@inproceedings{429a30c6fd964973a1b687a56c84350a,
title = "MagNet: A Machine Learning Framework for Magnetic Core Loss Modeling",
abstract = "This paper presents a two-stage machine learning framework - MagNet - for magnetic core loss modeling. The first stage of MagNet is a waveform transformation network, which generates 2-D images(tensors) and extracts both the frequency and time domain features from the magnetic excitation waveforms; the second stage of MagNet is a convolutional neural network (CNN), which is trained to recognize the patterns in the 2-D images and predict the core loss based on regression. MagNet is supported by a hardware-in-the-loop (HIL) data acquisition system. The system can automatically generate a large amount of data to train the neural network models. MagNet achieved an average relative error of around 5% for single-frequency core loss prediction. In addition to experimental measurements, MagNet can also be trained with data provided on the datasheets of magnetic materials to improvethe accuracy.",
keywords = "convolutional neural network, core loss modeling, machine learning, wavelet transform",
author = "Haoran Li and Lee, {Seungjae Ryan} and Min Luo and Sullivan, {Charles R.} and Yuxin Chen and Minjie Chen",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 21st IEEE Workshop on Control and Modeling for Power Electronics, COMPEL 2020 ; Conference date: 09-11-2020 Through 12-11-2020",
year = "2020",
month = nov,
day = "9",
doi = "10.1109/COMPEL49091.2020.9265869",
language = "English (US)",
series = "2020 IEEE 21st Workshop on Control and Modeling for Power Electronics, COMPEL 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2020 IEEE 21st Workshop on Control and Modeling for Power Electronics, COMPEL 2020",
address = "United States",
}