Modeling the effects of ultrasound power and reactor dimension on the biodiesel production yield: Comparison of prediction abilities between response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS)

Mostafa Mostafaei, Hossein Javadikia and Leila Naderloo

Energy, 2016, vol. 115, issue P1, 626-636

Abstract: Biodiesel is as an alternative petro-diesel fuel produced from the renewable resources. The use of novel technologies such as ultrasound technology for biodiesel production intensifies the reaction and reduces the process cost. The present study is aimed to evaluate and compare the prediction and simulating efficiency of the response surface methodology (RSM) and adaptive Neuro-fuzzy inference system (ANFIS) approaches for modeling the transesterification yield achieved in ultrasonic reactor. The influence of independent variables (reactor diameter, liquid height and ultrasound intensity) on the conversion of fatty acid methyl esters (FAME) was investigated by Box-Behnken design of RSM and two ANFIS approaches (hybrid and back-propagation optimization methods). All models were compared statistically based on the training and validation data set by the coefficient of determination (R2), root mean squares error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE) and mean relative percent deviation (MRPD). The calculated R2 for RSM and two ANFIS models were 0.9669, 0.9812 and 0.9808, respectively. All models indicated good predictions, however, the ANFIS models were more precise compared to the RSM model, which proves that the ANFIS is a powerful tool for modeling and optimizing FAME production in ultrasound reactor.

Keywords: Modeling; Ultrasound reactor; Biodiesel production; RSM; ANFIS; FAME efficiency (search for similar items in EconPapers)
Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544216312695
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:115:y:2016:i:p1:p:626-636

DOI: 10.1016/j.energy.2016.09.028

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().