Bayesian Multi-Objective Optimisation and Multi-Fidelity Reduced-Order Models for Digital Twinning. EMPS College Home fees Studentship, PhD in Computer Science. Ref: 4337
About the award
Dr Tinkle Chugh, Department of Computer Science, Streatham Campus, University of Exeter
Dr Konstantinos Agathos, Department of Engineering, Streatham Campus, University of Exeter
Department of Computer Science, Streatham Campus, Devon, University of Exeter
The University of Exeter’s College of Engineering, Mathematics and Physical Sciences is inviting applications for a fully-funded PhD studentship to commence in January 2022 or as soon as possible thereafter. The studentship will cover Home tuition fees plus an annual tax-free stipend of at least £15,609 for 3.5 years full-time, or pro rata for part-time study.
This College studentship is open to UK and Irish nationals, who if successful in their application will receive a full studentship including payment of university tuition fees at the home fees rate.
Digital twinning is emerging as a powerful tool for guiding the design and life-cycle management of structural systems. While the technology holds significant potential for substantially improving the performance and reducing maintenance costs of structural systems, it also presents several challenges. In particular, the concept relies on digital representations of real-life systems that run along with their physical counterpart and can be updated with real-time data to reflect changes undergone during the system’s life cycle. Satisfying these requirements might not be possible with conventional methods since high-fidelity physics-based models require increased run times, which are prohibitive for real-time application, while low-fidelity models might not be able to represent the system’s response under all possible operating conditions. In addition to the above, there might be conflicting objectives to be achieved by the digital representation of a system. For instance, multiple elements of the system’s response might be of interest, requiring multiple models to achieve optimal results. Balancing these objectives can take a substantial amount of time and resources.
To tackle the above challenges, the project will develop model order reduction techniques that allow the creation of families of models of varying resolution. Subsequently, Bayesian multi-objective optimisation will be used in guiding the reconfiguration of these multi-fidelity models and achieving the conflicting objectives. Bayesian multi-objective optimisation methods have the advantages of finding so-called approximated Pareto optimal solutions in the least number of function evaluations. Moreover, they provide uncertainty in addition to the point predictions, which can be helpful in decision making and exploring the search space. The resulting model will accurately represent and predict the response of the system, based on real-time data. In the project, you will be exploring different engineering systems, such as wind turbine blades and aircraft wings and will create their digital twins using Bayesian Multi-Objective Optimisation and Multi-Fidelity Reduced-Order models.
This PhD project is a collaborative project between Computer Science and Engineering and will promote interdisciplinary research. The PhD candidate will be part of a team of academic researchers working in the areas of machine learning, optimisation and their applications, especially in digital twins. Moreover, the PhD candidate will have the opportunities to travel for further collaboration and participate in the international research community.
This studentship is open to UK and Irish nationals, who if successful in their application will receive a full studentship including payment of university tuition fees at the home fees rate.
Applicants for this studentship must have obtained, or be about to obtain, a First or Upper Second Class UK Honours degree, or the equivalent qualifications gained outside the UK, in an appropriate area of science or technology.
The project will suit a student with a degree in a numerate discipline (e.g., computer science, physics, mathematics, engineering) who has a background in programming (preferably Python). An experience in Bayesian methods and/or finite element analysis, as well as willingness to learn data-driven optimisation methods and machine learning techniques are desirable.
If English is not your first language you will need to have achieved at least 6.0 in IELTS and no less than 6.0 in any section by the start of the project.
Alternative tests may be acceptable (see http://www.exeter.ac.uk/postgraduate/apply/english/).
How to apply
In the application process you will be asked to upload several documents. Please note our preferred format is PDF, each file named with your surname and the name of the document, eg. “Smith – CV.pdf”, “Smith – Cover Letter.pdf”, “Smith – Transcript.pdf”.
• Letter of application (outlining your academic interests, prior project work experience and reasons for
wishing to undertake the project).
• Transcript(s) giving full details of subjects studied and grades/marks obtained (this should be an
interim transcript if you are still studying)
• Two references from referees familiar with your academic work. If your referees prefer, they can email
the reference direct to email@example.com quoting the studentship reference number.
• If you are not a national of a majority English-speaking country you will need to submit evidence of your proficiency in English. Please see the entry requirements information above.
The closing date for applications is midnight on 24th January 2022. Interviews will be held online on the week commencing 7th February 2022.
If you have any general enquiries about the application process please email firstname.lastname@example.org.
|Application deadline:||24th January 2022|
|Value:||Home tuition fees plus an annual tax-free stipend of at least £15,609 for 3.5 years full-time, or pro rata for part-time study.|
|Duration of award:||per year|
|Contact: PGR Admissions Officeemail@example.com|