Edge AI for predictive health management of electrified vehicles

Electrified vehicles (xEVs)—including battery electric vehicles (BEVs), hybrids (HEVs) and plug-in hybrids (PHEVs)—are essential to the UK’s Net Zero transport strategy. However, industry and regulators still lack scalable ways to understand how batteries and power electronics (e.g., inverters) age under real-world driving and environmental conditions. Laboratory tests cannot capture this variability, while cloud-based analytics are bandwidth-intensive and limited by privacy constraints.

This project will develop a novel Edge AI predictive health management system running on embedded hardware (e.g., microcontrollers and portable OBD-II/CAN data loggers). Using lightweight machine-learning models informed by physics-based ageing mechanisms and in-use operating patterns, the system will estimate State of Health (SoH) and Remaining Useful Life (RUL) under real-world driving conditions. This approach is timely given the EU’s mandatory OBFCM framework (2021), which highlights a broader shift from laboratory-based type approval to continuous real-world evaluation for assessing sustainable mobility solutions.

The project builds on the supervisory team’s expertise in transportation electrification and predictive modelling, including contributions to Horizon Europe HiPE and HiVEP projects (EV health modelling) and an IUK KTP (on-board monitoring). Methodological input from the European Commission’s Joint Research Centre (JRC)—whose analysis of OBFCM datasets from 7.7 million vehicles highlights the influence of driver behaviour and vehicle technology—creates a unique opportunity for impactful collaboration.

The student will receive interdisciplinary training across AI and robotics, energy storage, and EV power electronics. A secondment at JRC (Ispra) will provide hands-on experience with Europe’s leading real-world vehicle monitoring programmes and exposure to state-of-the-art methodologies.

You will need to meet the minimum entry requirements for our Robotics and Autonomous Systems PhD programme.

The ideal candidate will have:

• A good undergraduate and/or Master’s degree (typically a First or high 2:1, or equivalent) in , Automotive Engineering, Robotics, Mechanical Engineering, Electrical Engineering, Mechatronics, Computer Science, or a closely related discipline.
• A solid foundation in engineering mathematics, data analysis, and system modelling.
• Experience with programming in at least one relevant language (e.g. Python, MATLAB/Simulink, C/C++).
• Strong analytical skills and the ability to work independently on complex, interdisciplinary research problems.

Good written and verbal communication skills, with the ability to document research clearly and engage in technical discussions.

Open to any UK or international candidates. Up to 30% of our UKRI funded studentships can be awarded to candidates paying international rate fees. Find out more about eligibility.