MagNet Challenge for Data-Driven Power Magnetics Modeling

This article summarizes the main results and contributions of the MagNet Challenge 2023, an open-source research initiative for data-driven modeling of power magnetic materials. The MagNet Challenge has (1) advanced the state-of-the-art in power magnetics modeling; (2) set up examples for fostering an open-source and transparent research community; (3) developed useful guidelines and practical rules for conducting data-driven research in power electronics; and (4) provided a fair performance benchmark leading to insights on the most promising future research directions. The competition yielded a collection of publicly disclosed software algorithms and tools designed to capture the distinct loss characteristics of power magnetic materials, which are mostly open-sourced. We have attempted to bridge power electronics domain knowledge with state-of-the-art advancements in artificial intelligence, machine learning, pattern recognition, and signal processing. The MagNet Challenge has greatly improved the accuracy and reduced the size of data-driven power magnetic material models. The models and tools created for various materials were meticulously documented and shared within the broader power electronics community.

Authors

Institutions

Publication Details

Journal
IEEE Open Journal of Power Electronics
Published
2024-09-30
DOI
https://doi.org/10.1109/ojpel.2024.3469916
Citations
25
Primary Topic
Electric Motor Design and Analysis
Type
article
Field-Weighted Citation Impact
5.22

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

MagNet Challenge for Data-Driven Power Magnetics Modeling

Diego Serrano, Charles R. Sullivan, Wilhelm Kirchgässner, Dingsihao Lyu et al.
25 citations
IEEE Open Journal of Power Electronics
Electric Motor Design and Analysis
5.22
article

MagNet Challenge for Data-Driven Power Magnetics Modeling

Diego Serrano, Charles R. Sullivan, Wilhelm Kirchgässner, Dingsihao Lyu, Oliver Wallscheid, Min Yang, Emmanuel Havugimana, Bailey Sauter, C. Ragusa, Jing Xu, Lijun Hang, Chushan Li, Gaoyuan Wu, David J. Perreault, Fanghao Tian, Jian-De Li, Xiang Ma, Wilmar Martínez, Xiaobing Shen, Jacob Reynvaan, Jian Liu, Himanshu Bhusan Sandhibigraha, Sicheng Wang, Yan Zhou, Thomas Guillod, Ming Cheng, Zhongqi Shi, Yu Dou, Wei Qin, Ziheng Xiao, Tianming Luo, S.Y.R. Hui, Han Cui, Cao Zhan, Zhanlei Liu, Navid Rasekh, Reza Mirzadarani, Yi Tang, Jiyao Wang, Mohamad Ghaffarian Niasar, Jun Wang, Yun-Shan Hsieh, Vivek Thomas Chacko, Yue Wu, Kai Sun, Borja Alberdi, Xinyu Liu, Johann W. Kolar, Iosu Aizpuru, Zian Qin, Minmin Zhang, Asier Arruti, Shivangi Sinha, Chih‐Hsien Hsia, Ruijun Liu, Youkang Hu, J. A. Kong, Dragan Maksimović, Luigi Solimene, Sritharini Radhakrishnan, Till Piepenbrock, Wei Xu, Sichen Wang, Skye Reese, Mike K. Ranjram, Shukai Wang, Yang Li, Daniel Costinett, Yongbin Jiang, Yuchen Dong, Mecon Joshi, Vishnu Mahadeva Iyer, Hao Song, Tianxiang Hu, Yongliang Dang, Sinan Li, Nikolas Förster, Alfonso García Martínez, Syed Irfan Ali Meerza, Kody Froehle, Oliver Schweins, Anartz Agote, Dixant Bikal Sapkota, Puskar Neupane, Haoran Li, Duo Wang, Song Liu, Yiting Chen, Lu Wang, Yuchen Liu, Ying Zhang, Chen Chen, Rui Zhang, Xia Chen, Yinan Yao, Yibo Lu, Zheng Wang, Lichen Yu, Minjie Chen, Chengbo Li, Boyu Zhang, Yukun Zhang, Bowen Su, Yiyi Wang, Hao Wu, Lie Zhang, Lizhong Zhang, Shuai Jiang, Yunhao Xiao, Neeraj Agrawal, Lumeng Xu, Martin Stoiber, Qiujie Huang, Zhengzhao Li, Alessio Giuffrida, Fabio Marmello, Simone Morra, Qingcheng Sui, T. Shen, David Shumacher, Tom McKeague, Bo Li, Tzu-Chieh Hsu, Shahabuddin Khan, Binyu Cui, Nicolò Lombardo, Marco Pasquale, Neha Rajput, Chaoying Mei, Rui Zhao, Yaohua Li, Na Wang
article en
25 citations

Abstract

This article summarizes the main results and contributions of the MagNet Challenge 2023, an open-source research initiative for data-driven modeling of power magnetic materials. The MagNet Challenge has (1) advanced the state-of-the-art in power magnetics modeling; (2) set up examples for fostering an open-source and transparent research community; (3) developed useful guidelines and practical rules for conducting data-driven research in power electronics; and (4) provided a fair performance benchmark leading to insights on the most promising future research directions. The competition yielded a collection of publicly disclosed software algorithms and tools designed to capture the distinct loss characteristics of power magnetic materials, which are mostly open-sourced. We have attempted to bridge power electronics domain knowledge with state-of-the-art advancements in artificial intelligence, machine learning, pattern recognition, and signal processing. The MagNet Challenge has greatly improved the accuracy and reduced the size of data-driven power magnetic material models. The models and tools created for various materials were meticulously documented and shared within the broader power electronics community.

IEEE Open Journal of Power ElectronicsVol. 6
Dartmouth College (US), National Taipei University of Technology (TW), Google (United States) (US), The University of Sydney (AU), Tribhuvan University (NP), Mondragon Unibertsitatea (ES), City University of Hong Kong (HK), Nanyang Technological University (SG), Politecnico di Torino (IT), Hebei University of Technology (CN), University of Colorado Boulder (US), Princeton University (US), Paderborn University (DE), University of Bristol (GB), Nanjing University of Posts and Telecommunications (CN), Silicon Austria Labs (Austria) (AT), Würth Elektronik (Germany) (DE), Zhejiang University-University of Edinburgh Institute (CN), Enphase Energy (United States), Hangzhou Dianzi University (CN), École Polytechnique Fédérale de Lausanne (CH), Arizona State University (US), Indian Institute of Science Bangalore (IN), Massachusetts Institute of Technology (US), University of Tennessee at Knoxville (US), Southeast University (CN), Fuzhou University (CN), Xi'an Jiaotong University (CN), University of Hong Kong (HK), Delft University of Technology (NL), Tsinghua University (CN), KU Leuven (BE)
National Science Foundation, Princeton University, Advanced Research Projects Agency - Energy, Advanced Research Projects Agency
Affordable and clean energy
Openalex Percentile: Top 4%
Electric Motor Design and Analysis
5.22
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.