[1]高 超,刘泽辉,曹 栋,等.基于1DCNN-BiLSTM的电力电缆故障诊断[J].郑州大学学报(工学版),2023,44(05):86-92.[doi:10.13705/j.issn.1671-6833.2023.02.011]
　GAO Chao,LIU Zehui,CAO Dong,et al.Fault Diagnosis of Power Cable Based on 1DCNN-BiLSTM[J].Journal of Zhengzhou University (Engineering Science),2023,44(05):86-92.[doi:10.13705/j.issn.1671-6833.2023.02.011]
点击复制

基于1DCNN-BiLSTM的电力电缆故障诊断()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
44
期数:
2023年05期
页码:
86-92
栏目:
出版日期:
2023-08-20

文章信息/Info

Title:
Fault Diagnosis of Power Cable Based on 1DCNN-BiLSTM
作者:
高 超1;  刘泽辉1;  曹 栋2;  姚利娜2
1. 国网河南省电力公司电力科学研究院,河南 郑州 450052; 2. 郑州大学 电气与信息工程学院,河南 郑州 450001
Author(s):
GAO Chao1 ;  LIU Zehui1;  CAO Dong2;  YAO Lina2
1. State Grid Henan Electric Power Company Economic and Technological Research Institute, Zhengzhou 450052, China; 2. School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China
关键词:
电力电缆;  故障诊断;  一维卷积神经网络;  双向长短时记忆网络; 短路
Keywords:
power cable;  fault diagnosis;  one-dimensional convolutional neural network;  bidirectional long shortterm memory network;  short circuit
分类号:
TM732
DOI:
10.13705/j.issn.1671-6833.2023.02.011
文献标志码:
A
摘要:
为了提升电力电缆故障诊断的准确率,解决电缆故障诊断中过程烦琐、效率低、识别精度不高等问题,使其 能够在电缆故障发生时准确地诊断出故障类型,提出了一种基于连续卷积神经网络( CNN) 和双向长短网络记忆 (BiLSTM)的电缆故障检测方法。 通过 Simulink 搭建仿真模型,提取单相接地短路、两相接地短路、两相相间短路、 三相短路故障的电压信号,构建故障样本集。 将信号输入到该网络模型,一维卷积神经网络提取电缆故障信号的 局部特征,双向长短时记忆网络捕捉故障信号时序信息,基于自动提取的特征实现对电缆故障的诊断。 经仿真结 果验证,该方法能够对电力电缆的 4 种短路故障进行识别和分类,对单相接地短路故障和三相短路故障分类的正 确概率达到 97%,对两相接地短路和两相相间短路分类的正确概率达到 92%,整体准确率达到 98. 37%。 通过对损 失函数曲线、准确率曲线的分析,证明该方法能够取得较好的电缆故障诊断效果。 最后使用实际数据进行验证,结 果表明该方法具有可行性。
Abstract:
In order to improve the accuracy of fault diagnosis of power cable failure to ensure a cable fault detection method based on convolution neural network (CNN) and bi-directional long short term memory (BiLSTM) was proposed in this paper. The simulation model was built through Simulink to extract the voltage signals of single-phase ground short circuit, two-phase ground short circuit, two-phase phase short circuit and three-phase short circuit faults, and to generate the fault sample. Then the fault voltage signals were input into the network model, to obtain the local features through CNN, to obtain the fault signal timing information through BiLSTM, and to realize the diagnosis of cable fault based on the automatically extracted features. The simulation results showed that this method could accurately classify the four short-circuit faults of power cables, the accuracy rate of single-phase grounding short-circuit fault and three-phase short-circuit fault was 97%, the accuracy rate of two-phase ground short circuit and two-phase short circuit was 92%, and the overall accuracy rate was 98. 37%. In addition, through the analysis of loss function curve and accuracy curve, it was proved that this method could achieve better cable fault diagnosis effectiveness. Finally, the actual data was used to verify the feasibility of the method.

参考文献/References:

[1] 黄夏, 梁日干, 杨毅, 等. 配电电缆故障诊断方法研 究[ J] . 电工技术, 2021(7) : 72-73. 

HUANG X, LIANG R G, YANG Y, et al. Research on fault diagnosis method of distribution cable [ J] . Electric engineering, 2021(7) : 72-73. 
[2] 张伟, 何邦乐, 王东源, 等. LIRA 在输电电缆故障诊 断中的研究与应用[ J] . 电力大数据, 2021, 24( 11) : 23-31. 
ZHANG W, HE B L, WANG D Y, et al. Research and application of LIRA in transmission cable fault diagnosis [ J ] . Power Systems and Big Data, 2021, 24 (11) : 23-31. 
[3] 肖旰, 周莉, 李敬兆, 等. 基于 EEMD 融合 BAS-CNN 的高压电缆故障诊断[ J] . 电子测量技术, 2022, 45 (4) : 160-167. 
XIAO G, ZHOU L, LI J Z, et al. High-voltage cable fault diagnosis based on EEMD and BAS-CNN[ J]. Electronic Measurement Technology, 2022, 45(4): 160-167.
 [4] 任志玲, 张媛媛. 矿下电缆故障诊断的能量熵和 PSOBP 算 法 [ J ] . 系 统 仿 真 学 报, 2015, 27 ( 5 ) : 1044 -1049. 
REN Z L, ZHANG Y Y. Energy entropy and particle swarm optimization BP neural network of fault diagnosis techniques of coal mine cable[ J] . Journal of System Sim- ulation, 2015, 27(5) : 1044-1049. 
[5] 高金峰, 秦瑜瑞, 殷红德. 基于小波包变换和支持向 量机的故障选线方法[ J] . 郑州大学学报( 工学版) , 2020, 41(1) : 63-69. 
GAO J F, QIN Y R, YIN H D. Fault line selection based on wavelet packet transform and support vector machine [ J] . Journal of Zhengzhou University ( Engineering Science) , 2020, 41(1) : 63-69. 
[6] 苏立. 基于 HHT 变换和 FOALSSVM 的电缆故障诊断 [ J] . 计算机与现代化, 2017(9) : 96-101, 105. 
SU L. Cable fault diagnosis based on HHT transform and FOALSSVM [ J ] . Computer and Modernization, 2017 (9) : 96-101, 105. 
[7] 林伟, 罗群, 陈龑斌. 基于深度学习算法的大型飞机 电缆故障识别[ J] . 机械设计与制造工程, 2022, 51 (1) : 62-66. 
LIN W, LUO Q, CHEN Y B. Cable fault identification of large aircraft based on deep learning algorithm[ J] . Machine Design and Manufacturing Engineering, 2022, 51 (1) : 62-66.
 [8] 汪颖, 卢宏, 杨晓梅, 等. 堆叠自动编码器与 S 变换 相结合的电缆早期故障识别方法[ J] . 电力自动化设 备, 2018, 38(8) : 117-124. 
WANG Y, LU H, YANG X M, et al. Cable incipient fault identification based on stacked autoencoder and Stransform [ J ] . Electric Power Automation Equipment, 2018, 38(8) : 117-124. 
[9] 王坤. 基于深度学习的电力电缆故障定位技术[ D] . 西安: 西安电子科技大学, 2020. 
WANG K. Power cable fault location technology based on deep learning[D] . Xi′an: Xidian University, 2020. 
[10] 唐金锐, 尹项根, 张哲, 等. 配电网故障自动定位技术 研究综述[J]. 电力自动化设备, 2013, 33(5): 7-13. 
TANG J R, YIN X G, ZHANG Z, et al. Survey of fault location technology for distribution networks[ J] . Electric Power Automation Equipment, 2013, 33(5) : 7-13.
 [11] ALBERTO R,MARKUS H,FRANCO S,et al. A study on the effects of recursive convolutional layers in convolutional neural networks[J]. Neurocomputing, 2021, 460: 59-70.
[12] MESHRAM S, KUMAR M A. Long short-term memory network for learning sentences similarity using deep contextual embeddings[ J] . International Journal of Information Technology, 2021, 13: 1633-1641.
 [13] 卜佑军, 张桥, 陈博, 等. 基于 CNN 和 BiLSTM 的钓 鱼 URL 检测技术研究[ J] . 郑州大学学报( 工学版) , 2021, 42(6) : 14-20. 
BU Y J, ZHANG Q, CHEN B, et al. Research on phishing URL detection technology based on CNN-BiLSTM [ J] . Journal of Zhengzhou Uni

相似文献/References:

[1]雷文平,宋圣霖,郝旺身,等.基于FV-FBE的滚动轴承故障诊断研究[J].郑州大学学报(工学版),2020,41(05):82.[doi:10.13705/j.issn.1671-6833.2020.03.020]
　LEI Wenping,SONG Shenglin,HAO Wangshen,et al.Fault Diagnosis of Rolling Bearing Based on FV-FBE[J].Journal of Zhengzhou University (Engineering Science),2020,41(05):82.[doi:10.13705/j.issn.1671-6833.2020.03.020]
[2]王杰,王晓换..滚动轴承故障诊断虚拟系统的实现[J].郑州大学学报(工学版),2010,31(02):120.
　WANG Jie,WANG Xiaochange.Development of a Virtual Fault Diagnostic System For Rolling Bearing[J].Journal of Zhengzhou University (Engineering Science),2010,31(05):120.
[3]王忠勇,张振兴,段琳琳,等.基于故障树的某型舰炮故障诊断系统的设计与实现[J].郑州大学学报(工学版),2010,31(03):46.[doi:10.3969/j.issn.1671-6833.2010.03.012]
　Wang Zhongyong,ZHANG Zhenxing,DUAN Linlin,et al.Design and implementation of a certain type of naval gun fault diagnosis system based on fault tree[J].Journal of Zhengzhou University (Engineering Science),2010,31(05):46.[doi:10.3969/j.issn.1671-6833.2010.03.012]
[4]刘景艳,李玉东,杨晓邦..遗传神经网络在齿轮故障诊断中的应用[J].郑州大学学报(工学版),2012,33(03):36.[doi:10.3969/j.issn.1671-6833.2012.03.009]
　LIU Jingyan,LI Yudong,YANG Xiaobang.Application of Genetic Neural Network to Gear Fault Diagnosis[J].Journal of Zhengzhou University (Engineering Science),2012,33(05):36.[doi:10.3969/j.issn.1671-6833.2012.03.009]
[5]廖晓辉,梁恒娜,丁倩..基于小波变换的电力电缆故障测距研究[J].郑州大学学报(工学版),2013,34(03):6.[doi:10.3969/j.issn.1671-6833.2013.03.002]
　LIAOXiao-hui,LIANGHengna,DING Qian.Research of Power Cable Fault Location Based on Wavelet TransfeIrm[J].Journal of Zhengzhou University (Engineering Science),2013,34(05):6.[doi:10.3969/j.issn.1671-6833.2013.03.002]
[6]齐保林,李凌均,李志农..基于支持向量机的故障模式识别研究[J].郑州大学学报(工学版),2007,28(01):9.[doi:10.3969/j.issn.1671-6833.2007.01.003]
　Qi Baolin,LI Lingjun,Li Zhinong.Research on failure mode recognition based on support vector machine[J].Journal of Zhengzhou University (Engineering Science),2007,28(05):9.[doi:10.3969/j.issn.1671-6833.2007.01.003]
[7]刘艳芳,周晓微,梁萌..人工神经网络在生物过程中的应用[J].郑州大学学报(工学版),2007,28(02):121.[doi:10.3969/j.issn.1671-6833.2007.02.031]
　LIU Yanfang,ZHOU Xiaowei,Liang Meng.Application of artificial neural networks in biological processes[J].Journal of Zhengzhou University (Engineering Science),2007,28(05):121.[doi:10.3969/j.issn.1671-6833.2007.02.031]
[8]石金彦,黄士涛,雷文平..粗糙集与决策树结合诊断故障的数据挖掘方法[J].郑州大学学报(工学版),2003,24(01):109.[doi:10.3969/j.issn.1671-6833.2003.01.027]
　Shi Jinyan,HUANG Shitao,Raven Ping.A data mining method that combines rough sets with decision trees to diagnose failures[J].Journal of Zhengzhou University (Engineering Science),2003,24(05):109.[doi:10.3969/j.issn.1671-6833.2003.01.027]
[9]毕果,韩捷,梁川..基于矢量振动信号的AR功率谱分析及应用[J].郑州大学学报(工学版),2003,24(02):80.[doi:10.3969/j.issn.1671-6833.2003.02.021]
　Bego,Han Jie,Liang Chuan.AR power spectrum analysis and application based on vector vibration signal[J].Journal of Zhengzhou University (Engineering Science),2003,24(05):80.[doi:10.3969/j.issn.1671-6833.2003.02.021]
[10]张鸿河,关惠玲..基于包络分析的自行火炮变速箱故障诊断研究[J].郑州大学学报(工学版),2003,24(03):91.[doi:10.3969/j.issn.1671-6833.2003.03.023]

更新日期/Last Update: 2023-09-04