Modeling of oil Extraction From Flaxseed by Using Microwave Pretreatment With Artificial Neural Network

Abstract

In the oil extraction, the suitable treatment of the seeds before extraction is the most critical steps to produce high quality and efficiency products. In this research, in order to model the process of oil extraction from flax seeds, the researchers applied pre-treated with microwave within different processing times (90, 180 and 270 S) and powers (180, 540, and 900 W) and the efficiency of oil extraction, acidity, refractive index, density, acid number, and the oil color were studied. To predict the changes' trend the artificial neural network in MATLAB R2013a software was used. The results showed that by increasing microwave time and power efficiency of oil extraction, index acid and acidity, density and oil color increased. Analysis of variance results showed that the studied microwave pre-treated had no effect on the refractive index. By studying the various networks of back propagation feed forward network with topologies 2-8-6 with a correlation coefficient of more than 0.999 and the mean squared error of less than 0.001 and with using sigmoid hyperbolic of tangent activation function, the Resilient back propagation and learning cycle of 1000 were specified as the best neural model. The results of the optimized and selected models were evaluated and these models with high correlation coefficients (over 0.844), were able to predict the changes' trend. According to the complexity and multiplicity of the effective factors in food industry processes and the results of this research, the neural network can be introduced as an acceptable model for modeling these processes.

Keywords

• artificial neural network
• flaxseed
• microwave
• modeling
• oil extraction