×

zbMATH — the first resource for mathematics

Aerodynamic shape design using evolutionary algorithms and new gradient-assisted metamodels. (English) Zbl 1178.76310
Summary: Aerodynamic shape design and optimization problems based on evolutionary algorithms and surrogate evaluation tools, i.e., the so-called metamodels, have recently found widespread use. Using metamodels, trained either separately from or during the optimization loop, a considerable reduction in the overall computing cost can be achieved. To support metamodel-based evolutionary algorithms, a class of new metamodels which utilize both known responses and response gradients for their training is proposed. The new gradient-assisted metamodels are extensions of standard multi-layer perceptrons and radial basis function networks. To demonstrate the prediction capabilities of the proposed metamodels and investigate different implementation modes within search algorithms along with the relevant CPU cost, a number of 2D and 3D aerodynamic shape (namely airfoils and turbomachinery blades) design problems are analyzed. Single- and two-objective problems, aiming at designing shapes that reproduce known pressure distributions at specific operating points, are considered. The exact evaluation tool is a numerical solver of the compressible fluid flow equations. The necessary gradient of the objective function is obtained by formulating and numerically solving adjoint equations.

MSC:
76N25 Flow control and optimization for compressible fluids and gas dynamics
76M25 Other numerical methods (fluid mechanics) (MSC2010)
65K10 Numerical optimization and variational techniques
PDF BibTeX Cite
Full Text: DOI
References:
[1] D. Buche, N. Schraudolph, P. Koumoutsakos, Accelerating evolutionary algorithms using fitness function models, in: GECCO 2003.
[2] Adeli, H.; Karim, A., Neural network model for optimization of cold-formed steel beams, J. struct. engrg. (ASCE), 123, 11, 1535-1544, (1997)
[3] Arslan, M.A.; Hajela, P., Counter propagation neural networks in decomposition based optimal design, Comput. struct., 65, 5, 641-650, (1997) · Zbl 0933.74528
[4] Shich, R.C., Massively parallel structural design using stochastic optimization and mixed neural net/finite element analysis methods, Comput. syst. engrg., 5, 4-6, 455-467, (1994)
[5] Simpson, T.W.; Peplinski, J.D.; Koch, P.N.; Allen, J.K., Metamodels for computer-based engineering design: survey and recommendations, Engrg. comput., 17, 129-150, (2001) · Zbl 0985.68599
[6] Jin, Y., A comprehensive survey of fitness approximation in evolutionary computation, Soft comput., 9, 1, 3-12, (2003)
[7] Giannakoglou, K.C., Design of optimal aerodynamic shapes using stochastic optimization methods and computational intelligence, Progr. aeros. sci., 38, 43-76, (2002)
[8] Shyy, W.; Papila, N.; Vaidyanathan, R.; Tucker, K., Global design optimization for aerodynamics and rocket propulsion components, Progr. aeros. sci., 37, 59-118, (2001)
[9] Myers, R.; Montgomery, D., Response surface methodology: process and product optimization using designed experiments, (1995), Wiley New York · Zbl 1161.62392
[10] Dayhoff, J.E., Neural network architectures: an introduction, (1990), Van Nostrand Reinhold New York
[11] Haykin, S., Neural networks, (1998), Prentice Hall International New Jersey
[12] Cichocki, A.; Unbenhauen, R., Neural networks for optimization and signal processing, (1993), Wiley New York
[13] Matheron, G., The intrinsic random functions and their applications, Adv. appl. prob., 5, 439-468, (1973) · Zbl 0324.60036
[14] Ratle, A., Accelerating the convergence of evolutionary algorithms by fitness landscape approximation, (), 87-96
[15] M. Trosset, A. Padula, Designing and analyzing computational experiments for global optimization, Rice University, Technical Report 00-25, 2000.
[16] A.P. Giotis, M. Emmerich, B. Naujoks, K.C. Giannakoglou, T. Bäck, Low-cost stochastic optimization for engineering applications, in: K. Giannakoglou et al. (Eds.), EUROGEN 2001—Evolutionary Methods for Design, Optimisation and Control with Applications to Industrial Problems, Athens, Greece, September 2001.
[17] M. Emmerich, A. Giotis, M. Ozdemir, T. Bäck, K.C. Giannakoglou, Metamodel-assisted evolution strategies, in: PPSN VII, Granada, Spain, 2002.
[18] Wilmes, L.; Bäck, T.; Jin, Y.; Sendhoff, B., Comparing neural networks and Kriging for fitness approximation in evolutionary computation, Proc. IEEE congr. evol. comput., 3, 1910-1917, (2003)
[19] T.W. Simpson, T.M. Mauery, J.J. Korte, F. Mistree, Comparison of response surface and kriging models for multidisciplinary design optimization, AIAA Paper 98-4755, 1998.
[20] N. Papila, W. Shyy, N. Fitz-Coy, R. Haftka, Assessment of neural net and polynomial-based techniques for aerodynamic applications, AIAA Paper 99-3167, 1999.
[21] Montgomery, D., Design and analysis of experiments, (1997), Wiley New York · Zbl 0910.62067
[22] K.C. Giannakoglou, Designing turbomachinery blades using evolutionary methods, ASME Paper 99-GT-181, 1999.
[23] K.C. Giannakoglou, Acceleration of genetic algorithms using artificial neural networks—theoretical background, Von-Karman Institute Lecture Series 2000-07, May 2000.
[24] K.C. Giannakoglou, A.P. Giotis, Acceleration of genetic algorithms using artificial neural networks—application of the method, Von-Karman Institute Lecture Series 2000-07, May 2000.
[25] Giannakoglou, K.C.; Giotis, A.P.; Karakasis, A.P.M.K., Low-cost genetic optimization based on inexact pre-evaluations and the sensitivity analysis of design parameters, J. inverse problems engrg., 9, 389-412, (2001)
[26] Karakasis, M.; Giotis, A.P.; Giannakoglou, K.C., Inexact information aided, low-cost, distributed genetic algorithms for aerodynamic shape optimization, Int. J. numer. methods fluids, 43, 1149-1166, (2003) · Zbl 1032.76654
[27] Nair, P.; Keane, A., Evolutionary optimization of computationally expensive problems via surrogate modeling, Aiaa j., 41, 4, 687-696, (2003)
[28] Y. Ong, P. Lum, P. Nair, D. Shi, Z. Zhang, Global convergence of unconstrained and bound constrained surrogate-assisted evolutionary search in aerodynamic shape design, in: Proceedings of the 1999 Congress on Evolutionary Computation (CEC2003), Australia, 2003.
[29] H. Ulmer, F. Streichert, A. Zell, Evolution strategies assisted by Gaussian processes with improved pre-selection criterion, in: Proceedings of the 1999 Congress on Evolutionary Computation (CEC2003), Australia, 2003. · Zbl 1028.68912
[30] F. van Keulen, K. Vervenne, Gradient-enhanced response surface building, in: 3rd ISSMO/AIAA Internet Conference on Approximations in Optimization, October 2002.
[31] Kodiyalam, S.; Gurumoorthy, R., Neural networks with modified backpropagation learning applied to structural optimization, Aiaa j., 34, 2, 408-412, (1996) · Zbl 0894.73092
[32] R.S. Sellar, S.M. Batill, Concurrent subspace optimization using gradient-enhanced neural network approximations, Paper AIAA-96-4019, in: 6th AIAA/NASA/USAF/ISSMO Symposium on Multidisciplinary Analysis and Optimization, Bellevue, Washington, September 1996.
[33] W. Liu, S.M. Batill, Gradient-enhanced neural network response surface approximations, Paper AIAA-2000-4923, 2000.
[34] F. van Keulen, B. Liu, R.T. Haftka, Noise and discontinuity issues in response surfaces based on functions and derivatives, Paper AIAA-2000-1363, 2000.
[35] H.S. Chung, J.J. Alonso, Using gradients to construct cokriging approximation models for high-dimensional design optimization problems, AIAA Paper 2002-0317, 2002.
[36] I.C. Kampolis, D.I. Papadimitriou, K.C. Giannakoglou, Evolutionary optimization using a new radial basis function network and the adjoint formulation, J. Inverse Problems Sci. Engrg., in press. · Zbl 1146.76609
[37] M.B. Giles, N.A. Pierce, Improved lift and drag estimates using adjoint Euler equations, AIAA Paper 99-3293, 1999.
[38] M.B. Giles, N.A. Pierce, Adjoint equations in CFD: duality, boundary conditions and solution behaviour, AIAA Paper 97-1850, 1997.
[39] Jameson, A., Aerodynamic design via control theory, J. sci. comput., 3, 33-260, (1988)
[40] A. Jameson, J. Reuther, Control theory based airfoil design using the Euler equations, AIAA Paper 94-4272-CP, 1994.
[41] A. Jameson, Optimum aerodynamic design using CFD and control theory, AIAA Paper 95-1729-CP, 1995.
[42] A. Jameson, J.J. Alonso, J.J. Reuther, L. Martinelli, J.C. Vassberg, Aerodynamic shape optimization techniques based on control theory, AIAA Paper 98-2538, 1998.
[43] Jameson, A.; Pierce, N.; Martinelli, L., Optimum aerodynamic design using the Navier-Stokes equations, J. theor. comp. fluid. mech., 10, 213-237, (1998) · Zbl 0912.76067
[44] D.I. Papadimitriou, K.C. Giannakoglou, A continuous adjoint method with objective function derivatives based on boundary integrals for inviscid and viscous flows, J. Comput. Fluids, in press. · Zbl 1177.76369
[45] EASY, The Evolutionary Algorithm SYstem. Available from: <http://velos0.ltt.mech.ntua.gr/EASY>.
[46] M. Karakasis, K.C. Giannakoglou, On the use of surrogate evaluation models in multi-objective evolutionary algorithms, in: ECCOMAS 2004, Jyvaskyla, Finland, 2004.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.