Back to search results

PhD in Trusted Deep Learning For Multi-Domain Engineering Systems

University of Sheffield - Department of Automatic Control and Systems Engineering

Qualification Type: PhD
Location: Sheffield
Funding for: UK Students, EU Students
Funding amount: £19,609 per annum
Hours: Full Time
Placed On: 3rd September 2021
Closes: 5th October 2021

Machine learning and artificial intelligence have been shown by our research team and the wider research community to be very powerful in predicting complex machine behaviour and consequently diagnose their health. This information is encapsulated in a model and leads to more sustainable operation only if it is trusted.

Trust in sophisticated models can come from their interpretability, consistency with physical models and ability to explain their output. They must be built upon data rich in information and of known provenance. This project addresses the challenges in producing trusted predictions using all knowledge sources (from different domains) to better understand asset behaviour and health, while accommodating the realities of imperfect training data sets.

Working on real Industrial problems (with our sponsor Rolls-Royce) you will develop cutting edge skills as a data scientist and engineer to build models of complex data sets.

  • Develop machine learning techniques and models to fuse knowledge (mathematical model or expert beliefs) and data from different engineering domains (vibration, thermal, engine performance, etc.)
  • Train these models on real data to produce predictions of complex systems, such as gas turbines and hybrid electric propulsion systems.
  • Using machine learning techniques to incorporate new sources of maintenance data, such as 3D component scans and visual imaging, to better understand system condition.
  • Provide insight into the limits of diagnosis given the existing sensors and develop methods to evaluate the value of new sensors and their placement.

We are seeking an enthusiastic and intellectually curious UK or EU national to work on this project who is motivated by seeing realisation of their research in real engineering applications.

Full details of how to apply can be found by clicking the apply button.

Home / EU fees and EPSRC stipend for 21/22 currently £15,609 plus 4k top-up for 3.5 years.

EU and UK nationals only.

Preferred start date Autumn term start 21; can accommodate Feb 22 start.

We require applicants to have either an undergraduate honours degree (2:1) or MSc (Merit or Distinction) in a relevant science or engineering subject from a reputable institution.

We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

Subject Area(s):


PhD tools
More PhDs from University of Sheffield

Show all PhDs for this organisation …

More PhDs like this
Join in and follow us

Browser Upgrade Recommended has been optimised for the latest browsers.

For the best user experience, we recommend viewing on one of the following:

Google Chrome Firefox Microsoft Edge