A neuro-fuzzy system for looper tension control in rolling mills

被引：54

作者：

Janabi-Sharifi, F ^{[1
]}

机构：

[1] Ryerson Univ, Robot & Mfg Automat Lab, Mech & Ind Engn Dept, Toronto, ON M5B 2K3, Canada

来源：

CONTROL ENGINEERING PRACTICE | 2005年 / 13卷 / 01期

基金：

加拿大自然科学与工程研究理事会;

关键词：

fuzzy control; self-tuning control; tension control; rolling; neural networks; automatic process control (closed loop); steel industry;

D O I：

10.1016/j.conengprac.2003.09.013

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A looper tension control system is common to many rolling processes. Conventional tension controllers for mill actuation systems are based on a rolling model. They therefore cannot deal effectively with unmodeled dynamics and large parameter variations that can lead to scrap runs and machinery damage. In this paper, this problem is tackled by designing a fuzzy controller that possesses different tuning schemes for both off-line and on-line tuning of fuzzy control elements. It is shown that the proposed methods outperform conventional control techniques. Finally, the effects of various design options are discussed and some practical remarks are made. (C) 2004 Elsevier Ltd. All rights reserved.

引用

页码：1 / 13

页数：13

共 24 条

[1]

ANBE Y, 1996, P IFAC WORLD C 1996, P439

[2]

[Anonymous], 1996, CONTROL HDB

[3]

BOULTER BT, 2001, P 40 IEEE C DEC CONT, P4974

[4] DESIGN OF FUZZY-LOGIC CONTROLLERS BASED ON GENERALIZED T-OPERATORS [J].

GUPTA, MM ;

QI, J .

FUZZY SETS AND SYSTEMS, 1991, 40 (03) :473-489

[5] THEORY OF T-NORMS AND FUZZY INFERENCE METHODS [J].

GUPTA, MM ;

QI, J .

FUZZY SETS AND SYSTEMS, 1991, 40 (03) :431-450

[6]

HEARNS G, 1996, P 13 TRIENN IFAC WOR, P445

[7] Looper H-infinity control for hot-strip mills [J].

Imanari, H ;

Morimatsu, Y ;

Sekiguchi, K ;

Ezure, H ;

Matuoka, R ;

Tokuda, A ;

Otobe, H .

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 1997, 33 (03) :790-796

[8]

Janabi-Sharifi F, 2000, IEEE DECIS CONTR P, P376, DOI 10.1109/CDC.2000.912789

[9]

Janabi-Sharifi F, 2000, IEEE SYS MAN CYBERN, P3722, DOI 10.1109/ICSMC.2000.886589

[10] SELF-LEARNING FUZZY CONTROLLERS BASED ON TEMPORAL BACK PROPAGATION [J].

JANG, JSR .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (05) :714-723

← 1 2 3 →