Neural network based PID gain tuning of chemical plant controller

Yoshihiro Abe, Masami Konishi, Jun Imai, Ryusaku Hasegawa, Masamori Watanabe, Hiroaki Kamijo

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In these years, plant control systems are highly automated and applied to many industries. The control performances change with the passage of time, because of the deterioration of plant facilities. This is why human experts tune the control system to improve the total plant performances. In this study, PID control system for the oil refining chemical plant process is treated. In oil refining, there are thousands of the control loops in the plant to keep the product quality at the desired value and to secure the safety of the plant operation. According to the ambiguity of the interference between control loops, it is difficult to estimate the plant dynamical model accurately. Using neuro emulator and recurrent neural networks model (RNN model) for emulation and tuning parameters, PID gain tuning system of chemical plant controller is constructed. Through numerical experiments using actual plant data, effect of the proposed method was ascertained.

Original languageEnglish
JournalIEEJ Transactions on Industry Applications
Volume128
Issue number7
DOIs
Publication statusPublished - 2008

Fingerprint

Chemical plants
Tuning
Neural networks
Control systems
Controllers
Refining
Recurrent neural networks
Three term control systems
Deterioration
Industry
Experiments
Oils

Keywords

  • Flow rate controller
  • Gain tuning
  • Neuro emulator
  • Oil refining plant
  • PID controller
  • RNN model

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Neural network based PID gain tuning of chemical plant controller. / Abe, Yoshihiro; Konishi, Masami; Imai, Jun; Hasegawa, Ryusaku; Watanabe, Masamori; Kamijo, Hiroaki.

In: IEEJ Transactions on Industry Applications, Vol. 128, No. 7, 2008.

Research output: Contribution to journalArticle

Abe, Yoshihiro ; Konishi, Masami ; Imai, Jun ; Hasegawa, Ryusaku ; Watanabe, Masamori ; Kamijo, Hiroaki. / Neural network based PID gain tuning of chemical plant controller. In: IEEJ Transactions on Industry Applications. 2008 ; Vol. 128, No. 7.
@article{e4ed0a50080d4e17bc12dda7dafd047f,
title = "Neural network based PID gain tuning of chemical plant controller",
abstract = "In these years, plant control systems are highly automated and applied to many industries. The control performances change with the passage of time, because of the deterioration of plant facilities. This is why human experts tune the control system to improve the total plant performances. In this study, PID control system for the oil refining chemical plant process is treated. In oil refining, there are thousands of the control loops in the plant to keep the product quality at the desired value and to secure the safety of the plant operation. According to the ambiguity of the interference between control loops, it is difficult to estimate the plant dynamical model accurately. Using neuro emulator and recurrent neural networks model (RNN model) for emulation and tuning parameters, PID gain tuning system of chemical plant controller is constructed. Through numerical experiments using actual plant data, effect of the proposed method was ascertained.",
keywords = "Flow rate controller, Gain tuning, Neuro emulator, Oil refining plant, PID controller, RNN model",
author = "Yoshihiro Abe and Masami Konishi and Jun Imai and Ryusaku Hasegawa and Masamori Watanabe and Hiroaki Kamijo",
year = "2008",
doi = "10.1541/ieejias.128.940",
language = "English",
volume = "128",
journal = "IEEJ Transactions on Industry Applications",
issn = "0913-6339",
publisher = "The Institute of Electrical Engineers of Japan",
number = "7",

}

TY - JOUR

T1 - Neural network based PID gain tuning of chemical plant controller

AU - Abe, Yoshihiro

AU - Konishi, Masami

AU - Imai, Jun

AU - Hasegawa, Ryusaku

AU - Watanabe, Masamori

AU - Kamijo, Hiroaki

PY - 2008

Y1 - 2008

N2 - In these years, plant control systems are highly automated and applied to many industries. The control performances change with the passage of time, because of the deterioration of plant facilities. This is why human experts tune the control system to improve the total plant performances. In this study, PID control system for the oil refining chemical plant process is treated. In oil refining, there are thousands of the control loops in the plant to keep the product quality at the desired value and to secure the safety of the plant operation. According to the ambiguity of the interference between control loops, it is difficult to estimate the plant dynamical model accurately. Using neuro emulator and recurrent neural networks model (RNN model) for emulation and tuning parameters, PID gain tuning system of chemical plant controller is constructed. Through numerical experiments using actual plant data, effect of the proposed method was ascertained.

AB - In these years, plant control systems are highly automated and applied to many industries. The control performances change with the passage of time, because of the deterioration of plant facilities. This is why human experts tune the control system to improve the total plant performances. In this study, PID control system for the oil refining chemical plant process is treated. In oil refining, there are thousands of the control loops in the plant to keep the product quality at the desired value and to secure the safety of the plant operation. According to the ambiguity of the interference between control loops, it is difficult to estimate the plant dynamical model accurately. Using neuro emulator and recurrent neural networks model (RNN model) for emulation and tuning parameters, PID gain tuning system of chemical plant controller is constructed. Through numerical experiments using actual plant data, effect of the proposed method was ascertained.

KW - Flow rate controller

KW - Gain tuning

KW - Neuro emulator

KW - Oil refining plant

KW - PID controller

KW - RNN model

UR - http://www.scopus.com/inward/record.url?scp=72149124495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72149124495&partnerID=8YFLogxK

U2 - 10.1541/ieejias.128.940

DO - 10.1541/ieejias.128.940

M3 - Article

AN - SCOPUS:72149124495

VL - 128

JO - IEEJ Transactions on Industry Applications

JF - IEEJ Transactions on Industry Applications

SN - 0913-6339

IS - 7

ER -