Neural-networks-based feedback linearization versus model predictive control of continuous alcoholic fermentation process

Farouq S. Mjalli, Sameer Al-Asheh

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves.

Original languageEnglish
Pages (from-to)1191-1200
Number of pages10
JournalChemical Engineering and Technology
Volume28
Issue number10
DOIs
Publication statusPublished - Oct 2005

Fingerprint

Feedback linearization
Model predictive control
Fermentation
fermentation
Neural networks
Controllers
Ethanol
control system
Systems analysis
ethanol
Control systems

ASJC Scopus subject areas

  • Polymers and Plastics
  • Environmental Science(all)
  • Chemical Engineering (miscellaneous)

Cite this

Neural-networks-based feedback linearization versus model predictive control of continuous alcoholic fermentation process. / Mjalli, Farouq S.; Al-Asheh, Sameer.

In: Chemical Engineering and Technology, Vol. 28, No. 10, 10.2005, p. 1191-1200.

Research output: Contribution to journalArticle

@article{2fc9c96beaed42e38dbfa30c7fe73efc,
title = "Neural-networks-based feedback linearization versus model predictive control of continuous alcoholic fermentation process",
abstract = "In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves.",
author = "Mjalli, {Farouq S.} and Sameer Al-Asheh",
year = "2005",
month = "10",
doi = "10.1002/ceat.200500166",
language = "English",
volume = "28",
pages = "1191--1200",
journal = "Chemical Engineering and Technology",
issn = "0930-7516",
publisher = "Wiley-VCH Verlag",
number = "10",

}

TY - JOUR

T1 - Neural-networks-based feedback linearization versus model predictive control of continuous alcoholic fermentation process

AU - Mjalli, Farouq S.

AU - Al-Asheh, Sameer

PY - 2005/10

Y1 - 2005/10

N2 - In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves.

AB - In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves.

UR - http://www.scopus.com/inward/record.url?scp=26944501261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26944501261&partnerID=8YFLogxK

U2 - 10.1002/ceat.200500166

DO - 10.1002/ceat.200500166

M3 - Article

VL - 28

SP - 1191

EP - 1200

JO - Chemical Engineering and Technology

JF - Chemical Engineering and Technology

SN - 0930-7516

IS - 10

ER -