Geometric properties of partial least squares for process monitoring

Gang LI; S. Joe QIN; Donghua ZHOU

doi:10.1016/j.automatica.2009.10.030

Geometric properties of partial least squares for process monitoring

Gang LI, S. Joe QIN^*, Donghua ZHOU

^*Corresponding author for this work

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

356 Citations (Scopus)

Abstract

Projection to latent structures or partial least squares (PLS) produces output-supervised decomposition on input X, while principal component analysis (PCA) produces unsupervised decomposition of input X. In this paper, the effect of output Y on the X-space decomposition in PLS is analyzed and geometric properties of the PLS structure are revealed. Several PLS algorithms are compared in a geometric way for the purpose of process monitoring. A numerical example and a case study are given to illustrate the analysis results. © 2009 Elsevier Ltd. All rights reserved.

Original language	English
Pages (from-to)	204-210
Number of pages	7
Journal	Automatica
Volume	46
Issue number	1
Early online date	18 Nov 2009
DOIs	https://doi.org/10.1016/j.automatica.2009.10.030
Publication status	Published - Jan 2010
Externally published	Yes

Funding

This work was supported by the national 973 projects under Grants 2010CB731800 and 2009CB32602, and NSFC under Grants 60721003 and 60736026, and the Changjiang Professorship (S. Joe Qin) by the Ministry of Education of PR China.

Keywords

Partial least squares (PLS)
Process monitoring
Simplified PLS (SIMPLS)
Weight-deflated PLS (W-PLS)

Access to Document

10.1016/j.automatica.2009.10.030

Cite this

@article{85befc1c60c54007a7a86eda7588ebf0,

title = "Geometric properties of partial least squares for process monitoring",

abstract = "Projection to latent structures or partial least squares (PLS) produces output-supervised decomposition on input X, while principal component analysis (PCA) produces unsupervised decomposition of input X. In this paper, the effect of output Y on the X-space decomposition in PLS is analyzed and geometric properties of the PLS structure are revealed. Several PLS algorithms are compared in a geometric way for the purpose of process monitoring. A numerical example and a case study are given to illustrate the analysis results. {\textcopyright} 2009 Elsevier Ltd. All rights reserved.",

keywords = "Partial least squares (PLS), Process monitoring, Simplified PLS (SIMPLS), Weight-deflated PLS (W-PLS)",

author = "Gang LI and QIN, {S. Joe} and Donghua ZHOU",

year = "2010",

month = jan,

doi = "10.1016/j.automatica.2009.10.030",

language = "English",

volume = "46",

pages = "204--210",

journal = "Automatica",

issn = "0005-1098",

publisher = "Elsevier Ltd",

number = "1",

}

TY - JOUR

T1 - Geometric properties of partial least squares for process monitoring

AU - LI, Gang

AU - QIN, S. Joe

AU - ZHOU, Donghua

PY - 2010/1

Y1 - 2010/1

N2 - Projection to latent structures or partial least squares (PLS) produces output-supervised decomposition on input X, while principal component analysis (PCA) produces unsupervised decomposition of input X. In this paper, the effect of output Y on the X-space decomposition in PLS is analyzed and geometric properties of the PLS structure are revealed. Several PLS algorithms are compared in a geometric way for the purpose of process monitoring. A numerical example and a case study are given to illustrate the analysis results. © 2009 Elsevier Ltd. All rights reserved.

AB - Projection to latent structures or partial least squares (PLS) produces output-supervised decomposition on input X, while principal component analysis (PCA) produces unsupervised decomposition of input X. In this paper, the effect of output Y on the X-space decomposition in PLS is analyzed and geometric properties of the PLS structure are revealed. Several PLS algorithms are compared in a geometric way for the purpose of process monitoring. A numerical example and a case study are given to illustrate the analysis results. © 2009 Elsevier Ltd. All rights reserved.

KW - Partial least squares (PLS)

KW - Process monitoring

KW - Simplified PLS (SIMPLS)

KW - Weight-deflated PLS (W-PLS)

UR - http://www.scopus.com/inward/record.url?scp=73049084841&partnerID=8YFLogxK

U2 - 10.1016/j.automatica.2009.10.030

DO - 10.1016/j.automatica.2009.10.030

M3 - Journal Article (refereed)

SN - 0005-1098

VL - 46

SP - 204

EP - 210

JO - Automatica

JF - Automatica

IS - 1

ER -

Geometric properties of partial least squares for process monitoring

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this