Modeling and Optimizing Winding Arrangement for Gapped Planar Magnetics based on Artificial Neural Network

Hanqing Cao; Bima Nugraha Sanusi; Ziwei Ouyang

doi:10.1109/APEC48143.2025.10977484

Modeling and Optimizing Winding Arrangement for Gapped Planar Magnetics based on Artificial Neural Network

Hanqing Cao, Bima Nugraha Sanusi, Ziwei Ouyang

Technical University of Denmark

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Fringing loss dominated nonlinear winding loss in gapped inductor poses a great challenge for magnetic loss characterization due to the lack of full physical models. This paper investigates the impact of winding arrangements on the AC resistance in gapped inductors, using an EI core as a case study. It specifically examines how the distance of the conductor from the gap affects AC resistance. The study reveals that asymmetric winding arrangements exhibit lower AC resistance compared to symmetric ones. To facilitate rapid computation of eddy current losses, the generation of frequency-based AC resistance maps, and the analysis of AC resistance under various winding configurations, a software tool based on an artificial neural network (ANN) model is developed. The proposed ANN-based model uses 5.7 μs with a deviation less than 4.29% with respect to FEA simulations.

Original language	English
Title of host publication	Proceedings of 2025 IEEE Applied Power Electronics Conference and Exposition
Publisher	IEEE
Publication date	2025
Pages	1810-1815
Article number	10977484
ISBN (Print)	979-8-3315-1612-3
DOIs	https://doi.org/10.1109/APEC48143.2025.10977484
Publication status	Published - 2025
Event	2025 IEEE Applied Power Electronics Conference and Exposition - Georgia World Conference Center, Atlanta, United States Duration: 16 Mar 2025 → 20 Mar 2025

Conference

Conference	2025 IEEE Applied Power Electronics Conference and Exposition
Location	Georgia World Conference Center
Country/Territory	United States
City	Atlanta
Period	16/03/2025 → 20/03/2025

Keywords

Resistance
Analytical models
Computational modeling
Magnetic cores
Windings
Estimation
Artificial neural networks
Magnetic losses
Inductors
Software tools

Access to Document

10.1109/APEC48143.2025.10977484

OpenUrl availability

Full text

Cite this

@inproceedings{7b23d799f9844f84b63c310a55ea002e,

title = "Modeling and Optimizing Winding Arrangement for Gapped Planar Magnetics based on Artificial Neural Network",

abstract = "Fringing loss dominated nonlinear winding loss in gapped inductor poses a great challenge for magnetic loss characterization due to the lack of full physical models. This paper investigates the impact of winding arrangements on the AC resistance in gapped inductors, using an EI core as a case study. It specifically examines how the distance of the conductor from the gap affects AC resistance. The study reveals that asymmetric winding arrangements exhibit lower AC resistance compared to symmetric ones. To facilitate rapid computation of eddy current losses, the generation of frequency-based AC resistance maps, and the analysis of AC resistance under various winding configurations, a software tool based on an artificial neural network (ANN) model is developed. The proposed ANN-based model uses 5.7 μs with a deviation less than 4.29% with respect to FEA simulations.",

keywords = "Resistance, Analytical models, Computational modeling, Magnetic cores, Windings, Estimation, Artificial neural networks, Magnetic losses, Inductors, Software tools",

author = "Hanqing Cao and Sanusi, {Bima Nugraha} and Ziwei Ouyang",

year = "2025",

doi = "10.1109/APEC48143.2025.10977484",

language = "English",

isbn = "979-8-3315-1612-3",

pages = "1810--1815",

booktitle = "Proceedings of 2025 IEEE Applied Power Electronics Conference and Exposition",

publisher = "IEEE",

address = "United States",

note = "2025 IEEE Applied Power Electronics Conference and Exposition, APEC 2025 ; Conference date: 16-03-2025 Through 20-03-2025",

}

Cao, H, Sanusi, BN & Ouyang, Z 2025, Modeling and Optimizing Winding Arrangement for Gapped Planar Magnetics based on Artificial Neural Network. in Proceedings of 2025 IEEE Applied Power Electronics Conference and Exposition., 10977484, IEEE, pp. 1810-1815, 2025 IEEE Applied Power Electronics Conference and Exposition, Atlanta, Georgia, United States, 16/03/2025. https://doi.org/10.1109/APEC48143.2025.10977484

Modeling and Optimizing Winding Arrangement for Gapped Planar Magnetics based on Artificial Neural Network. / Cao, Hanqing; Sanusi, Bima Nugraha ; Ouyang, Ziwei.
Proceedings of 2025 IEEE Applied Power Electronics Conference and Exposition. IEEE, 2025. p. 1810-1815 10977484.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Modeling and Optimizing Winding Arrangement for Gapped Planar Magnetics based on Artificial Neural Network

AU - Cao, Hanqing

AU - Sanusi, Bima Nugraha

AU - Ouyang, Ziwei

PY - 2025

Y1 - 2025

N2 - Fringing loss dominated nonlinear winding loss in gapped inductor poses a great challenge for magnetic loss characterization due to the lack of full physical models. This paper investigates the impact of winding arrangements on the AC resistance in gapped inductors, using an EI core as a case study. It specifically examines how the distance of the conductor from the gap affects AC resistance. The study reveals that asymmetric winding arrangements exhibit lower AC resistance compared to symmetric ones. To facilitate rapid computation of eddy current losses, the generation of frequency-based AC resistance maps, and the analysis of AC resistance under various winding configurations, a software tool based on an artificial neural network (ANN) model is developed. The proposed ANN-based model uses 5.7 μs with a deviation less than 4.29% with respect to FEA simulations.

AB - Fringing loss dominated nonlinear winding loss in gapped inductor poses a great challenge for magnetic loss characterization due to the lack of full physical models. This paper investigates the impact of winding arrangements on the AC resistance in gapped inductors, using an EI core as a case study. It specifically examines how the distance of the conductor from the gap affects AC resistance. The study reveals that asymmetric winding arrangements exhibit lower AC resistance compared to symmetric ones. To facilitate rapid computation of eddy current losses, the generation of frequency-based AC resistance maps, and the analysis of AC resistance under various winding configurations, a software tool based on an artificial neural network (ANN) model is developed. The proposed ANN-based model uses 5.7 μs with a deviation less than 4.29% with respect to FEA simulations.

KW - Resistance

KW - Analytical models

KW - Computational modeling

KW - Magnetic cores

KW - Windings

KW - Estimation

KW - Artificial neural networks

KW - Magnetic losses

KW - Inductors

KW - Software tools

U2 - 10.1109/APEC48143.2025.10977484

DO - 10.1109/APEC48143.2025.10977484

M3 - Article in proceedings

SN - 979-8-3315-1612-3

SP - 1810

EP - 1815

BT - Proceedings of 2025 IEEE Applied Power Electronics Conference and Exposition

PB - IEEE

T2 - 2025 IEEE Applied Power Electronics Conference and Exposition

Y2 - 16 March 2025 through 20 March 2025

ER -

Modeling and Optimizing Winding Arrangement for Gapped Planar Magnetics based on Artificial Neural Network

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this