一种新的基于深度置信网络的电能质量扰动分类方法
DOI:
作者:
作者单位:

长沙理工大学电气与信息工程学院

作者简介:

通讯作者:

基金项目:

国家自然科学基金项目资助(51507015, 61673388);湖南省自然科学基金项目资助(2018JJ2439);湖南省教育厅优秀青年项目资助(18B130)


A new method of power quality disturbance classification based on deep belief network
Author:
Affiliation:

School of Electrical and Information Engineering,Changsha University of Science and Technology

Fund Project:

  • 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:

    针对在噪声干扰下多重扰动识别正确率不高的问题,提出了一种新的基于深度置信网络的电能质量扰动分类方法。首先,对电能质量扰动信号进行平稳小波多尺度变换,再利用软阀值函数处理估计小波系数重构原始信号,从而实现了对电能质量扰动信号的去噪。进一步,提出利用深度置信网络对重构后的单一扰动信号和多重扰动信号进行分类识别,仿真结果表明该方法对7种单一扰动和13种多重扰动信号的识别正确率均较高,即使在20dB噪声干扰下,其分类正确率高达到93%以上,证明了该方法抗噪声干扰的能力较强。

    Abstract:

    Abstact: In view of the low correct rate of power quality disturbance identification under the problem of noise interference, a new method of power quality disturbance classification based on deep belief network was proposed. A smooth wavelet multiscale transform is performed on the power quality disturbance signal, and then the soft threshold function is used to process the estimated wavelet coefficients for reconstructing the original signal. Further, it is proposed to use deep confidence network to classify and recognize the reconstructed single disturbance signal and multiple disturbance signals. The simulation results demonstrate that the correct rate of this method for seven typical single disturbances and thirteen mixed disturbances is high. Even under 20dB noise interference, the classification correct rate is as high as 93% or more, which proves that the method has a strong ability to resist noise interference.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2021-01-01
  • 最后修改日期:2021-03-18
  • 录用日期:2021-03-19
  • 在线发布日期: