Data-driven numerical modelling for thermal management in proton exchange membrane (PEM) fuel cell

Doctoral Training Grant Funding Information 

This funding model includes a 36 month fully funded PhD Studentship, set in-line with UK Research & Innovation values. For 2025/6, this will be £20,780 per year. The tax-free stipend will be paid monthly. This PhD Studentship also includes a Full-Time Fee Scholarship for up to 3 years. The funding is subject to your continued registration on the research degree, making satisfactory progression within your PhD, as well as attendance on and successful completion of the Postgraduate Certificate in Research Practice.

All applicants will receive the same stipend irrespective of fee status. 

Application Closing Date: 

Midday (UK Time) on Wednesday 17th September 2025 for a start date of 2nd February 2026.

How to Apply 

To apply, please follow the below steps:

1. Complete the BCU Online Application Form.
2. Complete the Doctoral Studentship Proposal Form in full, ensuring that you quote the project ID. You will be required to upload your proposal in place of a personal statement on the BCU online application form.
3. Upload two references to your online application form (at least one of which must be an academic reference). 
4. Upload your qualification(s) for entry onto the research degree programme. This will be Bachelor/Master’s certificate(s) and transcript(s). 
5. International applicants must also provide a valid English language qualification. Please see the list of English language qualifications accepted here. Please check the individual research degree course page for the required scores. 

Frequently Asked Questions 

To help support you to complete your application, please consult the frequently asked questions below: 

Project title: Data-driven numerical modelling for thermal management in proton exchange membrane (PEM) fuel cell

Project Lead: Associate Professor Noel Perera

Project ID: 36 - 45488534

Project description:

As a key enabler of future low-carbon energy infrastructures, hydrogen holds strategic importance in decarbonising energy production, enhancing system resilience, and advancing sustainable development objectives. In the transportation sector, hydrogen fuel cell vehicles (FCVs) are gaining traction as a viable alternative to internal combustion engines (ICEs), offering superior thermodynamic efficiency, lower acoustic emissions, and minimal local pollutants. Compared to battery electric vehicles (BEVs), FCVs exhibit advantages in terms of rapid refuelling, higher gravimetric energy density, and operational stability across a broader range of conditions without the end of life environmental concerns associated with lithium-ion battery disposal.

The increasing global demand for sustainable and efficient energy solutions has brought hydrogen fuel cells, particularly proton exchange membrane fuel cells (PEMFCs), to the forefront of energy research. PEMFCs are known for their high efficiency, low operating temperatures, and zero-emission output, making them ideal for transportation and stationary power applications. However, their performance and durability are highly dependent on effective thermal management due to the heat generated during electrochemical reactions. PEMFCs typically operate within a temperature range of 70–80 °C and demonstrate electrical efficiencies ranging from 40% to 60%. Approximately 96% of the heat generated within a fuel cell is removed via the thermal management system. Given the typical temperature gradient of 40–60 °C between the fuel cell’s operating temperature and ambient conditions, effective thermal management remains a critical engineering challenge.

Traditional approaches to modelling thermal behaviour in PEMFCs rely on numerical simulations such as Computational Fluid Dynamics (CFD), which provide detailed insight but are computationally intensive and time-consuming. The growing capabilities of data-driven technologies, utilising machine learning (ML) with CFD offers a transformative solution. It enables real-time thermal modelling while maintaining computational efficiency offering rapid prediction and optimisation of thermal management in PEMFCs. Presently there is limited published literature on combining data-driven technologies with CFD outputs for thermal analysis of PEMFCs. Hence this proposal aims to develop a robust hybrid modelling framework to capture the distinct thermal characteristics of PEMFCs, to enhance its thermal management capabilities.

This research aims to develop a hybrid framework of numerical simulation underpinned by data driven technologies to improve the thermal management of PEMFCs.

The objectives are:

1. Develop a CFD model to simulate thermal behaviour in PEMFCs under selected operating conditions.

2. Identify and analyse the impact of operational parameters such as temperature, pressure and flow rate on the thermal performance.

3. Generate simulation dataset to train ML models for temperature prediction and heat flux estimation

4. Utilise ML models to predict temperature distribution and hotspot identification.

5. Perform parametric studies to assess the sensitivity of thermal behaviour to operating parameters.

6. Evaluate and validate the integrated approach using published benchmark data or experimental results

7. Develop optimisation strategies for improving heat dissipation and overall thermal management.

Anticipated findings and contributions to knowledge:

The contribution to new knowledge is the development of a robust hybrid modelling framework incorporating data-driven technologies such as ML underpinning the CFD outputs to improve the thermal management of PEMFCs.

Anticipated key research findings of this proposal are:

1. A hybrid CFD–ML framework capable of fast and accurate thermal prediction in PEMFCs.
2. Reduced computational cost for design iterations and system control.
3. Insights into dominant parameters affecting the PEMFCs thermal behaviour.
4. Enhanced design guidelines for PEMFC thermal management systems.
5. Optimised fuel cell configurations for enhanced heat dissipation
6. A methodological foundation extendable to other electrochemical energy systems.

Person Specification:

Entry Requirements:

• To apply for our Engineering PhD Research Degree you should have, or expect to be awarded, a Master’s degree in a relevant subject area from a British or overseas university.
• Exceptional candidates without a Master’s degree, but holding a first class or upper second class Bachelor’s degree in a relevant subject area, may be considered.
• We also welcome enquiries from potential PhD researchers with appropriate levels of professional experience.

 Essential Criteria:

• Good background in heat transfer, thermodynamics, and electrochemical system physics. Familiar with PEM fuel cell operation and associated degradation/thermal issues.
• Experience with CFD software such as ANSYS Fluent, OpenFOAM, COMSOL or similar with an understanding of turbulence modelling, conjugate heat transfer, and multiphysics coupling.
• Knowledge of Machine Learning (ML) algorithms relevant to regression, surrogate modelling, or physics-informed models. Reasonable Python/ MATLAB proficiency for ML model development (TensorFlow, PyTorch, scikit-learn).
• Strong analytical mindset with good attention to detail

• Excellent written and verbal communication skills. Ability to present research findings effectively to both technical and non-technical audiences.

• Ability to lead and manage projects plus design measurable project goals.
• Excellent interpersonal and collaborative skills, demonstrating the ability to work effectively both alone and within interdisciplinary teams.
• Ability to independently manage research tasks, demonstrating self-direction and initiative, balanced with openness to feedback and collaboration.
• Open to continuous professional development, actively seeking to expand knowledge and technical skills throughout the PhD programme.

Desirable Criteria:

• Familiarity with High-Performance Computing (HPC) for large CFD runs.
• Knowledge of control systems engineering for applying fast ML-based predictions to real-time thermal management.
• Published or presented work in relevant fields, demonstrating capability in academic dissemination.

Overseas applicants:

International applicants must also provide a valid English language qualification, such as International English Language Test System (IELTS) or equivalent with an overall score of 6.5 with no band below 6.0.  

Contact:

If you have any questions or need further information, please use the contact details below: 

- For enquiries about the project content, please contact: noel.perera@bcu.ac.uk.

- For enquiries about the application process, please contact: research.admissions@bcu.ac.uk