On the use of multiple surrogates within a differential evolution procedure for high-lift airfoil design
by Ioannis K. Nikolos
International Journal of Advanced Intelligence Paradigms (IJAIP), Vol. 5, No. 4, 2013

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.

Online publication date: Wed, 30-Jul-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Advanced Intelligence Paradigms (IJAIP):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com