TY - JOUR
T1 - Parameter Estimation of Power Electronic Converters with Physics-Informed Machine Learning
AU - Zhao, Shuai
AU - Peng, Yingzhou
AU - Zhang, Yi
AU - Wang, Huai
N1 - Publisher Copyright:
© 1986-2012 IEEE.
PY - 2022/10/1
Y1 - 2022/10/1
N2 - 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 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.
AB - 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 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.
KW - Buck converter
KW - condition monitoring
KW - deep neural network
KW - physics-informed machine learning (PIML)
KW - prognostics and health management
UR - http://www.scopus.com/inward/record.url?scp=85130501937&partnerID=8YFLogxK
U2 - 10.1109/TPEL.2022.3176468
DO - 10.1109/TPEL.2022.3176468
M3 - Journal article
AN - SCOPUS:85130501937
SN - 0885-8993
VL - 37
SP - 11567
EP - 11578
JO - IEEE Transactions on Power Electronics
JF - IEEE Transactions on Power Electronics
IS - 10
ER -