Design mining interacting wind turbines

Preen, R. and Bull, L. (2016) Design mining interacting wind turbines. Evolutionary Computation, 24 (1). pp. 89-111. ISSN 1063-6560 Available from: http://eprints.uwe.ac.uk/25798

[img]
Preview
PDF - Published Version
Available under License All Rights Reserved.

891kB

Publisher's URL: http://dx.doi.org/10.1162/EVCO_a_00144

Abstract/Description

An initial study of surrogate-assisted evolutionary algorithms used to design verticalaxis wind turbines wherein candidate prototypes are evaluated under fan generated wind conditions after being physically instantiated by a 3D printer has recently been presented. Unlike other approaches, such as computational fluid dynamics simulations, no mathematical formulations were used and no model assumptions were made. 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.

Item Type:Article
Uncontrolled Keywords:3-D printing, coevolution, fitness approximation, neural network, partnering
Faculty/Department:Faculty of Environment and Technology > Department of Computer Science and Creative Technologies
ID Code:25798
Deposited By: Dr R. Preen
Deposited On:22 Jun 2015 08:09
Last Modified:11 Jun 2016 15:18

Request a change to this item

Total Document Downloads in Past 12 Months

Document Downloads

Total Document Downloads

More statistics for this item...