Simulating Flow in Partly Porous Region Using RBF Neural Network and the Bees Algorithm

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.

[1]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[2]  Duc Truong Pham,et al.  APPLICATION OF THE BEES ALGORITHM TO THE TRAINING OF RADIAL BASIS FUNCTION NETWORKS FOR CONTROL CHART PATTERN RECOGNITION , 2006 .

[3]  Stephen Whitaker,et al.  Momentum transfer at the boundary between a porous medium and a homogeneous fluid-I. Theoretical development , 1995 .

[4]  Enrique Sanchez-Palencia,et al.  On boundary conditions for fluid flow in porous media , 1975 .

[5]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[6]  D. Pham,et al.  THE BEES ALGORITHM, A NOVEL TOOL FOR COMPLEX OPTIMISATION PROBLEMS , 2006 .

[7]  Walter K. Nader,et al.  Prediction of transport processes within porous media: Creeping flow relative to a fixed swarm of spherical particles , 1974 .

[8]  M. J. D. Powell,et al.  Restart procedures for the conjugate gradient method , 1977, Math. Program..

[9]  L. E. Scales,et al.  Introduction to Non-Linear Optimization , 1985 .

[10]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[11]  Philip E. Gill,et al.  Practical optimization , 1981 .

[12]  Oscar Castillo,et al.  Path planning for autonomous mobile robot navigation with ant colony optimization and fuzzy cost function evaluation , 2009, Appl. Soft Comput..

[13]  中山 顕,et al.  PC-aided numerical heat transfer and convective flow , 1995 .

[14]  Ricardo Martínez-Soto,et al.  Optimization of Interval Type-2 Fuzzy Logic Controllers for a Perturbed Autonomous Wheeled Mobile Robot Using Genetic Algorithms , 2009, Soft Computing for Hybrid Intelligent Systems.

[15]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[16]  M. Grae Worster,et al.  Interfacial conditions between a pure fluid and a porous medium: implications for binary alloy solidification , 2006, Journal of Fluid Mechanics.

[17]  Zafer Bingul,et al.  A Fuzzy Logic Controller tuned with PSO for 2 DOF robot trajectory control , 2011, Expert Syst. Appl..

[18]  S. Whitaker.  The method of volume averaging , 1998 .

[19]  Derivation of Matching Conditions at the Contact Surface Between Fluid-Saturated Porous Solid and Bulk Fluid , 1999 .