About the project
You will contribute to developing the exciting capability in AI-powered NDT, working alongside researchers using acoustics to interrogate and characterise structures and materials of different scales and complexities. ISVR is a member of the UK's Research Centre for Non-Destructive Evaluation and runs projects in both ultrasonic and X-ray imaging.
This PhD project tackles a long-standing challenge in ultrasonic non-destructive testing – characterisation and inspection of thick weld sections. Such welds are safety-critical in various industries, e.g. nuclear energy. However, they are notoriously difficult to inspect because their complex microstructure deviates and scatters ultrasound. Up to now, we can only learn about the grain layout destructively, using EBSD or metallography, which is holding the industry back in reliable asset management. This project aims to push the boundaries of characterisation, allowing for in-situ characterisation accounting for likely uncertainties in sensor positions, weld geometry and alike. To achieve this, we will explore various artificial intelligence tools combined with physics-based modelling and inversion.
The project will involve algorithm development and testing, numerical and analytical ultrasound simulation, and EBSD datasets processing. You will have access to IRIDIS - our powerful high-performance computing cluster- and muVIS advanced material characterisation facilities in the School of Engineering. You will also benefit from interactions with our industrial and academic partners across Europe, including ultrasonic measurements on industry-relevant samples.
