Deep Belief Network Based Method for Feature Extraction and Source Identification of Voltage Sag

Danqi LI; Fei MEI; Chenyu ZHANG; Haoyuan SHA; Jianyong ZHENG; Taoran LI

doi:10.7500/AEPS20190306004

您当前的位置：

首页 >

文章列表页 >

Deep Belief Network Based Method for Feature Extraction and Source Identification of Voltage Sag

Application Research | 更新时间：2025-06-16

- Deep Belief Network Based Method for Feature Extraction and Source Identification of Voltage Sag
- Automation of Electric Power Systems Vol. 44, Issue 4, Pages: 150-158(2020)
- 作者机构：
  
  1. 东南大学电气工程学院,江苏省南京市 210096
  2. 河海大学能源与电气学院,江苏省南京市 211100
  3. 国网江苏省电力有限公司电力科学研究院,江苏省南京市 211103
- 作者简介：
- 基金信息：
  
  Key R&D Program of Jiangsu Province
- DOI：10.7500/AEPS20190306004
  CLC：
- Received：06 March 2019，
  
  Revised：2019-05-15，
  
  Published Online：16 July 2019，
  
  Published：25 February 2020
- 稿件说明：
移动端阅览
李丹奇,梅飞,张宸宇等.基于深度置信网络的电压暂降特征提取及源辨识方法[J].电力系统自动化,2020,44(04):150-158.

LI Danqi,MEI Fei,ZHANG Chenyu,et al.Deep Belief Network Based Method for Feature Extraction and Source Identification of Voltage Sag[J].Automation of Electric Power Systems,2020,44(04):150-158.
李丹奇,梅飞,张宸宇等.基于深度置信网络的电压暂降特征提取及源辨识方法[J].电力系统自动化,2020,44(04):150-158. DOI： 10.7500/AEPS20190306004.

LI Danqi,MEI Fei,ZHANG Chenyu,et al.Deep Belief Network Based Method for Feature Extraction and Source Identification of Voltage Sag[J].Automation of Electric Power Systems,2020,44(04):150-158. DOI： 10.7500/AEPS20190306004.

摘要

提出一种基于深度置信网络(DBN)的电压暂降特征提取与暂降源辨识方法

利用DBN的特征提取能力对实测波形数据进行特征自提取

解决了人工提取特征过度依赖专家经验

受未知特征影响较大不具备一般性的问题。采用多隐层结构网络学习特征最终实现暂降源辨识。该模型集特征提取器与分类器于一体

优化了模型结构框架

提高了暂降源辨识效率。对模型最优参数进行选择

建立适用于电压暂降实测数据类型的DBN模型

对电网实测暂降数据进行特征提取与暂降源辨识

通过对比验证了DBN方法在特征提取与暂降源识别上的优越性

适用于实际工程。

Abstract

A method for voltage sag feature extraction and sag source identification based on deep belief network (DBN) is proposed. The feature extraction ability of DBN is used to extract the feature data from the measured waveform data

which solves the problem that the artificial features rely too much on expert experiences and are short of generality. The multi-hidden layer structure network learning feature is used to realize the identification of the sag source. The model integrates feature extractor and classifier together to optimize the model structure and improve the efficiency of sag source identification. The optimal parameters of the model are selected

and DBN model for the measured voltage sag data is established. The feature extraction and sag source identification of the real-time measured sag data of power grid are carried out. The superiority of DBN method in feature extraction and sag source identification is verified

which is available for practical engineering.

关键词

Keywords

references

肖湘宁 . 电能质量分析与控制 [M]. 北京 : 中国电力出版社 , 2010 .

XIAO Xiangning . Power quality analysis and control [M]. Beijing : China Electric Power Press , 2010 .

肖湘宁 , 徐永海 . 电能质量问题剖析 [J]. 电网技术 , 2001 , 25 ( 3 ): 66 - 69 .

XIAO Xiangning , XU Yonghai . Power quality analysis and its development [J]. Power System Technology , 2001 , 25 ( 3 ): 66 - 69 .

杨进 , 肖湘宁 . 电能质量监测技术发展新趋势——网络化、信息化、标准化 [J]. 电力自动化设备 , 2004 , 24 ( 11 ): 83 - 87 .

YANG Jin , XIAO Xiangning . New trend of power quality monitoring technology—networking, informatization and standardization [J]. Electric Power Automation Equipment , 2004 , 24 ( 11 ): 83 - 87 .

陶顺 , 肖湘宁 . 电力系统电能质量评估体系架构 [J]. 电工技术学报 , 2010 , 25 ( 4 ): 171 - 175 .

TAO Shun , XIAO Xiangning . Power system power quality assessment system architecture [J]. Transactions of China Electrotechnical Society , 2010 , 25 ( 4 ): 171 - 175 .

ZHANG Lidong , BOLLEN M H J . Characteristic of voltage dips (sags) in power systems [C]// 8th International Conference on Harmonics and Quality of Power, October 14-16 , 1998 , Athens , Greece .

BOLLEN M H J , GOOSENS P , ROBERT A . Assessment of voltage dips in HV-networks: deduction of complex voltages from the measured RMS voltages [J]. IEEE Transactions on Power Delivery , 2004 , 19 ( 2 ): 783 - 790 .

王克星 , 宋政湘 , 陈德桂 , 等 . 基于小波变换的配电网电压暂降的干扰源辨识 [J]. 中国电机工程学报 , 2003 , 23 ( 6 ): 29 - 34 .

WANG Kexing , SONG Zhengxiang , CHEN Degui , et al . Interference source identification of voltage sag in distribution system based on wavelet transform [J]. Proceedings of the CSEE , 2003 , 23 ( 6 ): 29 - 34 .

赵凤展 , 杨仁刚 . 基于短时傅里叶变换的电压暂降扰动检测 [J]. 中国电机工程学报 , 2007 , 27 ( 10 ): 28 - 34 .

ZHAO Fengzhan , YANG Rengang . Voltage sag disturbance detection based on short time Fourier transform [J]. Proceedings of the CSEE , 2007 , 27 ( 10 ): 28 - 34 .

黄南天 , 徐殿国 , 刘晓胜 . 基于S变换与SVM的电能质量复合扰动识别 [J]. 电工技术学报 , 2011 , 26 ( 10 ): 23 - 30 .

HUANG Nantian , XU Dianguo , LIU Xiaosheng . Identification of power quality complex disturbances based on S transform and SVM [J]. Transactions of China Electrotechnical Society , 2011 , 26 ( 10 ): 23 - 30 .

AXELBERG P G , GU I Y , BOLLEN M H . Support vector machine for classification of voltage disturbances [J]. IEEE Transactions on Power Delivery , 2007 , 22 ( 3 ): 1297 - 1303 .

SINGH M , CHACKO S T , ZADGAONKAR A S . Detection of voltage sag by artificial neural network and mitigation using DSTATCOM [C]// 2nd International Conference on Power, Control and Embedded Systems, December 17-19 , 2012 , Allahabad , India .

VALTIERRA-RODRIGUEZ M , ROMERO-TRONCOSO R D J , GARCIA-PEREZ R A . Detection and classification of single and combined power quality disturbances using neural networks [J]. IEEE Transactions on Industrial Electronics , 2014 , 61 ( 5 ): 2473 - 2482 .

MEI Fei , REN Yong , WU Qingliang , et al . Online recognition method for voltage sags based on a deep belief network [J]. Energies , 2019 , 12 ( 1 ): 43 .

LIU Zhigang , ZHANG Qiaoge . An approach to recognize the transient disturbances with spectral kurtosis [J]. IEEE Transactions on Instrumentation and Measurement , 2014 , 63 ( 1 ): 46 - 55 .

ALAM M R , MUTTAQI K M , BOUZERDOUM A . A new approach for classification and characterization of voltage dips and swells using 3-d polarization ellipse parameters [J]. IEEE Transactions on Power Delivery , 2015 , 30 ( 3 ): 1344 - 1353 .

SHA Haoyuan , MEI Fei , ZHANG Chenyu , et al . Identification method for voltage sags based on K -means-singular value decomposition and least squares support vector machine [J]. Energies , 2019 , 12 ( 6 ): 1137 .

LI Danqi , MEI Fei , ZHANG Chenyu , et al . Self-supervised voltage sag source identification method based on CNN [J]. Energies , 2019 , 12 ( 6 ): 1059 .

王志群 , 朱守真 , 周双喜 . 电能质量扰动的专家概率分类器模型 [J]. 电力系统自动化 , 2004 , 28 ( 8 ): 45 - 49 .

WANG Zhiqun , ZHU Shouzhen , ZHOU Shuangxi . Expert probability classification for power quality disturbances [J]. Automation of Electric Power Systems , 2004 , 28 ( 8 ): 45 - 49 .

陈鹏伟 , 肖湘宁 , 陶顺 . 直流微网电能质量问题探讨 [J]. 电力系统自动化 , 2016 , 40 ( 10 ): 148 - 158 .

CHEN Pengwei , XIAO Xiangning , TAO Shun . Discussion on power quality of DC microgrid [J]. Automation of Electric Power Systems , 2016 , 40 ( 10 ): 148 - 158 .

HINTON G E , SALAKHUTDINOV R R . Reducing the dimensionality of data with neural networks [J]. Science , 2006 , 313 ( 5786 ): 504 - 507 .

BALOUJI E , SALOR O . Classification of power quality events using deep learning on event images [C]// 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA) , April 19 - 20 , 2017 , Shahrekord, Iran: 216 - 221 .

BALOUJI E , GU I Y , BOLLEN M H , et al . A LSTM-based deep learning method with application to voltage dip classification [C]// 18th International Conference on Harmonics and Quality of Power (ICHQP), May 13-16 , 2018 , Ljubljana , Slovenia .

TAMILSELVAN P , WANG P . Failure diagnosis using deep belief learning based health state classification [J]. Reliability Engineering & System Safety , 2013 , 115 ( 7 ): 124 - 135 .

TRAN V T , ALTHOBIANI F , BALL A . An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks [J]. Expert Systems with Applications , 2014 , 41 ( 9 ): 4113 - 4122 .

SHAO H , JIANG H , ZHANG X , et al . Rolling bearing fault diagnosis using an optimization deep belief network [J]. Measurement Science & Technology , 2015 , 26 ( 11 ): 115002 .

LI Chuan , SANCHEZ R V , ZURITA G , et al . Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis [J]. Neurocomputing , 2015 , 168 : 119 - 127 .

GEOFFREY E H . A practical guide to training restricted Boltzmann machines [J]. Momentum , 2012 , 9 ( 1 ): 599 - 619 .

BENGIO Y . Learning deep architectures for AI [J]. Foundations & Trends in Machine Learning , 2009 , 2 ( 1 ): 1 - 127 .

史鹤欢 , 许悦雷 , 杨志军 , 等 . 基于深度置信网络的目标识别方法 [J]. 计算机应用 , 2014 , 34 ( 11 ): 3314 - 3317 .

SHI Hehuan , XU Yuelei , YANG Zhijun , et al . Target recognition method based on deep confidence network [J]. Computer Applications , 2014 , 34 ( 11 ): 3314 - 3317 .

CHEN Erkang , YANG Xiaokang , ZHA Hongyuan , et al . Learning object classes from image thumbnails through deep neural networks [C]// IEEE International Conference on Acoustics, March 31-April 4 , 2008 , Las Vegas , USA: 829 .

SALAKHUTDINOV R , HINTON G E . Using deep belief nets to learn covariance kernels for Gaussian processes [C]// International Conference on Neural Information Processing Systems , December 3 , 2007 , Vancouver, Canada.

朱乔木 , 党杰 , 陈金富 , 等 . 基于深度置信网络的电力系统暂态稳定评估方法 [J]. 中国电机工程学报 , 2018 , 38 ( 3 ): 735 - 743 .

ZHU Qiaomu , DANG Jie , CHEN Jinfu , et al . Power system transient stability assessment method based on deep confidence network [J]. Proceedings of the CSEE , 2018 , 38 ( 3 ): 735 - 743 .

WOLD S . Principal component analysis [J]. Chemometrics & Intelligent Laboratory Systems , 1987 , 2 ( 1 ): 37 - 52 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Transient Stability Assessment of Power Systems Based on Multi-scale Graph Attention Network

Adaptive Assessment of Power System Transient Stability Based on Active Transfer Learning

Recognition Method of Voltage Sag Source Based on Optimized Extreme Learning Machine

Refined Transient Stability Evaluation for Power System Based on Ensemble Deep Belief Network

Ultra-short-term Load Forecasting Considering Missing Data in Anomalous Scenarios

Related Author

FU Taiguoyi

DU Youtian

LYU Hao

LI Zonghan

LIU Jun

LI Baoqin

WU Junyong

LI Lusu

Related Institution

School of Automation Science and Engineering, Xi’an Jiaotong University

National Key Laboratory of Grid Security (China Electric Power Research Institute)

School of Electrical Engineering, Xi’an Jiaotong University

School of Electrical Engineering, Beijing Jiaotong University

College of Electrical Engineering, Sichuan University

⁰