论文信息 - Design of a neural network observer to control a FED-batch bioprocess

Design of a neural network observer to control a FED-batch bioprocess

The present paper deals with the production of Saccharomyces cerevisiae, described by a sixth order nonlinear state space model. The control objective is to ensure the process stability and desirable specifications in the presence of disturbances and lack of reliable state measurements. First, the model of the process and its properties are presented. Next the ability of multi-layer Neural Networks to act as reliable emulators of the system dynamics is tested by simulation results and a training strategy is proposed to improve their performance. Finally, a non-linear adaptive observer is designed by means of artificial neural networks.

O. I. Kosmidou | Y. S. Boutalis

[1] J. Gauthier,et al. A simple observer for nonlinear systems applications to bioreactors , 1992 .

[2] Jovan D. Bošković,et al. Comparison of linear, nonlinear and neural-network-based adaptive controllers for a class of fed-batch fermentation processes , 1995, Autom..

[3] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[4] Jan F. M. Van Impe,et al. Nonlinear and Adaptive Control in Biotechnology: A Tutorial , 1995, Eur. J. Control.

[5] D. Dochain,et al. On-Line Estimation and Adaptive Control of Bioreactors , 2013 .

[6] Hassan Hammouri,et al. A high gain observer for a class of uniformly observable systems , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.