Neural Network-Based Control Strategies Applied to a Fed-Batch Crystallization Process

This paper is focused on issues of process modeling and two model based control strategies of a fed-batch sugar crystallization process applying the concept of artificial neural networks (ANNs). 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. The control task is rather challenging due to the strong nonlinearity of the process dynamics and variations in the crystallization kinetics. Two control alternatives are considered - model predictive control (MPC) and feedback linearizing control (FLC). Adequate ANN process models are first built as part of the controller structures. MPC algorithm outperforms the FLC approach with respect to satisfactory reference tracking and smooth control action. However, the MPC is computationally much more involved since it requires an online numerical optimization, while for the FLC an analytical control solution was determined.

[1]  N. T. Russell,et al.  Modular modelling of an evaporator for long-range prediction , 1997, Artif. Intell. Eng..

[2]  S. Feyo de Azevedo,et al.  Monitoring crystallization. I: On-line monitoring of white sugar crystallization through software sensors , 1993 .

[3]  Edward Schlossmacher.  Modeling and Simulation in Chemical Engineering , 1975 .

[4]  Ladislav Beránek,et al.  Simulation of a stirred sugar boiling pan. , 1990 .

[5]  Z. Nagy,et al.  Robust nonlinear model predictive control of batch processes , 2003 .

[6]  David Q. Mayne,et al.  Constrained model predictive control: Stability and optimality , 2000, Autom..

[7]  Lyle H. Ungar,et al.  A hybrid neural network‐first principles approach to process modeling , 1992 .

[8]  Petia Georgieva,et al.  Knowledge-based hybrid modelling of a batch crystallisation when accounting for nucleation, growth and agglomeration phenomena , 2003 .

[9]  R. Maciel Filho,et al.  Processing modelling development through artificial neural networks and hybrid models , 2000 .

[10]  J. Rawlings,et al.  Model identification and control of solution crystallization processes: a review , 1993 .

[11]  Kumpati S. Narendra,et al.  Issues in the application of neural networks for tracking based on inverse control , 1999, IEEE Trans. Autom. Control..

[12]  S. Feyo de Azevedo,et al.  Modeling of Sugar Crystallization through Knowledge Integration , 2003 .

[13]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[14]  A. Randolph,et al.  Theory of Particulate Processes: Analysis and Techniques of Continuous Crystallization , 1971 .

[15]  Kumpati S. Narendra,et al.  Nonlinear adaptive control using neural networks and multiple models , 2001, Autom..

[16]  Alfred Jean Philippe Lauret,et al.  Hybrid modelling of a sugar boiling process , 2000, 1212.5251.

[17]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[18]  Richard D. Braatz,et al.  First-principles and direct design approaches for the control of pharmaceutical crystallization , 2005 .

[19]  R. Hanus,et al.  A new training method for hybrid models of bioprocesses , 1999 .

[20]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.