Intelligent diagnosis method for distribution network fault based on multi-source heterogeneous data fusion

By establishing a dual-segment buffer structure and wavelet transform method in the distribution network, high-fidelity recording and early identification of intermittent flashover faults are achieved, solving the problem of difficulty in capturing fault precursors in existing technologies and improving the accuracy and completeness of fault identification.

CN121786709BActive Publication Date: 2026-06-05STATE GRID ANHUI ELECTRIC POWER CO LTD & COUNTY POWER SUPPLY CO +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
STATE GRID ANHUI ELECTRIC POWER CO LTD & COUNTY POWER SUPPLY CO
Filing Date
2026-03-05
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing power distribution network monitoring technologies are unable to fully record and capture key transient information of intermittent flashover faults, making it impossible to accurately identify fault precursors and affecting fault location and troubleshooting.

Method used

A method based on multi-source heterogeneous data fusion is adopted to establish a dual-segment buffer structure, collect line electrical quantities in real time, detect transient disturbance events through the forward buffer, freeze the data and align it with the waveform data recorded in the backward buffer to form a complete transient waveform, and combine wavelet transform and feature extraction to achieve high-fidelity recording of the flashover and flash-connection process.

Benefits of technology

It enables continuous, traceable, and high-fidelity recording of the entire process of power line interruption and reconnection, significantly improving the early fault identification capability and analysis reliability. It also solves the problems of discontinuity and pseudo-abrupt changes in multi-buffered data splicing, thereby improving the accuracy and completeness of fault identification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121786709B_ABST
    Figure CN121786709B_ABST
Patent Text Reader

Abstract

The application discloses a distribution network fault intelligent diagnosis method based on multi-source heterogeneous data fusion and relates to the technical field of distribution network fault diagnosis, and comprises the following steps: a double-section buffer structure containing a forward buffer area and a backward buffer area is established, line electrical quantities are collected in real time, and the forward buffer area is written in cycles; real-time analysis is conducted on the data of the forward buffer area, and suspicious signs of transient disturbance events are detected; when the suspicious signs are detected, the data of the forward buffer area is frozen, and whether the event starting condition is met is judged based on the data; if the event starting condition is met, the backward buffer area is started to record waves, and transient buffer data are obtained; the frozen forward buffer area data and the transient buffer data are time-aligned and corrected, and complete transient waveforms are formed; through the method of establishing double-section transient buffer, micro-amplitude fluctuation detection and forward-backward data splicing and correction, the problems that the intermittent flash-off and flash-on fault process cannot be recorded completely and the precursors are difficult to capture are solved.
Need to check novelty before this filing date? Find Prior Art