A method and system for identifying power fault points based on deep learning technology

By constructing a grid equivalent model and generating theoretical reference values ​​to correct the electrical quantity data, the accuracy of fault positioning under the topology changes of the grid is solved, and the accuracy and reliability of fault point identification in the deep learning model is improved.

CN120317156BActive Publication Date: 2025-08-22HANGZHOU HUANYU VISION TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202510804774.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-17
Publication Date
2025-08-22
Estimated Expiration
2045-06-17

AI Technical Summary

Technical Problem

The existing fault positioning system based on historical data training cannot accurately identify the fault location when facing changes in the power grid topology structure, resulting in deviations in positioning results and even errors, affecting the reliability of power supply.

Method used

By obtaining the electrical quantity data when the fault occurs and the current grid topology information, a grid equivalent model is constructed, a theoretical reference value is generated to correct the original electrical quantity data, a corrected feature quantity is generated, and a deep learning model is used to locate the fault.

Benefits of technology

It improves the accuracy and reliability of fault point identification under the topological changes of the power grid, reduces the impact of topological changes on the positioning results, and ensures accurate judgment of fault locations.

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

Abstract

The present application provides a method and system for identifying power fault points based on deep learning technology, which relates to the field of power system technology. The key points of its technical solution are: obtaining the original electrical quantity data collected from monitoring points along the line at the time of fault occurrence and the current power grid topology information; constructing a power grid equivalent model under the current operating state based on the current power grid topology information and pre-stored power grid component parameters; performing power grid physical calculations based on the power grid equivalent model to generate theoretical reference values ​​for correcting the original electrical quantity data; correcting the original electrical quantity data using the theoretical reference values ​​to generate corrected feature quantities; inputting the corrected feature quantities into a fault location judgment unit to output fault location information. The present application provides a method and system for identifying power fault points based on deep learning technology, which has the advantage of improving the accuracy and reliability of fault point identification under changes in power grid topology.
Need to check novelty before this filing date? Find Prior Art