Data-Driven Physics-Informed Reliability Prediction of Power Electronics for Net Zero Applications University of Glasgow in United Kingdom

This PhD project, 'Data-Driven Physics-Informed Reliability Prediction of Power Electronics for Net Zero Applications', is based at the University of Glasgow in partnership with Toshiba Europe. Power electronics are crucial for net-zero applications such as electrified transportation and renewable energy systems, but they are also a major source of system failures due to high electrothermal stress in power semiconductors. The project aims to develop a novel physics-informed, data-driven approach for accurately modelling and predicting the reliability of power electronics in these contexts.

Through the creation of high-quality lifecycle datasets—using experimental tests and industry input—the research will enable robust statistical learning and hybrid modelling approaches for reliability prediction. The methodology will be extended to develop a real-time, multi-modal health monitoring and prognostics framework, integrating electrothermal, operational, and hybrid data streams. This will allow responsive lifetime prediction under diverse mission profiles, representative of real-world net-zero systems.

Beyond reliability prediction, the project will explore creative extensions such as sustainability-aware modelling (including lifecycle efficiency and degradation-aware operation) and multi-modal data fusion for enhanced device failure prediction and early warning mechanisms. These innovations aim to uncover deeper correlations between electrothermal stress, failure mechanisms, and system lifetime, ultimately reducing failure rates and improving the performance and sustainability of renewable energy systems.

The student will join the Autonomous Systems and Connectivity (ASC) Division at the University of Glasgow, a dynamic research environment with strong international links and expertise in advanced engineering and applied sciences. The project offers close academic and industrial supervision, weekly meetings, and mentorship. A placement of at least six months with the industrial sponsor (Toshiba Europe) is included, with possible extensions. Research outcomes will be disseminated through leading international conferences and engagement with communities such as the IEEE Power Electronics Society (PELS UK&I Chapter), as well as through industry collaboration. Developed prototypes will be evaluated in real operational environments to deliver impact beyond academia.

Learning and development opportunities include collaboration with the industrial sponsor, training in advanced software, hardware, and technologies for power semiconductor, power electronics, and AI applications, opportunities to attend workshops, conferences, and seminars, and access to unique facilities such as the CryoElectric Research Lab at the University of Glasgow and Power Electronics Labs at Toshiba Europe.

Academic criteria: Candidates should hold or expect to gain a first-class degree or a good 2.1 (or equivalent) in Engineering or a related subject. Desirable skills include modelling and analysis of power semiconductor devices, reliability modelling and lifetime prediction, computational intelligence and machine learning methods, experience with MATLAB/Simulink, SolidWorks, PSpice or equivalent tools, and hardware experience in power electronics systems. Applicants whose first language is not English must demonstrate proficiency in English (IELTS 6.5 or equivalent).

Funding: The scholarship is funded under an EPSRC IDLA partnership with Toshiba Europe. Tuition fees (home rate) are covered and a competitive stipend (over £22,000) is provided for four years. International applicants must cover the tuition fee difference between Home and International rates, which may be met through external funding or self-funded top-up.

Application process: Interested candidates should contact Dr Sheng Wang (Sheng.Wang@glasgow.ac.uk) with a CV and a one-page cover letter to discuss suitability. Interviews will be conducted on a rolling basis during the advertisement period. The application deadline is 15 June 2026, with a start date of 30 September 2026.