半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于深度置信网络的电压暂降特征提取及源辨识方法
作者:
作者单位:

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:

李丹奇(1996—),女,通信作者,硕士研究生,主要研究方向:电力系统及其自动化。E-mail:ldq19960313@163.com
梅飞(1982—),男,博士,主要研究方向:电力电子技术。E-mail:mario82@163.com
张宸宇(1989—),男,博士,工程师,主要研究方向:电能质量治理技术。E-mail:yu_z@sina.com

通讯作者:

基金项目:

江苏省重点研发计划资助项目(BE2017030)。


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

1.School of Electrical Engineering, Southeast University, Nanjing 210096, China;2.College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China;3.Electric Power Research Institute of State Grid Jiangsu Electric Power Co., Ltd., Nanjing 211103, China

Fund Project:

This work is supported by Key R&D Program of Jiangsu Province (No. BE2017030).

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    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 by comparison, which is available for practical engineering.

    表 1 基于DBN的电压暂降特征提取方法获得的特征Table 1 Features obtained by the method of voltage sag feature extraction based on DBN
    表 4 Table 4
    图1 DBN模型结构Fig.1 Structure of DBN model
    图2 不同参数下提取特征的特征离散距离Fig.2 Discrete distance of features extracted from different parameters
    图3 不同参数下每次迭代的误差损失率Fig.3 Error loss rate of each iteration with different parameters
    图4 DBN提取特征的二维投影Fig.4 2D projection for feature extraction based on DBN
    图5 S变换提取特征的二维投影Fig.5 2D projection for feature extraction based on S transform
    图 基于DBN的电压暂降特征提取方法流程图Fig. Flow chart of voltage sag feature extraction method based on DBN
    图 算例流程图Fig. Flow chart of Simulation example
    图 特征离散程度原理图Fig. Characteristic dispersion degree schematic diagram
    表 3 不同电压暂降源辨识方法正确率Table 3 Accuracy of different identification methods for voltage sag sources
    表 2 基于DBN的电压暂降源辨识方法正确率Table 2 Accuracy rate of voltage sag source identification method based on DBN
    参考文献
    相似文献
    引证文献
引用本文

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(4):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(4):150-158. DOI:10.7500/AEPS20190306004.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-03-06
  • 最后修改日期:2019-05-15
  • 录用日期:2019-05-27
  • 在线发布日期: 2020-02-16
  • 出版日期: