Artificial neural network–genetic algorithm-based optimization of biodiesel production from Simarouba glauca

Loading...
Thumbnail Image
Files
Date
2018-02-13
Authors
Sivamani, Selvaraju
Selvakumar, Selvaraj
Rajendran, Karthik
Muthusamy, Shanmugaprakash
Journal Title
Journal ISSN
Volume Title
Publisher
Taylor & Francis
Research Projects
Organizational Units
Journal Issue
Abstract
A transesterification reaction was carried out employing an oil of paradise kernel (Simarouba glauca), a non-edible source for producing Simarouba glauca methyl ester (SGME) or biodiesel. In this study, the effects of three variables – reaction temperature, oil-to-alcohol ratio and reaction time – were studied and optimized using response surface methodology (RSM) and an artificial neural network (ANN) on the free fatty acid (FFA) level. Formation of methyl esters due to a reduction in FFA was observed in gas chromatography–mass spectroscopy (GC–MS) analysis. It was inferred that optimum conditions such as an oil-to-alcohol ratio of 1:6.22, temperature of 67.25 and duration of 20 h produce a better yield of biodiesel with FFA of 0.765 ± 0.92%. The fuel properties of paradise oil meet the requirements for biodiesel, by Indian standards. The results indicate that the model is in substantial agreement with current research, and simarouba oil can be considered a potential oil source for biodiesel production.
Description
Keywords
Biodiesel , Optimization , Transesterification , Artificial neural network , Response surface methodology
Citation
Sivamani, S., Selvakumar, S., Rajendran, K. and Muthusamy, S. (2018) 'Artificial neural network–genetic algorithm-based optimization of biodiesel production from Simarouba glauca', Biofuels, In Press, doi:10.1080/17597269.2018.1432267
Copyright
© 2018. This is an Accepted Manuscript of an article published by Taylor & Francis in Biofuels on 13 Feb 2018, available online: http://www.tandfonline.com/10.1080/17597269.2018.1432267