Frontiers of Chemical Science and Engineering

, Volume 7, Issue 3, pp 357–365

Predicting the yield of pomegranate oil from supercritical extraction using artificial neural networks and an adaptive-network-based fuzzy inference system

Authors

  • J. Sargolzaei
    • Department of chemical engineeringFerdowsi university of Mashhad
    • Department of chemical engineeringFerdowsi university of Mashhad
Research Article

DOI: 10.1007/s11705-013-1336-3

Cite this article as:
Sargolzaei, J. & Moghaddam, A.H. Front. Chem. Sci. Eng. (2013) 7: 357. doi:10.1007/s11705-013-1336-3

Abstract

Various simulation tools were used to develop an effective intelligent system to predict the effects of temperature and pressure on an oil extraction yield. Pomegranate oil was extracted using a supercritical CO2 (SC-CO2) process. Several simulation systems including a back-propagation neural network (BPNN), a radial basis function neural network (RBFNN) and an adaptivenetwork-based fuzzy inference system (ANFIS) were tested and their results were compared to determine the best predictive model. The performance of these networks was evaluated using the coefficient of determination (R2) and the mean square error (MSE). The best correlation between the predicted and the experimental data was achieved using the BPNN method with an R2 of 0.9948.

Keywords

oil recoveryartificial intelligenceextractionneural networkssupercritical extraction
Download to read the full article text

Copyright information

© Higher Education Press and Springer-Verlag Berlin Heidelberg 2013