سال انتشار: ۱۳۹۱

محل انتشار: بیستمین کنفرانس سالانه مهندسی مکانیک

تعداد صفحات: ۴

نویسنده(ها):

H. Zargartalebi – Graduate Student, Department of Mechanical Engineering, Shahid Chamran University
B. Attaran – Graduate Student, Department of Mechanical Engineering, Shahid Chamran University
A.R Noghrehabadi – Assistant Professor, Department of Mechanical Engineering, Shahid Chamran University
A. Ghanbarzadeh – Asistant Professor, Department of Mechanical Engineering, Shahid Chamran University

چکیده:

The ability of neural network to solve Simultaneous flow in saturated porous medium and free fluid in various Reynolds ranges is studied. These regions must be solved by Naviar-Stocks equation and equation of motion in porous region with proper interface boundary condition. Considering Darcy, Forchheimer and Brinkman terms in equation of motion in porous medium compels us to solve whole domain numerically. In order to reduce the computational cost, different kinds of neural networks are used. Various Reynolds numbers are applied as the input feature for the neural networks. This paper presents an algorithm using optimized radial basis neural network via the Bees Algorithm for simulation of flow in partly porous region to enhance accuracy and performance. The optimum neural network results are in good agreement with numerical one and run time of the solution decreases noticeably.