolet pulse value and infrared temperature value corresponding to different failure;S4, based on the probability density distribution in S2 and the threshold value in S3 division, calculate the joint probability under different failure, and failure prediction is carried out according to probability value.Compared with prior art, the present application solves the problem of inaccurate single feature failure prediction, and has the advantages of high prediction accuracy.
Need to check novelty before this filing date? Find Prior Art