Efficient aerodynamic design through evolutionary programming and support vector regression algorithms

The shortening of the design cycle and the increase of the performance are nowadays the main challenges in aerodynamic design. The use of evolutionary algorithms (EAs) seems to be appropriate in a preliminary phase, due to their ability to broadly explore the design space and obtain global optima. Evolutionary algorithms have been hybridized with metamodels (or surrogate models) in several works published in the last years, in order to substitute expensive computational fluid dynamics (CFD) simulations. In this paper, an advanced approach for the aerodynamic optimization of aeronautical wing profiles is proposed, consisting of an evolutionary programming algorithm hybridized with a support vector regression algorithm (SVMr) as a metamodel. Specific issues as precision, dataset training size and feasibility of the complete approach are discussed and the potential of global optimization methods (enhanced by metamodels) to achieve innovative shapes that would not be achieved with traditional methods is assessed.

[1]  Kyriakos C. Giannakoglou,et al.  A grid-enabled asynchronous metamodel-assisted evolutionary algorithm for aerodynamic optimization , 2009, Genetic Programming and Evolvable Machines.

[2]  Gene Hou,et al.  Overview of Sensitivity Analysis and Shape Optimization for Complex Aerodynamic Configurations , 1999 .

[3]  Ataur Rahman,et al.  Prediction of aerodynamic characteristics of an aircraft model with and without winglet using fuzzy logic technique , 2011 .

[4]  Kelly Cohen,et al.  Nonlinear estimation of transient flow field low dimensional states using artificial neural nets , 2012, Expert Syst. Appl..

[5]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[6]  Meng-Sing Liou,et al.  Progress in design optimization using evolutionary algorithms for aerodynamic problems , 2010 .

[7]  Kyriakos C. Giannakoglou,et al.  Design of optimal aerodynamic shapes using stochastic optimization methods and computational intelligence , 2002 .

[8]  M. Drela.  XFOIL: An Analysis and Design System for Low Reynolds Number Airfoils , 1989 .

[9]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[10]  Kyriakos C. Giannakoglou,et al.  A multilevel approach to single- and multiobjective aerodynamic optimization , 2008 .

[11]  Pei-Wen Chen,et al.  Estimating the shift size in the process mean with support vector regression and neural networks , 2011, Expert Syst. Appl..

[12]  Bento Silva de Mattos,et al.  Aerodynamic Coefficient Prediction of Airfoils Using Neural Networks , 2008 .

[13]  Kyriakos C. Giannakoglou,et al.  CFD-based analysis and two-level aerodynamic optimization on Graphics Processing Units , 2010 .

[14]  K. Giannakoglou,et al.  Aerodynamic shape design using evolutionary algorithms and new gradient-assisted metamodels , 2006 .

[15]  Hui Jiang,et al.  Grey relational grade in local support vector regression for financial time series prediction , 2012, Expert Syst. Appl..

[16]  Sancho Salcedo-Sanz,et al.  Short term wind speed prediction based on evolutionary support vector regression algorithms , 2011, Expert Syst. Appl..

[17]  Xin Yao,et al.  Evolutionary programming made faster , 1999, IEEE Trans. Evol. Comput..

[18]  Alan M. Shih,et al.  Development of an efficient aerodynamic shape optimization framework , 2009, Math. Comput. Simul..

[19]  Yaochu Jin,et al.  A comprehensive survey of fitness approximation in evolutionary computation , 2005, Soft Comput..

[20]  Zhong-Hua Han,et al.  A New Cokriging Method for Variable-Fidelity Surrogate Modeling of Aerodynamic Data , 2010 .

[21]  Luca Di Angelo,et al.  Neural Network Based Geometric Primitive for Airfoil Design , 2003, Shape Modeling International.

[22]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[23]  J. Pereira,et al.  Surrogate models based on function and derivative values for aerodynamic global optimization , 2010 .

[24]  B. Schölkopf,et al.  Asymptotically Optimal Choice of ε-Loss for Support Vector Machines , 1998 .

[25]  Sancho Salcedo-Sanz,et al.  Improving the training time of support vector regression algorithms through novel hyper-parameters search space reductions , 2009, Neurocomputing.

[26]  Pei Li,et al.  MANUAL AERODYNAMIC OPTIMIZATION OF AN OBLIQUE FLYING WING , 1998 .

[27]  Régis Duvigneau,et al.  Low cost PSO using metamodels and inexact pre-evaluation: Application to aerodynamic shape design , 2009 .

[28]  Kyriakos C. Giannakoglou,et al.  Grid enabled, hierarchical distributed metamodel-assisted evolutionary algorithms for aerodynamic shape optimization , 2008, Future Gener. Comput. Syst..

[29]  David B. Fogel,et al.  An introduction to simulated evolutionary optimization , 1994, IEEE Trans. Neural Networks.

[30]  A. Jahangirian,et al.  Aerodynamic shape optimization using efficient evolutionary algorithms and unstructured CFD solver , 2011 .