Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation

Mohammad Anwar Hosen, Mohd Azlan Hussain, Farouq S. Mjalli

Research output: Contribution to journalArticle

71 Citations (Scopus)

Abstract

Controlling batch polymerization reactors imposes great operational difficulties due to the complex reaction kinetics, inherent process nonlinearities and the continuous demand for running these reactors at varying operating conditions needed to produce different polymer grades. Model predictive control (MPC) has become the leading technology of advanced nonlinear control adopted for such chemical process industries. The usual practice for operating polymerization reactors is to optimize the reactor temperature profile since the end use properties of the product polymer depend highly on temperature. This is because the end use properties of the product polymer depend highly on temperature. The reactor is then run to track the optimized temperature set-point profile. In this work, a neural network-model predictive control (NN-MPC) algorithm was implemented to control the temperature of a polystyrene (PS) batch reactors and the controller set-point tracking and load rejection performance was investigated. In this approach, a neural network model is trained to predict the future process response over the specified horizon. The predictions are passed to a numerical optimization routine which attempts to minimize a specified cost function to calculate a suitable control signal at each sample instant. The performance results of the NN-MPC were compared with a conventional PID controller. Based on the experimental results, it is concluded that the NN-MPC performance is superior to the conventional PID controller especially during process startup. The NN-MPC resulted in smoother controller moves and less variability.

Original languageEnglish
Pages (from-to)454-467
Number of pages14
JournalControl Engineering Practice
Volume19
Issue number5
DOIs
Publication statusPublished - May 2011

Fingerprint

Model predictive control
Model Predictive Control
Batch reactors
Experimental Investigation
Reactor
Batch
Polystyrenes
Neural Network Model
Neural Networks
Neural networks
Controllers
Polymers
PID Controller
Polymerization
Point Sets
Temperature
Controller
Process Industry
Reaction Kinetics
Reaction kinetics

Keywords

  • Batch reactor
  • Model predictive control (MPC)
  • Neural network based model predictive control (NN-MPC)
  • Polymerization reactor
  • Polystyrene

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Applied Mathematics
  • Computer Science Applications

Cite this

Control of polystyrene batch reactors using neural network based model predictive control (NNMPC) : An experimental investigation. / Hosen, Mohammad Anwar; Hussain, Mohd Azlan; Mjalli, Farouq S.

In: Control Engineering Practice, Vol. 19, No. 5, 05.2011, p. 454-467.

Research output: Contribution to journalArticle

@article{78d9cb72350a488b85e1e3f33236684f,
title = "Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation",
abstract = "Controlling batch polymerization reactors imposes great operational difficulties due to the complex reaction kinetics, inherent process nonlinearities and the continuous demand for running these reactors at varying operating conditions needed to produce different polymer grades. Model predictive control (MPC) has become the leading technology of advanced nonlinear control adopted for such chemical process industries. The usual practice for operating polymerization reactors is to optimize the reactor temperature profile since the end use properties of the product polymer depend highly on temperature. This is because the end use properties of the product polymer depend highly on temperature. The reactor is then run to track the optimized temperature set-point profile. In this work, a neural network-model predictive control (NN-MPC) algorithm was implemented to control the temperature of a polystyrene (PS) batch reactors and the controller set-point tracking and load rejection performance was investigated. In this approach, a neural network model is trained to predict the future process response over the specified horizon. The predictions are passed to a numerical optimization routine which attempts to minimize a specified cost function to calculate a suitable control signal at each sample instant. The performance results of the NN-MPC were compared with a conventional PID controller. Based on the experimental results, it is concluded that the NN-MPC performance is superior to the conventional PID controller especially during process startup. The NN-MPC resulted in smoother controller moves and less variability.",
keywords = "Batch reactor, Model predictive control (MPC), Neural network based model predictive control (NN-MPC), Polymerization reactor, Polystyrene",
author = "Hosen, {Mohammad Anwar} and Hussain, {Mohd Azlan} and Mjalli, {Farouq S.}",
year = "2011",
month = "5",
doi = "10.1016/j.conengprac.2011.01.007",
language = "English",
volume = "19",
pages = "454--467",
journal = "Control Engineering Practice",
issn = "0967-0661",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Control of polystyrene batch reactors using neural network based model predictive control (NNMPC)

T2 - An experimental investigation

AU - Hosen, Mohammad Anwar

AU - Hussain, Mohd Azlan

AU - Mjalli, Farouq S.

PY - 2011/5

Y1 - 2011/5

N2 - Controlling batch polymerization reactors imposes great operational difficulties due to the complex reaction kinetics, inherent process nonlinearities and the continuous demand for running these reactors at varying operating conditions needed to produce different polymer grades. Model predictive control (MPC) has become the leading technology of advanced nonlinear control adopted for such chemical process industries. The usual practice for operating polymerization reactors is to optimize the reactor temperature profile since the end use properties of the product polymer depend highly on temperature. This is because the end use properties of the product polymer depend highly on temperature. The reactor is then run to track the optimized temperature set-point profile. In this work, a neural network-model predictive control (NN-MPC) algorithm was implemented to control the temperature of a polystyrene (PS) batch reactors and the controller set-point tracking and load rejection performance was investigated. In this approach, a neural network model is trained to predict the future process response over the specified horizon. The predictions are passed to a numerical optimization routine which attempts to minimize a specified cost function to calculate a suitable control signal at each sample instant. The performance results of the NN-MPC were compared with a conventional PID controller. Based on the experimental results, it is concluded that the NN-MPC performance is superior to the conventional PID controller especially during process startup. The NN-MPC resulted in smoother controller moves and less variability.

AB - Controlling batch polymerization reactors imposes great operational difficulties due to the complex reaction kinetics, inherent process nonlinearities and the continuous demand for running these reactors at varying operating conditions needed to produce different polymer grades. Model predictive control (MPC) has become the leading technology of advanced nonlinear control adopted for such chemical process industries. The usual practice for operating polymerization reactors is to optimize the reactor temperature profile since the end use properties of the product polymer depend highly on temperature. This is because the end use properties of the product polymer depend highly on temperature. The reactor is then run to track the optimized temperature set-point profile. In this work, a neural network-model predictive control (NN-MPC) algorithm was implemented to control the temperature of a polystyrene (PS) batch reactors and the controller set-point tracking and load rejection performance was investigated. In this approach, a neural network model is trained to predict the future process response over the specified horizon. The predictions are passed to a numerical optimization routine which attempts to minimize a specified cost function to calculate a suitable control signal at each sample instant. The performance results of the NN-MPC were compared with a conventional PID controller. Based on the experimental results, it is concluded that the NN-MPC performance is superior to the conventional PID controller especially during process startup. The NN-MPC resulted in smoother controller moves and less variability.

KW - Batch reactor

KW - Model predictive control (MPC)

KW - Neural network based model predictive control (NN-MPC)

KW - Polymerization reactor

KW - Polystyrene

UR - http://www.scopus.com/inward/record.url?scp=79954572280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954572280&partnerID=8YFLogxK

U2 - 10.1016/j.conengprac.2011.01.007

DO - 10.1016/j.conengprac.2011.01.007

M3 - Article

AN - SCOPUS:79954572280

VL - 19

SP - 454

EP - 467

JO - Control Engineering Practice

JF - Control Engineering Practice

SN - 0967-0661

IS - 5

ER -