Characterisation of cast austenitic stainless steels using ultrasonic backscatter and artificial intelligence

About the project

If you enjoy numerical modelling and are you interested in the application of artificial intelligence (AI) to engineering problems, this may be the right project for you.

Our main aim is to combine the power of finite element modelling with artificial intelligence to develop ultrasonic characterisation of castings in-situ. Whilst helping to improve the way the industry manages safety-critical assets, you'll develop a transferrable skillset comprising:

Stainless steel castings possess outstanding corrosion resistance and mechanical properties. For these reasons, they underpin numerous safety-critical installations and are ubiquitous in, e.g. nuclear power plants. However, their excellent performance comes at a cost - they are challenging to inspect for damage in situ.

Ultrasound - the preferred inspection method - suffers from the coarse-grained microstructure, which scatters and attenuates injected acoustic energy making reflections from defects illegible. Having some knowledge about the microstructure before testing offers game-changing possibilities.

First, one could tailor the inspection protocol to minimise the detrimental effect of noise. Second, it would help select the correct procedure for a specific defect which is a crucial maintenance challenge. Unfortunately, such information is currently only available from destructive tests.

Your PhD will pave the way towards in-situ microstructure characterisation using ultrasound and help transform common inspection practice. You'll employ artificial intelligence to support developing the physical understanding of how microstructure reveals itself in ultrasonic backscatter.

Using GPU-powered ultrasound simulations, you will run a large set of virtual experiments for numerous synthetically created microstructures with carefully controlled parameters. Learning from data, including choosing a suitable AI methodology, and proposing in-situ characterisation methods is the promise of this project.

You will use Southampton's High-Performance Computing facility, as well as advanced material characterisation techniques in the School of Engineering. The true potential of the methods you propose will be showcased using ultrasonic measurements on samples of industrial relevance.

As a PhD student, you will be a part of the Dynamics Group within the University's Institute of Sound and Vibration Research. 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.

• numerical modelling
• large data analysis
• AI (which would prove useful on many potential future career paths)

Dr Michal Kalkowski PhD

• Non-destructive testing
• Material characterisation and imaging with ultrasound
• Guided waves

Professor Thomas Blumensath

• I develop and study advanced algorithms that can solve challenging inverse problems by efficiently exploiting complex prior information. Using techniques from mathematics, statistics and machine learning, my work concentrates primarily on problems in x-ray tomographic image reconstruction and modelling.
• I work closely with state-of-the-art imaging facilities (µ-VIS, the National Research Facility in Lab-based XCT, the UK’s synchrotron facility at the Diamond Light Source, and ISIS neutron imaging beamline) to find practical solutions to a range of important scientific problems from plant science to manufacturing.
• My research interests cover areas such as: Theoretical and computational methods for Signal and Image Processing (Machine Learning, Compressed Sensing, Statistical Signal and Image Processing, Quantum Computing, Inverse Problems, Optimisation, X-ray Tomographic Imaging); Advanced tomographic imaging strategies: (limited angle tomography and laminography, Spectral X-ray imaging, Stereo and extreme limited view tomography); Efficient computational methods for tomographic reconstruction, including GPU acceleration, distributed computation and advanced optimisation strategies, Constrained optimisation for ill-conditioned and underdetermined tomographic inverse problems, Applications of X-ray tomography to the inspection of manufactured components, Multimodal tomographic imaging

Entry requirements

UK 2:1 honours degree, or its international equivalent.

A background in finite element modelling and Python is highly desirable.

Fees and funding

For UK students, tuition fees and a stipend of £16,062 tax-free each year for up to 3.5 years.

How to apply

Apply now

You need to:

Applications should include:

• choose programme type (Research), 2022/23, Faculty of Physical Sciences and Engineering
• choose PhD Engineering & Environment (Full time)
• add name of the supervisor (Michal Kalkowski) in section 2
• your cv (resumé)
• 2 reference letters
• degree transcripts to date

Faculty of engineering and physical sciences

Email: feps-pgr-apply@soton.ac.uk

Project leader

Feel free to contact Michal Kalkowski for an informal chat about the project and pursuing a PhD in Southampton.

Email: m.kalkowski@soton.ac.uk

We look forward to hearing from you!

Research areas