Digital Twins in Power Electronics: A Comprehensive Approach to Enhance Virtual Thermal Sensing

The traditional approaches in material research and hardware design are insufficient to address the evolving operation and maintenance (O&M) demands in contemporary power electronics. Overengineering and data acquisition practices lead to unsustainable costs and reduced profit margins. Digital twins (DTs), defined as real-time simulation models of physical systems, emerge as promising solutions to meet stringent O&M requirements. In power electronics, DTs offer significant potential in thermal management, crucial for control performance, safety, and system lifespan. This article aims to analyze the development of computationally efficient and high-fidelity DTs tailored for power electronics applications, emphasizing their predictive reliability of critical temperatures. The proposed physics-based approach is enhanced by integrating data-driven artificial intelligence (AI)-based techniques to achieve this goal. The predictive reliability of the DTs produced through this workflow is then experimentally validated for a power electronic converter designed for induction heating applications. Experimental results show that the integration of data-driven AI-based techniques allows for maintaining very high predictive accuracy even when multiple semiconductor component suppliers are considered for the same product, which is often the case for industrial products. In addition, by implementing and executing the DT in a low-power microprocessor, the real-time execution is demonstrated, affirming its practical applicability.