PhD Studentship: Machine Learning Tools for Improving Energy Transfer in Nonlinear Systems

Supervisory Team: Daniil Yurchenko and Tim Waters 

This is a unique project to study how a combination of Machine Learning (ML) tools and Sparce Identification (SI) can be used for improving energy transfer and optimal performance of complex nonlinear systems. The project output will have significant impacts in the area of data-driven methods, ML and SI, vibration mitigation, vibration isolation and vibration energy harvesting.  

Project Description 

Design and understanding of nonlinear models are required for optimal performance and for accurate reproduction of dynamical behaviour. One of the intriguing phenomena in nonlinear systems is Targeted Energy Transfer (TET), where the goal is to transfer energy within a nonlinear system between subsystems. The theory of linear dynamical systems is well-developed in the context of tuned mass dampers, in contrast to nonlinear systems, where often individual nonlinear mechanisms are considered to be model-specific. A majority of these approaches rely on perturbation theory, which is valid for weak nonlinearities over finite time. TET is a nonlinear alternative that can also be generalized to multi-degree-of-freedom systems. In the traditional TET formulation, the nonlinearities are given for all degrees of freedom (for instance of cubic order), and the energy-transfer subsystem is tuned to an optimal set of parameters (coefficients) to mitigate undesirable dynamics of the primary system. 

Based on the existing publications this leaves a number of gaps in the TET’s state-of-the-art.

1. The typical approximate methods used to analyse TET are not applicable to fully nonlinear effects and are infeasible for necessary multi-degree-of-freedom (MDOF) systems.
2. A given nonlinearity in the system may not be optimal, and traditional methods do not scale to exploring the full range of potential nonlinear mechanisms.
3. There is no established framework for fast identification of the optimal nonlinear system for efficient TET from purely experimental data.

To address these gaps the project will combine ML optimization algorithms, such as Surrogate Optimization (SO), data-driven methods and SI. 

This project will require a student with: 

• Applied Mathematics, Mechanical Engineering, Physics degree;
• Great programming skills in one of the Engineering languages (Matlab, Python, Julia, etc) to explore nonlinear dynamical systems and optimisation algorithms;
• Great mathematical skills;
• Great communication skills; 

If you wish to discuss any details of the project informally, please contact Daniil Yurchenko, Dynamics Research Group, Email: d.yurchenko@soton.ac.uk, Tel: +44 (0) 2380 59406. 

Entry Requirements

An undergraduate degree in one of the subjects above. The UK and international students are eligible to apply, however, international applicants will have to pass the required English test. 

Closing Date: Applications should be received no later than 01 May 2024 for standard admissions, but later applications may be considered depending on the funds remaining in place. 

Funding:

For UK/international students, Tuition Fees and a stipend of £18,622 tax-free per annum for up to 3.5 years. 

How To Apply

Applications should be made online. Select programme type (Research), 2023/24, Faculty of Physical Sciences and Engineering, next page select “PhD Engineering & Environment (Full time)”. In Section 2 of the application form you should insert the name of the supervisorDaniil Yurchenko. 

Applications should include:

Research Proposal

Curriculum Vitae

Two reference letters

Degree Transcripts to date

Apply online: https://www.southampton.ac.uk/courses/how-to-apply/postgraduate-applications.page 

For further information please contact: feps-pgr-apply@soton.ac.uk

Advert information