Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Improving Ultrasonic Imaging using Machine Learning (Enhanced Stipend - Rolls Royce EngD)


   Department of Electronic and Electrical Engineering

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof Charles Macleod  Applications accepted all year round  Competition Funded PhD Project (European/UK Students Only)

About the Project

This EngD will work collaboratively between the Centre for Ultrasonic Engineering (Prof. C. MacLeod), the Department of Mathematics and Statistics (Dr. K. Tant) and Rolls Royce. This project promises to be an exciting, fun and industrially relevant project, working alongside skilled engineers and scientists with state-of-the-art robotic equipment to deliver meaningful industrial change. 

Research Project

Ultrasonic non-destructive evaluation (NDE) describes the practice of transmitting sound waves through solid objects and analysing the resulting scattered waves to construct images of the object’s interior, facilitating defect detection and materials characterisation. 

The ultimate aim of this project is to investigate enhanced ultrasonic NDE of metal components directly at the point of manufacture, to deliver high-quality components right, first time. Importantly, this in-process approach requires the development of real-time data processing algorithms. Machine learning algorithms used in conjunction with models and simulations of wave propagation will be explored to facilitate this.

Specifically, this project will examine how to compensate for the effects that thermal gradients, complex build geometries and heterogeneous microstructures have on the probing ultrasonic waves. Three research questions will be addressed: 

i)               Can complex and dynamic build geometries be accurately mapped out in near real-time using in-process ultrasonic inspection data, where extreme thermal gradients (generated by the manufacturing process) cause distortion of the expected wave paths?

ii)             Can this knowledge of the component geometry, coupled with models of the thermal gradient be used to better constrain and drive the microstructure characterisation problem? 

iii)           Can the knowledge from steps i) an ii) be used to reliably image components as they are built?

The final deliverable of the project will be a fully automated in loop capability, to be demonstrated on test structures manufactured for aerospace and energy applications (with other industrial members applications supported as appropriate). 

Funding 

For UK students, Tuition Fees and a generous enhanced stipend of £26,168 tax-free per annum for up to 4 years. The student will also have access to substantial international travel and project funds.

Research Environment

The student will be based in the newly opened £2.1M Sensor Enabled Automation & Control Hub (SEARCH) Laboratory at the University of Strathclyde, working alongside a research team of over 35 researchers and PhD Students, while also having access to state of the art sensor, robotic and welding equipment. The student will work in collaboration and spend time on site working with the lead industry partner (Rolls Royce) to gain a greater appreciation of the specific industrial challenges and opportunity for automated inspection during fusion welding.

This EngD will be aligned to the EPSRC Centre for Doctoral Training in Future Innovation in Non-Destructive evaluation (FIND). The student will undertake specific industrial technical training courses (Ultrasonics, Welding and KUKA Advanced Robotic Programming) along with the University Research Development Program (RDP) to deliver training and development on traditional PhD activities such as presentations, conferences and technical writing. 


Computer Science (8) Engineering (12) Mathematics (25) Physics (29)

Where will I study?

 About the Project