Full length paper
Multi-way partial least squares in monitoring batch processes

https://doi.org/10.1016/0169-7439(95)00043-7Get rights and content

Abstract

Multivariate statistical procedures for monitoring the progress of batch processes are developed. Multi-way partial least squares (MPLS) is used to extract the information from the process measurement variable trajectories that is more relevant to the final quality variables of the product. The only information needed is a historical database of past successful batches. New batches can be monitored through simple monitoring charts which are consistent with the philosophy of statistical process control. These charts monitor the batch operation and provide on-line predictions of the final product qualities. Approximate confidence intervals for the predictions from PLS models are developed. The approach is illustrated using a simulation study of a styrene-butadiene batch reactor.

References (32)

  • G.J. Birky et al.

    Comput. Chem. Eng.

    (1990)
  • C.E. Marsh et al.

    ISA Trans.

    (1991)
  • B. Skagerberg et al.

    Chemom. Intell. Lab. Syst.

    (1992)
  • P. Geladi et al.

    Anal. Chim. Acta

    (1986)
  • P. Geladi

    Chemom. Intell. Lab. Syst.

    (1989)
  • A.K. Smilde

    Chemom. Intell. Lab. Syst.

    (1992)
  • S. Wold

    Chemom. Intell. Lab. Syst.

    (1992)
  • A. Phatak et al.

    Anal. Chim. Acta

    (1993)
  • R. Iserman

    Automatica

    (1984)
  • P. Nomikos et al.

    AIChE J.

    (1994)
  • G.J. Hahn et al.

    J. Appl. Stat.

    (1987)
  • S.A. Vander Wiel et al.

    Technometrics

    (1992)
  • J. Kresta et al.

    Can. J. Chem. Eng.

    (1991)
  • B.M. Wise et al.

    Process Contr. Qual.

    (1990)
  • P. Nomikos et al.

    Technometrics

    (1995)
  • S. Wold et al.

    J. Chemom.

    (1987)
  • Cited by (715)

    View all citing articles on Scopus
    View full text