Rejection of the Feed-Flow Disturbances in a Multi-Component Distillation Column Using a Multiple Neural Network Model-Predictive Controller

Document Type: Research Article


The Petroleum University of Technology, P.O. Box 63431, Ahwaz, I.R. IRAN


This article deals with the issues associated with developing a new design methodology for the nonlinear model-predictive control (MPC) of a chemical plant. A combination of multiple neural networks is selected and used to model a nonlinear multi-input multi-output (MIMO) process with time delays.  An optimization procedure for a neural MPC algorithm based on this model is then developed. The proposed scheme has been tested on a model of an 18-plate multi-component distillation column. The algorithm provides excellent disturbance rejection for this process.


Main Subjects

[1] Billings, S.A. and Fakhouri, S.Y., Automatica, 18, 15 (1982).
[2] Leontardis, I. J. and Billings, S.A., Int. J. Contorl. 41, 303 (1985).
[3] Temeng, K. O., Schnelle, P.D. and McAvoy, T. J., Journal of Process Control, 5, 19 (1995).
[4] Lennox, B., Montague, G. A., Frith, A. M., Gent, G. and Beuan, V., Journal of Process Control, 11, 497 (2001).
[5] Duarte,  M., Suarez,  A.  and Bassi,  D.,  Powder Technology, 115, 193 (2001).
[6] Show, A. M. and Doyle, F. J., Journal of Process Control, 7, 255 (1997).
[7] Franks, R. G. E., John Wiley & Sons, “Modeling and Simulation in Chemical Engineering”, pp. 249-254 (1972).
[8] Garcia, C. E. and Morshedi, A. M., Cehm. Eng. Commun., 46, 073 (1986).
[9] Baharin, I. B. Hasan, M. D., Advances in Engineering Software, 22, 191 (1995).