Dynamic Models for L-histidine Fed-batch Fermentation by Corynebacterium glutamicum

To predict and control feed batch fermentations of Corynebacterium glutamicun TQ2226 which can produce L-histidine, in this paper, we use a recurrent neural network model(RNNM). The control variables are the limiting substrate and the feeding conditions. The multi-input and multi-output RNNM proposed has seven outputs, nineteen neurons, twelve inputs, in the hidden layer, and 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 RNNM generalization was carried out reproducing a C. glutamicum fermentation not included in the learning process. It attains an error approximation of 1.8%.