Width Prediction Model and Control System using Neural Network and Fuzzy in Hot Strip Finishing Mills

- Journal title : Journal of Institute of Control, Robotics and Systems
- Volume 13, Issue 4, 2007, pp.296-303
- Publisher : Institute of Control, Robotics and Systems
- DOI : 10.5302/J.ICROS.2007.13.4.296

Title & Authors

Width Prediction Model and Control System using Neural Network and Fuzzy in Hot Strip Finishing Mills

Hwang, I-Cheal; Park, Cheol-Jae;

Hwang, I-Cheal; Park, Cheol-Jae;

Abstract

This paper proposes a new width control system composed of an ANWC(Automatic Neural network based Width Control) and a fuzzy-PID controller in hot strip finishing mills which aims at obtaining the desirable width. The ANWC is designed using a neural network based width prediction model to minimize a width variation between the measured width and its target value. Input variables for the neural network model are chosen by using the hypothesis testing. The fuzzy-PlD control system is also designed to obtain the fast looper response and the high width control precision in the finishing mill. It is shown through the field test of the Pohang no. 1 hot strip mill of POSCO that the performance of the width margin is considerably improved by the proposed control schemes.

Keywords

hot strip mill;neural network;width control;finishing mill;fuzzy PID;looper control;statistical testing;

Language

Korean

References

1.

T. Shibahara, 'Edger set-up model at roughing train in hot strip mill,' ISIJ, vol. 67, no. 15, pp. 2509-2515, 1981

2.

T. Sasaki, 'Mathematical model of width change in the hot strip finishing train,' CAMPISIJ, vol. 9, pp. 304-307, 1996

3.

K. Yamada, S. Ogawa, and M. Ataka, 'Three dimensional analysis of at rolling using rigid-plastic finite element method coupled with roll deformation analysis,' NUMIFORM92, pp. 755-760, 1992

4.

lsii, 'Analysis of width deviation for hot strip finishing mill,' Japan Society for Technology of Plasticity, pp. 219-222, 1992

5.

C. J. Park and D. M. Lee, 'Input selection technology of neural network and its application for hot strip mill,' IFAC World Congress, 2005

6.

A. Hacquin and P. Montmitonnet, 'Coupling of roll and strip deformation in three-dimensional simulation of hot rolling,' Simulation of Mat. Proc., pp. 921-927, 1995

7.

A. Helmi and J. Alexander, 'Geometric factors affecting spread in hot at rolling of steel,' JISI, no. 206, pp. 1110-1117, 1968

8.

A. Ishii, 'Variation of strip width during hot finishing rolling,' CAMP-ISIJ, vol. 9, pp. 300-303, 1996

9.

J. Price, 'The hot strip mill looper system,' IEEE Transactions on Industry Applications, vol. IA-9, no. 5, pp. 556-562, 1973

10.

A. Mizuta, H. Ibata, Y. Yamamoto, S. Saito, S. Honda, and M. Kitamura, 'Control method and its performance,' Transactions of the Iron and Steel Institute of Japan, vol. 26, p. B21, 1986

11.

D. A. Davies, 'Application of hydraulic agc and width control to a hot strip mill,' Iron and Steel Engineer, vol. 66, no. 8, pp. 39-44,1989

12.

Anon, 'A new roll force awc system for roughing train in hot strip mill,' Transactions of the Iron and Steel Institute of Japan, vol. 27, no. 12, p. 993, 1987

13.

S. Nakamura, M. Takahashi, and Y. Chida, 'Slab width control for hot direct rolling,' Transactions of the Iron and Steel Institute of Japan, vol. 28, pp. 110-116, 1988

14.

H. Yoneda, 'Development of accurate width control technology in hot strip finishing mill,' CAMP-ISIJ, vol. 9, pp. 312-315, 1996

15.

T. Ogura, 'Advanced width control for hot finishing mill,' CAMP-lSIJ, vol. 9, p. 324, 1996

16.

S. Murata, 'Development of width control technology in finishing line of hot strip mill,' CAMP-ISIJ, vol. 9, pp. 308-311, 1996

17.

H. Senda, 'Development of the width control system in no.3 hot strip mill at Chiba Works,' CAMP-ISIJ, vol. 11, p. 356, 1998

18.

T. Takahara, 'Improvement of width accuracy in Fukuyama no.1 hot strip mill,' CAMPISIJ, vol. 10, p. 391, 1997

19.

JISF, The theory and practice of the steel rolling. JISF, 1983

20.

S. Kunimatsu, T. Fujii, and T. Tsujino, 'Quadratic stabilization of lLQ servo systems with generalized reference inputs,' T. SICE, vol. 39, no. 3, pp. 307-309, 2003

21.

H. lmanari, Y. Morimatsu, K. Sekiguchi, H. Ezure, R. Matuoka, A. Tokuda, and H. Otobe, 'Looper H-Infinity control for hot strip mills,' IEEE Transactions on Industry Applications, vol. 33, no. 3, pp. 790-796, 1997

22.

J. W. Lee, W. H. Kwon, and J. H. Choi, 'On stability of constrained receding horizon control with finite terminal weighting matrix,' Automatica, vol. 34, no. 12, pp. 1607-1612, 1998

23.

D. Yu, J. Gomm, and D. Williams, 'Neural model input selection for a mimo chemical process,' Engineering Applications of Artificial intelligence, vol. 13, pp. 15-23, 2000

24.

W. Wu and D. Massart, 'Artificial neural networks in classification of NIR spectral data : Selection of the input,' Chemometrics and Intelligent Laboratory Systems, vol. 35, pp. 127-135,1996

25.

A. Back and T. Trappenberg, 'Selecting inputs for modeling using normalized higher order statistics and independent component analysis,' IEEE Transactions on Neural Networks, vol. 12, no. 3, pp. 612-617, 2001

26.

C. Ledoux and J. Grandin, 'Two original weight pruning methods based on statistical tests and rounding techniques,' lEE Proc. Vision, Image Signa! Process. vol. 141, no. 4, pp. 230-236, 1994

27.

R. Reed, 'Pruning algorithms: a survey,' IEEE Trans. Neural Netw. , vol. 4, no. 5, pp. 740-747, 1993

28.

J. Luo, B. Hu, X. Ling, and R, Liu, 'Principal independent component analysis,' IEEE Transactions on Neural Networks, voI. 10, no. 4,pp.912-917,1999

29.

N. Kambhatla and T. Leen, 'Dimension reduction by local principal component analysis,' Neural Comput., vol. 9, no. 7, pp. 1493-1516,1997

30.

S. Ross, Introduction to Probability and Statistics for Engineers and Scientists, Academic Press, 2000

31.

S. Z. He, 'Fuzzy self-tuning of PID controller,' Fuzzv Sets and Systems, pp. 37-46,1993