Developing grey-box models for structural dynamics: optimising the balance between physics and data-based learning
Where structures operate in complex dynamic environments (e.g. offshore), current technology is unable to sufficiently quantify or predict their behaviours to provide an accurate estimate of remaining fatigue life. In direct collaboration with aerospace and offshore industries, this project will develop a transformative approach for response prediction and fatigue usage quantification that takes advantage of the strengths of established knowledge and physics-based models in combination with the flexibility and power of artificial intelligence. The ability to accurately predict current condition and remaining life of our high value assets is crucial to guarantee safety, maximise use and minimise maintenance costs.
In this PhD project you will be responsible for developing new models that combine machine learning with the more traditional physics-based approaches. You will explore how to establish an optimal balance between these two components and you will develop a means of validation (i.e. ensuring the model reflects the real structure and its environment). There will some experimental aspects to this project where the successful candidate will benefit from working in our new and state of the art facility, the Laboratory for Verification and Validation (see lvv.ac.uk).
• Please note, this position is only open to UK and EU citizens with 3 or more years residency.
• This studentship covers the cost of tuition fees and provides an annual tax-free stipend at the standard UK research rate (£14,777 in 2018/19), with the possibility that this amount may be topped up.
• The start date for this project will be September 2018.
• For further information about this project please contact Dr Elizabeth Cross ([Email Address Removed])
This studentship covers the cost of tuition fees and provides an annual tax-free stipend at the standard UK research rate (£14,777 in 2018/19), with the possibility that this amount may be topped up.
How good is research at University of Sheffield in Aeronautical, Mechanical, Chemical and Manufacturing Engineering?
Mechanical engineering and Advanced manufacturing
FTE Category A staff submitted: 44.60
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities