MagNet: An Open-Source Database for Data-Driven Magnetic Core Loss Modeling
Authors:
- 20 March 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 588-595
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.Keywords
Funding Information
- Princeton University
This publication has 25 references indexed in Scilit:
- Deep learningNature, 2015
- Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition2015
- A Systematic Approach to Modeling Impedances and Current Distribution in Planar MagneticsIEEE Transactions on Power Electronics, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Neural network-based software tool for predicting magnetic performance of strip-wound magnetic cores at medium to high frequencyIEE Proceedings - Science, Measurement and Technology, 2004
- A Dynamic Core Loss Model for Soft Ferromagnetic and Power Ferrite Materials in Transient Finite Element AnalysisIEEE Transactions on Magnetics, 2004
- Summary of losses in magnetic materialsIEEE Transactions on Magnetics, 2002
- Neural networks for the prediction of magnetic transformer core characteristicsIEEE Transactions on Magnetics, 2000
- Ferrite core loss for power magnetic components designIEEE Transactions on Magnetics, 1991
- 30 years of adaptive neural networks: perceptron, Madaline, and backpropagationProceedings of the IEEE, 1990