EvoDevo: Bioinspired Generative Design via Evolutionary Graph-Based Development

Authors: Farajollah Tahernezhad‑Javazm†, Andrew R. Colligan†, Imelda Friel, Simon J. Hickinbotham, Paul Goodall, Edgar Buchanan Berumen, Mark Price, Trevor T. Robinson & Andy M. Tyrrell

Journal: Data-Driven Intelligent Modeling and Optimization Algorithms for Industrial Processes: 2nd Edition

Proposes an evolutionary development approach to generative design where graph neural network agents are evolved to optmize truss structures.

                              
@inproceedings{buchanan2024qd
                              
 title={EvoDevo: Bioinspired Generative Design via Evolutionary Graph-Based Development},
                              
 author={Farajollah Tahernezhad‑Javazm†, Andrew R. Colligan†, Imelda Friel, Simon J. Hickinbotham, Paul Goodall, Edgar Buchanan Berumen, Mark Price, Trevor T. Robinson & Andy M. Tyrrell},
                              
 booktitle={Data-Driven Intelligent Modeling and Optimization Algorithms for Industrial Processes: 2nd Edition},
                              
 year={2025},
                              
 doi={https://doi.org/10.3390/a18080467}
                              
}
                            

A Quality Diversity Study in EvoDevo Processes for Engineering Design

Authors: Edgar Buchanan, Simon J. Hickinbotham, Rahul Dubey, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell

Conference: IEEE World Congress on Computational Intelligence, 2024

Study of the effects of quality and diversity (QD) algorithms in Evolutionary Development (EvoDevo) processes for engineering design.

                              
@inproceedings{buchanan2024qd
                              
 title={A Quality Diversity Study in EvoDevo Processes for Engineering Design},
                              
 author={Edgar Buchanan, Simon J. Hickinbotham, Rahul Dubey, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell},
                              
 booktitle={IEEE World Congress on Computational Intelligence},
                              
 year={2024},
                              
 doi={https://doi.org/10.15124/cda83da3-f849-4ce4-8135-a137cd52ade2}
                              
}
                            

Evolving Novel Gene Regulatory Networks for Structural Engineering Designs

Authors: Rahul Dubey, Simon J. Hickinbotham, Andrew R. Colligan, Imelda Friel, Edgar Buchanan, Mark Price & Andrew M. Tyrrell

Journal: Artificial Life, 2024

Exploration of different gene regulatory networks (GRNs) for the optimization of structural engineering designs in an Evolutionary-Development algorithm.

                              
@inproceedings{dubey2024grn
                              
 title={Evolving Novel Gene Regulatory Networks for Structural Engineering Designs},
                              
 author={Rahul Dubey, Simon J. Hickinbotham, Andrew R. Colligan, Imelda Friel, Edgar Buchanan, Mark Price & Andrew M. Tyrrell},
                              
 booktitle={Artificial Life},
                              
 year={2024}
                              
}
                            

Investigation of Starting Conditions in Generative Processes for the Design of Engineering Structures

Authors: Edgar Buchanan, Rahul Dubey, Simon J. Hickinbotham, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell

Conference: Proceedings of the IEEE Symposium Series on Computational Intelligence, SSCI, 2023

A study into how the initial structure of an EvoDevo process influences the ability to learn development rules.

                              
@inproceedings{buchanan2023is
                              
 title={Investigation of Starting Conditions in Generative Processes for the Design of Engineering Structures},
                              
 author={Edgar Buchanan, Rahul Dubey, Simon J. Hickinbotham, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell},
                              
 booktitle={2023 IEEE Symposium Series on Computational Intelligence (SSCI)},
                              
 year={2023},
                              
 doi={http://dx.doi.org/10.1109/SSCI52147.2023.10371945}
                              
}
                            

Theory of Evolutionary Systems Engineering

Authors: Simon J. Hickinbotham, Rahul Dubey, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell

Conference: Proceedings of the IEEE Symposium Series on Computational Intelligence, SSCI, 2023

A theory for the use of the von Neumann's Universal Constructor Architecture (UCA) as common language between multidisciplinary applications for evolving engineering systems.

                              
@inproceedings{hickinbotham2023ese
                              
 title={Theory of Evolutionary Systems Engineering},
                              
 author={Simon J. Hickinbotham, Rahul Dubey, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell},
                              
 booktitle={2023 IEEE Symposium Series on Computational Intelligence (SSCI)},
                              
 year={2023},
                              
 doi={http://dx.doi.org/10.1109/SSCI52147.2023.10371943}
                              
}
                            

A Bio-Inspired Evolution-Development Method for Modelling and Optimisation of Buffer Allocation in Unreliable Serial Production Line

Authors: Zhiwei Zhao, Paul Goodall, Andrew West, Andrew R. Colligan, Imelda Friel, Simon J. Hickinbotham, Mark Price & Yan Jin

Conference: 3rd International Conference on Mechanical, Aerospace and Automotive Engineering (CMAAE 2023), 2023

A bio-inspired evolutionary-development approach for modelling and optimizing buffer allocations in a production line.

                              
@inproceedings{zhao2023ba
                              
 title={A Bio-Inspired Evolution-Development Method for Modelling and Optimisation of Buffer Allocation in Unreliable Serial Production Line},
                              
 author={Zhiwei Zhao, Paul Goodall, Andrew West, Andrew R. Colligan, Imelda Friel, Simon J. Hickinbotham, Mark Price & Yan Jin},
                              
 booktitle={3rd International Conference on Mechanical, Aerospace and Automotive Engineering (CMAAE 2023)},
                              
 year={2023}
                              
}
                            

Evolving Design Modifiers

Authors: Simon J. Hickinbotham, Rahul Dubey, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell

Conference: Proceedings of the IEEE Symposium Series on Computational Intelligence, SSCI, 2022

Applying the biological concept of Evolutionary Developmental (EvoDevo) to evolve growth rules via neural networks to parameter truss structures for multi-objective problems.

                              
@inproceedings{hickinbotham2022edm
                              
 title={Evolving Design Modifiers},
                              
 author={Simon J. Hickinbotham, Rahul Dubey, Imelda Friel, Andrew R. Colligan, Mark Price & Andrew M. Tyrrell},
                              
 booktitle={2022 IEEE Symposium Series on Computational Intelligence (SSCI)},
                              
 year={2022},
                              
 doi={10.1109/SSCI51031.2022.10022087}
                              
}
                            

Hierarchical CADNet: Learning from B-Reps for Machining Feature Recognition

Authors: Andrew R. Colligan, Trevor T. Robinson, Declan C. Nolan, Yang Hua & Weijuan Cao

Journal: Computer-Aided Design, 2022

Proposed a graph convolutional neural network architecture for learning from B-Rep CAD models and a complex CAD model dataset called MFCAD++ with labeled machining features.

                              
@inproceedings{colligan2022hiercadnet
                              
 title={Hierarchical CADNet: Learning from B-Reps for Machining Feature Recognition},
                              
 author={Andrew R. Colligan, Trevor T. Robinson, Declan C. Nolan, Yang Hua & Weijuan Cao},
                              
 booktitle={Computer-Aided Design},
                              
 year={2022},
                              
 doi={https://doi.org/10.1016/j.cad.2022.103226},
                              
}
                            

Point Cloud Dataset Creation for Machine Learning on CAD Models

Authors: Andrew R. Colligan, Trevor T. Robinson, Declan C. Nolan & Yang Hua

Journal: Computer-Aided Design and Applications, 2021

A method of generating labelled point clouds from B-Rep CAD models suitable for machine learning applications.

                              
@inproceedings{colligan2021pc
                              
 title={Point Cloud Dataset Creation for Machine Learning on CAD Models},
                              
 author={Andrew R. Colligan, Trevor T. Robinson, Declan C. Nolan & Yang Hua},
                              
 booktitle={Computer-Aided Design and Applications},
                              
 year={2021},
                              
 doi={https://doi.org/10.14733/cadaps.2021.760-771},
                              
}
                            

Graph Representation of 3D CAD Models for Machining Feature Recognition with Deep Learning

Authors: Weijuan Cao, Trevor T. Robinson, Yang Hua, Flavien Boussuge, Andrew R. Colligan & Wanbin Pan

Conference: ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, 2020

First approach to propose the use of graph neural networks to learn from B-Rep CAD models. Introduced the benchmark MFCAD dataset for machining feature recognition.

                              
@inproceedings{cao2020
                              
 title={Graph Representation of 3D CAD Models for Machining Feature Recognition with Deep Learning},
                              
 author={Weijuan Cao, Trevor T. Robinson, Yang Hua, Flavien Boussuge, Andrew R. Colligan & Wanbin Pan},
                              
 booktitle={ASME 2020 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference},
                              
 year={2020},
                              
 doi={https://doi.org/10.1115/DETC2020-22355},
                              
}
                            

Generative Design System

A prototype of generative design system using neuroevolution. This system allowed users to optimize 2D and 3D truss structures for multi-objective optimization problems. Neural network agents are evolved to optimize design solutions allowing for re-deployment to other similar design problems. I built a 3D modeling environment using Flask, React and React Three Fiber allowing users to generate truss structures and boundary conditions. After training, users could select design solutions from a Pareto chart and instantly view high resolution 3D models of them.

Stiffened Plate Generative Design

This project is a generative design methodology for stiffened plates. Using neuroevolution, agents are evolved to respond to simulation states with the goal of minimizing the total volume and displacement of the initial design. The agents' action spaces control the width of stiffeners reinforcing the plate. The state space includes the displacement and volume of the stiffeners and the displacement of the plate sections. The state features are found using the Finite Element Analysis (FEA) solver Calculix, where the stiffeners are represented as beam elements and the plate sections as shell elements.

Signed Distance Function (SDF) Experiments

A website of different experiments using signed distance functions (SDFs). The website uses three.js and Open GL Shader Language (GLSL) for rendering SDF models using ray marching.

Relational Learning for CAD Models

Code from a MEng Master's project by David Philpott in which I was a supervisor. The repo contains open-source code for using relational learning to cluster together similar entities in CAD models.

Micro CT Scan to Triangular Mesh

Experimental code for generating triangular meshes from micro CT scans. The code was used to generate meshes of titanium lattices from micro CT scan data.

FeatureNet: TensorFlow 2 Implementation

A TensorFlow 2 implementation of the FeatureNet paper. This approach can classify and segment machining features in CAD models by converting the B-Rep to voxel models and using 3D convolutional neural networks.