A power grid step-by-step positioning method, device, equipment and storage medium based on improved cluster analysis

By improving cluster analysis and semi-supervised machine learning technology, the characteristic quantities of grid fault recording data and protection information data are extracted, and the grid disturbances and faults are accurately positioned, the problem of difficulty in accurately positioning in the existing technology is solved, and the safety and stability of grid operation are improved.

CN119740059APending Publication Date: 2025-04-01WUHAN ZHONGYUAN HUADIAN SCI & TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202411799781.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-09
Publication Date
2025-04-01

AI Technical Summary

Technical Problem

It is difficult for the prior art to accurately locate the fault of no tripping or the fault of small abnormal current in the power grid, making it difficult to eliminate potential hidden dangers in the power grid.

Method used

The grid disturbance distribution positioning method based on improved clustering analysis is adopted to determine the location of the disturbance or fault by collecting fault recording data and protecting information data, and the feature quantity is extracted, and the unsupervised K-mean clustering and semi-supervised machine learning technology is used.

Benefits of technology

The step-by-step positioning of grid disturbances and faults is realized, the possibility of misjudgment is reduced, the available sample data is expanded, and the safety and stability of grid operation is improved.

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

Abstract

The present invention discloses a method, device, equipment and storage medium for locating the distribution of power grid disturbances based on improved cluster analysis, which belongs to the technical field of power grid disturbance or fault location. The method is applicable to systems or devices such as fault recording and security master stations, and includes the following steps: collecting fault recording and protection information data; extracting classification feature quantities through fault recording voltage data; classifying data based on an improved cluster analysis method; extracting new features for data closest to the disturbance or fault area; and determining the power grid disturbance location based on a semi-supervised machine learning method. The present invention combines unsupervised cluster analysis with a semi-supervised machine learning method, and realizes the function of locating power grid disturbances or faults while taking into account the situation where protection fails to operate or security data cannot be obtained, which is of great significance for eliminating hidden dangers in the power grid and improving the level of safe operation of the power grid.
Need to check novelty before this filing date? Find Prior Art