MagNet: An Open-Source Database for Data-Driven Magnetic Core Loss Modeling

Haoran Li, Diego Serrano, Thomas Guillod, Evan Dogariu, Andrew Nadler, Shukai Wang, Min Luo, Vineet Bansal, Yuxin Chen, Charles R. Sullivan, Minjie Chen

Research output: Contribution to conferencePaperpeer-review

36 Scopus citations

Abstract

This paper introduces an open-source database-MagNet-for data-driven magnetic core loss modeling. MagNet aims to support data-driven magnetics research by hosting a large amount of experimentally measured excitation waveform data for many materials across a variety of operating conditions. This database in its current state contains over 150,000 excitation waveforms for six ferrite materials-TDK{N27, N49, N87}, Ferroxcube{3C90, 3C94}, Fair-Rite{78}-in the 50 kHz to 500 kHz, 10 mT to 300 mT range for sinusoidal, triangle, and trapezoidal waveforms. This paper presents the purposes of building MagNet, introduces the data acquisition system and data format, discusses the data quality, and presents a few examples of using this database with data driven methods.

Original languageEnglish (US)
Pages588-595
Number of pages8
DOIs
StatePublished - 2022
Event37th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2022 - Houston, United States
Duration: Mar 20 2022Mar 24 2022

Conference

Conference37th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2022
Country/TerritoryUnited States
CityHouston
Period3/20/223/24/22

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Keywords

  • core loss
  • data-driven method
  • machine learning
  • neural network
  • power magnetics

Fingerprint

Dive into the research topics of 'MagNet: An Open-Source Database for Data-Driven Magnetic Core Loss Modeling'. Together they form a unique fingerprint.

Cite this