Multivariate Statistical Monitoring Procedures for Fermentation Supervision: An Industrial Case Study

This paper describes a case study in which multivariate statistical procedures have been developed to assist in the supervision of an industrial fed-batch fermentation process. Currently supervisory control of the industrial fermentation is aided through use of the G2 realtime knowledge based system...

Full description

Saved in:
Bibliographic Details
Published inIFAC Proceedings Volumes Vol. 31; no. 8; pp. 399 - 404
Main Authors Montague, G.A., Hiden, H.G., Kornfeld, G.
Format Journal Article
LanguageEnglish
Published 01.05.1998
Subjects
fault detection
fermentation processses
implementation
monitoring
multivariate statistical process control
fermentation processses
monitoring
multivariate statistical process control
fault detection
implementation
Online AccessGet full text

Cover

More Information
Summary:This paper describes a case study in which multivariate statistical procedures have been developed to assist in the supervision of an industrial fed-batch fermentation process. Currently supervisory control of the industrial fermentation is aided through use of the G2 realtime knowledge based system. The rule based system is complemented by a number of algorithmic methods. While rules are useful for detecting deviations in single variables, complex interactions between fermentation conditions during batch operation can lead to more subtle deviations. One approach that can be used in such circumstances is Multi-way principal component analysis. This provides early indications of deviations from nominal batch process behaviour and subsequently contribution plots can be utilised to assist in identifying the causes.
ISSN:1474-6670
DOI:10.1016/S1474-6670(17)40218-7