PhD Studentship: AI-Enhanced Battery State of Health Estimation Using Ring Probabilistic Logic Neural Networks

3 Year, full-time PhD studentship

Eligibility: Open to home, EU and international students

Bursary p.a.: £20,780

University fees and bench fees: This studentship will cover university fees at the home rate. However, international students and EU students without Settled Status will need to cover the difference between the home rate and the international. Visas and associated costs are not covered.

Closing date: 20th February 2026

Interviews: TBC (online)

Start date:  September 2026 

Project Title: AI-Enhanced Battery State of Health Estimation Using Ring Probabilistic Logic Neural Networks

Director of Studies: Prof Shahab Resalati

Supervisors: Dr Aydin Azizi 

Contact: Prof Shahab Resalati (sresalati@brookes.ac.uk) 

Requirements: 

Entry requirements: 

Applicants should have a first or upper second-class honours degree from a Higher Education Institution in the UK or acceptable equivalent qualification.

English language requirements:

International/EU applicants must have a valid IELTS Academic test certificate (or equivalent) with an overall minimum score of 6.0 and no score below 5.5 issued in the last 2 years by an approved test centre. 

Project Description:

Accurate estimation of battery State of Health (SOH) is vital for safety, performance, and longevity in electric vehicles and energy storage systems. Current models struggle to balance accuracy, generalisability, and computational efficiency across diverse operating conditions. This project proposes a novel AI-based framework, the Ring Probabilistic Logic Neural Network (RPLNN), which fuses probabilistic logic and neural computation to enhance SOH prediction robustness and interpretability. The project will develop, train, and experimentally validate the RPLNN model using lithium-ion cell data supplied by Jaguar Land Rover (JLR).

Unlike conventional deep models that learn opaque mappings, the RPLNN constrains information flow through a ring-based structure governed by probabilistic logic rules. This approach improves interpretability, data efficiency, and resistance to data drift, addressing key limitations in current AI-based SOH methods. 

Application process

Apply directly via the university portal (via the above 'Apply' button). Please include the following in your application:

• A cover letter
• A CV
• Details of two referees, at least one from an academic background
• A research proposal
• Copies of your previous degree certificates and transcripts
• A scan of your passport
• Evidence of a valid IELTS or other valid English language qualification, in line with Oxford Brookes’ requirements (international and EU candidates only)

For any queries, please contact tde-tdestudentships@brookes.ac.uk

Advert information