Advertisement

PCA-Enhanced Metamodel-Assisted Evolutionary Algorithms for Aerodynamic Optimization

  • Varvara G. AsoutiEmail author
  • Stylianos A. Kyriacou
  • Kyriakos C. Giannakoglou
Part of the Springer Tracts in Mechanical Engineering book series (STME)

Abstract

This paper deals with evolutionary algorithms (EAs) assisted by surrogate evaluation models or metamodels (metamodel-assisted EAs, MAEAs) which are further accelerated by exploiting the principal component analysis (PCA) of the elite members of the evolving population. In each generation of the MAEA, PCA is used to (a) better guide the application of evolution operators and (b) train metamodels, in the form of radial basis functions networks, on patterns of smaller dimension. Note that the present MAEA relies upon “local” metamodels which are trained on-line, separately for each and every population member. Compared to previous works by the same authors, this paper proposes a new way to apply the PCA technique. In particular, the front of non-dominated solutions is divided into sub-fronts and the PCA is applied “locally” to each sub-front. The proposed method is demonstrated in multi-objective, constrained, aerodynamic optimization problems.

Keywords

Principal Component Analysis Design Variable Pareto Front Radial Basis Function Network Wind Turbine Blade 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

The authors express their thanks to Professors S. Voutsinas and V. Riziotis, NTUA, for providing the necessary data and evaluation software for the wind turbine aeroelastic optimization case and their constructive comments and suggestions. This study has been co-financed by the European Union (European Social Fund-ESF) and Greek national funds through the Operational Program “Education and Lifelong Learning” of the National Strategic Reference Framework (NSRF)—Research Funding Program: THALES. Investing in knowledge society through the European Social Fund.

References

  1. 1.
    Asouti VG, Giannakoglou KC (2009) Aerodynamic optimization using a parallel asynchronous evolutionary algorithm controlled by strongly interacting demes. Eng Optim 41:241–257MathSciNetCrossRefGoogle Scholar
  2. 2.
    Axler S (1997) Linear algebra done right. Springer, New YorkzbMATHCrossRefGoogle Scholar
  3. 3.
    Büche D, Schraudolph N, Koumoutsakos P (2005) Accelerating evolutionary algorithms with Gaussian process fitness function models. IEEE Trans Syst Man Cyber 35:183–194CrossRefGoogle Scholar
  4. 4.
    Drela M, Giles MB (1987) Viscous-inviscid analysis of transonic and low Reynolds number airfoils. J Am Inst Aeronaut Astronaut 25:1347–1355zbMATHCrossRefGoogle Scholar
  5. 5.
    Giannakoglou KC (2002) Design of optimal aerodynamic shapes using stochastic optimization methods and computational intelligence. Prog Aerosp Sci 38:43–76CrossRefGoogle Scholar
  6. 6.
    Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, Upper Saddle RiverzbMATHGoogle Scholar
  7. 7.
    Karakasis MK, Giannakoglou KC (2006) On the use of metamodel-assisted, multi-objective evolutionary algorithms. Eng Optim 38:941–957MathSciNetCrossRefGoogle Scholar
  8. 8.
    Karakasis MK, Giotis AP, Giannakoglou KC (2003) Inexact information aided, low-cost, distributed genetic algorithms for aerodynamic shape optimization. Int J Numer Methods Fluids 43:1149–1166zbMATHCrossRefGoogle Scholar
  9. 9.
    Kyriacou SA, Weissenberger S, Giannakoglou KC (2012) Design of a matrix hydraulic turbine using a metamodel-assisted evolutionary algorithm with PCA-driven evolution operators. Int J Math Model Numer Optim 3:45–63zbMATHGoogle Scholar
  10. 10.
    Kyriacou SA, Asouti VG, Giannakoglou KC (2014) Efficient PCA-driven EAs and metamodel-assisted EAs, with applications in turbomachinery. Eng Optim 46:895–911CrossRefGoogle Scholar
  11. 11.
    Ong YS, Lum KY, Nair PB, Shi DM, Zhang ZK(2003) Global convergence of unconstrained and bound constrained surrogate-assisted evolutionary search in aerodynamic shape design. Congr Evol Comput 3:1856–1863Google Scholar
  12. 12.
    Riziotis VA, Voutsinas SG (1997) Gast: a general aerodynamic and structural prediction tool for wind turbines. In: Proceedings of the EWEC-1997, DublinGoogle Scholar
  13. 13.
    Shyy W, Papila N, Vaidyanathan R, Tucker K (2001) Global design optimization for aerodynamics and rocket propulsion components. Prog Aerosp Sci 37:59–118CrossRefGoogle Scholar
  14. 14.
    Ulmer H, Streichert F, Zell A (2003) Evolution strategies assisted by Gaussian processes with improved pre-selection criterion. Congr Evol Comput 1:692–699Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Varvara G. Asouti
    • 1
    Email author
  • Stylianos A. Kyriacou
    • 1
  • Kyriakos C. Giannakoglou
    • 1
  1. 1.Parallel CFD & Optimization UnitNational Technical University of AthensAthensGreece

Personalised recommendations