England (Commonwealth Union) – Artificial Intelligence (AI) continues to be a significant factor in multiple areas of our lives, mostly beneficial but some invasive. This has been raising concerns among privacy activists and civil liberties groups who have emphasized that the expansion of AI should in no way be applied to violate people’s privacy.
A new and more effective method of modelling and designing power electronic converters utilizing AI has been produced by a research team from Cardiff University and the Compound Semiconductor Applications (CSA) Catapult. The method can save time by lowering design times for technology by up to 78% when contrasted with traditional approaches and applied to produce a device with an efficiency greater than 98%.
The study was published in the IEEE Open Journal of Power Electronics and IEEE Transactions on Power Electronics.
A power converter, an electrical device that transforms electrical energy, is able to convert alternating current into direct current and vice versa. It is also capable of altering the voltage or frequency of a current. Power converters play a role in a wide variety of technologies, from mobile phones, computers and televisions to renewable energy and EVs.
Current procedures of designing power converters are dependent on complex mathematical models that largely elevate the computational time and complexity of the design procedure. A well-designed power electronic converter needs high efficiency, low volume, be lightweight and be economical with minimal failure rate.
The team explored a new design procedure, applying a form of AI referred to as artificial neural networks, that applies algorithms and computing systems imitating the interconnected human brain neural network.
“Automated power electronics design optimization enables the full exploitation of wide bandgap power semiconductor advantages when compared to their silicon counterparts. We are excited to be working with Cardiff University in this innovative area,” said Dr Ingo Lüdtke, Head of Power Electronics at CSA Catapult who Co-authored the study.
