Two-step Principal Component Analysis for Dynamic Processes

被引:0
作者
Lou, Zhijiang [1 ]
Tuo, Jianyong [1 ]
Wang, Youqing [1 ,2 ]
机构
[1] Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 10029, Peoples R China
[2] Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China
来源
2017 6TH INTERNATIONAL SYMPOSIUM ON ADVANCED CONTROL OF INDUSTRIAL PROCESSES (ADCONIP) | 2017年
关键词
Process monitoring; principal component analysis (PCA); dynamic PCA (DPCA); discrete-time state space model; state space PCA (SS-PCA); ORDER CUMULANTS ANALYSIS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A enhanced principal component analysis (PCA), termed as Two-step PCA (TS-PCA), is proposed to handle the dynamic characteristic of industry processes. Differently from the traditional dynamic PCA (DPCA) using the "time lag shift" structure, TS-PCA adopts a new structure to present the dynamic property in the process data. By using this new structure, TS-PCA can extract the time-uncorrelated components from the dynamic data and use it for process monitoring. In addition, it can update the expectation and standard variance of the process data at each step for data normalization.
引用
收藏
页码:73 / 77
页数:5
相关论文
共 11 条
  • [1] Improved subspace identification with prior information using constrained least squares
    Alenany, A.
    Shang, H.
    Soliman, M.
    Ziedan, I.
    [J]. IET CONTROL THEORY AND APPLICATIONS, 2011, 5 (13) : 1568 - 1576
  • [2] A PLANT-WIDE INDUSTRIAL-PROCESS CONTROL PROBLEM
    DOWNS, JJ
    VOGEL, EF
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 1993, 17 (03) : 245 - 255
  • [3] Online monitoring of nonlinear multivariate industrial processes using filtering KICA-PCA
    Fan, Jicong
    Qin, S. Joe
    Wang, Youqing
    [J]. CONTROL ENGINEERING PRACTICE, 2014, 22 : 205 - 216
  • [4] Dynamic higher-order cumulants analysis for state monitoring based on a novel lag selection
    Jia, Guijin
    Wang, Youqing
    Huang, Biao
    [J]. INFORMATION SCIENCES, 2016, 331 : 45 - 66
  • [5] Disturbance detection and isolation by dynamic principal component analysis
    Ku, WF
    Storer, RH
    Georgakis, C
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1995, 30 (01) : 179 - 196
  • [6] Statistical monitoring of dynamic processes based on dynamic independent component analysis
    Lee, JM
    Yoo, C
    Lee, IB
    [J]. CHEMICAL ENGINEERING SCIENCE, 2004, 59 (14) : 2995 - 3006
  • [7] Defining the structure of DPCA models and its impact on process monitoring and prediction activities
    Rato, Tiago J.
    Reis, Marco S.
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2013, 125 : 74 - 86
  • [8] Online Monitoring of Multivariate Processes Using Higher-Order Cumulants Analysis
    Wang, Youqing
    Fan, Jicong
    Yao, Yuan
    [J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2014, 53 (11) : 4328 - 4338
  • [9] A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process
    Yin, Shen
    Ding, Steven X.
    Haghani, Adel
    Hao, Haiyang
    Zhang, Ping
    [J]. JOURNAL OF PROCESS CONTROL, 2012, 22 (09) : 1567 - 1581
  • [10] Modeling and monitoring of nonlinear multi-mode processes
    Zhang, Yingwei
    Li, Shuai
    [J]. CONTROL ENGINEERING PRACTICE, 2014, 22 : 194 - 204