Hybrid modelling of biotechnological processes using neural networks

被引：61

作者：

Chen, L

Bernard, O

Bastin, G

Angelov, P

机构：

[1] Univ Catholique Louvain, CESAME, B-1348 Louvain, Belgium

[2] Inria, Projet Comore, F-06902 Sophia Antipolis, France

[3] Loughborough Univ Technol, Loughborough LE11 3TU, Leics, England

来源：

CONTROL ENGINEERING PRACTICE | 2000年 / 8卷 / 07期

关键词：

biotechnology; identification; modelling; neural networks;

D O I：

10.1016/S0967-0661(00)00036-8

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The hybrid modelling approach for bioprocesses combines a neural network representation of the reaction rates with a mass-balance description of the reactor. A procedure for the identification of hybrid models is proposed and illustrated with an experimental case-study. The key feature is a state transformation which allows to identify separately the kinetic models of the reaction rates even if they occur simultaneously in the reactor. (C) 2000 Elsevier Science Ltd. All rights reserved.

引用

页码：821 / 827

页数：7

共 8 条

[1]

BASTIN G, 1990, LINE ESTIMATION ADAP

[2]

Bernard O, 1999, BIOTECHNOL BIOENG, V65, P558, DOI 10.1002/(SICI)1097-0290(19991205)65:5<558::AID-BIT9>3.0.CO

[3]

2-A

[4]

BERNARD O, 1998, P NOLCOS IFAC S ENSC, P448

[5]

Chen L., 1995, Proceedings of the Third European Control Conference. ECC 95, P2426

[6] Structural identifiability of the yield coefficients in bioprocess models when the reaction rates are unknown [J].

Chen, L ;

Bastin, G .

MATHEMATICAL BIOSCIENCES, 1996, 132 (01) :35-67

[7] Hybrid modelling of biochemical processes: A comparison with the conventional approach [J].

deAzevedo, SF ;

Dahm, B ;

Oliveira, FR .

COMPUTERS & CHEMICAL ENGINEERING, 1997, 21 :S751-S756

[8] A HYBRID NEURAL NETWORK-1ST PRINCIPLES APPROACH TO PROCESS MODELING [J].

PSICHOGIOS, DC ;

UNGAR, LH .

AICHE JOURNAL, 1992, 38 (10) :1499-1511

← 1 →