An AI-driven power distribution fault location system and method

The AI-driven fault location system utilizes a topology response collaborative constraint model and a reinforcement learning strategy model to eliminate false fault paths and enhance path scoring discrimination capabilities. This solves the problems of information lag and high operation and maintenance costs in traditional power distribution fault location, achieving efficient and accurate fault identification and location.

CN121770157BActive Publication Date: 2026-06-09BEIJING LONGDEYUAN INTELLIGENT ELECTRIC POWER CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING LONGDEYUAN INTELLIGENT ELECTRIC POWER CO LTD
Filing Date
2025-12-23
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Traditional power distribution fault location relies on manual inspection, which suffers from information lag, slow response, and high operation and maintenance costs. Especially in multi-feeder and multi-bus structures, there are many path assumptions and the scoring system lacks feedback enhancement mechanisms, resulting in poor fault location accuracy and convergence.

Method used

An AI-driven fault location system is constructed by using state projection construction units, state collision elimination units, differential comparison scoring units, and structural feedback location units. It utilizes topological response collaborative constraint models, AI response scoring models, and reinforcement learning strategy models to build a multi-distributed state space structure mapping system, eliminate false fault paths, enhance path scoring discrimination capabilities, and achieve accurate fault location.

Benefits of technology

It significantly reduces the candidate path search space, improves the accuracy and efficiency of fault identification, ensures the uniqueness of fault location results and the reliability of operation and maintenance decisions, and reduces operation and maintenance costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121770157B_ABST
    Figure CN121770157B_ABST
Patent Text Reader

Abstract

This invention relates to the field of power distribution fault location technology, specifically to an AI-driven power distribution fault location system and method. The system includes: a state projection construction unit that constructs multiple fault state projection surfaces; a state collision elimination unit that uses a topology response collaborative constraint model to identify structural logic conflicts and uses a structural collision-driven multi-path filtering mechanism to eliminate fault state projection surfaces with structural logic conflicts; a differential comparison scoring unit that uses an AI response scoring model to generate confidence scores for each candidate fault state projection surface and uses a working condition semantic embedding model to correct the confidence scores; a structural feedback location unit that uses the AI ​​response scoring model to update and sort the confidence score sequence to determine the fault point; and a fault terminal processing and display unit that displays the fault points of each power distribution station and generates inspection tasks and maintenance work orders. This invention combines AI-driven intelligent judgment and location of power distribution faults and constructs a fault identification method for multi-site maintenance scenarios.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Power equipment fault diagnosis method based on adaptive fuzzy reasoning

    CN120688007A

  • Power distribution automation operation and maintenance method based on electric power big data

    CN121172983A