AES Semigas


7 December 2022

Cardiff and CSA Catapult develop AI method to optimize wide-bandgap power electronic converters

A new and more efficient way of modeling and designing power electronic converters using artificial intelligence (AI) has been created by a team at Cardiff University and the Compound Semiconductor Applications (CSA) Catapult (headquartered in Newport, South Wales). CSA Catapult’s Power Electronics laboratory enables innovation through comprehensive modeling, characterization, integration and validation facilities for power converters with higher efficiency and reliability with reduced size, weight and system cost. Working strategically with academic partners like Cardiff University, CSA Catapult bridges the gap between research and application development.

Existing methods of designing power converters largely rely on complex mathematical models that significantly increase the computational time and complexity of the design process. The new method has reduced design times for technology by up to 78% compared with traditional approaches and was used to create a device with an efficiency of over 98% (IEEE Open Journal of Power Electronics and IEEE Transactions on Power Electronics).

A well-designed power electronic converter must have high efficiency, small volume, be lightweight and have low cost and a low failure rate. Therefore, the main goal of a power converter design method is to identify the best trade-off among these performance indicators.

In their study, the team explored a new design method using artificial neural networks (ANN) that uses algorithms and computing systems that mimic the interconnected neural networks of the human brain. The ANN was trained on an existing dataset of over 2000 designs, so the team could select the most appropriate design for the desired efficiency and power density. The team selected four major components for the ANN-based design, including the gallium nitride (GaN) power field-effect transistors (FETs), inductors, capacitors, and heat-sinks.

The design approach was validated through experimental tests on a GaN-based single-phase inverter that was created using the specified design. The efficiency and power density of the device was well matched to the design and within the range of existing devices, making it technically competitive and commercially viable.

“Accurate and fast transient modelling/simulation approaches are essential to efficiently and to rapidly optimize the performance of wide-bandgap power electronics systems,” says the study’s co-author Dr Wenlong Ming, senior lecturer at Cardiff University and senior research fellow at CSA Catapult.

“Automated power electronics design optimization enables the full exploitation of wide-bandgap power semiconductor advantages when compared to their silicon counterparts,” adds co-author Dr Ingo L├╝dtke, head of power electronics at CSA Catapult.

Established in 2017 by UK Government agency Innovate UK (which provides funding and support for business innovation as part of UK Research and Innovation), CSA Catapult is a not-for-profit organization focused on accelerating the adoption of compound semiconductors and on bringing applications to life in four technology areas: power electronics, RF & microwave, advanced packaging, and photonics. It works across the UK in a range of industry sectors from automotive to medical, and from digital communications to aerospace.

Tags: CSA Catapult Power electronics