Application of Feed Forward Neural Networks in Modeling and Control of a Fed-Batch Crystallization Process

This paper is focused on issues of nonlinear dynamic process modeling and model-based predictive control of a fed-batch sugar crystallization process applying the concept of artificial neural networks as computational tools. The control objective is to force the operation into following optimal supersaturation trajectory. It is achieved by manipulating the feed flow rate of sugar liquor/syrup, considered as the control input. A feed forward neural network (FFNN) model of the process is first built as part of the controller structure to predict the process response over a specified (prediction) horizon. The predictions are supplied to an optimization procedure to determine the values of the control action over a specified (control) horizon that minimizes a predefined performance index. The control task is rather challenging due to the strong nonlinearity of the process dynamics and variations in the crystallization kinetics. However, the simulation results demonstrated smooth behavior of the control actions and satisfactory reference tracking.

• Petia Georgieva
• Sebastião Feyo de Azevedo

• Feed forward neural network
• process modelling
• model predictive control
• crystallization process.

[1] J. B. Rawlings, S. M. Miller, and W. R. Witkowski., "Model
identification and control of solution crystallization processes: a
review", Ind. Eng. Chem. Res., 32(7):1275-1296, July 1993.
[2] Nagy Z. K. and R. D. Braatz,. Robust nonlinear model predictive control
of batch processes. AIChE J., 49:1776-1786, 2003.
[3] Fujiwara, M. Z. K. Nagy, J. W. Chew, and R. D. Braatz First-principles
and direct design approaches for the control of pharmaceutical
crystallization. J. of Process Control, 15:493-504, 2005 (invited).
[4] Feyo de Azevedo, S., Chorão, J., Gonçalves, M.J. and Bento, L., 1994,
On-line Monitoring of White Sugar Crystallization through Software
Sensors. Int. Sugar JNL., 96:18-26.
[5] S. Haykin S. (1994), Neural Networks: A comprehensive foundation,
Prentice Hall, UK.
[6] Russell N.T. and H.H.C. Bakker (1997), Modural modelling of an
evaporator for long-range prediction, Artificial Intelligence in
Engineering, 11, 347-355.
[7] Zorzetto L.F.M., R. Maciel Filho and M.R. Wolf-Maciel (2000), Process
modelling development through artificial neural networks and hybrid
models, Computers and Chemical Engineering, 24, 1355-1360.
[8] Georgieva P., Meireles, M. J. and Feyo de Azevedo, S., 2003, KBHM of
fed-batch sugar crystallization when accounting for nucleation, growth
and agglomeration phenomena. Chem Eng Sci, 58:3699-3711.
[9] Ditl, P., Beranek L., & Rieger, Z. (1990). Simulation of a stirred sugar
boiling pan. Zuckerind., 115, 667-676.
[10] A.D. Randolph, M.A. Larson, Theory of Particulate Processes -
Analyses and Techniques of Continuous Crystallization, Academic Pres,
1988.
[11] P. Lauret, H. Boyer, J.C. Gatina, Hybrid modelling of a sugar boiling
process, Control Engineering Practice, 8, 2000, 299-310.
[12] Hagan M. T., M. Menhaj (1994), "Training feedforward networks with
the Marquardt algorithm," IEEE Transactions on Neural Networks, vol.
5, no.6, pp. 989-993.
[13] D.C. Psichogios, L. H. Ungar, A hybrid neural network - first principles
approach to process modelling, AIChE J., 38(10), 1992, 1499-1511.
[14] Graefe, J., Bogaerts, P., Castillo, J., Cherlet, M., Werenne, J.,
Marenbach, P., & Hanus, R. (1999). A new training method for hybrid
models of bioprocesses. Bioprocess Engineering, 21, 423-429.
[15] V. Galvanauskas, P. Geogieva, S. Feyo de Azevedo, Dynamic
optimization of industrial sugar crystallization process based on a hybrid
(mechanistic +ANN) model, submitted for publication to IJCNN,
Vancouver, Canada, June 2006.