Multi-Fidelity Aerodynamic Dataset Generation of a Fighter Aircraft with a Deep Neural-Genetic Network

Millidere M., Gomec F. S., Kurt H. B., AKGÜL F.

AIAA Aviation and Aeronautics Forum and Exposition, AIAA AVIATION Forum 2021, Virtual, Online, 2 - 06 August 2021 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.2514/6.2021-3007
  • City: Virtual, Online
  • Middle East Technical University Affiliated: Yes


© 2021, American Institute of Aeronautics and Astronautics Inc.. All rights reserved.This paper is a follow-up study on prior research work on multi-fidelity aerodynamic dataset generation. The prior work studied a comparison of modified Variable-Complexity Modelling and co-Kriging methods applied to F-16 fighter aircraft. In this research, the multi-fidelity deep neural-genetic network method is introduced. The results provide evidence that the deep neural-genetic network method in this paper can be employed in dealing with the aerodynamic data fusion problem.