Prediction of Ethanol Concentration in Biofuel Production Using Artificial Neural Networks

Abstract

Environmentally friendly and important enhancements in biofuel production technology are necessary in order to cut back production prices and create it as a competitive resource material. This study performed a cost-effective bioprocess to provide bio-ethanol from sugarcane molasses by chosen strains of the yeast S. cerevisiae, through experiments at laboratory, pilot and industrial scales. Artificial neural networks are shown to be powerful tools for system modeling. The objective of this study was to develop a straightforward, accurate and time saving prognosticative model for alcohol production. Results recommend that artificial neural networks provide a good means of effective recognizing patterns in data and accurately predicting ethanol concentration based on investigating inputs. The ethanol concentration evaluated in experiments of industrial biofuel production and this research develops a simple, accurate, nondestructive and time saving artificial neural networks model for estimation of ethanol concentration in batch ethanol fermentation from molasses based on live and dead yeast cells, sugar concentration.