Estimation Method for Magnetization Distribution in Permanent Magnet Using Deep Neural Network

被引：2

作者：

Sasaki, Hidenori ^{[1
]}

Takasu, Daichi ^{[1
]}

Nakamura, Narichika ^{[1
]}

Okamoto, Yoshifumi ^{[1
]}

机构：

[1] Hosei Univ, Dept Elect & Elect Engn, Koganei, Tokyo, Japan

来源：

TWENTIETH BIENNIAL IEEE CONFERENCE ON ELECTROMAGNETIC FIELD COMPUTATION (IEEE CEFC 2022) | 2022年

关键词：

Biot-Savart low; Deep Learning; Magnetization Estimation; Nd-Fe-B Magnet;

D O I：

10.1109/CEFC55061.2022.9940784

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

A new estimation method for magnetization distribution (MD) in permanent magnets using a deep neural network (DNN) is proposed. It estimates the physical MD from the measured magnetic flux density distribution. The proposed method overcomes problems of indefiniteness and using a new method of constructing training data that models the realistic MD. The DNN trained on the data calculated by the Biot-Savart method can accurately estimate the MD for measured and untrained data.

引用

页数：2

共 7 条

[1] Characterization of Permanent Magnet Magnetization
Arbenz, Laure
Chadebec, Olivier
Espanet, Christophe
Rtimi, Youness
Cauffet, Gilles
[J]. IEEE TRANSACTIONS ON MAGNETICS, 2017, 53 (11)
[2] colab, NOTEBOOKS WELCOME IP
[3] Duchi J, 2011, J MACH LEARN RES, V12, P2121
[4] Igarashi H, 2000, IEEE T MAGN, V36, P1168, DOI 10.1109/20.877648
[5] Keras, US
[6] Nakai N., 2015, P 17 INT S EL FIELDS
[7] Nondestructive Estimation of Magnetization Distribution in Permanent Magnet Using Quasi-Newton Method Based on 2-D Fourier Series Expansion
Nakamura, Narichika
Okamoto, Yoshifumi
Osanai, Kenta
Doi, Satoshi
Aoki, Tetsuya
Okazaki, Keichi
[J]. IEEE TRANSACTIONS ON MAGNETICS, 2020, 56 (01)

← 1 →