Study on Fault Arc Recognition Based on Back-Propagation Neural Network

In view of the problems of low loop current and ineffective detection of traditional line protection equipment when series fault arc occurs, a fault arc recognition neural network model based on wavelet analysis and backpropagation(BP) neural network is established to identify the fault arc quickly...

Full description

Saved in:
Bibliographic Details
Main Author: QIAO Weide
Format: Article
Language:English
Published: Editorial Department of Journal of Nantong University (Natural Science Edition) 2020-09-01
Series:Nantong Daxue xuebao. Ziran kexue ban
Subjects:
Online Access:https://ngzke.cbpt.cnki.net/portal/journal/portal/client/paper/c7b3604de635df2d1aed18726cd53914
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In view of the problems of low loop current and ineffective detection of traditional line protection equipment when series fault arc occurs, a fault arc recognition neural network model based on wavelet analysis and backpropagation(BP) neural network is established to identify the fault arc quickly and accurately. Frequency doubling wavelet analysis is applied to extract the characteristics of fault arc signal. Vector, firefly-particle swarm optimization algorithm is used to optimize the initial structure parameters of BP neural network. BP neural network is trained by improving BP algorithm and 630 sets of learning samples. Through testing and comparative experimental analysis, the BP neural network model optimized by the firefly-particle swarm optimization algorithm can realize the quick and accurate fault arc identification, verify the effectiveness of the series fault arc identification method, and provide a reference for fault arc diagnosis and protection technology.
ISSN:1673-2340