科技创新与应用2025，Vol.15Issue(14)：63-67,5.DOI:10.19981/j.CN23-1581/G3.2025.14.014
适用于深度学习训练的配电网故障历史样本数据生成研究
摘要
Abstract
With the development of smart grid and deep learning technology,the use of historical fault samples for training has become a powerful means of fault data processing in distribution networks.This study adopts a dynamic iterative strategy:firstly,the deep learning model is used to identify the fault types of the distribution network,and the key data is summarized and extracted from the identification process.Then,through a continuous iterative process,the historical sample data generated each time is fed back into the model.Finally,a system model of 10 kV line protection detection test is built in Matlab/Simulink,and a simulation test example is built for verification,and the experimental results show that the model is effective and feasible.关键词
配电网故障/故障检测/深度学习/动态迭代/历史样本数据Key words
distribution network failures/fault detection/deep learning/dynamic iteration/historical sample data分类
信息技术与安全科学引用本文复制引用
郭海东,唐先均,朱学,孟斌,吴达,张发..适用于深度学习训练的配电网故障历史样本数据生成研究[J].科技创新与应用,2025,15(14):63-67,5.基金项目
中国华电集团科研基金(CATL-ND-ESS-2024030046577) （CATL-ND-ESS-2024030046577）
