Applicability of Neural Networks for the Fermentation of Propionic Acid by Propionibacterium acidipropionici

According to our best knowledge, this is the first report applying Artificial neural networks (ANN) for simulation of batch propionic acid (PA) fermentation. Therefore, main focus research was investigate applicability ANN on PA fermentations. To demonstrate this, we used results 40 Propionibacterium acidipropionici fermentations (ca 2,000 data points) build up ANN, and additional two independent prediction capability observed ANN. Analyzing predicted output parameters observed, that ratio acetic (PA/AA) variables can only be after normalization. Finally, fit model measured fine (average correlation coefficients over 0.9). A special feature also tested: fermentation time as an input parameter, thus making suitable predict course well which satisfying.