{"title":"Computational Fluid Dynamics Expert System using Artificial Neural Networks","authors":"Gonzalo Rubio, Eusebio Valero, Sven Lanzan","volume":63,"journal":"International Journal of Computer and Information Engineering","pagesStart":413,"pagesEnd":418,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/5734","abstract":"The design of a modern aircraft is based on three pillars: theoretical results, experimental test and computational simulations.\r\nAs a results of this, Computational Fluid Dynamic (CFD) solvers are\r\nwidely used in the aeronautical field. These solvers require the correct\r\nselection of many parameters in order to obtain successful results. Besides, the computational time spent in the simulation depends on\r\nthe proper choice of these parameters.\r\nIn this paper we create an expert system capable of making an\r\naccurate prediction of the number of iterations and time required for the convergence of a computational fluid dynamic (CFD) solver.\r\nArtificial 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\r\nrequired for the convergence of a CFD solver.","references":"[1] L. Wu, J. Fang, Z. Yang, S. Wu, Study on a neural network model for\r\nhigh speed turbulent boundary layer inducing optical distortions, Optik\r\n- International Journal for Light and Electron Optics, Vol. 122, No. 17,\r\npp. 1572 - 1575, 2011.\r\n[2] M. Bellman, J. Straccia, B. Morgan, K. Maschmeyer, R. Agarwal, Improving Genetic Algorithm Efficiency with an Artificial Neural Network\r\nfor Optimization of Low Reynolds Number Airfoils, AIAA 2009-1096, 47th\r\nAIAA Aerospace Sciences Meeting Including The New Horizons Forum\r\nand Aerospace Exposition 5-8 January 2009, Orlando, Florida\r\n[3] N.K. Peyada, A.K. Ghosh, Aircraft parameter estimation using a new\r\nfiltering technique based upon a neural network and Gauss-Newton\r\nmethod, The Aeronautical Journal, April 2009, Volume 113, No 1142\r\n243\r\n[4] T. Hill, P. Lewicki, Statistics: methods and applications: a comprehensive\r\nreference for science, industry and data mining, The Aeronautical\r\nJournal, April 2009, Volume 113, No 1142 243\r\n[5] K.-K. Sung, Learning and Example Selection for Object and Pattern Detection, MIT AI Lab, Jan. 1996\r\n[6] T. Gerhold, V. Hannemann, D. Schwamborn, On the Validation of the\r\nDLR-TAU Code, New Results in Numerical and Experimental Fluid\r\nMechanics, Notes on Numerical Fluid Mechanics, 72, pp. 426-433, 1999\r\n[7] R. L'opez, Aircraft parameter estimation using a new filtering technique\r\nbased upon a neural network and Gauss-Newton method, The Aeronautical\r\nJournal, April 2009, Volume 113, No 1142 243\r\n[8] K. Hornik,M. Stinchcombe, H. White, Multilayer feedforward networks\r\nare universal approximators, Neural Newtorks, 2(5):359-366, 1989\r\n[9] R. L'opez,(2010) Flood: An Open Source Neural Networks C++ Library\r\n(Version 2) [software]\r\n[10] C. Fefferman, Existence and smoothness of the Navier-Stokes equation,\r\nClay Millenium Problems 2000\r\n[11] H-C. Fu, Y-P. Lee, C-C. Chiang, H-T. Pao, Divide-and-Conquer Learning\r\nand Modular Perceptron Networks, IEEE transactions on neural networks, Vol 12, No 2, March 2001\r\n[12] G. Zhang, M. Hu, B. Patuwo, D. Indro, Artificial neural networks in\r\nbankruptcy prediction: General framework and cross-validation analysis,\r\nEuropean Journal of Operational Research 116(1999) 16\u252c\u259232\r\n[13] S. Lek, J.F. Gu'egan, Aircraft parameter estimation using a new filtering\r\ntechnique based upon a neural network and Gauss-Newton method, The\r\nAeronautical Journal, April 2009, Volume 113, No 1142 243\r\n[14] C.M. Bishop, Neural Networks for Pattern Recognition, Oxford: Oxford\r\nUniversity Press","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 63, 2012"}