Toggle Main Menu Toggle Search

Open Access padlockePrints

Statistical performance monitoring using state space modelling and wavelet analysis

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


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


This paper describes the application of multiresolution analysis to the states and the model residuals calculated through the application of canonical variate analysis (CVA) for process performance monitoring. Applyting Hotelling T2 to the states and residuals and calculating the statistical limits will materialise in an excess of false alarms since the CVA model states and model residuals are observed to exhibit serial correlation. By aplying wavelets to the states, the auto-correlation is removed and the standard monitoring metrics can then be applied. The performance and sensitivity of the proposed methodology was assessed for different monitoring indices using average run length (ARL) and false alarm rate as performance indicators. The basis of the study was a benchmark simulation of a continuous stirred tank reactor. © 2005 Elsevier B.V. All rights reserved.

Publication metadata

Author(s): Alawi A, Morris A, Martin E

Publication type: Article

Publication status: Published

Journal: Computer Aided Chemical Engineering

Year: 2005

Volume: 20

Issue: C

Pages: 1459-1464

ISSN (print): 1570-7946

ISSN (electronic):

Publisher: Elsevier BV


DOI: 10.1016/S1570-7946(05)80085-9


Altmetrics provided by Altmetric