M. Zarein - Department of Mechanical and Biosystems Engineering, Tarbiat Modares University, Tehran, Islamic Republic of Iran.
M. H. Khoshtaghaza - Department of Mechanical and Biosystems Engineering, Tarbiat Modares University, Tehran, Islamic Republic of Iran.
B. Ghobadian - Department of Mechanical and Biosystems Engineering, Tarbiat Modares University, Tehran, Islamic Republic of Iran.
H. Ameri Mahabadi - Department of Electrical Engineering, University of Malaya (UM), Kuala Lumpur, Malaysia

The purpose of this research was to predict and optimize the fish biodiesel characteristics using its permittivity properties. The parameters of biodiesel permittivity properties such as έ, dielectric constant, and ε″, loss factor at microwave frequencies of ۴۳۴, ۹۱۵, and ۲,۴۵۰ MHz, were used as input variables. The fish biodiesel characteristics, as Fatty Acid Methyl Ester (FAME) content and flash point at three different levels of reaction time ۳, ۹, and ۲۷ min and catalyst concentrations ۱, ۱.۵, and ۲% w woil-۱, were selected as output parameters for the models. Linear Regression (LR), the Multi-Layer Perceptron (MLP), and the Radial Basis Function (RBF) as the methods of Artificial Neural Networks (ANN), and the response surface methodology were compared for prediction and optimization of FAME content and flash point. A comparison of the results showed that the RBF recorded higher coefficient of determination at frequency of ۲,۴۵۰ MHz as ۰.۹۹۹ and ۰.۹۸۸ and lower root mean square error as ۰.۰۰۹ and ۰.۰۲۳ for FAME content and flash point, respectively. The optimum condition was obtained using RSM by FAME content of ۸۹.۸۸% and flash point of ۱۵۲.۷°C with desirability of ۰.۹۹۸.

Keywords: Permittivity properties, Prediction, FAME content, Optimization, RSM, RSM., خواص دی الکتریک, پیش بینی, محتوای FAME, بهینه سازی