CFD Online Logo CFD Online URL
www.cfd-online.com
[Sponsors]
Home > Jobs > Job Record #16994

CFD Jobs Database - Job Record #16994

Job Record #16994
TitleTowards Fully Digital: Uncertainty-based Design Optimisation
CategoryPhD Studentship
EmployerUniversity of Southampton
LocationUnited Kingdom
InternationalYes, international applications are welcome
Closure DateFriday, March 12, 2021
Description:
Applications are invited for a fully funded PhD studentship working on 
machine learning to address some of today’s engineering challenges. The PhD 
student will join an international 
research collaboration between world-leading research teams based at the 
University of Southampton, which is a member of the Russell Group and ranked 
in the world’s top 100 
Universities, and ZHAW, one of the leading universities of applied sciences 
in Switzerland. Among other international awards, the Southampton team was 
honoured to receive the 2018 Best 
Technical Paper Award (https://aerospaceamerica.aiaa.org/bulletin/november-
2019-aiaa-bulletin/) from American Institute of Aeronautics and Astronautics 
(AIAA).

Numerical modelling of complex physical systems has become one of the most 
important steps in the efficient design and analysis of aerospace systems. 
However, due to the complexity of 
the physics and the computational modelling of multi-scale dynamical 
systems, computational costs may be prohibitive. Consequently, predictive 
models and control schemes that cannot 
account for or take advantage of efficient algorithms have very limited 
applicability. The crucial question posed in this PhD project is: “Can we 
develop a sparsely-interconnected 
reduced order model, combining data-driven learning with a physics-based 
nonlinear reduced order modelling technique?”
The PhD project builds on the methodology developed by Dr Da Ronch for 
coupled, non-linear systems. The resulting nonlinear reduced order model 
contains a quadratic tensor, with size 
growing as the cube of the selected modes. The overarching idea is to 
develop a framework, which is both model- and data-driven, to extract a 
compact, reduced representation of the 
reduced order model. Sparsity features of the model are maximised by 
appropriate machine learning algorithms that identify the relevant 
interactions. The minimization of the 
sensitivity to aleatory uncertainties is part of the requirements for the 
reduced order models. The work will focus on systems involving fluid 
mechanics and fluid-structure interaction 
problems.

The 3.5-years studentship covers UK/EU level tuition fees. It is planned to 
start the project in 2021, preferably no later than 31 July. The funding 
available is competitive and will 
only be awarded to an outstanding applicant. As part of the selection 
process, the strength of the whole application is considered, including 
academic qualifications, personal 
statement, CV and references. Applicants should have a good first degree in 
relevant engineering subjects or mathematics. Ideally the candidate should 
have some experience in 
aerodynamics and fluid structure interactions, but it is not necessary to 
have experience in machine learning to apply.

The successful applicant will be encouraged to further develop analytical 
and computational skills, work closely with team members, and submit the 
research results to high-quality 
journals. The project involves periods spent abroad at the partner 
organisation, based in Zurich. After successfully completing the PhD, the 
applicant will be well-prepared for a 
rewarding industrial or academic career, leveraging on the network of 
contacts created as part of the research project.

Contact Information:
Please mention the CFD Jobs Database, record #16994 when responding to this ad.
NameAndrea Da Ronch
Emaila.da-ronch@soton.ac.uk
Email ApplicationYes
Record Data:
Last Modified12:19:56, Wednesday, February 24, 2021

[Tell a Friend About this Job Advertisement]

Go to top Go to top