Shape optimization with surface-mapped CPPNs

Richards, Daniel Courtney and Amos, Martyn (2017) Shape optimization with surface-mapped CPPNs. IEEE Transactions on Evolutionary Computation, 21 (3). pp. 391-407. ISSN 1089-778X

[thumbnail of Richards_ieee_tevc_shape_opt]
Preview
PDF (Richards_ieee_tevc_shape_opt)
Richards_ieee_tevc_shape_opt.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (8MB)

Abstract

Shape optimization techniques are becoming increasingly important in design and engineering. This growing significance reflects the need to exploit advances in digital fabrication technologies, and the desire to create new types of surface designs for various engineering applications. Evolutionary algorithms offer several key advantages for shape optimization, but they can also be restricted, especially as design problems scale up in size. A key challenge for evolutionary shape optimization is to overcome these challenges in order to apply evolutionary algorithms to large-scale, "real-world" engineering problems. This paper presents a new evolutionary approach to shape optimization using what we call "surface-mapped CPPNs". Our method outperforms a state-of-the-art gradient-based method on a simple benchmark problem, and scales well as degrees of freedom are added to the design problem. Our results demonstrate that surface-mapped CPPNs offer practical ways of approaching large-scale, real-world engineering problems with evolutionary algorithms, opening up exciting new opportunities for engineering design.

Item Type:
Journal Article
Journal or Publication Title:
IEEE Transactions on Evolutionary Computation
Additional Information:
©2017 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1712
Subjects:
?? COMPUTATIONAL THEORY AND MATHEMATICSTHEORETICAL COMPUTER SCIENCESOFTWARE ??
ID Code:
81567
Deposited By:
Deposited On:
14 Sep 2016 10:38
Refereed?:
Yes
Published?:
Published
Last Modified:
20 Sep 2023 00:55