Batch-to-batch control of fed-batch processes using control-affine feedforward neural network

A control strategy for fed-batch processes is proposed based on control affine feed-forward neural network (CAFNN). Many fed-batch processes can be considered as a class of control affine nonlinear systems. CAFNN is constructed by a special structure to fit the control affine system. It is similar to a multi-layer feed-forward neural network, but it has its own particular feature to model the fed-batch process. CAFNN can be trained by a modified Levenberg–Marquardt (LM) algorithm. However, due to model-plant mismatches and unknown disturbances, the optimal control policy calculated based on the CAFNN model may not be optimal when applied to the fed-batch process. In terms of the repetitive nature of fed-batch processes, iterative learning control (ILC) can be used to improve the process performance from batch to batch. Due to the special structure of CAFNN, the gradient information of CAFNN can be computed analytically and applied to the batch-to-batch ILC. Under the ILC strategy from batch to batch, endpoint product qualities of fed-batch processes can be improved gradually. The proposed control scheme is illustrated on a simulated fed-batch ethanol fermentation process.

[1]  W. Ramirez,et al.  Optimal production of secreted protein in fed‐batch reactors , 1988 .

[2]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[3]  Jay H. Lee,et al.  Iterative learning control-based batch process control technique for integrated control of end product properties and transient profiles of process variables , 2003 .

[4]  Jie Zhang,et al.  Product Quality Trajectory Tracking in Batch Processes Using Iterative Learning Control Based on Time-Varying Perturbation Models , 2003 .

[5]  A.G. Alleyne,et al.  A survey of iterative learning control , 2006, IEEE Control Systems.

[6]  Jay H. Lee,et al.  Model-based iterative learning control with a quadratic criterion for time-varying linear systems , 2000, Autom..

[7]  Jie Zhang,et al.  A batch-to-batch iterative optimal control strategy based on recurrent neural network models , 2005 .

[8]  Dominique Bonvin,et al.  Optimal operation of batch reactors—a personal view , 1998 .

[9]  Panos J. Antsaklis,et al.  Neural networks for control systems , 1990, IEEE Trans. Neural Networks.

[10]  E. Rogers,et al.  Iterative learning control for discrete-time systems with exponential rate of convergence , 1996 .

[11]  Babatunde A. Ogunnaike,et al.  Recursive data-based prediction and control of batch product quality , 1998 .

[12]  Jay H. Lee,et al.  Convergence of constrained model-based predictive control for batch processes , 2000, IEEE Trans. Autom. Control..

[13]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[14]  Rein Luus,et al.  Optimal control of nonlinear systems with unspecified final times , 1996 .

[15]  R. Luus.  On the application of iterative dynamic programming to singular optimal control problems , 1992 .

[16]  J Hong,et al.  Optimal substrate feeding policy for a fed batch fermentation with substrate and product inhibition kinetics , 1986, Biotechnology and bioengineering.

[17]  Zhihua Xiong,et al.  Modelling and optimal control of fed-batch processes using a novel control affine feedforward neural network , 2004, Neurocomputing.

[18]  Jie Zhang,et al.  A Reliable Neural Network Model Based Optimal Control Strategy for a Batch Polymerization Reactor , 2004 .

[19]  Jie Zhang,et al.  A neural network-based strategy for the integrated batch-to-batch control and within-batch control of batch processes , 2005 .