A Recurrent Neural Network for Controlling a Fed-Batch Fermentation of B. t.
The paper proposed to use a new Recurrent Neural Network Model (RNNM) to stabilize fermentation process of Bacillus thuringiensis from fermentation kinetic data. The multi-input multi-output RNNM proposed, have ten inputs, six outputs, sixteen neurones in the hidden layer, and also global and local feedbacks. The weight update learning algorithm designed, is a version of the well known backpropagation through time algorithm, directed to the RNNM learning. The approximation error for the last epoch of learning is about 2% and the total time of learning is 201 epochs, where the size of epoch is 115 iterations.
KeywordsHide Layer Mean Square Error Specific Growth Rate Bacillus Thuringiensis Recurrent Neural Network
Unable to display preview. Download preview PDF.
- G. Muralikrishnan and M. Chidambaram. “Control of bioreactors using a neural network model. Bioprocess Engineering”, pp. 35–39, Vol. 12, 1995.Google Scholar
- I. Baruch, I. Stoyanov, E. Gortcheva. “Topology and Learning of a Class Recurrent Neural Networks”, ELEKTRIK, Turkish Journal of Electrical Engineering and Computer Sciences, pp. 35–43, Vol. 4, 1996.Google Scholar
- I. Baruch, I. Stoyanov and T. Arsenov. “An improved RTNN model for dynamic systems identification and time series prediction”. In: Proc. of the 4-th Int. Symp. MMAR201997, Aug. 26-29, 1997, Miedzyzdroje, Poland, (S. Domek, Z. Emirsajlov, R. Kaszynski, Eds.), pp. 711–716, TU of Szczecin, Poland, Vol. 2, 1997.Google Scholar