A multi-grounding point lightning stroke fault judging method and device

By constructing a lightning electromagnetic transient simulation model and optimizing a fault prediction model, the problem that traditional models cannot realistically reproduce lightning strike faults at multiple grounding points is solved, and high-precision fault judgment and reliable fault prediction are achieved.

CN122410380APending Publication Date: 2026-07-17HEYUAN POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-13
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Traditional electromagnetic transient simulation models for lightning strikes cannot realistically reproduce the triggering process of lightning strikes with multiple grounding points, and the judgment accuracy of fault prediction models is not high, which affects the safe operation of electrical systems.

Method used

A lightning electromagnetic transient simulation model is constructed, and a full-dimensional and detailed simulation is performed through a bifurcation lightning model, a signal control model, and an electrical component model. Combined with multi-dimensional convolutional feature extraction and attention weight allocation, the fault prediction model is optimized to improve the judgment accuracy.

Benefits of technology

It achieves high-precision judgment of lightning strike faults with multiple grounding points, improves the accuracy and reliability of fault classification, reduces the false negative rate, and provides highly reliable electromagnetic transient characteristic data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122410380A_ABST
    Figure CN122410380A_ABST
Patent Text Reader

Abstract

The application provides a multi-ground-point lightning stroke fault judgment method and device, and relates to the field of lightning stroke fault analysis. The method comprises the following steps: obtaining historical lightning stroke fault working condition data of a target electrical system, wherein the historical lightning stroke fault working condition data comprises historical electrical working condition data, historical electromagnetic transient characteristic data and historical fault categories; constructing a bifurcated lightning model, a signal control model and an electrical element model according to the historical electrical working condition data, wherein the bifurcated lightning model, the signal control model and the electrical element model constitute a lightning electromagnetic transient simulation model; constructing an initial fault prediction model, and performing iterative parameter optimization on the initial fault prediction model through the historical electromagnetic transient characteristic data and the historical fault categories to obtain a final fault prediction model; inputting to-be-detected electrical working condition data into the lightning electromagnetic transient simulation model to perform lightning simulation, and obtaining simulation electromagnetic transient characteristic data; inputting the simulation electromagnetic transient characteristic data into the final fault prediction model to perform fault prediction, and obtaining a final fault category.
Need to check novelty before this filing date? Find Prior Art