Integrating experimental advances with machine learning for digital transformation in materials performance evaluation and structural integrity

The UK is leading the global fight against climate change, with a commitment to achieve net-zero greenhouse gas emissions by 2050. A cornerstone of this strategy is the development of nuclear fusion, a promising clean energy source. However, realising fusion energy requires overcoming significant engineering challenges, particularly ensuring the structural integrity of fusion materials and components in extreme environments. Effective materials performance evaluation is essential for structural integrity management, enabling the extension of lifetimes and the reduction of maintenance costs. This project addresses these challenges by combining experimental breakthroughs with advanced machine learning (ML) to transform how structural integrity is assessed and predicted. While ML holds transformative potential, challenges such as resistance to new methods and the reliance on high-quality datasets must be overcome. Partnering with the National Physical Laboratory ensures access to critical datasets, cutting-edge facilities, and industrial validation. This collaboration enhances data reliability and fosters confidence in ML-powered solutions. By delivering robust, scalable, and transferable approaches, this project advances structural integrity management, supports the UK’s fusion energy ambitions, and provides innovative tools for sustainable technologies across engineering sectors.

You will need to meet the minimum entry requirements for our Engineering Materials PhD programme.

Applicants should have (or expect to obtain by the start date) at least an Upper Second Bachelor’s degree, and preferably a Master’s degree, in an appropriate discipline (e.g. engineering, material sciences, mechanical engineering, physics, chemistry or a related subject).

Open to candidates who pay UK/home rate fees. See UKCISA for further information.