Skip to Main content Skip to Navigation

Model Reduction and Adaption of Optimum-shape design in aerodynamics by Neural Networks

Marios K. Karakasis 1 Jean-Antoine Desideri 1
1 OPALE - Optimization and control, numerical algorithms and integration of complex multidiscipline systems governed by PDE
CRISAM - Inria Sophia Antipolis - Méditerranée , JAD - Laboratoire Jean Alexandre Dieudonné : UMR6621
Abstract : A method to reduce the dimension of the initial search space in an optimizati- on problem is proposed. The method consists in the identification of the sub-space with the greatest impact on the cost or fitness function. Optimization is restricted in this sub-space, achieving, thus, a considerable reduction of the computational cost, due to more effective exploration. The Model Reduction is the result of mathematical analysis performed on approximations of the cost/fitness function supplied by Artificial Neural Networks, trained during the optimization process. The Model Reduction is coupled with Genetic Algorithms and performed in a self-adaptive way during the genetic evolution.
Document type :
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Rapport de Recherche Inria <>
Submitted on : Tuesday, May 23, 2006 - 7:45:37 PM
Last modification on : Wednesday, October 14, 2020 - 4:24:26 AM
Long-term archiving on: : Sunday, April 4, 2010 - 10:52:27 PM


  • HAL Id : inria-00072085, version 1


Marios K. Karakasis, Jean-Antoine Desideri. Model Reduction and Adaption of Optimum-shape design in aerodynamics by Neural Networks. [Research Report] RR-4503, INRIA. 2002. ⟨inria-00072085⟩



Record views


Files downloads