Moradi, Gholamreza, Mohadesi, Majid, Karami, Bita, Moradi, Ramin. (1394). Using Artificial Neural Network for Estimation of Density and Viscosities of Biodiesel–Diesel Blends. , 49(2), 153-165. doi: 10.22059/jchpe.2015.1807
Gholamreza Moradi; Majid Mohadesi; Bita Karami; Ramin Moradi. "Using Artificial Neural Network for Estimation of Density and Viscosities of Biodiesel–Diesel Blends". , 49, 2, 1394, 153-165. doi: 10.22059/jchpe.2015.1807
Moradi, Gholamreza, Mohadesi, Majid, Karami, Bita, Moradi, Ramin. (1394). 'Using Artificial Neural Network for Estimation of Density and Viscosities of Biodiesel–Diesel Blends', , 49(2), pp. 153-165. doi: 10.22059/jchpe.2015.1807
Moradi, Gholamreza, Mohadesi, Majid, Karami, Bita, Moradi, Ramin. Using Artificial Neural Network for Estimation of Density and Viscosities of Biodiesel–Diesel Blends. , 1394; 49(2): 153-165. doi: 10.22059/jchpe.2015.1807

Using Artificial Neural Network for Estimation of Density and Viscosities of Biodiesel–Diesel Blends

Journal of Chemical and Petroleum Engineering
مقاله 8، دوره 49، شماره 2، اسفند 2015، صفحه 153-165    اصل مقاله (615.76 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22059/jchpe.2015.1807
نویسندگان
Gholamreza Moradi* 1؛ Majid Mohadesi2؛ Bita Karami1؛ Ramin Moradi3
1Catalyst Research Center, Chemical Engineering Department, Faculty of Engineering, Razi University, Kermanshah, I. R. Iran
2Chemical Engineering Department, Faculty of Energy, Kermanshah University of Technology, Kermanshah, I. R. Iran
3Faculty of Mechanical Engineering, Sharif University of Technology, Tehran, I. R. Iran
چکیده
In recent years, biodiesel has been considered as a good alternative of diesel fuels. Density and viscosity are two important properties of these fuels. In this study, density and kinematic viscosity of biodiesel-diesel blends were estimated by using artificial neural network (ANN). A three-layer feed forward neural network with Levenberg-Marquard (LM) algorithm was used for learning empirical data (previous studies data and this study empirical data). Input data for estimating density and kinematic viscosity includes components volume fraction, temperature and pure component properties (pure density at 293.15 K and pure kinematic viscosity at 313.15 K). Results of neural network simulation for density and kinematic viscosity showed a high accuracy (mean relative error for density and kinematic viscosity are 0.021% and 0.73%, respectively).
 
کلیدواژه‌ها
Artificial Neural Network؛ Biodiesel؛ Blend؛ Density؛ Kinematic viscosity
مراجع
آمار
تعداد مشاهده مقاله: 2,385
تعداد دریافت فایل اصل مقاله: 1,524