Adaptive and predictive control of liquid-liquid extractors using neural-based instantaneous linearization technique

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Nonlinearity of the extraction process is addressed via the application of instantaneous linearization to control the extract and raffinate concentrations. Two feed-forward neural networks with delayed inputs and outputs were trained and validated to capture the dynamics of the extraction process. These nonlinear models were then adopted in an instantaneous linearization algorithm into two control algorithms. The self-tuning adaptive control strategy was compared to an approximate model predictive control in terms of set point tracking capability, efficiency and stability. For the case of large, abrupt set point changes, the performance of the self-tuning algorithm was poor, especially for the raffinate control. The approximate model predictive control strategy was superior to the self-tuning control in terms of its ability to force the output to following the set point trajectory efficiently with smooth controller moves.

Original languageEnglish
Pages (from-to)539-549
Number of pages11
JournalChemical Engineering and Technology
Volume29
Issue number5
DOIs
Publication statusPublished - May 2006

Fingerprint

Linearization
liquid
Tuning
Model predictive control
Liquids
nonlinearity
Feedforward neural networks
trajectory
Trajectories
Controllers

ASJC Scopus subject areas

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

Cite this

@article{7dadfbc4553d4392996f0b889e53b165,
title = "Adaptive and predictive control of liquid-liquid extractors using neural-based instantaneous linearization technique",
abstract = "Nonlinearity of the extraction process is addressed via the application of instantaneous linearization to control the extract and raffinate concentrations. Two feed-forward neural networks with delayed inputs and outputs were trained and validated to capture the dynamics of the extraction process. These nonlinear models were then adopted in an instantaneous linearization algorithm into two control algorithms. The self-tuning adaptive control strategy was compared to an approximate model predictive control in terms of set point tracking capability, efficiency and stability. For the case of large, abrupt set point changes, the performance of the self-tuning algorithm was poor, especially for the raffinate control. The approximate model predictive control strategy was superior to the self-tuning control in terms of its ability to force the output to following the set point trajectory efficiently with smooth controller moves.",
author = "Mjalli, {Farouq S.}",
year = "2006",
month = "5",
doi = "10.1002/ceat.200500271",
language = "English",
volume = "29",
pages = "539--549",
journal = "Chemical Engineering and Technology",
issn = "0930-7516",
publisher = "Wiley-VCH Verlag",
number = "5",

}

TY - JOUR

T1 - Adaptive and predictive control of liquid-liquid extractors using neural-based instantaneous linearization technique

AU - Mjalli, Farouq S.

PY - 2006/5

Y1 - 2006/5

N2 - Nonlinearity of the extraction process is addressed via the application of instantaneous linearization to control the extract and raffinate concentrations. Two feed-forward neural networks with delayed inputs and outputs were trained and validated to capture the dynamics of the extraction process. These nonlinear models were then adopted in an instantaneous linearization algorithm into two control algorithms. The self-tuning adaptive control strategy was compared to an approximate model predictive control in terms of set point tracking capability, efficiency and stability. For the case of large, abrupt set point changes, the performance of the self-tuning algorithm was poor, especially for the raffinate control. The approximate model predictive control strategy was superior to the self-tuning control in terms of its ability to force the output to following the set point trajectory efficiently with smooth controller moves.

AB - Nonlinearity of the extraction process is addressed via the application of instantaneous linearization to control the extract and raffinate concentrations. Two feed-forward neural networks with delayed inputs and outputs were trained and validated to capture the dynamics of the extraction process. These nonlinear models were then adopted in an instantaneous linearization algorithm into two control algorithms. The self-tuning adaptive control strategy was compared to an approximate model predictive control in terms of set point tracking capability, efficiency and stability. For the case of large, abrupt set point changes, the performance of the self-tuning algorithm was poor, especially for the raffinate control. The approximate model predictive control strategy was superior to the self-tuning control in terms of its ability to force the output to following the set point trajectory efficiently with smooth controller moves.

UR - http://www.scopus.com/inward/record.url?scp=33646725472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646725472&partnerID=8YFLogxK

U2 - 10.1002/ceat.200500271

DO - 10.1002/ceat.200500271

M3 - Article

VL - 29

SP - 539

EP - 549

JO - Chemical Engineering and Technology

JF - Chemical Engineering and Technology

SN - 0930-7516

IS - 5

ER -