A quality diversity study in EvoDevo processes for engineering design

Edgar Buchanan Berumen; Simon John Hickinbotham; Rahul Dubey; Imelda Friel; Andrew Colligan; Mark Price; Andy Tyrrell

A quality diversity study in EvoDevo processes for engineering design

Edgar Buchanan Berumen, Simon John Hickinbotham, Rahul Dubey, Imelda Friel, Andrew Colligan, Mark Price, Andy Tyrrell

Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results.

Original language	English
Title of host publication	IEEE World Congress on Computational Intelligence 2024
Publisher	IEEE
Publication status	Published - 5 Jul 2024
Event	IEEE World Congress on Computational Intelligence 2024 - Yokohama, Japan Duration: 30 Jun 2024 → 5 Jul 2024

Conference

Conference	IEEE World Congress on Computational Intelligence 2024
Abbreviated title	IEEE WCCI 2024
Country/Territory	Japan
City	Yokohama
Period	30/06/24 → 5/07/24

Bibliographical note

This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.

Keywords

EvoDevo
Generative Design
structural engineering
quality diversity
Neural networks

Access to Document

EBB__CEC_2024
This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.
Accepted author manuscript, 1.8 MBLicence: CC BY

A quality diversity study in EvoDevo processes for engineering design
Buchanan Berumen, E. (Creator), Hickinbotham, S. J. (Creator), Dubey, R. (Creator), Friel, I. (Creator), Colligan, A. (Creator), Price, M. (Creator) & Tyrrell, A. (Creator), University of York, 15 Mar 2024
DOI: 10.15124/cda83da3-f849-4ce4-8135-a137cd52ade2
Dataset

Cite this

@inproceedings{aabdebb3b41d4ca4b704c4d88df9c5f1,

title = "A quality diversity study in EvoDevo processes for engineering design",

abstract = "For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results.",

keywords = "EvoDevo, Generative Design, structural engineering, quality diversity, Neural networks",

author = "{Buchanan Berumen}, Edgar and Hickinbotham, {Simon John} and Rahul Dubey and Imelda Friel and Andrew Colligan and Mark Price and Andy Tyrrell",

note = "This is an author-produced version of the published paper. Uploaded in accordance with the University{\textquoteright}s Research Publications and Open Access policy. ; IEEE World Congress on Computational Intelligence 2024, IEEE WCCI 2024 ; Conference date: 30-06-2024 Through 05-07-2024",

year = "2024",

month = jul,

day = "5",

language = "English",

booktitle = "IEEE World Congress on Computational Intelligence 2024",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - A quality diversity study in EvoDevo processes for engineering design

AU - Buchanan Berumen, Edgar

AU - Hickinbotham, Simon John

AU - Dubey, Rahul

AU - Friel, Imelda

AU - Colligan, Andrew

AU - Price, Mark

AU - Tyrrell, Andy

N1 - This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.

PY - 2024/7/5

Y1 - 2024/7/5

N2 - For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results.

AB - For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results.

KW - EvoDevo

KW - Generative Design

KW - structural engineering

KW - quality diversity

KW - Neural networks

M3 - Conference contribution

BT - IEEE World Congress on Computational Intelligence 2024

PB - IEEE

T2 - IEEE World Congress on Computational Intelligence 2024

Y2 - 30 June 2024 through 5 July 2024

ER -

A quality diversity study in EvoDevo processes for engineering design

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Datasets

A quality diversity study in EvoDevo processes for engineering design

Cite this