Design mining interacting wind turbines

Preen, Richard J.; Preen, Richard; Bull, Larry

Abstract

© 2016 by the Massachusetts Institute of Technology. An initial study has recently been presented of surrogate-assisted evolutionary algorithms used to design vertical-axis wind turbines wherein candidate prototypes are evaluated under fan-generated wind conditions after being physically instantiated by a 3D printer. Unlike other approaches, such as computational fluid dynamics simulations, no mathematical formulations were used and no model assumptions weremade. This paper extends that work by exploring alternative surrogate modelling and evolutionary techniques. The accuracy of various modelling algorithms used to estimate the fitness of evaluated individuals from the initial experiments is compared. The effect of temporally windowing surrogate model training samples is explored. A surrogateassisted approach based on an enhanced local search is introduced; and alternative coevolution collaboration schemes are examined.

• Journal Article Type: Article
• Online Publication Date: Mar 10, 2016
• Publication Date: Mar 1, 2016
• Deposit Date: Jun 22, 2015
• Publicly Available Date: Jun 10, 2016
• Journal: Evolutionary Computation
• Print ISSN: 1063-6560
• Electronic ISSN: 1530-9304
• Publisher: Massachusetts Institute of Technology Press (MIT Press)
• Peer Reviewed: Peer Reviewed
• Volume: 24
• Issue: 1
• Pages: 89-111
• DOI: https://doi.org/10.1162/EVCO_a_00144
• Keywords: 3-D printing, coevolution, fitness approximation, neural network, partnering
• Public URL: https://uwe-repository.worktribe.com/output/914728
• Publisher URL: http://dx.doi.org/10.1162/EVCO_a_00144
• Contract Date: Mar 11, 2016