Modeling of gain tuning operation for hot strip looper controller by recurrent neural network

Masami Konishi, Syuya Imajo, Jun Imai, Tatsushi Nishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

In this paper, neural network model representing gain modulating action by human was developed for looper height controller in hot strip mills. The developed neural network model is that of the recurrent type neural network (RNN) which calculates the appropriate PII) gains of looper height controller based on the modification data of human operation as the training data. Further, learning algorithm for 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 action by human can be realized by the model. The model could also cope with disturbance such as change in roll gap because of its learning mechanism that may lead to the stabilization of threading operation of hot strip mills.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Control Applications
Pages890-895
Number of pages6
Volume2
Publication statusPublished - 2004
Event2004 IEEE International Conference on Control Applications - Taipei, Taiwan, Province of China
Duration: Sep 2 2004Sep 4 2004

Other

Other2004 IEEE International Conference on Control Applications
CountryTaiwan, Province of China
CityTaipei
Period9/2/049/4/04

Fingerprint

Recurrent neural networks
Tuning
Controllers
Strip mills
Neural networks
Learning algorithms
Stabilization

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Konishi, M., Imajo, S., Imai, J., & Nishi, T. (2004). Modeling of gain tuning operation for hot strip looper controller by recurrent neural network. In Proceedings of the IEEE International Conference on Control Applications (Vol. 2, pp. 890-895)

Modeling of gain tuning operation for hot strip looper controller by recurrent neural network. / Konishi, Masami; Imajo, Syuya; Imai, Jun; Nishi, Tatsushi.

Proceedings of the IEEE International Conference on Control Applications. Vol. 2 2004. p. 890-895.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Konishi, M, Imajo, S, Imai, J & Nishi, T 2004, Modeling of gain tuning operation for hot strip looper controller by recurrent neural network. in Proceedings of the IEEE International Conference on Control Applications. vol. 2, pp. 890-895, 2004 IEEE International Conference on Control Applications, Taipei, Taiwan, Province of China, 9/2/04.
Konishi M, Imajo S, Imai J, Nishi T. Modeling of gain tuning operation for hot strip looper controller by recurrent neural network. In Proceedings of the IEEE International Conference on Control Applications. Vol. 2. 2004. p. 890-895
Konishi, Masami ; Imajo, Syuya ; Imai, Jun ; Nishi, Tatsushi. / Modeling of gain tuning operation for hot strip looper controller by recurrent neural network. Proceedings of the IEEE International Conference on Control Applications. Vol. 2 2004. pp. 890-895
@inproceedings{835097fdf8d343aab4ce89be2a98f2a8,
title = "Modeling of gain tuning operation for hot strip looper controller by recurrent neural network",
abstract = "In this paper, neural network model representing gain modulating action by human was developed for looper height controller in hot strip mills. The developed neural network model is that of the recurrent type neural network (RNN) which calculates the appropriate PII) gains of looper height controller based on the modification data of human operation as the training data. Further, learning algorithm for 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 action by human can be realized by the model. The model could also cope with disturbance such as change in roll gap because of its learning mechanism that may lead to the stabilization of threading operation of hot strip mills.",
author = "Masami Konishi and Syuya Imajo and Jun Imai and Tatsushi Nishi",
year = "2004",
language = "English",
volume = "2",
pages = "890--895",
booktitle = "Proceedings of the IEEE International Conference on Control Applications",

}

TY - GEN

T1 - Modeling of gain tuning operation for hot strip looper controller by recurrent neural network

AU - Konishi, Masami

AU - Imajo, Syuya

AU - Imai, Jun

AU - Nishi, Tatsushi

PY - 2004

Y1 - 2004

N2 - In this paper, neural network model representing gain modulating action by human was developed for looper height controller in hot strip mills. The developed neural network model is that of the recurrent type neural network (RNN) which calculates the appropriate PII) gains of looper height controller based on the modification data of human operation as the training data. Further, learning algorithm for 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 action by human can be realized by the model. The model could also cope with disturbance such as change in roll gap because of its learning mechanism that may lead to the stabilization of threading operation of hot strip mills.

AB - In this paper, neural network model representing gain modulating action by human was developed for looper height controller in hot strip mills. The developed neural network model is that of the recurrent type neural network (RNN) which calculates the appropriate PII) gains of looper height controller based on the modification data of human operation as the training data. Further, learning algorithm for 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 action by human can be realized by the model. The model could also cope with disturbance such as change in roll gap because of its learning mechanism that may lead to the stabilization of threading operation of hot strip mills.

UR - http://www.scopus.com/inward/record.url?scp=17744373943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17744373943&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:17744373943

VL - 2

SP - 890

EP - 895

BT - Proceedings of the IEEE International Conference on Control Applications

ER -