|本期目录/Table of Contents|

[1]余琼芳,徐静,杨艺.基于CNN_LSTM模型的复杂支路故障电弧检测*[J].中国安全生产科学技术,2022,18(4):204-210.[doi:10.11731/j.issn.1673-193x.2022.04.029]
　YU Qiongfang,XU Jing,YANG Yi.Fault arc detection of complex branch based on CNN_LSTM model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(4):204-210.[doi:10.11731/j.issn.1673-193x.2022.04.029]
点击复制

基于CNN_LSTM模型的复杂支路故障电弧检测*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
18
期数:
2022年4期
页码:
204-210
栏目:
职业安全卫生管理与技术
出版日期:
2022-04-30

文章信息/Info

Title:
Fault arc detection of complex branch based on CNN_LSTM model
文章编号:
1673-193X(2022)-04-0204-07
作者:
余琼芳; 徐静; 杨艺
(1.河南理工大学 电气工程与自动化学院，河南 焦作 454003;
2.大连理工大学 北京研究院博士后科研工作站，北京 100000)
Author(s):
YU Qiongfang;  XU Jing;  YANG Yi
（1.School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo Henan 454003,China;
2.Postdoctoral Programme of Beijing Research Institute,Dalian University of Technology,Beijing 100000,China）
关键词:
低压交流系统; 串联故障电弧; 复杂支路; 支路故障; 卷积神经网络; 长短时记忆网络
Keywords:
low voltage AC system;  series fault arc;  complex branch;  branch fault;  convolutional neural network;  long short-term memory network
分类号:
X934
DOI:
10.11731/j.issn.1673-193x.2022.04.029
文献标志码:
A
摘要:
在低压交流配电系统中，当多支路并联的复杂系统的某1支路中出现串联电弧故障时，识别难度大幅提升。为了预防此类情况引发的电气火灾，提出1种卷积神经网络(CNN)与长短时记忆网络(LSTM)结合的串联故障电弧检测方法。首先，搭建实验平台用以采集不同负载在不同支路下发生故障时和正常工作时的干路电流数据;然后,构建CNN_LSTM模型并做出相应改进，将电流数据直接输入到模型中，由模型自主提取波形特征并进行分类。研究结果表明:该方法可以快速、准确地识别出电弧故障，准确率达99.04%以上，且能够较为准确地检测出是哪类负载所在的支路发生电弧故障，准确率达97.90%，可为复杂支路下的电弧故障识别研究提供参考。
Abstract:
In the low voltage AC distribution system,the difficulty of identification is greatly increased when the series arc fault occurs in one branch of the complex system with multiple branches in parallel.To prevent the electrical fires caused by such conditions,a detection method of series fault arc combining with the convolutional neural network (CNN) and long short-time memory network (LSTM) was proposed.Firstly,an experimental platform was built to collect the data of the trunk circuit current of different loads under different branches at fault and normal operation.Then the CNN_LSTM model was built and improved accordingly.The current data was directly input into the model,and the waveform features were extracted and classified by the model independently.The results showed that this method could quickly and accurately identify the arc faults,and the accuracy reached more than 99.04%.Moreover,it could more accurately detect the branch where the arc fault occurred with which kind of load,with the accuracy of 97.90%.It provides reference for the research of arc fault identification under complex branches.

参考文献/References:

［1］LEZAMAJ,SCHWEITZER P,TISSERAND E,et al.An embedded system for AC series arc detection by inter-period correlations of current［J］.Electric Power Systems Research,2015,129：227-234.
［2］GIOVANNI A,GIUSEPPE C,ANTONIO C,et al.Characterization of DC series arc faults in PV systems based on current low frequency spectral analysis［J］.Measurement,2021,182(5)：109770.
［3］VASILE C,IOANA C.Arc fault detection & localization by eletromagnetic-acoustic remote sensing［J］.IOP Conference Series:Materials Science and Engineering,2017,198(1):12004-12009.
［4］白辉,许志红.基于小波包变换和高阶累积量的电弧故障识别方法［J］.电力自动化设备,2020,40(11):195-202,224,203. BAI Hui,XU Zhihong.Arcfault identification method based on wavelet packet transform and high-order accumulator［J］.Electric Power Automation Equipment,2020,40(11):195-202,224,203.
［5］丁鑫,竺红卫,殷浩楠,等.基于快速傅里叶变换(FFT)的交流电器电弧快速检测法［J］.电器与能效管理技术,2015(21):8-12. DING Xin,ZHU Hongwei,YIN Haonan,et al.Fastdetection method for ac arc based on FFT［J］.Electrical & Energy Management Technology,2015(21):8-12.
［6］余琼芳,黄高路,杨艺，等.基于AlexNet深度学习网络的串联故障电弧检测方法［J］.电子测量与仪器学报,2019,33(3):145-152. YU Qiongfang,HUANG Gaolu,YANG Yi,et al.Series arc fault detection method based on AlexNet deep learning network［J］.Journal of Electronic Measurement and Instrumentation,2019,33(3):145-152.
［7］林靖怡,王尧,李奎,等.基于自组织特征映射网络的电弧故障检测方法［J］.电力自动化设备,2020,40(8):210-219. LIN Jingyi,WANG Yao,LI Kui,et al.Arc fault detection method based on self-organizing feature mapping network［J］.Electric Power Automation Equipment,2020,40(8):210-219.
［8］陈烜,冷继伟,李海峰.基于全相位谱和深度学习的串联故障电弧识别方法［J］.电力系统保护与控制,2020,48(17):1-8. CHEN Xuan,LENG Jiwei,LI Haifeng.Series fault arc recognition method based on an all-phase spectrum and deep learning［J］.Power System Protection and Control,2020,48(17):1-8.
［9］苏晶晶,许志红.基于EMD和PNN的故障电弧多变量判据诊断方法［J］.电力自动化设备,2019,39(4):106-113. SU Jingjing,XU Zhihong.Diagnosis method of multi- variable criterion based on EMD and PNN for arc fault diagnosis［J］.Electric Power Automation Equipment,2019,39(4):106-113.
［10］余琼芳,胡亚倩,杨艺.基于小波特征及深度学习的故障电弧检测［J］.电子测量与仪器学报,2020,34(3):100-108. YU Qiongfang,HU Yaqian,YANG Yi.Arc fault detection based on wavelet feature and deep learning［J］.Journal of Electronic Measurement and Instrumentation,2020,34(3):100-108.
［11］全国低压电器标准化技术委员会.电弧故障保护电器（AFDD）的一般要求：GB/T 31143—2014［S］.北京：中国标准出版社，2014.
［12］胡恩瑞.基于卷积神经网络的故障电弧检测算法研究［D］.杭州：浙江大学,2020.
［13］赵怀军,秦海燕,刘凯,等.基于相关理论及零休特征融合的串联故障电弧检测方法［J］.仪器仪表学报,2020,41(4):218-228. ZHAO Huaijun,QIN Haiyan,LIU Kai,et al.A seriesfault arc detection method based on the fusion ofcorrelation theory and zero current feature［J］.Chinese Journal of Scientific Instrument,2020,41(4):218-228.
［14］LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition［J］.Proceedings of the IEEE.Institute of Electrical and Electronics Engineers,1998,86 (11):2278-2324.
［15］HOCHREITER S,SCHMIDHUBER J.Long short-term memory［J］.Neural Computation,1997,9(8):1735-1780.

相似文献/References:

[1]王泽伦,高洪鑫,刘艳丽,等.SVD在串联故障电弧检测及选相中的应用*[J].中国安全生产科学技术,2020,16(9):160.[doi:10.11731/j.issn.1673-193x.2020.09.025]
　WANG Zelun,GAO Hongxin,LIU Yanli,et al.Application of SVD in series fault arc detection and phase selection[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(4):160.[doi:10.11731/j.issn.1673-193x.2020.09.025]

备注/Memo

备注/Memo:
收稿日期： 2021-07-20
* 基金项目： 国家自然科学基金项目(61601172)
作者简介： 余琼芳，博士，副教授，主要研究方向为检测技术与自动化。
通信作者： 徐静，硕士研究生，主要研究方向为现代检测技术与装置。
更新日期/Last Update: 2022-05-13