%A P R Patnaik
%O Copyright of this article belongs to  Canadian Society for Chemical Engineering.
%J Canadian Journal of Chemical Engineering
%T Neural and hybrid neural modelling and control of fed-batch fermentation for streptokinase: Comparative evaluation under nonideal conditions.
%X Fermentations involving competition between two or
more kinds of cells under nonideal conditions show
complex profi les that are sensitive to the extra-cellular
environment. These fermentations therefore require
accurate and rapid on-line data acquisition and control.
However, both on-line measurements and modelling
are diffi cult and expensive for large bioreactors, thus
limiting the usefulness of model-based control. While
neural networks offer an alternative, they require
extensive training and can be diffi cult to optimize
for large arrays. Hybrid networks combining
a few neural networks with some mathematical
equations offer a good compromise. The possibility of
using a hybrid model for simulation-cum-control has
been examined here for the fed-batch production of
streptokinase. Under noideal conditions, hybrid neural
models outperformed both mathematical models
and arrays of neural networks, thus suggesting their
viability for large-scale fermentation monitoring and
control.
Les fermentations provoquant une comp?tition entre
deux ou plusieurs sortes de cellules dans des conditions
non id?ales montrent des profi ls complexes qui
sont sensibles ? l?environnement extra-cellulaires. Ces
fermentations n?cessitent donc une acquisition et un
contr?le en continu des donn?es qui soient pr?cis et
rapides. Toutefois, les mesures et la mod?lisation en
continu sont diffi ciles et co?teuses pour les grands
bior?acteurs, ce qui limite l?utilit? du contr?le bas? sur
des mod?les. Les r?seaux neuronaux sont une autre
possibilit?, mais ceux-ci n?cessitent un entra?nement
pouss? et peuvent ?tre diffi ciles ? optimiser pour de
grands dispositifs. Les r?seaux hybrides combinant
r?seaux neuronaux et ?quations math?matiques
offrent un bon compromis. La possibilit? d?utiliser
un mod?le hybride pour la simulation et le contr?le
a ?t? examin?e dans ce travail pour la production
? alimentation discontinue de streptokinase. Dans
des conditions non id?ales, les mod?les neuronaux
hybrides offrent une meilleure performance que les
mod?les math?matiques ou les dispositifs de r?seaux
neuronaux, et il pourrait donc s?av?rer viable pour la
surveillance et le contr?le de fermentation ? grande
?chelle
%N 3
%K streptokinase, fed-batch fermentation,
nonideal conditions, hybrid neural network.
%P 599-607
%V 82
%D 2004
%I wiley
%L open954