AI-Enhanced EMC Digital Twin for Automotive WBG Converters

AI-Enhanced EMC Digital Twin for Automotive WBG Converters

Eligibility: UK/International (including EU) graduates with the required entry requirements

Duration: Full-Time – between three and three and a half years fixed term

Interview date: Will be confirmed to shortlisted candidates

The global shift toward electric mobility requires automotive power electronics with elevated power density, thermal performance, and efficiency. Adopting Wide-Bandgap (WBG) semiconductors, like Silicon Carbide (SiC) and Gallium Nitride (GaN), enables extreme switching frequencies and reduced losses. However, the fast switching transients produce severe high-frequency electromagnetic interference (EMI). Ensuring compliance with automotive standards (such as CISPR 25) traditionally requires extensive physical pre compliance testing late in the product cycle, resulting in costly iterations.

This PhD project addresses this bottleneck by developing a predictive, multi-domain Electromagnetic Compatibility (EMC) Digital Twin framework. The research combines electromagnetic modelling, machine learning, and hardware validation to deliver rapid virtual pre-compliance evaluation for automotive power converters.

This 3.5-year PhD studentship aims to develop an AI-driven Digital Twin capable of predicting high-frequency conducted and radiated emissions against CISPR standards, bridging 3D virtual simulations with real-world physical compliance testing.

The student will undertake a structured programme of virtual modelling, AI development, and experimental validation. Initial activity will involve designing baseline and degraded EMI layout prototypes for WBG converters and extracting layout parasitics using 3D electromagnetic solvers. Using these datasets, dual AI surrogates will be developed: a Gaussian Process Regression (GPR) model for low-frequency conducted emissions, and a Physics-Informed Neural Network (PINN) that embeds Maxwell’s equations to predict spatial radiated fields. These surrogates will be integrated into a unified digital twin. Finally, the virtual framework will be validated and calibrated against prototype hardware.

Experimental diagnostics will utilise Coventry University’s pre-compliance laboratories to calibrate the AI models. By improving the reliability of virtual EMC screening, this project will help reduce the cost, risk, and time required to develop next-generation automotive power electronics.

Funding

Tuition fees and bursary

The successful candidate will receive comprehensive research training including technical, personal and professional skills. All researchers at Coventry University (from PhD to Professor) are part of the Doctoral and Researcher College, which provides support with high-quality training and career development activities.

Entry requirements

• A minimum of a 2:1 first degree in a relevant discipline/subject area with a minimum 60% mark in the project element or equivalent with a minimum 60% overall module average.

PLUS

• The potential to engage in innovative research and to complete the PhD within 3.5 years.
• A minimum of English language proficiency (IELTS academic overall minimum score of 6.5 with a minimum of 6.0 in each component).

Additional requirements

This studentship is suitable for candidates with a background in Electrical/Electronic Engineering, Power Electronics, Automotive Engineering, Computer Science, Applied Mathematics, or a related discipline. Applicants must be highly motivated, possess strong analytical problem-solving skills, and be able to rapidly master new simulation environments, analytical evaluation techniques, and experimental frameworks.

Ideal candidates will also possess the following technical skills and competencies:

• Strong theoretical knowledge of circuit analysis, power electronics, or electromagnetic principles.
• Experience in mathematical or computational programming.
• Knowledge of circuit simulation tools (SPICE/PWL based).
• Knowledge of, or a willingness to learn, 3D electromagnetic simulation tools.
• An interest in, or basic knowledge of, artificial intelligence and machine learning frameworks.

All applications require full supporting documentation, a covering letter, plus a 2000-word supporting statement showing how the applicant’s expertise and interests are relevant to the project.

Priory Street
Coventry CV1 5FB
United Kingdom

#J-18808-Ljbffr

Full job description from WhatJobs. Apply for this role →