Title: On the use of multiple surrogates within a differential evolution procedure for high-lift airfoil design
Authors: Ioannis K. Nikolos
Addresses: Department of Production Engineering and Management, Technical University of Crete, University Campus, 73100, Chania, Greece
Abstract: In this work a differential evolution (DE) algorithm is combined with two artificial neural networks (ANNs), which are used as surrogate models to decrease the computational effort of the optimisation procedure. The surrogate models can be used either separately or in combination, in an attempt to automatically select the most effective one in each generation of the evolutionary algorithm. Although the focus is on the use of ANNs as surrogate models, other types of models are also reviewed and their use in combination with evolutionary algorithms (EAs) is discussed. The proposed procedure is used to optimise the design of a high-lift, low Reynolds number airfoil, with respect to its performance in a wide range of different angles of attack. The candidate airfoil designs are automatically produced by deforming a reference airfoil, using the freeform deformation (FFD) procedure. The results of the optimisation procedure, with different combinations of the embedded surrogate models, are discussed, providing useful conclusions regarding the cooperation of multiple surrogates with EAs.
Keywords: multiple surrogate models; engineering design optimisation; artificial neural networks; ANNs; differential evolution; airfoil optimisation; high-lift airfoil design; freeform deformation; FFD; evolutionary algorithms.
International Journal of Advanced Intelligence Paradigms, 2013 Vol.5 No.4, pp.319 - 341
Received: 08 Feb 2013
Accepted: 30 Mar 2013
Published online: 30 Jul 2014 *