On design mining: Coevolution and Surrogate models

Preen, R. and Bull, L. (2017) On design mining: Coevolution and Surrogate models. Artificial Life, 23 (2). pp. 186-205. ISSN 1064-5462 Available from: http://eprints.uwe.ac.uk/31963

This is the latest version of this item.

[img]
Preview
PDF - Published Version
Available under License Creative Commons Attribution 3.0.

1MB

Publisher's URL: http://www.mitpressjournals.org/doi/full/10.1162/A...

Abstract/Description

Design mining is the use of computational intelligence techniques to iteratively search and model the attribute space of physical objects evaluated directly through rapid prototyping to meet given objectives. It enables the exploitation of novel materials and processes without formal models or complex simulation. In this article, we focus upon the coevolutionary nature of the design process when it is decomposed into concurrent sub-design-threads due to the overall complexity of the task. Using an abstract, tunable model of coevolution, we consider strategies to sample subthread designs for whole-system testing and how best to construct and use surrogate models within the coevolutionary scenario. Drawing on our findings, we then describe the effective design of an array of six heterogeneous vertical-axis wind turbines.

Item Type:Article
Uncontrolled Keywords:3D printing, coevolution, shape optimisation, surrogate models, turbine, wind energy
Faculty/Department:Faculty of Environment and Technology > Department of Computer Science and Creative Technologies
ID Code:31963
Deposited By: Dr R. Preen
Deposited On:02 Jun 2017 10:23
Last Modified:23 Jun 2017 02:57

Available Versions of this Item

Request a change to this item

Total Document Downloads in Past 12 Months

Document Downloads

Total Document Downloads

More statistics for this item...