Toggle Main Menu Toggle Search

Open Access padlockePrints

Dynamic multivariate statistical process control using partial least squares and canonical variate analysis

Lookup NU author(s): Dr Alexandros Simoglou, Professor Elaine Martin, Emeritus Professor Julian Morris


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


Multivariate statistical techniques have been shown to be useful tools for multivariate statistical process control (MSPC) and process modelling. However, these approaches have been mainly applied to static systems. In the present work, a well known system representation, the state space model, is developed to deal with dynamic situations. The states of the system are approximated using two multivariate statistical projection techniques, Partial Least Squares (PLS) and Canonical Variate Analysis (CVA). These two model representations are compared both in terms of their predictive ability and also their monitoring power using a simulation example. An application to an industrial fluidised bed reactor will be presented at the conference following company approval.

Publication metadata

Author(s): Martin EB; Morris AJ; Simoglou A

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: European Symposium on Computer Aided Process Engineering-9

Year of Conference: 1999

Pages: S277-S280

ISSN: 0098-1354

Publisher: Pergamon

Library holdings: Search Newcastle University Library for this item

Series Title: Computers & Chemical Engineering