Predictive control of a bench-scale chemical reactor based on neural-network models

The authors have developed a reliable long-range predictor, comprising two neural networks with external feedback in series, and investigated its applicability for model predictive control on a simulation example. The networks use external feedback of the process state, yielding a state-space mapping that eliminates the drawbacks of the input-output mapping of the feedforward networks. This paper applies the long-range predictor to the model predictive control of an experimental bench-scale semi-batch chemical reactor. Examples of yield maximization for a reaction with complex kinetics are used to assess the proposed predictive control scheme. Control performance is compared for predictors based on the proposed external-feedback networks and on conventional feedforward networks. Results for various operating conditions, disturbances, and included analytical models demonstrate the superiority of the proposed control scheme in experiments.

[1]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[2]  D. Rippin,et al.  Semi-batch process optimization under uncertainty: Theory and experiments , 1998 .

[3]  A. J. Morris,et al.  Artificial neural networks in process engineering , 1991 .

[4]  B. Schenker,et al.  STATE PREDICTION FOR CHEMICAL REACTORS USING FEEDBACK NEURAL NETWORKS , 1993 .

[5]  M. N. Karim,et al.  Use of Recurrent Neural Networks for Bioprocess Identification in On-line Optimization by Micro-Genetic Algorithms , 1992, 1992 American Control Conference.

[6]  J. R. Bourne,et al.  Heat transfer from exothermically reacting fluid in vertical unstirred vessels—I. temperature and flow fields , 1987 .

[7]  Fivos Panetsos,et al.  Control of batch reactors using neural networks , 1992 .

[8]  Heinrich Zollinger,et al.  Azo Coupling Reactions Structures and Mechanisms , 1983, Preparative Organic Chemistry.

[9]  Thomas F. Edgar,et al.  Adaptive control strategies for process control: A survey , 1986 .

[10]  PAUL J. WERBOS,et al.  Generalization of backpropagation with application to a recurrent gas market model , 1988, Neural Networks.

[11]  Mukul Agarwal,et al.  Long-range prediction for poorly-known systems , 1995 .

[12]  A. J. Morris,et al.  Predictive Control of Distillation Columns Using Dynamic Neural Networks , 1992 .

[13]  B. Schenker,et al.  Feedback Neural Nets for Supervision of Dynamic Processes , 1992 .

[14]  Hans Schuler,et al.  Zur frühzeitigen Erkennung gefährlicher Reaktionszustände in chemischen Reaktoren , 1981 .

[15]  P J Webros BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .

[16]  Norio Baba,et al.  A new approach for finding the global minimum of error function of neural networks , 1989, Neural Networks.

[17]  B. Schenker,et al.  Using a-priori information in networks , 1991 .

[18]  Won-Kyoo Lee,et al.  Neural Networks Approach to Automatic Startup and Control of An Exothermic Batch Reactor , 1991, 1991 American Control Conference.