Archivio Istituzionale della RicercaThis paper summarizes the main results and contributions of the MagNet Challenge 2023, an open-source research initiative for data-driven modeling of power magnetic ma- terials. 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 com- munity; (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 advance- ments 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.
MagNet Challenge for Data-Driven Power Magnetics Modeling / Chen, Minjie; Li, Haoran; Wang, Shukai; Guillod, Thomas; Serrano, Diego; Forster, Nikolas; Kirchgassner, Wilhelm; Piepenbrock, Till; Schweins, Oliver; Wallscheid, Oliver; Huang, Qiujie; Li, Yang; Dou, Yu; Li, Bo; Li, Sinan; Havugimana, Emmanuel; Chacko, Vivek Thomas; Radhakrishnan, Sritharini; Ranjram, Mike; Sauter, Bailey; Reese, Skye; Sinha, Shivangi; Zhang, Lizhong; Mckeague, Tom; Cui, Binyu; Rasekh, Navid; Wang, Jun; Liu, Song; Martinez, Alfonso; Liu, Xinyu; Mei, Chaoying; Zhao, Rui; Wu, Gaoyuan; Wu, Hao; Zhang, Rui; Song, Hao; Zhang, Lie; Lu, Yibo; Hang, Lijun; Rajput, Neha; Sandhibigraha, Himanshu Bhusan; Agrawal, Neeraj; Iyer, Vishnu Mahadeva; Shen, Xiaobing; Tian, Fanghao; Sui, Qingcheng; Kong, Jiaze; Martinez, Wilmar; Arruti, Asier; Alberdi, Borja; Agote, Anartz; Aizpuru, Iosu; Zhang, Minmin; Chen, Xia; Dong, Yuchen; Wang, Duo; Shen, Tianming; Zhou, Yan; Li, Yaohua; Wang, Sicheng; Wu, Yue; Jiang, Yongbin; Xiao, Ziheng; Tang, Yi; Hsieh, Yun-Shan; Li, Jian-De; Yu, Li-Chen; Hsu, Tzu-Chieh; Liu, Yu-Chen; Hsia, Chin-Hsien; Chen, Chen; Giuffrida, Alessio; Lombardo, Nicolo; Marmello, Fabio; Morra, Simone; Pasquale, Marco; Solimene, Luigi; Ragusa, Carlo Stefano; Reynvaan, Jacob; Stoiber, Martin; Li, Chengbo; Qin, Wei; Ma, Xiang; Zhang, Boyu; Wang, Zheng; Cheng, Ming; Xu, Wei; Wang, Jiyao; Hu, Youkang; Xu, Jing; Shi, Zhongqi; Sapkota, Dixant Bikal; Neupane, Puskar; Joshi, Mecon; Khan, Shahabuddin; Su, Bowen; Xiao, Yunhao; Yang, Min; Sun, Kai; Li, Zhengzhao; Mirzadarani, Reza; Liu, Ruijun; Wang, Lu; Luo, Tianming; Lyu, Dingsihao; Niasar, Mohamad Ghaffarian; Qin, Zian; Meerza, Syed Irfan Ali; Froehle, Kody; Cui, Han Helen; Costinett, Daniel; Liu, Jian; Liu, Zhanlei; Zhan, Cao; Dang, Yongliang; Zhang, Yukun; Wang, Na; Chen, Yiting; Zhang, Yiming; Li, Chushan; Yao, Yinan; Hu, Tianxiang; Xu, Lumeng; Wang, Yiyi; Wang, Sichen; Jiang, Shuai; Shumacher, David; Maksimovic, Dragan; Hui, Ron S. Y.; Kolar, Johann W.; Perreault, David J.; Sullivan, Charles R.. - In: IEEE OPEN JOURNAL OF POWER ELECTRONICS. - ISSN 2644-1314. - (2024), pp. 1-16. [10.1109/ojpel.2024.3469916]
MagNet Challenge for Data-Driven Power Magnetics Modeling
Solimene, Luigi;Ragusa, Carlo Stefano;
2024
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 ma- terials. 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 com- munity; (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 advance- ments 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.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2993061