基于分层分块DLPPCA-SVM的复杂工业过程监测与故障诊断方法
作者:
作者单位:

1.国网辽宁省电力有限公司;2.东北大学;3.东软集团股份有限公司通信与企业互联事业部

作者简介:

通讯作者:

中图分类号:

TP273

基金项目:

国家重点研发计划资助(2017YFB0902100)


Monitoring and Fault Diagnosis Method of Complex Industrial Process Based on DLPPCA-SVM
Author:
Affiliation:

1.State Grid Liaoning Electric Power Co., Ltd.;2.Northeastern University;3.Communication and Enterprises Interconnection Division of Neusoft Corporation

Fund Project:

State Key R&D Program Support(2017YFB0902100)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    本文针对工业过动态性及非线性强等特点提出了一种基于动态局部保持主成分分析法的过程监测方法,该方法通过构造扩展矩阵来解决动态过程中各采样点间相关性强的问题,并将LPP与PCA结合从而实现提取流形结构的最大方差信息。在此基础上针对复杂工业过程变量复杂多变呈不同特性的特点,提出了基于分层分块DLPPCA-SVM(Dynamic Locality Preserving Principal Component Analysis-Support Vector Machine,DLPPCA-SVM)的过程监测及故障诊断方法,该方法针对不同的特性的子块分别采用DLPPCA和PCA进行建模,并利用支持向量机进行故障诊断。将该方法用于TE过程和发电机组的在线监测和故障诊断,仿真结果验证了所提方法的有效性。

    Abstract:

    In this paper, a process monitoring method based on dynamic local keeping principal component analysis is proposed to solve the problem of strong correlation between sampling points in dynamic process by constructing extended matrix. LPP and PCA are combined to maximize the overall variance while keeping the local structure unchanged. On this basis, a process monitoring and fault diagnosis method based on layered and block DLPPCA-SVM(Dynamic Locality Preserving Principal Component Analysis-Support Vector Machine,DLPPCA-SVM) is proposed for complex industrial processes with different characteristics. DLPPCA and PCA are used to model the sub blocks with different characteristics, and support vector machine is used for fault diagnosis. The method is applied to the on-line monitoring and fault diagnosis of TE process and generator set. The simulation results verify the effectiveness of the proposed method.

    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:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-11-22
  • 最后修改日期:2022-01-22
  • 录用日期:2021-02-10
  • 在线发布日期: 2021-03-03
  • 出版日期: