title: Further enhancement of fed-batch streptokinase yield in the presence of inflow noise by coupled neural networks
creator: Patnaik, P R
subject: QD Chemistry
description: Noise carried by the feed stream is a common feature of large-scale bioreactor operations. This noise may be modelled by a set of time-dependent Gaussian distributions. Recent studies have shown that neither unfiltered nor completely filtered noise is desirable. The best performance requires optimally filtered noise. A previous publication in this journal showed that streptokinase (SK) activity in a fed-batch fermentation can be improved substantially through controlled static filtering. Later work with β-galactosidase showed that dynamic filtering by means of a neuralnetwork was superior, especially when it was coupled to a neural filter. That concept has been applied to SK. Coupling of two neuralnetworks increased the peak SK activity (in g/l) by 42% over that for a noise-free feed whereas the improvement with a static filter was 22%
publisher: Elsevier Science
date: 2001
type: Article
type: PeerReviewed
format: application/pdf
identifier: http://crdd.osdd.net/open/869/1/patnaik2001.4.pdf
relation: http://dx.doi.org/10.1016/S0032-9592(01)00190-X
identifier:   Patnaik, P R  (2001) Further enhancement of fed-batch streptokinase yield in the presence of inflow noise by coupled neural networks.  Process Biochemistry, 37 (2).  pp. 145-151.  ISSN 13595113     
relation: http://crdd.osdd.net/open/869/