AlGaN Power Electronics for Electric Vehicles: AI-Enhanced Design, Simulation, and Characterization

About the project

About the Project Applications are invited for a self-funded, 3 year full-time or 6 year part-time PhD project. The PhD will be based in the School of Electrical and Mechanical Engineering and supervised by Dr Mahsa Mehrad . The work on this project will: Develop next-generation AlGaN power electronic devices for high-efficiency electric vehicles (EV). Combine TCAD simulation, electrical measurements, and AI-based optimization to accelerate device design. Explore ultra-high-voltage AlGaN HEMT architectures for on-board chargers, DC–DC converters, and inverter stages. Use machine learning models to predict device behaviour, reliability, and degradation under EV operating conditions. Design and simulate advanced AlGaN-based power devices using TCAD tools to achieve high efficiency and high breakdown performance for EV applications. Perform advanced electrical characterization of AlGaN prototype devices using state-of-the-art measurement techniques. Apply AI and machine learning methods to accelerate device optimization, predict performance, and analyze reliability trends. Evaluate device behaviour under realistic EV operating conditions (high voltage, high temperature, fast switching). Collaborate with semiconductor and automotive industry partners, gaining experience in translating research into practical power electronics solutions. Project description Electric vehicles (EVs) are placing unprecedented demands on power electronic systems, requiring devices that can switch faster, operate at higher voltages, withstand higher temperatures, and maintain long-term reliability. To meet these challenges, wide-bandgap semiconductor materials—especially Aluminum Gallium Nitride (AlGaN)—are emerging as a key technology. This project investigates the design, modelling, characterisation, and AI-assisted optimisation of AlGaN high-electron-mobility transistors (HEMTs) for next-generation EV power electronics. The research integrates advanced simulation, innovative characterisation methods, and data-driven performance prediction to accelerate the development of efficient, compact, and robust semiconductor devices. The increasing global adoption of electric vehicles is driving the need for more efficient, compact, and reliable power electronic systems. Power devices are central to EV performance, influencing drivetrain efficiency, charging speed, thermal management, and battery lifetime. As conventional silicon devices approach their limits, wide-bandgap semiconductors offer a transformative opportunity. Among these materials, Aluminium Gallium Nitride (AlGaN) is particularly promising due to its high breakdown field, low on-resistance, and inherent robustness in demanding operating environments. This PhD project aims to advance the design and understanding of AlGaN high-electron-mobility transistors (HEMTs) tailored specifically for EV applications. The research will combine detailed numerical simulation, precision electrical characterisation, and artificial intelligence (AI) methodologies to accelerate device optimisation. Simulation activities will involve the use of TCAD tools to analyse device physics, explore design variations, and evaluate performance trade-offs under realistic automotive conditions, including high voltage, high temperature, and fast-switching regimes. Complementing the simulation work, the project will employ advanced electrical measurement techniques to characterise prototype AlGaN devices. Measurements may include static and dynamic I–V characterisation, capacitance evaluation, switching performance analysis, and reliability testing. These experiments will generate high-quality datasets essential for validating simulation models and informing device improvement strategies. A key component of the project involves integrating AI and machine learning tools to enhance predictive modelling and design optimisation. By learning from simulation and measurement data, AI models will be developed to predict device behaviour, identify critical performance determinants, and accelerate the exploration of design space. This data-driven approach aims to reduce development cycles and uncover design solutions that might not emerge through conventional engineering methods. The outcomes of this project will contribute to the broader understanding of AlGaN device physics and reliability, while providing practical pathways for improving EV power electronics. The research has the potential for significant real-world impact, supporting cleaner transportation technologies and advancing the capabilities of wide-bandgap semiconductors. The student will be embedded within a supportive research environment, gaining expertise in semiconductor device simulation, electrical characterisation, data analytics, and AI-based modelling. Collaboration with academic and industrial partners may further enrich the research experience and broaden future career opportunities. General admissions criteria You'll need a good first degree from an internationally recognised university (minimum upper second class or equivalent, depending on your chosen course) or a master’s degree in electrical engineering, Electronic Engineering, Semiconductor Devices, Materials Science, Physics, or a related area. In exceptional cases, we may consider equivalent professional experience and/or Qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0. International students will require a study visa from UKVI to pursue the degree in the UK. If the research is in a sensitive or technological subject, the student may also need to secure an Academic Technology Approval Scheme (ATAS) certificate from the UK Foreign Office. Specific candidate requirements A strong academic background in the related field. Knowledge of semiconductor device physics, especially wide-bandgap or III-nitride materials (e.g., GaN, AlGaN). Experience with numerical simulation tools is highly desirable. Familiarity with electrical characterisation techniques is an advantage. Interest or experience in machine learning / AI methods for modelling, optimisation, or data analysis. Strong analytical skills and the ability to interpret complex physical phenomena. Ability to work independently and as part of a multidisciplinary research team. Good written and spoken communication skills for writing reports, publishing research findings, and presenting at conferences. How to Apply We’d encourage you to contact Dr Mahsa Mehrad ( mahsa.mehrad@port.ac.uk ) to discuss your interest before you apply, quoting the project code. When you are ready to apply, please follow the ' Apply now ' link on the Electronic Engineering PhD subject area page and select the link for the relevant intake. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘ How to Apply ’ page offers further guidance on the PhD application process. When applying please quote project code: SEM10420526

Research areas