Tutorials

We have learned by now to design and produce small and robust power electronic equipment, supported by developments in material and device sciences. A rising awareness as to the full life cycle of these products is observed nowadays – health and condition monitoring  (HCM) technologies presenting a major lever in mitigating our impact on our planet, in the context of resource use and waste.

The tutorial will start by a review of the HCM perimeter – the business models, impeding legislation, the equipment suitable for being addressed by HCM and a brief summary of common technologies used to implement HCM. We will then move to Remaining Useful Life (RUL) Estimation concepts for power modules – the basic building blocks, their requirements, what are the cost-driven choices and the common implementations. The tutorial will wrap up with advanced techniques, stemming from RUL, that can be used for adding real value to HCM for lifetime extension such as stress steering and self-healing.

This scientific tutorial explores the emerging role of Artificial Intelligence (AI) techniques in revolutionizing power electronics engineering processes. The presentation begins with an overview of the AI hype cycle, highlighting key technologies influencing various levels of power electronics design and optimization. The tutorial then delves into three main topics.
First, it compares sampling and optimization approaches for large-scale simulations, discussing the limitations of random and genetic algorithm methods in high-dimensional spaces. The presentation introduces AI-motivated searching strategies, particularly focusing on Continuous Active Random Search (CARS), which offers an adaptable trade-off inspired by Reinforcement Learning (RL) techniques.
Second, the tutorial examines inter- and extrapolation of engineering data using both established and novel neural network architectures. It showcases the MagNet Challenge, demonstrating accurate prediction of magnetic losses, and compares standard fully connected Neural Networks (NN) with Kolmogorov-Arnold Networks (KAN) for power electronics circuit simulations. The discussion addresses challenges in modeling highly non-linear behaviors and precise prediction of realistic operation points in resonant converter topologies.
Lastly, the tutorial explores Physics-Informed Neural Networks (PINN) for transformer design, highlighting their ability to predict relevant power electronic quantities for arbitrary 2D transformer geometries without relying on empirical data. This approach opens new possibilities for on-the-fly optimizations in power electronics design purely driven by the fundamental physical equations.
Through these topics, the tutorial provides a comprehensive overview of how AI is transforming power electronics engineering, offering insights into advanced modeling, optimization, and design techniques.

This two-part tutorial series presents innovative approaches to enhance power electronics through advanced thermal simulations and generative AI. Participants will gain insights into the latest tools and techniques for creating accurate thermal models and optimizing power modules, ensuring reliability, efficiency, and longevity. The sessions offer practical knowledge and real-world examples, providing attendees with valuable skills for the future of power electronics.

Part 1: Power Electronics Package Modelling for Advanced Thermal Simulations (Christian Mentin)

Explore the use of advanced thermal simulations in designing power electronics packages. Learn about cutting-edge tools and techniques for accurate thermal modelling, enabling the prediction and resolution of heat-related issues.

Part 2: Generative AI-Driven Characterization and Optimization of Power Modules (Varaha Satya Bharath Kurukuru)

Discover how generative AI transforms the design and optimization of power modules. This session demonstrates AI’s role in automating and enhancing the characterization process, leading to precise thermal measurement and control. Learn how AI-driven optimization results in power modules with extended lifetime and superior performance.

Join us to explore how you can seamlessly transition from offline simulation to real controller implementation, maintaining model continuity design phases through practical implementation and testing. Offline and real-time simulations impose distinct requirements that influence the choice of modelling approach, numerical solver, system architecture, as well as their usability across different development stages. This tutorial will showcase how Typhoon HIL’s integrated model-based engineering solutions address these challenges, demonstrating how you can streamline the development of your power electronics research or product. Using an example, we will cover the integrated workflow from early design in offline simulations, through automatic code generation for target microcontrollers, to real-world testing using real-time hardware-in-the-loop.