About the Project
We are looking for a highly motivated PhD student to work on an exciting interdisciplinary 4-year fully funded research project.
Industrial gas turbines can be used for producing electricity in remote areas, such as Oil and Gas rigs. During the operational phase emissions are produced in the exhaust (carbon dioxide and nitrous oxide), which have to be constantly monitored to ascertain with current regulations. Currently, the gold standard process of monitoring emissions is achieved by costly equipment called continuous emissions monitoring systems (CEMS). However, alternative approaches, such as predictive monitoring systems, are significantly less costly and easier to maintain. To achieve this, a combination of an emissions model and data driven approaches might be needed to exploit all available knowledge and capture variability across different gas turbine types and environmental conditions/settings.
Stemming from the above, the main aims of this project are a) to develop an accurate, generalisable and robust gas turbine predictive emissions monitoring system based on engine measurements and an emissions model and novel machine learning techniques, and b) to extensively validate its performance across a number of real-world scenarios, conditions and settings, as well as compare it against current state of the art systems. This interdisciplinary project requires skills and experience in machine learning and also some understanding of gas turbine operations.
This 4-year PhD project is a collaboration between the Department of Computing Science, University of Aberdeen and Siemens Energy Industrial Turbomachinery Ltd (Industrial Partner) and is supported by EPSRC industrial Cooperative Awards in Science & Technology (iCASE) scheme.
The successful PhD candidate will be enrolled onto a 4-year PhD programme with the University of Aberdeen.
The candidate will have access to state-of-the-art facilities, High Performance Computing resources, GPU equipment and also funding for other project costs, such as training, conferences, PC, etc.
The candidate is expected to spend at least 3 months of the 4-year award on the premises of the Industrial Partner (Siemens Energy Industrial Turbomachinery Ltd). All costs related to this will be covered.
Selection will be made on the basis of academic merit. The successful candidate should have, or expect to obtain, a UK Honours degree at 2.1 or above (or equivalent) in Computer Science, Engineering or Mathematics. Highly Desirable: MSc in Machine Learning, AI, Data Science, or similar.
Essential background and Knowledge: Strong skills in linear algebra, mathematics, programming (advanced Python), machine learning principles, problem solving.
Knowledge of: Machine Learning, Deep Learning, Artificial Intelligence, Time Series Analysis, Data-Driven and Model-Driven approaches, programming in Python.
Highly Desirable: experience on Gas Turbine Operational and/ Emission Data Analytics and First Principles
Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php
- Apply for the Degree of Doctor of Philosophy in Computing Science
- State the name of the lead supervisor as the Name of Proposed Supervisor
- State the exact project title on the application form
- All Degree Certificates/Academic Transcripts (officially translated into English and original)
- 2 Academic References on official headed paper and signed or sent from referees official email address
- Detailed CV
For any information or informal discussion please contact Dr Georgios Leontidis, interim Director for AI and Data & Associate Professor (SL) in Machine Learning firstname.lastname@example.org.
Closing date for applications: 1st of May 2021, but we reserve the right to close the advert earlier should a suitable candidate be found.
Starting date: Flexible – Late Summer / Early Autumn 2021
Prior to commencement of this PhD, a collaboration agreement will be drawn upon and signed by all parties involved, i.e. University, industry partner, and recruited student
Why not add a message here
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.