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%.
Guojun Zhang and Jessica Xu
N. Chen et al., "Dynamic Models for L-Histidine Fed-Batch Fermentation by Corynebacterium glutamicum", Advanced Materials Research, Vols. 160-162, pp. 1749-1755, 2011