Skip to main content

Research Repository

Advanced Search

On Design Mining: Coevolution and Surrogate Models

Preen, Richard; Bull, Larry

On Design Mining: Coevolution and Surrogate Models Thumbnail


Authors

Lawrence Bull Larry.Bull@uwe.ac.uk
School Director (Research & Enterprise) and Professor



Abstract

© 2017 Massachusetts Institute of Technology. Published under a Creative Commons Attribution 3.0 Unported (CC BY 3.0) license. 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.

Citation

Preen, R., & Bull, L. (2017). On Design Mining: Coevolution and Surrogate Models. Artificial Life, 23(2), 186-205. https://doi.org/10.1162/ARTL_a_00225

Journal Article Type Article
Acceptance Date Feb 2, 2017
Publication Date May 1, 2017
Deposit Date Feb 8, 2017
Publicly Available Date Mar 28, 2024
Journal Artificial Life
Print ISSN 1064-5462
Electronic ISSN 1530-9185
Publisher Massachusetts Institute of Technology Press (MIT Press)
Peer Reviewed Peer Reviewed
Volume 23
Issue 2
Pages 186-205
DOI https://doi.org/10.1162/ARTL_a_00225
Keywords 3D printing, coevolution, shape optimisation, surrogate models, turbine, wind energy
Public URL https://uwe-repository.worktribe.com/output/895931
Publisher URL http://www.mitpressjournals.org/doi/full/10.1162/ARTL_a_00225
Additional Information Additional Information : The dataset for this study is available from the UWE Research Data Repository: http://researchdata.uwe.ac.uk/166

Files





You might also like



Downloadable Citations