PhD Studentship: AI-Enhanced Battery State of Health Estimation Using Ring Probabilistic Logic Neural Networks Oxford Brookes University in United Kingdom

[Bursary of £20,780 per annum. University fees at the home rate are covered; international/EU students without Settled Status must pay the difference between home and international fees. Visas and associated costs are not covered.]

This fully funded PhD studentship at Oxford Brookes University offers an exciting opportunity to advance battery state of health (SOH) estimation for electric vehicles using innovative AI techniques. The project, in collaboration with Jaguar Land Rover, focuses on developing Ring Probabilistic Logic Neural Networks (RPLNN) to improve interpretability, data efficiency, and resistance to drift in battery SOH estimation. Unlike traditional deep learning models, the RPLNN framework integrates neural computation with probabilistic logic rules in a ring-based structure, addressing critical limitations in current AI-based approaches.

The studentship is open to home, EU, and international students. University fees at the home rate are covered, and a generous bursary of £20,780 per annum is provided. International and EU students without Settled Status must cover the difference between home and international fees, and visa costs are not included. The position is full-time for three years, with a start date in September 2026. The application deadline is 20 April 2026, and interviews will be held online.

Applicants should hold a Master’s degree (or equivalent) in Electrical Engineering, Control Engineering, Mechatronics, or Robotics, with a strong background in dynamic system theory. Essential skills include applied intelligent control techniques, machine learning, artificial intelligence, control systems, system modelling, and data-driven approaches. Experience with MATLAB/Simulink and relevant toolboxes, as well as knowledge of battery systems and battery management systems, is required. Candidates should demonstrate strong analytical and problem-solving abilities, excellent English communication skills, and motivation for high-quality research leading to publications.

Desirable qualifications include experience with machine learning or deep learning models, state estimation techniques (such as Kalman filters), prior battery modelling or testing experience, familiarity with electric vehicles, energy storage systems, or smart energy technologies, and evidence of research activity. International/EU applicants must provide a valid IELTS Academic test certificate (minimum overall score 6.0, no score below 5.5, issued within the last 2 years).

The project aims to address the challenge of balancing accuracy and computational efficiency in battery SOH estimation, which is crucial for electric vehicle safety and longevity. The RPLNN approach promises enhanced interpretability and robustness, making it a valuable contribution to the field of intelligent battery management.

To apply, candidates should contact [email protected] before submitting their application. Applications must be made directly via the university portal and should include a cover letter, CV, details of two referees (at least one academic), degree certificates and transcripts, a scan of the passport, and evidence of valid English language qualification if required. For further queries, applicants can contact [email protected].