Tahernezhadjavazm, Fred, Colligan, Andrew, Friel, Imelda et al. (6 more authors) (Accepted: 2025) EvoDevo: Bioinspired Generative Design via Evolutionary Graph-based Development. Algorithms. ISSN 1999-4893 (In Press)
Abstract
Automated generative design is increasingly used across engineering disciplines 1 to accelerate innovation and reduce costs. Generative design offers the prospect of simplifying manual design tasks by exploring the efficacy of solutions automatically. However, existing generative design frameworks rely heavily on expensive optimisation procedures and often produce customized solutions, lacking reusable generative rules that transfer across different problems. This work presents a bioinspired generative design algorithm utilising the concept of evolutionary development (EvoDevo). This evolves a set of developmental rules that can be inspired to apply for different engineering problems to rapidly develop designs without the need to run full optimisation procedures. In this approach, an initial design is decomposed into simple entities called cells that each independently control their local growth over a development cycle. In biology, the growth of cells is governed by a gene regulatory network (GRN), but there is no single widely-accepted model of this for artificial systems. The GRN responds to the state of the cell induced by external stimuli from its environment, which in this application is the loading regime on a bridge truss structure (but can be generalised to any engineering structure). Two models of GRN are investigated: graph neural networks (GNNs) and graph-based cartesian genetic programming (CGP). Both GRN models are evolved using a novel genetic search algorithm for parameter search, which can be re-used for other design problems. It is revealed that the CGP-based method produces results similar to those obtained using GNN-based methods, while offering more interpretability. In this work, it is shown that this EvoDevo approach is able to produce near-optimal truss structures via growth mechanisms such as moving vertices or changing edges features. The technique can be set up to provide design automation for a range of engineering design tasks.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Keywords: | Generative Design,Evolutionary Development,Gene Regulatory Network,Neuroevolution,Graph Neural Network,Cartesian Genetic Programming,Genetic Algorithm |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Electronic Engineering (York) |
Funding Information: | Funder Grant number EPSRC EP/V007335/1 |
Depositing User: | Pure (York) |
Date Deposited: | 21 Jul 2025 14:00 |
Last Modified: | 21 Jul 2025 14:00 |
Status: | In Press |
Refereed: | Yes |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:229440 |
Download
Filename: Fred_s_algorithms_paper-3727199-peer-review-r1.pdf
Description: Fred's algorithms paper-3727199-peer-review-r1
Licence: CC-BY 2.5
