Open-source Datasets
AI-Power generated open-source dataset for power electronics applications
Datasets for power electronics applications
Accelerating data-driven research in power electronics
Degradation dataset for power modules
A good end-of-life (EOL) criterion offers timely warnings prior to catastrophic failure while maximizing the utilization of devices. Apart from achieving this trade-off, ensuring consistency of utilization among different devices and conditions is equally important. Our recent paper provides a potential one: "gEOL: A Gradient-based End-of-Life Criterion for Power Semiconductor Modules" on IEEE Trans.Power Electronics. Its effectiveness has been substantiated through data from power cycling tests. The paper is open-access with the testing dataset at https://dx.doi.org/10.21227/ksrt-zq09
Physics-informed ML for Digital twin of Power Converter
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 research proposes a PIML-based parameter estimation method demonstrated by a case study of DC-DC Buck converter. A deep neural network and the dynamic models of the converter are seamlessly coupled. It overcomes the challenges related to training data, accuracy, and robustness which a typical data-driven approach has. This exemplary application envisions to provide a new perspective for tailoring existing machine learning tools for power electronics. The data and code are open-sourced at https://github.com/ms140429/PIML_Converter