PhD Vacancy
Modern low‑carbon energy systems such as photovoltaic (PV) arrays and battery energy storage systems (BESS) generate extensive measurement data (electrical, thermal, imaging and diagnostic).
However, there is currently no generic, metrology‑grounded AI/ML framework that fuses these heterogeneous data with physics‑based models to create trustworthy, asset‑specific digital twins with quantified uncertainty.
This project will develop a measurement‑science‑driven digital twin framework for energy assets, initially demonstrated on PV modules/fields and battery systems using existing NPL datasets. The work will integrate suitable physics‑based models (for example PV performance modelling, electro‑thermal and thermofluid dynamics) with deep learning and multi‑fidelity modelling.
Bayesian fusion/inference methods will also be integrated for state estimation, uncertainty quantification, anomaly detection, remaining‑life prediction and operational optimisation.
Research aims and indicative work packages: develop a generalisable, multisensory digital twin methodology for PV and battery systems that is metrology‑guided and uncertainty‑aware.
Indicative Work Packages
* Create Bayesian data fusion and uncertainty quantification approaches that deliver traceable confidence intervals for model outputs to aid decision making.
* Validate the framework using calibrated datasets (including ageing, diagnostic, thermal and electrical performance measurements).
* Demonstrate asset health assessment capabilities, including anomaly detection and remaining‑life prediction with quantified uncertainty.
* Align outputs with emerging best practice in digital metrology for energy systems and support dissemination through stakeholder engagement routes.
Training Environment and Collaboration
NPL will provide the measurement‑science foundation, calibrated datasets, specialist support in data science and uncertainty, and host the student for an extended placement with facilities and training.
Mansim will provide industrial supervision, training and access to commercial CFD/AI platforms and representative industrial case studies, supporting rapid translation of outcomes into practice.
Eligibility
Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science or engineering related discipline.
Essential: Degree in engineering, physical sciences, computer science, or a closely related discipline (typically first‑class or high 2:1, or equivalent; master’s welcome). Strong programming skills (e.g. Python, MATLAB, C/C++). Strength in at least two of: machine/deep learning, numerical modelling, statistics, optimisation, scientific computing. Ability to work across disciplines and collaborate with academic and industrial teams.
Desirable:
* Experience in Bayesian inference, probabilistic modelling, or uncertainty quantification.
* Experience in deep learning for time‑series, imagery, and/or multimodal data.
* Energy systems knowledge (PV, batteries) or experience with real measurement datasets.
* Physics‑based simulation, surrogate modelling, or multi‑fidelity methods.
}
Funding
This 3.5‑year PhD project is fully funded. Home students, and EU students with settled status, are eligible to apply. The successful candidate will receive an annual tax‑free stipend set at the UKRI rate (£21,805 for 2026/27) with tuition fees paid; we expect the stipend to increase each year. The start date is October 2026.
Link to apply: https://www.findaphd.com/phds/project/data-driven-digital-twins-for-measured-energy-systems/?p184389
#J-18808-Ljbffr