Cold rolling mill thickness control using the cascade-correlation neural network

• Autorzy: Frayman Y. , Wang L. , Wan C.
• Języki publikacji: EN

Abstrakty

EN

The improvements in thickness accuracy of a steel strip produced by a tandem cold-rolling mill are of substantial interest to the steel industry. In this paper, we designed a direct model-reference adaptive control (MRAC) scheme that exploits the natural level of excitation existing in the closed-loop with a dynamically constructed cascade-correlation neural network (CCNN) as a controller for cold rolling mill thickness control. Simulation results show that the combination of a such a direct MRAC scheme and the dynamically constructed CCNN significantly improves the thickness accuracy in the presence of disturbances and noise in comparison with to the conventional PID controllers.

Słowa kluczowe

EN

cascade-correlation neural network; cold rolling mill thickness control; direct MRAC; dynamic neural network construction

PL

konstrukcja dynamicznej sieci neuronowej; sieć neuronowa kaskadowo-korelacyjna; sterowanie grubością walcowni zimnej

• Wydawca: Systems Research Institute, Polish Academy of Sciences
• Czasopismo: Control and Cybernetics
• Rocznik: 2002
• Tom: Vol. 31, no. 2
• Strony: 327--342
• Opis fizyczny: Bibliogr. 25 poz.,rys., wykr.,

Twórcy

autor

Frayman Y.

• School of Computing and Mathematics Deakin University Geelong VIC 3217 Australia

autor

Wang L.

• School of Electrical and Electronic Engineering Nanyang Technological University Block S2 , Nanyang Avenue, Singapore 639798

autor

Wan C.

• School of Electrical and Electronic Engineering Nanyang Technological University Block S2 , Nanyang Avenue, Singapore 639798

Bibliografia

• ANDERSON, B.D.O. (1985) Adaptive systems, lack of persistency of excitation and bursting phenomena. Automatica, 21 (3), 247- 258.
• ASTROM, K. and WITTENMARK, B. (1990) Computer controlled systems, theory and design. 2nd ed. Prentice-Hall.
• BROWN, M. and HARRIS, C. (1994) Neurofuzzy Adaptive Modelling and Control. Prentice-Hall.
• DUTTON, K. and GROVES, C.N. (1996) Self-tuning control of a cold mill automatic gauge control system. International Journal of Control , 65, 573- 588.
• FAHLMAN, S. (1988) Faster-learning variations on back-propagation: An empirical study. 1988 Connectionist Models Summer School, 38 --51.
• FAHLMAN, S. and LEBIERE, C. (1990) The cascade-correlation learn ing architecture. Advances in Neural Information Processing Systems, 2, 524- 532.
• GRIMBLE, M.J. (1995) Polynomial Solution of the Standard H 00 Control Problem for Strip Mill Gauge Control. lEE Proceedings, part D - Control Theory and Applications, 142, 515-525.
• GUEZ, A ., RUSNAK, I. and BAR-KANA, l. (1992) Multiple objective optimization approach to adaptive and learning control. International Journal of Control, 56 (2), 469- 482.
• HAGGLUND, T. and AsTROM, K. (1996) Automatic tuning of PID controllers. The Control Handbook, CRC Press, 817- 826.
• HARRIS, C., MOORE, C. and BROWN, M. (1993) Int elligent Control: Aspects of Fuzzy Logic and Neural Nets. World Scientific.
• HAYKIN, S. (1999) Neural Networks: A Comprehensive Foundation. Prentice Hall, 2nd ed .
• HUNT, K., SBARBARO, D., ZBIKOWSKI, R. and GAWTHROP, P. (1992) Neural networks for control systems- a survey. Automatica, 28, 1083- 1112.
• Hwu, Y.J. and LENARD , J.G. (1996) Application of Neural Networks in the Prediction of Roll Force in Hot Rolling. Proceedings of the 37th Mechanical Working and Steel Processing Conference, 549- 554.
• KAVZOGLU, T. (1999) Determining Optimum Structure for Artificial Neural Networks. Proceedings of the 24th Annual Technical Conference and Exhibition of the Remote Sensing Society (Earth Observation: From Data to Information), 675-682.
• KOUSSOULASS, N.T. and DIMITRIADIS, E.K. (1989) Computational techniques for multi-criteria stochastic optimization and control. Control and dynamic systems, advances in theory and applications, 30 (3), 1- 17.
• KWOK, T.Y. and YEUNG, D .Y. (1997) Constructive algorithms for structure learning in feedforward neural networks for regression problems. IEEE Transactions on Neural Networks, 8 (3), 630- 645.
• LIN, C.-J. and LIN, C.T. (1996) Reinforcement learning for an ART-based adaptive learning control network. IEEE Transactions on Neural Networks, 7, 709- 731.
• MARS, P., CHEN J.R. and NAMBIAR R. (1996) Learning algorithms: theory and applications in signal processing, control and comm1mications. CRC Press, Boca Raton, FL.
• NARENDRA, K. and PATHASARATHY, K. (1990) Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks, 1, 4-27.
• NARENDRA, K. and MUKHOPADHYAY, S. (1994) Adaptive control of nonlinear multivariable systems using neural networks. Neural Networks, 7, 737- 752.
• PICHLER, R. and PFFAFFERMAYR, M. (1996) Neural Networks for On-Line Optimisation of the Rolling Process. Iron and Steel Review, August, 45 -56.
• POSTLETHWAITE, I. and GEDDES, J. (1994) Gauge Control in Tandem Cold Rolling Mills: A Multivariable Case Study Using H 00 Optimization. Proceedings 3rd IEEE Conference on Control Applications, 3, 1551- 1556.
• TSAKALIS, K.S. (1996) Performance limitations of adaptive parameter estimation and system identification algorithms in the absence of excitation. Automatica , 32 (4), 549- 560.
• TSAKALIS, K.S. (1997) Bursting scenario and performance limitations of adaptive algorithms in the absence of excitation. Kybernetika, 33 (1), 17 - 40.
• ZAKNICH, A. and ATTIKIOUZEL, Y. (1995) Application of artificial neural networks to nonlinear signal processing. Computational intelligence, a dynamic system perspective. IEEE P ress, New York, 292 - 311.