MagNet Challenge for Data-Driven Power Magnetics Modeling

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

doi:10.1109/OJPEL.2024.3469916

MagNet Challenge for Data-Driven Power Magnetics Modeling

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

Princeton University

Research output: Contribution to journal › Article › peer-review

Abstract

This paper 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.

Original language	American English
Journal	IEEE Open Journal of Power Electronics
DOIs	https://doi.org/10.1109/OJPEL.2024.3469916
State	Accepted/In press - 2024

ASJC Scopus subject areas

Electrical and Electronic Engineering

Keywords

Artificial Intelligence
Data-Driven Methods
Machine Learning
Open-Source
Power Ferrites
Power Magnetics

Access to Document

10.1109/OJPEL.2024.3469916

Cite this

Chen, M., Li, H., Wang, S., Guillod, T., Serrano, D., Förster, N., Kirchgässner, W., Piepenbrock, T., Schweins, O., Wallscheid, O., Huang, Q., Li, Y., Dou, Y., Li, B., Li, S., Havugimana, E., Chacko, V. T., Radhakrishnan, S., Ranjram, M., ... Sullivan, C. R. (Accepted/In press). MagNet Challenge for Data-Driven Power Magnetics Modeling. IEEE Open Journal of Power Electronics. https://doi.org/10.1109/OJPEL.2024.3469916

@article{6667767ee040497eb2e3e9f421dc5a65,

title = "MagNet Challenge for Data-Driven Power Magnetics Modeling",

abstract = "This paper 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.",

keywords = "Artificial Intelligence, Data-Driven Methods, Machine Learning, Open-Source, Power Ferrites, Power Magnetics",

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

year = "2024",

doi = "10.1109/OJPEL.2024.3469916",

language = "American English",

journal = "IEEE Open Journal of Power Electronics",

issn = "2644-1314",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Chen, M, Li, H, Wang, S, Guillod, T, Serrano, D, Förster, N, Kirchgässner, W, Piepenbrock, T, Schweins, O, Wallscheid, O, Huang, Q, Li, Y, Dou, Y, Li, B, Li, S, Havugimana, E, Chacko, VT, Radhakrishnan, S, Ranjram, M, Sauter, B, Reese, S, Sinha, S, Zhang, L, McKeague, T, Cui, B, Rasekh, N, Wang, J, Liu, S, Martinez, A, Liu, X, Mei, C, Zhao, R, Wu, G, Wu, H, Zhang, R, Song, H, Zhang, L, Lu, Y, Hang, L, Rajput, N, Sandhibigraha, HB, Agrawal, N, Iyer, VM, Shen, X, Tian, F, Sui, Q, Kong, J, Martinez, W, Arruti, A, Alberdi, B, Agote, A, Aizpuru, I, Zhang, M, Chen, X, Dong, Y, Wang, D, Shen, T, Zhou, Y, Li, Y, Wang, S, Wu, Y, Jiang, Y, Xiao, Z, Tang, Y, Hsieh, YS, Li, JD, Yu, LC, Hsu, TC, Liu, YC, Hsia, CH, Chen, C, Giuffrida, A, Lombardo, N, Marmello, F, Morra, S, Pasquale, M, Solimene, L, Ragusa, CS, Reynvaan, J, Stoiber, M, Li, C, Qin, W, Ma, X, Zhang, B, Wang, Z, Cheng, M, Xu, W, Wang, J, Hu, Y, Xu, J, Shi, Z, Sapkota, DB, Neupane, P, Joshi, M, Khan, S, Su, B, Xiao, Y, Yang, M, Sun, K, Li, Z, Mirzadarani, R, Liu, R, Wang, L, Luo, T, Lyu, D, Niasar, MG, Qin, Z, Meerza, SIA, Froehle, K, Cui, HH, Costinett, D, Liu, J, Liu, Z, Zhan, C, Dang, Y, Zhang, Y, Wang, N, Chen, Y, Zhang, Y, Li, C, Yao, Y, Hu, T, Xu, L, Wang, Y, Wang, S, Jiang, S, Shumacher, D, Maksimović, D, Hui, RSY, Kolar, JW, Perreault, DJ & Sullivan, CR 2024, 'MagNet Challenge for Data-Driven Power Magnetics Modeling', IEEE Open Journal of Power Electronics. https://doi.org/10.1109/OJPEL.2024.3469916

TY - JOUR

T1 - MagNet Challenge for Data-Driven Power Magnetics Modeling

AU - Chen, Minjie

AU - Li, Haoran

AU - Wang, Shukai

AU - Guillod, Thomas

AU - Serrano, Diego

AU - Förster, Nikolas

AU - Kirchgässner, Wilhelm

AU - Piepenbrock, Till

AU - Schweins, Oliver

AU - Wallscheid, Oliver

AU - Huang, Qiujie

AU - Li, Yang

AU - Dou, Yu

AU - Li, Bo

AU - Li, Sinan

AU - Havugimana, Emmanuel

AU - Chacko, Vivek Thomas

AU - Radhakrishnan, Sritharini

AU - Ranjram, Mike

AU - Sauter, Bailey

AU - Reese, Skye

AU - Sinha, Shivangi

AU - Zhang, Lizhong

AU - McKeague, Tom

AU - Cui, Binyu

AU - Rasekh, Navid

AU - Wang, Jun

AU - Liu, Song

AU - Martinez, Alfonso

AU - Liu, Xinyu

AU - Mei, Chaoying

AU - Zhao, Rui

AU - Wu, Gaoyuan

AU - Wu, Hao

AU - Zhang, Rui

AU - Song, Hao

AU - Zhang, Lie

AU - Lu, Yibo

AU - Hang, Lijun

AU - Rajput, Neha

AU - Sandhibigraha, Himanshu Bhusan

AU - Agrawal, Neeraj

AU - Iyer, Vishnu Mahadeva

AU - Shen, Xiaobing

AU - Tian, Fanghao

AU - Sui, Qingcheng

AU - Kong, Jiaze

AU - Martinez, Wilmar

AU - Arruti, Asier

AU - Alberdi, Borja

AU - Agote, Anartz

AU - Aizpuru, Iosu

AU - Zhang, Minmin

AU - Chen, Xia

AU - Dong, Yuchen

AU - Wang, Duo

AU - Shen, Tianming

AU - Zhou, Yan

AU - Li, Yaohua

AU - Wang, Sicheng

AU - Wu, Yue

AU - Jiang, Yongbin

AU - Xiao, Ziheng

AU - Tang, Yi

AU - Hsieh, Yun Shan

AU - Li, Jian De

AU - Yu, Li Chen

AU - Hsu, Tzu Chieh

AU - Liu, Yu Chen

AU - Hsia, Chin Hsien

AU - Chen, Chen

AU - Giuffrida, Alessio

AU - Lombardo, Nicolo

AU - Marmello, Fabio

AU - Morra, Simone

AU - Pasquale, Marco

AU - Solimene, Luigi

AU - Ragusa, Carlo Stefano

AU - Reynvaan, Jacob

AU - Stoiber, Martin

AU - Li, Chengbo

AU - Qin, Wei

AU - Ma, Xiang

AU - Zhang, Boyu

AU - Wang, Zheng

AU - Cheng, Ming

AU - Xu, Wei

AU - Wang, Jiyao

AU - Hu, Youkang

AU - Xu, Jing

AU - Shi, Zhongqi

AU - Sapkota, Dixant Bikal

AU - Neupane, Puskar

AU - Joshi, Mecon

AU - Khan, Shahabuddin

AU - Su, Bowen

AU - Xiao, Yunhao

AU - Yang, Min

AU - Sun, Kai

AU - Li, Zhengzhao

AU - Mirzadarani, Reza

AU - Liu, Ruijun

AU - Wang, Lu

AU - Luo, Tianming

AU - Lyu, Dingsihao

AU - Niasar, Mohamad Ghaffarian

AU - Qin, Zian

AU - Meerza, Syed Irfan Ali

AU - Froehle, Kody

AU - Cui, Han Helen

AU - Costinett, Daniel

AU - Liu, Jian

AU - Liu, Zhanlei

AU - Zhan, Cao

AU - Dang, Yongliang

AU - Zhang, Yukun

AU - Wang, Na

AU - Chen, Yiting

AU - Zhang, Yiming

AU - Li, Chushan

AU - Yao, Yinan

AU - Hu, Tianxiang

AU - Xu, Lumeng

AU - Wang, Yiyi

AU - Wang, Sichen

AU - Jiang, Shuai

AU - Shumacher, David

AU - Maksimović, Dragan

AU - Hui, Ron S.Y.

AU - Kolar, Johann W.

AU - Perreault, David J.

AU - Sullivan, Charles R.

PY - 2024

Y1 - 2024

N2 - This paper 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.

AB - This paper 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.

KW - Artificial Intelligence

KW - Data-Driven Methods

KW - Machine Learning

KW - Open-Source

KW - Power Ferrites

KW - Power Magnetics

UR - http://www.scopus.com/inward/record.url?scp=85206320836&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85206320836&partnerID=8YFLogxK

U2 - 10.1109/OJPEL.2024.3469916

DO - 10.1109/OJPEL.2024.3469916

M3 - Article

SN - 2644-1314

JO - IEEE Open Journal of Power Electronics

JF - IEEE Open Journal of Power Electronics

ER -

MagNet Challenge for Data-Driven Power Magnetics Modeling

Abstract

ASJC Scopus subject areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this