Online-optimized feed switching in semi-batch reactors using semi-empirical dynamic models

Abstract Short prediction horizons, as required by continuous processes, or accurate process models allow adequate on-line model-predictive input correction using conventional filter-based state estimation and model integration. For inadequately modeled time-varying or high-order systems requiring long prediction horizons, e.g. batch processes, a reliable, neural-network-based, semi-empirical predictor previously proposed by the authors (Schenker & Agarwal, 1995b, International Journal of Control, 62(1), 227–238) is better suited for model-predictive control. This work achieves satisfactory on-line optimization of the feed switching in a simulated semi-batch chemical reactor using the proposed scheme and compares it with other neural-network-based schemes and with conventional state filtering followed by model integration.

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

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

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

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

[5]  A. Jazwinski.  Stochastic Processes and Filtering Theory , 1970 .

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

[7]  F. Grund.  Forsythe, G. E. / Malcolm, M. A. / Moler, C. B., Computer Methods for Mathematical Computations. Englewood Cliffs, New Jersey 07632. Prentice Hall, Inc., 1977. XI, 259 S , 1979 .

[8]  Michael A. Malcolm,et al.  Computer methods for mathematical computations , 1977 .

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

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

[11]  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.

[12]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

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

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

[15]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

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

[17]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[18]  George E. P. Box,et al.  Empirical Model‐Building and Response Surfaces , 1988 .