A neural network model to determine the plate width set-up value in a hot plate mill
Tóm tắt
Performance of the process reducing the slab width in hot plate mill called edging is critical to produce rolled products with a desired dimension, which otherwise increase the yield loss caused by trimming. This process, therefore, requires a stringent width control performance. In this paper, an edger set-up model generating the desired slab width required for the control is proposed based upon the neural network approach. This neural network model accounts for variation of the dimension of incoming slabs to predict the preset value of the width as accurately as possible. A series of simulations were conducted to evaluate the performance of the neural network estimator for a variety of operating conditions needed for producing rolled products of various dimensions. The results show that the proposed model can estimate the preset value of the slab width with good accuracy, thereby enhancing the dimensional accuracy of rolled products. The estimation performance is discussed in detail for various process operation conditions.
Tài liệu tham khảo
Beese, J. G. (1980) Some problem areas in the rolling of hot steel slabs. AISE Year Book, pp. 353–360.
El-Kalay, A. K. E. H. A. and Sparling, L. G. M. (1968) Factors affecting friction and their effect upon load, torque, and spread in hot flat rolling. Journal of the Iron and Steel Institute of Japan, 206, 152–163.
Giles, S. W. and Tiley, J. B. (1994) Automatic width control at Dofasco's No. 2 hot strip mill. Iron and Steel Engineer, 71(1), 35–40.
Ginzburg, V. B. (1988) High Quality Steel Rolling: Theory and Practice, Marcel Dekker.
Ginzburg, V. B., Kaplan, N., Bakhtar, F. and Tabone, C. J. (1991) Width control in hot strip mills. Iron and Steel Engineer, 68(6), 25–39.
Haga, Y., Ogawa, Y., Yamawaki, M., Murakami, S., Matsuo, T. and Masuda, S. (1983) Development of New Plane View Control Technique in Plate Rolling (NKK-DBR). Nippon Kokan Technical Report, Overseas, 39, 21–30.
Haykin, S. (1994) Neural Network, Macmillan.
Helmi, A. and Alexander, J. M. (1968) Geometric factors affecting spread in hot flat rolling of steel. Journal of the Iron and Steel Institute of Japan, 206, 1110–1117.
Holtan, L. J. (1994) Automatic enhancement at Dofasco's No. 2 hot strip mill. Iron and Steel Engineer, 71(1), 35–40.
Inoue, M., Nishida, S., Omori, K., Okamura, I., Fujioka, K. and Katayama, N. (1989) Manufacture of trimmingfree plates. Kawasaki Steel Technical Report, 20, 71–77.
Jacek M. Z. (1992)Introduction to Artificial Neural Systems, West Publishing Co.
Okado, M., Ariizumi, T., Noma, Y., Yabuuchi, K. and Yamazaki, Y. (1981) Width behavior of head and tail of slabs at edge rolling in hot strip mills. Journal of the Iron and Steel Institute of Japan, 67(15), 2516–2525.
Rovelli, C. (1996) Thailand's first hot strip mill. Iron and Steel Engineer, 73, 24–26.
Rumelhart, D. E., McClelland, T. L. and the PDP Research Group (1986) Parallel Distributed Processing, MIT Press.
Shaw, D. A., Broukhiwyan, A. E., Koenig, K. A., Adams, G. D., Chatman, C. R. and Duzan, D. A. (1994) LTV steel Indianna Harbor work's 84-in. Hot strip mill automatic width control using hydraulic edger. Iron and Steel Engineer, 71(8), 43–51.
Shibahara, T., Misaka, Y., Kono, T., Koriki, M. and Takemoto, H. (1981) Edger set-up model at roughing train in hot strip mill. Journal of the Iron and Steel Institute of Japan, 67(15), 2509–2515.
Tazoe, N. et al. (1984) New forms of hot strip mill width rolling installations. AISE Spring Conference Dearborn, Mich., April 30-May 2.
Tsukamoto, H. and Kohmoto, E. (1987) U.S. Patent No. 4,672,830, June 16.