Hybrid modelling of biotechnological processes using neural networks

Authors
Chen, L Bernard, O Bastin, G Angelov, P
Citation
L. Chen et al., Hybrid modelling of biotechnological processes using neural networks, CON ENG PR, 8(7), 2000, pp. 821-827
Citations number
7
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
CONTROL ENGINEERING PRACTICE
ISSN journal
09670661 → ACNP
Volume
8
Issue
7
Year of publication
2000
Pages
821 - 827
Database
ISI
SICI code
0967-0661(200007)8:7<821:HMOBPU>2.0.ZU;2-4
Abstract
The hybrid modelling approach for bioprocesses combines a neural network re presentation of the reaction rates with a mass-balance description of the r eactor. A procedure for the identification of hybrid models is proposed and illustrated with an experimental case-study. The key feature is a state tr ansformation which allows to identify separately the kinetic models of the reaction rates even if they occur simultaneously in the reactor. (C) 2000 E lsevier Science Ltd. All rights reserved.