Presentation 2024-03-11
Design Methodology for Load-Independent WPT Systems Using Machine Learning
Naoki Fukuda, Yutaro Komiyama, Wenqi Zhu, Yinchen Xie, Ayano Komanaka, Akihiro Konishi, Kien Nguyen, Hiroo Sekiya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a design method for load-independent wireless power transfer (WPT) systems using machine learning. In the proposed design, machine learning is employed to determine the component values in the circuit model considering the parasitic components. This paper also presents an evaluation function for designing the WPT system with the class-EF inverter to achieve load-independent operation. Optimization results reveal that, solutions achieving higher precision output voltage regulation and efficiency compared to analytical load-independent designs are found. The load-independent WPT system designed using the proposed method demonstrates a close correlation between experimental waveforms and those derived from numerical computations, thereby confirming the validity of the design approach.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Class-EF inverter / particle swarm optimization / machine learning, load independence / load-independent / wireless power transfer
Paper # EE2023-58
Date of Issue 2024-03-04 (EE)

Conference Information
Committee EE
Conference Date 2024/3/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yoshiyasu Nakashima(NXTEC)
Vice Chair Hiroo Sekiya(Chiba Univ.) / Hiroaki Kusawake(JAXA)
Secretary Hiroo Sekiya(Aichi Inst. of Tech.) / Hiroaki Kusawake(Nagasaki Inst. of Applied Science)
Assistant Yuu Yonezawa(Nagoya Univ.) / Yudai Furukawa(Nagasaki Inst. of Applied Science) / Kazufumi Yuasa(NTT Facilities)

Paper Information
Registration To Technical Committee on Energy Engineering in Electronics and Communications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Design Methodology for Load-Independent WPT Systems Using Machine Learning
Sub Title (in English)
Keyword(1) Class-EF inverter
Keyword(2) particle swarm optimization
Keyword(3) machine learning, load independence
Keyword(4) load-independent
Keyword(5) wireless power transfer
1st Author's Name Naoki Fukuda
1st Author's Affiliation Chiba University(Chiba Univ.)
2nd Author's Name Yutaro Komiyama
2nd Author's Affiliation Chiba University(Chiba Univ.)
3rd Author's Name Wenqi Zhu
3rd Author's Affiliation Chiba University(Chiba Univ.)
4th Author's Name Yinchen Xie
4th Author's Affiliation Chiba University(Chiba Univ.)
5th Author's Name Ayano Komanaka
5th Author's Affiliation Chiba University(Chiba Univ.)
6th Author's Name Akihiro Konishi
6th Author's Affiliation Chiba University(Chiba Univ.)
7th Author's Name Kien Nguyen
7th Author's Affiliation Chiba University(Chiba Univ.)
8th Author's Name Hiroo Sekiya
8th Author's Affiliation Chiba University(Chiba Univ.)
Date 2024-03-11
Paper # EE2023-58
Volume (vol) vol.123
Number (no) EE-420
Page pp.pp.6-11(EE),
#Pages 6
Date of Issue 2024-03-04 (EE)