Hybridizing genetic algorithm with artificial neural network in the aerodynamic optimization of the forward swept wing


Vatandas E.

51st AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, Orlando, FL, United States Of America, 12 - 15 April 2010 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Orlando, FL
  • Country: United States Of America
  • Keywords: 3-D aerodynamic optimization, Artificial neural network, Hybrid techniques
  • Istanbul Gelisim University Affiliated: No

Abstract

The aim of this work is to outline an effective hybrid technique for aerodynamic optimization of forward swept wing (FSW) by using artificial neural network. Artificial Neural Network (ANN) is combined with the genetic optimization of a forward swept wing. It can be observed that, this technique is much more robust than Genetic Algorithm (GA) only methods. By using the method presented in this study, the drag coefficient of the forward swept wing can be reduced 35 percent faster than the classical GA reached in 500 calculations. It has been observed that, in the previous forward swept wing optimization with classical GA technique, the taper ratio has tendency to increase, while it is decreasing in the backward swept wing optimization. However in the hybrid method used in this work, taper ratio stays around its original value. Copyright © 2010 by the American Institute of Aeronautics and Astronautics, Inc.