Oil Extraction from Pistacia Khinjuk - Experimental and Prediction by Computational Intelligence Models

Subject Areas : food microbiology

Y. Vasseghian ¹ , Gh Zahedi ² , M Ahmadi ³

1 - Ph. D. Research Student of the Department of Chemical Engineering, Faculty of Engineering, Razi University, Kermanshah, Iran.
2 - Associate Professor of the Department of Chemical and Biological Engineering, Missouri University of Science and Technology, 65409, Rolla, USA.
3 - Assistant Professor of the Department of Chemical Engineering, Faculty of Engineering, Razi University, Kermanshah, Iran.

Received: 2015-03-10 Accepted : 2015-11-07 Published : 2016-01-01

Keywords: Artificial Neural Network, Adaptive neuro fuzzy inference, Modeling, Optimization, Pistacia&#x0D, &#x0D, Khinjuk,

Abstract :

This study investigates the oil extraction from Pistacia Khinjuk by the application of enzyme.Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) were applied formodeling and prediction of oil extraction yield. 16 data points were collected and the ANN was trained with onehidden layer using various numbers of neurons. A two-layered ANN provides the best results, using applicationof ten neurons in the hidden layer. Moreover, process optimization were carried out by using both methods topredict the best operating conditions which resulted in the maximum extraction yield of the Pistacia Khinjuk.The maximum extraction yield of Pistacia Khinjuk was estimated by ANN method to be 56.52% under theoperational conditions of temperature and enzyme concentration of 0.27, pH of 6, and the Ultrasonic time of 4.23h, while the optimum oil extraction yield by ANFIS method was 55.8% by applying the operationalcircumstances of enzyme concentration of 0.30, pH of 6.5, and the Ultrasonic time of 4.55 h. In addition, meansquared-error (MSE) and relative error methods were utilized to compare the predicted values of the oilextraction yield obtained for both models with the experimental data. The results of the comparisons revealed thesuperiority of ANN model as compared to ANFIS model.