Recursive PCA for adaptive process monitoring

Weihua LI*, H. Henry YUE, Sergio VALLE-CERVANTES, S. Joe QIN

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

781 Citations (Scopus)

Abstract

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 fixed-model monitoring approach. In this paper, we propose two recursive PCA algorithms for adaptive process monitoring. The paper starts with an efficient approach to updating the correlation matrix recursively. The algorithms, using rank-one modification and Lanczos tridiagonalization, are then proposed and their computational complexity is compared. The number of principal components and the confidence limits for process monitoring are also determined recursively. A complete adaptive monitoring algorithm that addresses the issues of missing values and outlines is presented. Finally, the proposed algorithms are applied to a rapid thermal annealing process in semiconductor processing for adaptive monitoring.
Original languageEnglish
Pages (from-to)471-486
Number of pages16
JournalJournal of Process Control
Volume10
Issue number5
Early online date22 Aug 2000
DOIs
Publication statusPublished - Oct 2000
Externally publishedYes
Event14th IFAC World Congress - Beijing, China
Duration: 5 Jul 19999 Jul 1999

Bibliographical note

Financial support for this project from National Science Foundation under CTS-9814340, DuPont and Advanced Micro Devices is gratefully acknowledged.

Keywords

  • Adaptive process monitoring
  • Lanczos tridiagonalization
  • Rank-one modification
  • Recursive principal component analysis

Fingerprint

Dive into the research topics of 'Recursive PCA for adaptive process monitoring'. Together they form a unique fingerprint.

Cite this