• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Chang, Peng (Chang, Peng.) | Wang, Pu (Wang, Pu.) | Gao, Xue-Jin (Gao, Xue-Jin.) (学者:高学金)

收录:

EI Scopus PKU CSCD

摘要:

The essence of the traditional multiway kernel independent component analysis(MKICA) method is that the independent component analysis(ICA) whitened principal component analysis(PCA) is replaced with KPCA by using second order statistics of the monitoring and controlling process, not by the stage characteristic of process data and higher-order cumulant information. To solve this problem, the high order cumulant analysis(HCA) and multiway kernel entropy independent component analysis(MKECA) are combined, and the analysis of high order cumulant multiway kernel entropy independent component analysis(HCA-MKEICA) method is proposed. Firstyly, the kernel entropy independent component analysis(KECA) method is used for original data conversion to solve the problem of nonlinear. Then, in the high-dimensional kernel entropy space, the HCA technology is used to construct the new statistics for process monitoring. Finally, the proposed method is applied to the microbial fermentation process, and the comparison results with the traditional methods show that the proposed method can achieve a better detection, and verify its effectivess. © 2017, Editorial Office of Control and Decision. All right reserved.

关键词:

Batch data processing Data handling Entropy Fermentation Higher order statistics Independent component analysis Process control Process monitoring

作者机构:

  • [ 1 ] [Chang, Peng]Department of Information, Beijing University of Technology, Beijing; 100124, China
  • [ 2 ] [Chang, Peng]Ministry of Education Engineering Center Digital Community, Beijing University of Technology, Beijing; 100124, China
  • [ 3 ] [Chang, Peng]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing; 100124, China
  • [ 4 ] [Wang, Pu]Department of Information, Beijing University of Technology, Beijing; 100124, China
  • [ 5 ] [Wang, Pu]Ministry of Education Engineering Center Digital Community, Beijing University of Technology, Beijing; 100124, China
  • [ 6 ] [Wang, Pu]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing; 100124, China
  • [ 7 ] [Gao, Xue-Jin]Department of Information, Beijing University of Technology, Beijing; 100124, China
  • [ 8 ] [Gao, Xue-Jin]Ministry of Education Engineering Center Digital Community, Beijing University of Technology, Beijing; 100124, China
  • [ 9 ] [Gao, Xue-Jin]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing; 100124, China

通讯作者信息:

  • [chang, peng]ministry of education engineering center digital community, beijing university of technology, beijing; 100124, china;;[chang, peng]beijing key laboratory of computational intelligence and intelligent system, beijing university of technology, beijing; 100124, china;;[chang, peng]department of information, beijing university of technology, beijing; 100124, china

电子邮件地址:

查看成果更多字段

相关关键词:

来源 :

Control and Decision

ISSN: 1001-0920

年份: 2017

期: 12

卷: 32

页码: 2273-2278

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次: 4

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:196/3603384
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司