Recursive PCA for adaptive process monitoring

  title={Recursive PCA for adaptive process monitoring},
  author={Weihua Li and Herman H Yue and Sergio Valle-Cervantes and S. Joe Qin},
While principal component analysis (PCA) has found wide application in process monitoring, slow and normal process changes often occur in real processes, which lead to false alarms for a ®xed-model monitoring approach. In this paper, we propose two recursive PCA algorithms for adaptive process monitoring. The paper starts with an ecient approach to updating the correlation matrix recursively. The algorithms, using rank-one modi®cation and Lanczos tridiagonalization, are then proposed and their… CONTINUE READING
Highly Influential
This paper has highly influenced 21 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 452 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 232 extracted citations

Recursive Slow Feature Analysis for Adaptive Monitoring of Industrial Processes

IEEE Transactions on Industrial Electronics • 2018
View 8 Excerpts
Highly Influenced

Power plant fault monitoring using Recursive Principal Component Analysis RPCA

2016 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC) • 2016
View 4 Excerpts
Highly Influenced

A monitoring method based on combination of EPCA and RPCA

The 27th Chinese Control and Decision Conference (2015 CCDC) • 2015
View 11 Excerpts
Highly Influenced

A dynamic split-and-merge approach for evolving cluster models

Evolving Systems • 2012
View 5 Excerpts
Highly Influenced

Weighted windowed PLS models for virtual metrology of an industrial plasma etch process

2010 IEEE International Conference on Industrial Technology • 2010
View 6 Excerpts
Highly Influenced

Data-driven Soft Sensors in the process industry

Computers & Chemical Engineering • 2009
View 5 Excerpts
Highly Influenced

453 Citations

Citations per Year
Semantic Scholar estimates that this publication has 453 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 26 references

Recursive PLS algorithms for adaptive data modeling, Comput

S.Joe Qin
Chem. Eng • 1998
View 12 Excerpts
Highly Influenced

Matrix computations (3. ed.)

View 8 Excerpts
Highly Influenced

A subspace approach to multidimensional fault identi®cation and reconstruction

R. Dunia, J. Qin
AIChE Journal 44 • 1998
View 7 Excerpts
Highly Influenced

Sensor fault identi- ®cation and reconstruction using principal component analysis

R. Dunia, J. Qin, T. F. Edgar, T. J. McAvoy
in: 13th IFAC World Congress, San Francisco • 1996
View 6 Excerpts
Highly Influenced

Modeling By Shortest Data Description *

View 5 Excerpts
Highly Influenced

Fast estimation of principal eigenspace using Lanczos algorithm

G. Xu, T. Kailath
SIAM J. Matrix Anal. Appl 15 • 1994
View 8 Excerpts
Highly Influenced

Detection of signals by information theoretic criteria

IEEE Trans. Acoustics, Speech, and Signal Processing • 1985
View 9 Excerpts
Highly Influenced

A new look at the statistical model identi®cation

H. Akaike
IEEE Trans. Auto. Con 19 • 1974
View 5 Excerpts
Highly Influenced

Adaptive batch monitoring using hierarchical PCA

S. Rannar, J. F. MacGregor, S. Wold
in: AIChE Annual Meeting, Los Angeles, 16±21 November 1997. W. Li et al. / Journal of Process Control 10 • 2000
View 1 Excerpt

Control procedures for residuals associated with principal component analysis

J. E. Jackson, G. Mudholkar
Technometrics 21 (1979) 341±349. 486 W. Li et al. / Journal of Process Control 10 • 2000
View 2 Excerpts

Similar Papers

Loading similar papers…