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

被引：52

作者：

Zhao, Shuai ^{[1
]}

Peng, Yingzhou ^{[1
]}

Zhang, Yi ^{[1
]}

Wang, Huai ^{[1
]}

机构：

[1] Aalborg Univ, Dept Energy, DK-9220 Aalborg, Denmark

来源：

IEEE TRANSACTIONS ON POWER ELECTRONICS | 2022年 / 37卷 / 10期

关键词：

Power electronics; Buck converters; Voltage; Parameter estimation; Data models; Task analysis; Neural networks; Buck converter; deep neural network; prognostics and health management; physics-informed machine learning (PIML); condition monitoring; NEURAL-NETWORKS; IDENTIFICATION; SYSTEMS;

D O I：

10.1109/TPEL.2022.3176468

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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.

引用

页码：11567 / 11578

页数：12

共 28 条

[1] Advances on System Identification Techniques for DC-DC Switch Mode Power Converter Applications [J].