Artificial neural network approach to modelling of alcoholic fermentation of thick juice from sugar beet processing | Modelovanje alkoholne fermentacije gustog soka šećerne repe primenom veštačkih neuronskih mreža
2012
Jokić, A.I., Tehnološki fakultet, Novi Sad (Serbia) | Grahovac, J.A., Tehnološki fakultet, Novi Sad (Serbia) | Dodić, J.M., Tehnološki fakultet, Novi Sad (Serbia) | Dodić, S.N., Tehnološki fakultet, Novi Sad (Serbia) | Popov, S.D., Tehnološki fakultet, Novi Sad (Serbia) | Zavargo, Z.Z., Tehnološki fakultet, Novi Sad (Serbia) | Vučurović, D.G., Tehnološki fakultet, Novi Sad (Serbia)
In this paper the bioethanol production in batch culture by free Saccharomyces cerevisiae cells from thick juice as intermediate product of sugar beet processing was examined. The obtained results suggest that it is possible to decrease fermentation time for the cultivation medium based on thick juice with starting sugar content of 5−15 g/kg. For the fermentation of cultivation medium based on thick juice with starting sugar content of 20 and 25 g/kg significant increase in ethanol content was attained during the whole fermentation process, resulting in 12.51 and 10.95 cubic dm/cubic meter ethanol contents after 48 h, respectively. Other goals of this work were to investigate the possibilities for experimental results prediction using artificial neural networks (ANNs) and to find its optimal topology. A feedforward back-propagation artificial neural network was used to test the hypothesis. As input variables fermentation time and starting sugar content were used. Neural networks had one output value, ethanol content, yeast cell number or sugar content. There was one hidden layer and the optimal number of neurons was found to be nine for all selected network outputs. In this study, transfer function was tansig and the selected learning rule was Levenberg–Marquardt. Results suggest that artificial neural networks are good prediction tool for selected network outputs. It was found that experimental results are in very good agreement with computed ones. The coefficient of determination (the R-squared) was found to be 0.9997, 0.9997 and 0.9999 for ethanol content, yeast cell number and sugar content, respectively.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Matica Srpska Library
Découvrez la collection de ce fournisseur de données dans AGRIS