Machine Learning-Enabled Optimisation for Small Modular Reactors in Maritime Propulsion

Maritime shipping is responsible for around 3% of CO₂ emissions globally. Between 2012 and 2018, these emissions significantly increased, largely due to the use of natural gas as fuel. Without further actions, the emissions are projected to grow considerably by 2050 [1]. To align with the Paris Agreement, significant emission reductions must occur in the sector, aiming for net-zero by 2050. This demonstrates the urgency and pressure the maritime industry faces in the development of innovative solutions to meet the targets. The UK government is on board with making maritime shipping greener and has rolled out new funding to help tackle this challenge [2].

A promising way to achieve this goal is the deployment of Small Modular Reactors (SMRs) on commercial ships. Even though nuclear-powered ships have been around for many years, mostly for military use, they would be a poor fit for commercial purposes due to, for example, high operational costs and the usage of highly enriched uranium fuel, which raises proliferation concerns [3].

In response to the outlined challenges, this project will focus on a development of a Small Modular Reactor for maritime shipments based on a Pressurised Water Reactor (PWR) system. PWRs have been widely used at sea, and their fuel has proven to be reliable over thousands of years of reactor operation [4]. Previous research [5, 6] has shown the inherent feasibility of utilising the boron-free PWR core design to power commercial ships. This advancement allows for extended operational lifetimes while eliminating the need for highly enriched uranium. However, the resulting reactor core design becomes very complex to optimise. To address this challenge effectively, the project will apply advanced optimisation techniques to develop the reactor core design suitable for commercial shipping.

In addressing the outlined challenges, the project will focus on:

• Developing a model of the Small Modular Pressurised Water Reactor (SM PWR) core using the latest nuclear simulation tools.
• Establishing a methodology for machine learning-based optimisation of the developed SM PWR core, focusing on genetic algorithms and neural networks.
• Addressing the reactor design limitations outlined in previous studies, particularly concerning safety requirements.
• Conducting a validation of the developed algorithms against openly available benchmarks for PWRs [7].

Applicant Eligibility

Candidates will have, or be due to obtain, a Master’s Degree or equivalent from a reputable University in an appropriate field of Engineering or Physics. Exceptional candidates with a First Class Bachelor’s Degree in an appropriate field will also be considered.

Application Process

Candidates wishing to apply should complete the University of Liverpool application form [How to apply for a PhD – University of Liverpool] applying for a PhD in Materials Engineering and uploading: Degree Certificates & Transcripts, an up-to-date CV, a covering letter/personal statement and two academic references.

Enquiries

Candidates wishing to discuss the research project should contact the primary supervisor ([email protected]), those wishing to discuss the application process should discuss this with the School PGR Office ([email protected]).

We want all of our staff and Students to feel that Liverpool is an inclusive and welcoming environment that actively celebrates and encourages diversity. We are committed to working with students to make all reasonable project adaptations including supporting those with caring responsibilities, disabilities or other personal circumstances. For example, If you have a disability you may be entitled to a Disabled Students Allowance on top of your studentship to help cover the costs of any additional support that a person studying for a doctorate might need as a result. 

We believe everyone deserves an excellent education and encourage students from all backgrounds and personal circumstances to apply.