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.

The application process has two stages; supervisors nominate one candidate to go 
forward to a panel interview which will award funding to 4 of the 8 QuEX 
projects being advertised. Further details and link to the application form are 
on the official web site at https://www.exeter.ac.uk/study/funding/award/?
id=5153