Supervisors

Professor Gavin Tabor, Department of Engineering, University of Exeter

Associate Professor Marcus Gallagher, School of Electrical Engineering & Computer Science, University of Queensland

Additional Supervisors:

Professor Jonathan Fieldsend, Department of Computer Science, University of Exeter

Join a world-leading, cross-continental research team

The University of Exeter and the University of Queensland are seeking exceptional students to join a world-leading, cross-continental research team tackling major challenges facing the world’s population in global sustainability and wellbeing as part of the QUEX Institute. The joint PhD programme provides a fantastic opportunity for the most talented doctoral students to work closely with world-class research groups and benefit from the combined expertise and facilities offered at the two institutions, with a lead supervisor within each university. This prestigious programme provides full tuition fees, stipend, travel funds and research training support grants to the successful applicants.  The studentship provides funding for up to 42 months (3.5 years) for both home and international students.

Eight generous, fully-funded studentships are available for the best applicants, four offered by the University of Exeter and four by the University of Queensland. This select group will spend at least one year at each University and will graduate with a joint degree from the University of Exeter and the University of Queensland.

Find out more about the PhD studentships click here

Successful applicants will have a strong academic background and track record to undertake research projects based in one of the three themes of:  Healthy Living, Global Environmental Futures and Digital Worlds and Disruptive Technologies.

The closing date for applications is mid-day Friday June 28th 2024 (BST), with interview to be w/c 29th July 2024 (tbc). The start date is expected to be Monday January 6th 2025.

Please note that of the eight Exeter led projects advertised, we expect that up to four studentships will be awarded.

Supervisors

Exeter Academic Lead: Professor Gavin Tabor

Queensland Academic Lead: Associate Professor Marcus Gallagher

THEME - Digital Worlds & Disruptive Technologies

Project Description

Computational Fluid Dynamics (CFD) is a key element of modern engineering R&D and of digital engineering processes in Industry4.0. In a CFD code, the fundamental equations of fluid flow are discretised and solved numerically; this process of discretisation involves splitting the domain of interest into subdomains called cells, which make up the mesh covering the domain. The process of creating this mesh, referred to as meshing, is one of the most critical steps in the CFD workflow, as the quality of the numerical solution (and sometimes even the ability of the CFD code to find a solution) can be very strongly dependent on the quality of the mesh. At the same time, the meshing process itself is complex and often involves considerable human time and expertise to accomplish. Automated meshing programmes (such as snappyHexMesh, sHM, from the OpenFOAM suite of CFD codes) have been developed, but these simply automate the construction of the mesh from a large number of input parameters; finding the correct inputs is still complex and (human-)time consuming. 

New developments in AI technologies present the potential to revolutionise the meshing process however. AI technologies such as Artificial Neural Networks (ANNs) are good at discovering and reproducing human expertise, and could be used to “learn” what makes a good mesh. Machine Learning (ML, a branch of AI) can be used to iteratively improve mesh quality, based on commonly used (and easy to evaluate) mesh quality metrics – essentially automating and improving on the typical ad hoc meshing and re-meshing cycle used by human CFD engineers. Finally, automated mesh generators such as sHM use text-based input files that can be reproduced by Large Language Models (LLMs) such as ChatGPT. This presents a completely new and disruptive methodology to create the input files for CFD simulation, using carefully honed query terms and re-trained LLMs. The aim of the proposed PhD project is to investigate all these aspects of AI applied to meshing, which represents a truly disruptive technology for this important engineering tool.

Background and Context. CFD is a critical component of modern engineering, and has also found many applications in areas of science and medicine. CFD codes typically use the Finite Volume (FV) method, in which the equations to be solved are discretised on a mesh comprising numerous polyhedral cells. This approach gives enormous flexibility to suit the mesh to the local flow conditions, however the quality of the solution can be critically dependent on the quality of the mesh. Meshing is commonly regarded as the single most important, challenging and human-time consuming task in the CFD workflow. A lot of meshing activity relies on simple mesh quality metrics, rules of thumb, experience, and repetition of the process in a human centered optimisation process. This has proved challenging to improve on through conventional approaches, but of course these are characteristics of problems that are susceptable to the modern tools of AI and Machine Learning!

Aims and Objectives. Overall there are two core aims of the project. The first is to apply Machine Learning optimisation techniques to meshing, to develop automated tools that could be used to iteratively improve mesh quality, “learn” strategies to mesh key types of geometry, and ultimately take over the whole meshing provess. The second core aim is to use Large Language Models (LLMs) such as ChatGPT to revolutionise the process of mesh development and case setup. Proximate objectives of the project include conducting a survey of meshing methodologies across a range of users and disciplines to identify common challenges and solutions that might be duplicated by AI.

Approaches and Methods. Mesh quality can be optimised through at least two AI-inspired methodologies. The first is to treat it as an optimisation problem; commonly accepted metrics can be used to rank different meshes, and techniques such as Bayesian Optimisation can be used to iteratively improve mesh quality. Another approach is to use Artificial Neural Networks (ANNs) to “learn” how to build a good mesh. With the case setup; many mesh input formats use plain text, similar to computer code; input files for OpenFOAM in particular were included in the training sets for ChatGPT and so that tool can already generate input files for the code. We aim to extend this through retraining LLMs to ensure robust and correct outputs. OpenFOAM will be used here as it is an open source CFD code with an estimated 50,000 users; it is non-proprietory, and can be easily modified to integrate with optimisation and ANN tools.

Expertise, Facilities and Capabilities. The team brings together complementary skills covering all aspects of the work. Prof Tabor is an international expert in CFD and OpenFOAM, and has extensive connections in industry, which will be leveraged to support the project. He has worked closely with Prof Fieldsend, whose research interests include multiobjective optimisation and application of machine learning techniques to computational modelling. In Queensland Prof Gallagher brings in research interests in AI, Optimisation and Machine Learning; including cross-disciplinary collaborations and real-world applications of AI techniques.

Entry requirements

Applicants should be highly motivated and have, or expect to obtain, either a first or upper-second class BA or BSc (or equivalent) in a relevant discipline.

If English is not your first language you will need to meet the English language requirements and provide proof of proficiency. Click here for more information and a list of acceptable alternative tests.

How to apply

Apply now

You will be asked to submit some personal details and upload a full CV, supporting statement, academic transcripts and details of two academic referees. Your supporting statement should outline your academic interests, prior research experience and reasons for wishing to undertake this project, with particular reference to the collaborative nature of the partnership with the University of Queensland, and how this will enhance your training and research.

Interview notifications will be date TBC.

Please quote reference 5153 on your application and in any correspondence about this studentship.

Owing to essential maintenance, our system will be unavailable between 17:00 BST on Thursday 27th June and 09:00 BST Monday 1st July 2024.

The application deadline has therefore be extended until 12:00 BST on Wednesday 3rd July.

Please accept our apologies for any inconvenience caused.

Summary