Parameter Estimation of Power Electronic Converters With Physics-Informed Machine Learning

Physics-informed machine learning (PIML) has been emerging as a promising tool for applications with domain knowledge and physical models. To uncover its potentials in power electronics, this article proposes PIML-based parameter estimation method demonstrated by case study of dc–dc Buck converter. A deep neural network the dynamic models converter are seamlessly coupled. It overcomes challenges related to training data, accuracy, robustness which typical data-driven approach has. This exemplary application envisions provide new perspective tailoring existing tools electronics.