Application of Machine Learning to Transformer Design Optimization

How to apply: uom.link/pgr-apply-2425 [uom.link]

This 3.5-year PhD studentship is open to Home (UK) applicants. The successful candidate will receive an annual tax-free stipend set at the UKRI rate (£20,780 for 2025/26; subject to annual uplift) plus £5,000 top-up, and tuition fees will be paid. We expect the stipend to increase each year.

We recommend that you apply early as the advert will be removed once the position has been filled.

Economically efficient design of high voltage power transformers is essential in addressing the escalating demands for electricity in the decarbonizing world. Traditional transformer design methodologies have predominantly relied on manual techniques, requiring the transformer designer to balance multiple competing objectives such as cost, dimensional constraints and operational performance. A power transformer is a complex physical system with inherent non-linearities and multidimensional aspects. Multiple design software platforms are used to fulfil the mechanical, thermal and electrical requirements and manual iterations are performed to identify the optimal design based on experience and expertise. The existing research has introduced the optimization of transformer design using brute force methods by using non-discriminate parameter variations and recently innovative approaches using artificial neural networks (ANNs) are also developed for the prediction of transformer parameters (no-load losses, winding gradient, load losses). Building upon this existing body of work, the proposed research project aims to explore AI models and ML algorithms which are suitable for transformer design optimization and develop a software tool which can aid the design processes.

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.

We strongly recommend that you contact the supervisors for this project before you apply. Please include a CV, details of your current level of study, academic background and any relevant experience and include a paragraph about your motivation to study this PhD project.

Please note that CVs cannot be sent through the FindAPhD website. You can email the supervisors directly at: Prof Zhongdong Wang (zhongdong.wang@mancheser.ac.uk) and Prof Peter Crossley (peter.crossley@manchester.ac.uk).

Advert information