Control of Continuous Stirred Tank Reactor using neural networks

Normah Abdullah, Tan Ching Yee, Azah Mohamed, Mohd. Marzuki Mustafa, Mohd Haniff Osman, Abu Bakar Mohamad

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background/Objectives: This paper presents the design of neuro controller NARMA-L2 for composition control in an isothermal Continuous Stirred Tank Reactor (CSTR) by manipulating the input feed composition. Methods/Statistical Analysis: The NARMA-L2 controller design is implemented in two stages in which the first stage is system identification to model the process and the second stage is designing the process controller. For controlling the product composition in the CSTR, the neuro controller NARMA-L2 is implemented in MATLAB Simulink environment. Findings: The simulation results show the superiority of the NARMA-L2 in accurately tracking the composition set-point changes in the CSTR and control the system better as compared to that of the conventional PID. The neuro controller NARMA-L2 can handle non-linear aspects of the CSTR by transforming its non-linear dynamic into an implicit algebraic model which can control the trajectory of the CSTR efficiently. Application/Improvements: The advantage of using the neuro controller NARMA-L2 is that it requires the minimal online computation compared to other neural network architecture for control such as model reference control and model predictive control.

Original languageEnglish
Article number95238
JournalIndian Journal of Science and Technology
Volume9
Issue number21
DOIs
Publication statusPublished - 2016

Fingerprint

Neural networks
Controllers
Chemical analysis
Model predictive control
Network architecture
MATLAB
Statistical methods
Identification (control systems)
Trajectories

Keywords

  • Continuous Stirred Tank Reactor (CSTR)
  • Neural networks
  • Neuro controller NARMA-L2
  • PID
  • System identification

ASJC Scopus subject areas

  • General

Cite this

Control of Continuous Stirred Tank Reactor using neural networks. / Abdullah, Normah; Yee, Tan Ching; Mohamed, Azah; Mustafa, Mohd. Marzuki; Osman, Mohd Haniff; Mohamad, Abu Bakar.

In: Indian Journal of Science and Technology, Vol. 9, No. 21, 95238, 2016.

Research output: Contribution to journalArticle

Abdullah, Normah ; Yee, Tan Ching ; Mohamed, Azah ; Mustafa, Mohd. Marzuki ; Osman, Mohd Haniff ; Mohamad, Abu Bakar. / Control of Continuous Stirred Tank Reactor using neural networks. In: Indian Journal of Science and Technology. 2016 ; Vol. 9, No. 21.
@article{32a373f1ddac455e86ec6a79d1c00fc7,
title = "Control of Continuous Stirred Tank Reactor using neural networks",
abstract = "Background/Objectives: This paper presents the design of neuro controller NARMA-L2 for composition control in an isothermal Continuous Stirred Tank Reactor (CSTR) by manipulating the input feed composition. Methods/Statistical Analysis: The NARMA-L2 controller design is implemented in two stages in which the first stage is system identification to model the process and the second stage is designing the process controller. For controlling the product composition in the CSTR, the neuro controller NARMA-L2 is implemented in MATLAB Simulink environment. Findings: The simulation results show the superiority of the NARMA-L2 in accurately tracking the composition set-point changes in the CSTR and control the system better as compared to that of the conventional PID. The neuro controller NARMA-L2 can handle non-linear aspects of the CSTR by transforming its non-linear dynamic into an implicit algebraic model which can control the trajectory of the CSTR efficiently. Application/Improvements: The advantage of using the neuro controller NARMA-L2 is that it requires the minimal online computation compared to other neural network architecture for control such as model reference control and model predictive control.",
keywords = "Continuous Stirred Tank Reactor (CSTR), Neural networks, Neuro controller NARMA-L2, PID, System identification",
author = "Normah Abdullah and Yee, {Tan Ching} and Azah Mohamed and Mustafa, {Mohd. Marzuki} and Osman, {Mohd Haniff} and Mohamad, {Abu Bakar}",
year = "2016",
doi = "10.17485/ijst/2016/v9i21/95238",
language = "English",
volume = "9",
journal = "Indian Journal of Science and Technology",
issn = "0974-6846",
publisher = "Indian Society for Education and Environment",
number = "21",

}

TY - JOUR

T1 - Control of Continuous Stirred Tank Reactor using neural networks

AU - Abdullah, Normah

AU - Yee, Tan Ching

AU - Mohamed, Azah

AU - Mustafa, Mohd. Marzuki

AU - Osman, Mohd Haniff

AU - Mohamad, Abu Bakar

PY - 2016

Y1 - 2016

N2 - Background/Objectives: This paper presents the design of neuro controller NARMA-L2 for composition control in an isothermal Continuous Stirred Tank Reactor (CSTR) by manipulating the input feed composition. Methods/Statistical Analysis: The NARMA-L2 controller design is implemented in two stages in which the first stage is system identification to model the process and the second stage is designing the process controller. For controlling the product composition in the CSTR, the neuro controller NARMA-L2 is implemented in MATLAB Simulink environment. Findings: The simulation results show the superiority of the NARMA-L2 in accurately tracking the composition set-point changes in the CSTR and control the system better as compared to that of the conventional PID. The neuro controller NARMA-L2 can handle non-linear aspects of the CSTR by transforming its non-linear dynamic into an implicit algebraic model which can control the trajectory of the CSTR efficiently. Application/Improvements: The advantage of using the neuro controller NARMA-L2 is that it requires the minimal online computation compared to other neural network architecture for control such as model reference control and model predictive control.

AB - Background/Objectives: This paper presents the design of neuro controller NARMA-L2 for composition control in an isothermal Continuous Stirred Tank Reactor (CSTR) by manipulating the input feed composition. Methods/Statistical Analysis: The NARMA-L2 controller design is implemented in two stages in which the first stage is system identification to model the process and the second stage is designing the process controller. For controlling the product composition in the CSTR, the neuro controller NARMA-L2 is implemented in MATLAB Simulink environment. Findings: The simulation results show the superiority of the NARMA-L2 in accurately tracking the composition set-point changes in the CSTR and control the system better as compared to that of the conventional PID. The neuro controller NARMA-L2 can handle non-linear aspects of the CSTR by transforming its non-linear dynamic into an implicit algebraic model which can control the trajectory of the CSTR efficiently. Application/Improvements: The advantage of using the neuro controller NARMA-L2 is that it requires the minimal online computation compared to other neural network architecture for control such as model reference control and model predictive control.

KW - Continuous Stirred Tank Reactor (CSTR)

KW - Neural networks

KW - Neuro controller NARMA-L2

KW - PID

KW - System identification

UR - http://www.scopus.com/inward/record.url?scp=84976384262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976384262&partnerID=8YFLogxK

U2 - 10.17485/ijst/2016/v9i21/95238

DO - 10.17485/ijst/2016/v9i21/95238

M3 - Article

AN - SCOPUS:84976384262

VL - 9

JO - Indian Journal of Science and Technology

JF - Indian Journal of Science and Technology

SN - 0974-6846

IS - 21

M1 - 95238

ER -