Human model for gain tuning of looper control in hot strip rolling

Shuya Imajo, Masami Konishi, Jun Imai, Tatsushi Nishi

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In recent years, many control systems have been developed and applied to hot rolling in order to improve the quality of the finished products. Due to the plant characteristics and the control system performance variations over time, human experts intervene and modulate control gains to maintain and to improve the control system performance. Through a breakthrough, we can expect to attain the fully automated modulation of control gains without human intervention. A neural network model representing gain modulating actions by human was developed for a looper height controller in hot strip mills. The developed neural network model is a recurrent type neural network (RNN) which calculates the appropriate PID gains of the looper height controller based on the modification data of human operations as training data. Further, a learning algorithm for the RNN model was developed to accelerate convergence of the gain modification process and to stabilize the looper movement. The neural gain tuning model was applied to the inter-stands looper height controller in hot strip mills. The usefulness of the developed model was checked through numerical experiments. From the experimental results, it was verified that the tuning actions by humans can be realized by the model. Through its learning mechanism, the model could also cope with disturbances such as changes in roll gap. This may lead to the stabilization of threading operations of hot strip mills.

Original languageEnglish
Pages (from-to)933-940
Number of pages8
JournalTetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan
Volume90
Issue number11
Publication statusPublished - Nov 2004

Fingerprint

strip
Tuning
tuning
Strip mills
Neural networks
controllers
Gain control
Control systems
Controllers
learning
Hot rolling
Learning algorithms
education
disturbances
Stabilization
stabilization
Modulation
modulation
products
Experiments

Keywords

  • Gain tuning
  • Hot strip mills
  • Identification model
  • Learning
  • Loop controller
  • Neural networks
  • PID controller

ASJC Scopus subject areas

  • Metals and Alloys

Cite this

Human model for gain tuning of looper control in hot strip rolling. / Imajo, Shuya; Konishi, Masami; Imai, Jun; Nishi, Tatsushi.

In: Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan, Vol. 90, No. 11, 11.2004, p. 933-940.

Research output: Contribution to journalArticle

Imajo, Shuya ; Konishi, Masami ; Imai, Jun ; Nishi, Tatsushi. / Human model for gain tuning of looper control in hot strip rolling. In: Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan. 2004 ; Vol. 90, No. 11. pp. 933-940.
@article{7dc5c277c0ed421eb53967b113b95266,
title = "Human model for gain tuning of looper control in hot strip rolling",
abstract = "In recent years, many control systems have been developed and applied to hot rolling in order to improve the quality of the finished products. Due to the plant characteristics and the control system performance variations over time, human experts intervene and modulate control gains to maintain and to improve the control system performance. Through a breakthrough, we can expect to attain the fully automated modulation of control gains without human intervention. A neural network model representing gain modulating actions by human was developed for a looper height controller in hot strip mills. The developed neural network model is a recurrent type neural network (RNN) which calculates the appropriate PID gains of the looper height controller based on the modification data of human operations as training data. Further, a learning algorithm for the RNN model was developed to accelerate convergence of the gain modification process and to stabilize the looper movement. The neural gain tuning model was applied to the inter-stands looper height controller in hot strip mills. The usefulness of the developed model was checked through numerical experiments. From the experimental results, it was verified that the tuning actions by humans can be realized by the model. Through its learning mechanism, the model could also cope with disturbances such as changes in roll gap. This may lead to the stabilization of threading operations of hot strip mills.",
keywords = "Gain tuning, Hot strip mills, Identification model, Learning, Loop controller, Neural networks, PID controller",
author = "Shuya Imajo and Masami Konishi and Jun Imai and Tatsushi Nishi",
year = "2004",
month = "11",
language = "English",
volume = "90",
pages = "933--940",
journal = "Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan",
issn = "0021-1575",
publisher = "Iron and Steel Institute of Japan",
number = "11",

}

TY - JOUR

T1 - Human model for gain tuning of looper control in hot strip rolling

AU - Imajo, Shuya

AU - Konishi, Masami

AU - Imai, Jun

AU - Nishi, Tatsushi

PY - 2004/11

Y1 - 2004/11

N2 - In recent years, many control systems have been developed and applied to hot rolling in order to improve the quality of the finished products. Due to the plant characteristics and the control system performance variations over time, human experts intervene and modulate control gains to maintain and to improve the control system performance. Through a breakthrough, we can expect to attain the fully automated modulation of control gains without human intervention. A neural network model representing gain modulating actions by human was developed for a looper height controller in hot strip mills. The developed neural network model is a recurrent type neural network (RNN) which calculates the appropriate PID gains of the looper height controller based on the modification data of human operations as training data. Further, a learning algorithm for the RNN model was developed to accelerate convergence of the gain modification process and to stabilize the looper movement. The neural gain tuning model was applied to the inter-stands looper height controller in hot strip mills. The usefulness of the developed model was checked through numerical experiments. From the experimental results, it was verified that the tuning actions by humans can be realized by the model. Through its learning mechanism, the model could also cope with disturbances such as changes in roll gap. This may lead to the stabilization of threading operations of hot strip mills.

AB - In recent years, many control systems have been developed and applied to hot rolling in order to improve the quality of the finished products. Due to the plant characteristics and the control system performance variations over time, human experts intervene and modulate control gains to maintain and to improve the control system performance. Through a breakthrough, we can expect to attain the fully automated modulation of control gains without human intervention. A neural network model representing gain modulating actions by human was developed for a looper height controller in hot strip mills. The developed neural network model is a recurrent type neural network (RNN) which calculates the appropriate PID gains of the looper height controller based on the modification data of human operations as training data. Further, a learning algorithm for the RNN model was developed to accelerate convergence of the gain modification process and to stabilize the looper movement. The neural gain tuning model was applied to the inter-stands looper height controller in hot strip mills. The usefulness of the developed model was checked through numerical experiments. From the experimental results, it was verified that the tuning actions by humans can be realized by the model. Through its learning mechanism, the model could also cope with disturbances such as changes in roll gap. This may lead to the stabilization of threading operations of hot strip mills.

KW - Gain tuning

KW - Hot strip mills

KW - Identification model

KW - Learning

KW - Loop controller

KW - Neural networks

KW - PID controller

UR - http://www.scopus.com/inward/record.url?scp=10944220828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10944220828&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:10944220828

VL - 90

SP - 933

EP - 940

JO - Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan

JF - Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan

SN - 0021-1575

IS - 11

ER -