Computational Fluid Dynamics Expert System using Artificial Neural Networks

The design of a modern aircraft is based on three pillars: theoretical results, experimental test and computational simulations. As a results of this, Computational Fluid Dynamic (CFD) solvers are widely used in the aeronautical field. These solvers require the correct selection of many parameters in order to obtain successful results. Besides, the computational time spent in the simulation depends on the proper choice of these parameters. In this paper we create an expert system capable of making an accurate prediction of the number of iterations and time required for the convergence of a computational fluid dynamic (CFD) solver. Artificial neural network (ANN) has been used to design the expert system. It is shown that the developed expert system is capable of making an accurate prediction the number of iterations and time required for the convergence of a CFD solver.

Authors:

• Gonzalo Rubio
• Eusebio Valero
• Sven Lanzan

Keywords:

• Artificial Neural Network
• Computational Fluid Dynamics
• Optimization

References:

[1] L. Wu, J. Fang, Z. Yang, S. Wu, Study on a neural network model for
high speed turbulent boundary layer inducing optical distortions, Optik
- International Journal for Light and Electron Optics, Vol. 122, No. 17,
pp. 1572 - 1575, 2011.
[2] M. Bellman, J. Straccia, B. Morgan, K. Maschmeyer, R. Agarwal, Improving Genetic Algorithm Efficiency with an Artificial Neural Network
for Optimization of Low Reynolds Number Airfoils, AIAA 2009-1096, 47th
AIAA Aerospace Sciences Meeting Including The New Horizons Forum
and Aerospace Exposition 5-8 January 2009, Orlando, Florida
[3] N.K. Peyada, A.K. Ghosh, Aircraft parameter estimation using a new
filtering technique based upon a neural network and Gauss-Newton
method, The Aeronautical Journal, April 2009, Volume 113, No 1142
243
[4] T. Hill, P. Lewicki, Statistics: methods and applications: a comprehensive
reference for science, industry and data mining, The Aeronautical
Journal, April 2009, Volume 113, No 1142 243
[5] K.-K. Sung, Learning and Example Selection for Object and Pattern Detection, MIT AI Lab, Jan. 1996
[6] T. Gerhold, V. Hannemann, D. Schwamborn, On the Validation of the
DLR-TAU Code, New Results in Numerical and Experimental Fluid
Mechanics, Notes on Numerical Fluid Mechanics, 72, pp. 426-433, 1999
[7] R. L'opez, Aircraft parameter estimation using a new filtering technique
based upon a neural network and Gauss-Newton method, The Aeronautical
Journal, April 2009, Volume 113, No 1142 243
[8] K. Hornik,M. Stinchcombe, H. White, Multilayer feedforward networks
are universal approximators, Neural Newtorks, 2(5):359-366, 1989
[9] R. L'opez,(2010) Flood: An Open Source Neural Networks C++ Library
(Version 2) [software]
[10] C. Fefferman, Existence and smoothness of the Navier-Stokes equation,
Clay Millenium Problems 2000
[11] H-C. Fu, Y-P. Lee, C-C. Chiang, H-T. Pao, Divide-and-Conquer Learning
and Modular Perceptron Networks, IEEE transactions on neural networks, Vol 12, No 2, March 2001
[12] G. Zhang, M. Hu, B. Patuwo, D. Indro, Artificial neural networks in
bankruptcy prediction: General framework and cross-validation analysis,
European Journal of Operational Research 116(1999) 16┬▒32
[13] S. Lek, J.F. Gu'egan, Aircraft parameter estimation using a new filtering
technique based upon a neural network and Gauss-Newton method, The
Aeronautical Journal, April 2009, Volume 113, No 1142 243
[14] C.M. Bishop, Neural Networks for Pattern Recognition, Oxford: Oxford
University Press