The White Papers were prepared by an ECPE Task Force comprising of almost 40 renowned international experts from industry and academia and is intended to promote dialogue within the power electronics community. 

Download Area

About the Task Force

The Task Force consists of Subgroups, chaired by Prof. Dr. Uwe W. Drofenik (Technical University of Vienna), Prof. Dr. Johann W. Kolar (ETH Zurich), Kevin Hermanns (PE Systems), Dr. Nima Tashakor (Volkswagen), Vasilij Baumann (InstruNEXT), Sven Meier (FAPS/Friedrich-Alexander Univ. Erlangen-Nuremberg), Dr. Mohammed Ali Khan (SDU Sønderborg), Dr. Varaha S. Bharath Kurukuru (SAL Silicon Austria Labs), Prof. Dr. Oliver Wallscheid (University of Siegen), that trace the fundamentals and application of AI methods and tools throughout the entire life cycle of a power electronics product from early development and manufacturing to the operational phase.

Motivation and scope

AI is changing how we live and work. The ECPE network therefore asked what impact AI already has on power electronics and where its future potential lies. The White Paper aims to raise awareness, provide a platform for discussion within the community and strengthen collaboration between industry and academia. AI's key potential lies in speed and, with it, cost: shorter development and testing times for faster time-to-market, optimized production with fewer failures and rejects, and intelligent condition and service-life monitoring in the field. The vision is not a fully automated engineering process but an AI-assisted engineer with outstanding work efficiency. The White Paper concentrates on the use of AI methods and tools in power electronics, not on the role of power electronics in AI data centres. AI is looked at through three lenses: pattern recognition with machine learning and deep neural networks, large language models as design assistants, and reinforcement learning for exploratory converter development.  

Why it matters

Across the use cases considered, the paper concludes that the main industrial opportunity of AI in power electronics lies not in replacing established engineering models, but in augmenting them where modeling effort, parameter drift or multidimensional nonlinearities limit conventional approaches. The most promising path is therefore hybrid AI: bounded, monitorable and physics-aligned methods that can be embedded into existing product architectures while meeting requirements on real-time capability, safety, cybersecurity and lifecycle robustness. With this orientation, the White Paper is intended to help developers, manufacturers and researchers put AI to work where it delivers the most value and to keep it reliable in real products.

'AI is entering power electronics at remarkable speed, bringing real opportunities: shorter development cycles, smarter production, and better monitoring of products in the field. That is why its use must be guided by methods that are transparent, robust and grounded in physics. Much research is still needed, and with this White Paper we want to advance the dialogue between industry and academia.'  Dipl.-Phys. Thomas Harder, General Manager of ECPE