Data recognition method and system for characteristic gases of cable thermal degradation

By collecting and processing cable thermal degradation gases with high precision, and combining the SVM model and the Grey Wolf optimization algorithm, the problem of accuracy in cable degradation identification has been solved, enabling early warning and accurate monitoring of cable faults, and ensuring the safety of the power system.

WO2026113173A1PCT designated stage Publication Date: 2026-06-04GUIZHOU POWER GRID CO LTD
View PDF 10 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
GUIZHOU POWER GRID CO LTD
Filing Date
2025-03-07
Publication Date
2026-06-04

AI Technical Summary

Technical Problem

Existing technologies cannot accurately identify the cable degradation process and fault type by observing changes in the type and concentration of gases released from the cable, and traditional monitoring methods have significant limitations.

Method used

A high-precision synchronous acquisition method was used to collect the gases released during the thermal degradation of cables. After filtering and noise reduction, the characteristic values ​​of the gas concentration were extracted. An SVM model was used for classification and anomaly detection. The hyperparameters of the SVM model were optimized by combining the Grey Wolf optimization algorithm to construct a data identification system for characteristic gases of cable thermal degradation.

Benefits of technology

It enables accurate identification of cable degradation processes and fault types, provides early warnings, reduces the risk of power equipment failures, and ensures the safe and stable operation of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025081336_04062026_PF_FP_ABST
    Figure CN2025081336_04062026_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of cable fault detection. Disclosed are a data recognition method and system for characteristic gases of cable thermal degradation. The method comprises: performing synchronous high-precision collection on a plurality of gases released during cable thermal degradation; preprocessing collected data; and packaging the preprocessed data, and then classifying the packaged data, and detecting whether there is an anomaly. In the present invention, an SVM model is used to perform classification and recognition, and therefore not only can classification of characteristics of different gases be efficiently performed, but whether data has deviated from a normal range can also be identified by means of anomaly detection. An optimal solution is searched for by means of dynamically adjusting positions of a wolf pack, such that the SVM model can adapt to complex cable degradation status, thereby improving the accuracy of recognition. The thermal degradation status of a cable can be analyzed on the basis of real-time monitoring data, such that the degradation process and possible fault types are accurately predicted, thereby providing early warning, reducing the risk of unexpected faults of a power device, and ensuring the safe and stable operation of a power system.
Need to check novelty before this filing date? Find Prior Art