Computer control of pH and DO in a laboratory fermenter using a neural network technique

A. Mészáros, A. Andrášik, P. Mizsey, Z. Fonyó, V. Illeová

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

In this contribution, the advantages of the artificial neural network approach to the identification and control of a laboratory-scale biochemical reactor are demonstrated. It is very important to be able to maintain the levels of two process variables, pH and dissolved oxygen (DO) concentration, over the course of fermentation in biosystems control. A PC-supported, fully automated, multi-task control system has been designed and built by the authors. Forward and inverse neural process models are used to identify and control both the pH and the DO concentration in a fermenter containing a Saccharomyces cerevisiae based-culture. The models are trained off-line, using a modified back-propagation algorithm based on conjugate gradients. The inverse neural controller is augmented by a new adaptive term that results in a system with robust performance. Experimental results have confirmed that the regulatory and tracking performances of the control system proposed are good.

Original languageEnglish
Pages (from-to)331-340
Number of pages10
JournalBioprocess and Biosystems Engineering
Volume26
Issue number5
DOIs
Publication statusPublished - Oct 2004

Fingerprint

Fermenters
Computer control
Dissolved oxygen
control system
dissolved oxygen
Oxygen
Neural networks
back propagation
artificial neural network
Fermentation
fermentation
Saccharomyces cerevisiae
Control systems
Backpropagation algorithms
Yeast
Controllers
laboratory
reactor

Keywords

  • Control system
  • Laboratory fermenter
  • Neural networks

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Applied Microbiology and Biotechnology
  • Biotechnology
  • Bioengineering
  • Environmental Science (miscellaneous)

Cite this

Computer control of pH and DO in a laboratory fermenter using a neural network technique. / Mészáros, A.; Andrášik, A.; Mizsey, P.; Fonyó, Z.; Illeová, V.

In: Bioprocess and Biosystems Engineering, Vol. 26, No. 5, 10.2004, p. 331-340.

Research output: Contribution to journalArticle

@article{5f500ad9c76740d587112277a52b0bab,
title = "Computer control of pH and DO in a laboratory fermenter using a neural network technique",
abstract = "In this contribution, the advantages of the artificial neural network approach to the identification and control of a laboratory-scale biochemical reactor are demonstrated. It is very important to be able to maintain the levels of two process variables, pH and dissolved oxygen (DO) concentration, over the course of fermentation in biosystems control. A PC-supported, fully automated, multi-task control system has been designed and built by the authors. Forward and inverse neural process models are used to identify and control both the pH and the DO concentration in a fermenter containing a Saccharomyces cerevisiae based-culture. The models are trained off-line, using a modified back-propagation algorithm based on conjugate gradients. The inverse neural controller is augmented by a new adaptive term that results in a system with robust performance. Experimental results have confirmed that the regulatory and tracking performances of the control system proposed are good.",
keywords = "Control system, Laboratory fermenter, Neural networks",
author = "A. M{\'e}sz{\'a}ros and A. Andr{\'a}šik and P. Mizsey and Z. Fony{\'o} and V. Illeov{\'a}",
year = "2004",
month = "10",
doi = "10.1007/s00449-004-0374-0",
language = "English",
volume = "26",
pages = "331--340",
journal = "Bioprocess and Biosystems Engineering",
issn = "1615-7591",
publisher = "Springer Verlag",
number = "5",

}

TY - JOUR

T1 - Computer control of pH and DO in a laboratory fermenter using a neural network technique

AU - Mészáros, A.

AU - Andrášik, A.

AU - Mizsey, P.

AU - Fonyó, Z.

AU - Illeová, V.

PY - 2004/10

Y1 - 2004/10

N2 - In this contribution, the advantages of the artificial neural network approach to the identification and control of a laboratory-scale biochemical reactor are demonstrated. It is very important to be able to maintain the levels of two process variables, pH and dissolved oxygen (DO) concentration, over the course of fermentation in biosystems control. A PC-supported, fully automated, multi-task control system has been designed and built by the authors. Forward and inverse neural process models are used to identify and control both the pH and the DO concentration in a fermenter containing a Saccharomyces cerevisiae based-culture. The models are trained off-line, using a modified back-propagation algorithm based on conjugate gradients. The inverse neural controller is augmented by a new adaptive term that results in a system with robust performance. Experimental results have confirmed that the regulatory and tracking performances of the control system proposed are good.

AB - In this contribution, the advantages of the artificial neural network approach to the identification and control of a laboratory-scale biochemical reactor are demonstrated. It is very important to be able to maintain the levels of two process variables, pH and dissolved oxygen (DO) concentration, over the course of fermentation in biosystems control. A PC-supported, fully automated, multi-task control system has been designed and built by the authors. Forward and inverse neural process models are used to identify and control both the pH and the DO concentration in a fermenter containing a Saccharomyces cerevisiae based-culture. The models are trained off-line, using a modified back-propagation algorithm based on conjugate gradients. The inverse neural controller is augmented by a new adaptive term that results in a system with robust performance. Experimental results have confirmed that the regulatory and tracking performances of the control system proposed are good.

KW - Control system

KW - Laboratory fermenter

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=8744263701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8744263701&partnerID=8YFLogxK

U2 - 10.1007/s00449-004-0374-0

DO - 10.1007/s00449-004-0374-0

M3 - Article

C2 - 15300481

AN - SCOPUS:8744263701

VL - 26

SP - 331

EP - 340

JO - Bioprocess and Biosystems Engineering

JF - Bioprocess and Biosystems Engineering

SN - 1615-7591

IS - 5

ER -