Application of latent variable methods to process control and multivariate statistical process control in industry

被引:252
作者
Kourti, T [1 ]
机构
[1] McMaster Univ, Dept Chem Engn, McMaster Adv Control Consortium, Hamilton, ON L8S 4L7, Canada
关键词
multivariate statistical process control; PLS; PCA; batch process monitoring; adaptive PLS; soft sensors; fault detection; fault isolation; data archiving; data compression; image analysis;
D O I
10.1002/acs.859
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Multivariate monitoring and control schemes based on latent variable methods have been receiving increasing attention by industrial practitioners in the last 15 years. Several companies have enthusiastically adopted the methods and have reported many success stories. Applications have been reported where multivariate statistical process control, fault detection and diagnosis is achieved by utilizing the latent variable space, for continuous and batch processes, as well as, for process transitions as for example start ups and re-starts. This paper gives an overview of the latest developments in multivariate statistical process control (MSPC) and its application for fault detection and isolation (FDI) in industrial processes. It provides a critical review of the methodology and describes how it is transferred to the industrial environment. Recent applications of latent variable methods to process control as well as to image analysis for monitoring and feedback control are discussed. Finally it is emphasized that the multivariate nature of the data should be preserved when data compression and data preprocessing is applied. It is shown that univariate data compression and reconstruction may hinder the validity of multivariate analysis by introducing spurious correlations. Copyright (c) 2005 John Wiley & Sons, Ltd.
引用
收藏
页码:213 / 246
页数:34
相关论文
共 85 条
[1]  
[Anonymous], 2003, P 35 ANN M CAN MIN P
[2]   Dealing with missing data in MSPC: several methods, different interpretations, some examples [J].
Arteaga, F ;
Ferrer, A .
JOURNAL OF CHEMOMETRICS, 2002, 16 (8-10) :408-418
[3]  
BENDWELL N, 2000, VECTEUR ENV, V33
[4]   The GIFI approach to non-linear PLS modeling [J].
Berglund, A ;
Kettaneh, N ;
Uppgård, LL ;
Wold, S ;
Bendwell, N ;
Cameron, DR .
JOURNAL OF CHEMOMETRICS, 2001, 15 (04) :321-336
[5]  
BHARATI M, 2004, TAPPI J, V3
[6]   Softwood lumber grading through on-line multivariate image analysis techniques [J].
Bharati, MH ;
MacGregor, JF ;
Tropper, W .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2003, 42 (21) :5345-5353
[7]   Multivariate image analysis for real-time process monitoring and control [J].
Bharati, MH ;
MacGregor, JF .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 1998, 37 (12) :4715-4724
[8]   SOME THEOREMS ON QUADRATIC FORMS APPLIED IN THE STUDY OF ANALYSIS OF VARIANCE PROBLEMS .1. EFFECT OF INEQUALITY OF VARIANCE IN THE ONE-WAY CLASSIFICATION [J].
BOX, GEP .
ANNALS OF MATHEMATICAL STATISTICS, 1954, 25 (02) :290-302
[9]  
BUNKOFSKE RJ, 2002, Patent No. 6442445
[10]  
Burnham AJ, 1996, J CHEMOMETR, V10, P31, DOI 10.1002/(SICI)1099-128X(199601)10:1<31::AID-CEM398>3.0.CO