Methods and equipment applicable to fault type diagnosis and section location in power distribution networks

By using deep convolutional neural networks and conditional adversarial generative networks in the distribution network, a high-quality fault waveform dataset is generated, which solves the problems of accuracy and adaptability in fault type and section location in the existing technology, realizes fast and reliable fault diagnosis and location, and improves the power supply reliability of the distribution network.

CN121878382BActive Publication Date: 2026-05-26KEDA INTELLIGENT ELECTRICAL TECH +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
KEDA INTELLIGENT ELECTRICAL TECH
Filing Date
2026-03-23
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing fault diagnosis methods for power distribution networks rely on manual feature extraction and identification, which are susceptible to noise and system interference, have poor adaptability, and are difficult to quickly and reliably locate fault types and sections, especially in complex interference scenarios where accuracy is insufficient.

Method used

Using single-point measurement of three-phase voltage, zero-sequence voltage, three-phase current, and zero-sequence current as the research objects, a high-quality, balanced fault waveform dataset is generated by constructing and training a deep convolutional neural network and combining it with a conditional adversarial generative network to locate the fault type and section.

Benefits of technology

It enables rapid and reliable identification of fault types and segment location under complex interference scenarios, improves the accuracy and response speed of the model, reduces power outage duration, and enhances the power supply reliability of the distribution network.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121878382B_ABST
    Figure CN121878382B_ABST
Patent Text Reader

Abstract

This invention discloses a method and device for fault type diagnosis and fault segment location in distribution networks. The method includes selecting eight-channel waveforms from a single measurement point on a faulty line: three-phase zero-sequence voltage, zero-sequence voltage, three-phase current, and zero-sequence current as the judgment waveforms. Based on fault waveform datasets collected from actual lines and batch simulation waveform datasets, a high-quality waveform dataset with broad coverage and balanced type distribution is generated through a conditional adversarial generative network. Each channel of the fault waveform undergoes classification and normalization, feature regions are extracted, and then the dimensions are expanded into a two-dimensional field matrix through field transformation. The eight sets of two-dimensional matrices are preprocessed into eight-channel two-dimensional matrix tensors. These tensors, combined with fault type and fault segment labels, form a model training set. This invention enables the classification and identification of fault types and fault segments in fault waveforms. This invention can accelerate fault investigation, improve the power supply reliability of distribution networks, and provide technical support for ground fault diagnosis that relies entirely on data-driven methods.
Need to check novelty before this filing date? Find Prior Art