Information Criterion for Determination Time Window Length of Dynamic PCA for Process Monitoring

Xiuxi LI; Yu QIAN; Junfeng WANG; S Joe QIN

doi:10.1016/S1570-7946(03)80158-X

Information Criterion for Determination Time Window Length of Dynamic PCA for Process Monitoring

Xiuxi LI
, Yu QIAN^*
, Junfeng WANG
, S Joe QIN

^*Corresponding author for this work

Research output: Journal Publications › Journal Article (refereed) › peer-review

2 Citations (Scopus)

Abstract

Principal component analysis (PCA) is based on and suitable to analysis of stationary processes. When it is applied to dynamic process monitoring, the moving time window approach is used to construct the data matrix to be analyzed. However, the length of the time window and the moving width between time widows are often empirically tested and selected. In this paper, a criterion for determining the time window length is proposed for dynamic process monitoring. A new algorithm of dynamic monitoring is then presented. The proposed selection criterion is used in the new algorithm. Finally, the proposed approach is successfully applied to a two-input two-output process and Tennessee Eastman process for dynamic monitoring. © 2003 Elsevier B.V. All rights reserved.

Original language	English
Pages (from-to)	461-466
Number of pages	6
Journal	Computer Aided Chemical Engineering
Volume	14
DOIs	https://doi.org/10.1016/S1570-7946(03)80158-X
Publication status	Published - Jun 2003
Externally published	Yes
Event	13th European Symposium on Computer Aided Process Engineering (ESCAPE-13) - Lappeenranta, Finland Duration: 1 Jun 2003 → 4 Jun 2003

Bibliographical note

Volume 14: European Symposium on Computer Aided Process Engineering-13
36th European Symposium of the Working Party on Computer Aided Process Engineering (ESCAPE)

Funding

Financial support from the National Natural Science Foundation of China (No. 29976015), the China Excellent Young Scientist Fund, China Major Basic Research Development Program (G20000263) are gratefully acknowledged.

Access to Document

10.1016/S1570-7946(03)80158-X

Cite this

@article{2a37fcafb9214158ae31b896cd01e64c,

title = "Information Criterion for Determination Time Window Length of Dynamic PCA for Process Monitoring",

abstract = "Principal component analysis (PCA) is based on and suitable to analysis of stationary processes. When it is applied to dynamic process monitoring, the moving time window approach is used to construct the data matrix to be analyzed. However, the length of the time window and the moving width between time widows are often empirically tested and selected. In this paper, a criterion for determining the time window length is proposed for dynamic process monitoring. A new algorithm of dynamic monitoring is then presented. The proposed selection criterion is used in the new algorithm. Finally, the proposed approach is successfully applied to a two-input two-output process and Tennessee Eastman process for dynamic monitoring. {\textcopyright} 2003 Elsevier B.V. All rights reserved.",

author = "Xiuxi LI and Yu QIAN and Junfeng WANG and QIN, \{S Joe\}",

note = "Volume 14: European Symposium on Computer Aided Process Engineering-13 36th European Symposium of the Working Party on Computer Aided Process Engineering (ESCAPE); 13th European Symposium on Computer Aided Process Engineering (ESCAPE-13) ; Conference date: 01-06-2003 Through 04-06-2003",

year = "2003",

month = jun,

doi = "10.1016/S1570-7946(03)80158-X",

language = "English",

volume = "14",

pages = "461--466",

journal = "Computer Aided Chemical Engineering",

issn = "1570-7946",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Information Criterion for Determination Time Window Length of Dynamic PCA for Process Monitoring

AU - LI, Xiuxi

AU - QIAN, Yu

AU - WANG, Junfeng

AU - QIN, S Joe

N1 - Volume 14: European Symposium on Computer Aided Process Engineering-13 36th European Symposium of the Working Party on Computer Aided Process Engineering (ESCAPE)

PY - 2003/6

Y1 - 2003/6

N2 - Principal component analysis (PCA) is based on and suitable to analysis of stationary processes. When it is applied to dynamic process monitoring, the moving time window approach is used to construct the data matrix to be analyzed. However, the length of the time window and the moving width between time widows are often empirically tested and selected. In this paper, a criterion for determining the time window length is proposed for dynamic process monitoring. A new algorithm of dynamic monitoring is then presented. The proposed selection criterion is used in the new algorithm. Finally, the proposed approach is successfully applied to a two-input two-output process and Tennessee Eastman process for dynamic monitoring. © 2003 Elsevier B.V. All rights reserved.

AB - Principal component analysis (PCA) is based on and suitable to analysis of stationary processes. When it is applied to dynamic process monitoring, the moving time window approach is used to construct the data matrix to be analyzed. However, the length of the time window and the moving width between time widows are often empirically tested and selected. In this paper, a criterion for determining the time window length is proposed for dynamic process monitoring. A new algorithm of dynamic monitoring is then presented. The proposed selection criterion is used in the new algorithm. Finally, the proposed approach is successfully applied to a two-input two-output process and Tennessee Eastman process for dynamic monitoring. © 2003 Elsevier B.V. All rights reserved.

UR - https://www.scopus.com/pages/publications/77957148905

U2 - 10.1016/S1570-7946(03)80158-X

DO - 10.1016/S1570-7946(03)80158-X

M3 - Journal Article (refereed)

SN - 1570-7946

VL - 14

SP - 461

EP - 466

JO - Computer Aided Chemical Engineering

JF - Computer Aided Chemical Engineering

T2 - 13th European Symposium on Computer Aided Process Engineering (ESCAPE-13)

Y2 - 1 June 2003 through 4 June 2003

ER -

Information Criterion for Determination Time Window Length of Dynamic PCA for Process Monitoring

Abstract

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this