Artificial Intelligence-Assisted Modelling of High-Rate Ductile Fracture

When materials such as metal are subjected to sudden loads, for example, during an explosion, they can bend and stretch before breaking. This type of failure is difficult to predict because many processes occur simultaneously within the material.

This PhD project aims to improve how we model and understand material failure. You will use state-of-the-art computational modelling techniques to develop more accurate computer simulations and apply Artificial Intelligence (AI) to enhance their precision and reliability.

Submit an informal enquiry Apply for this project HetSys training programme

Supervisors

Primary: Dr Emmanouil Kakouris, Engineering
Prof. James Kermode, Engineering

Project Partner: AWE-NST

A transcript of the video is available by clicking this link - transcript opens in another windowLink opens in a new window

Background

Understanding how materials fail under rapid and extreme forces is crucial for safety in engineering. In some cases, materials do not simply snap - they bend and stretch first, tiny voids form within, and these voids then grow and merge until the material eventually breaks. These processes occur rapidly and are difficult to capture using traditional modelling techniques. This project will employ a modern approach that treats cracking as an integral part of the material’s behaviour, making it easier to simulate complex fracture patterns. AI tools will accelerate the setup of simulations and help assess the confidence in the results. This will lead to more accurate predictions and safer designs in the future.

Project Objectives

This PhD project will develop new computational models to improve our understanding of how materials fail when subjected to rapid impact or stress. It will investigate how materials deform, form microscopic voids, and ultimately fracture. You will also use AI to enhance the models and increase the reliability of the results.

Outcomes

A novel computational model for simulating material failure under rapid loading;
Improved understanding of how materials deform and develop cracks prior to fracture;
AI-based tools to refine the model and assess confidence in the simulation results.

Skills that the student will learn

Understanding material behaviour under stress;
AI and machine learning fundamentals for scientific applications.
Scientific computing skills (e.g., Python, C++/Fortran).

To discuss this project further contact: Emmanouil.Kakouris@warwick.ac.ukLink opens in a new window

Please note that due to the nature of our project partner's work, nationality restrictions apply to applications for this project.

If you need guidance on this please email hetsys@warwick.ac.uk