Development of Encoder-Decoder Predicting Search Process of Level-set Method in Magnetic Circuit Design

Ryota Kawamata, Shinji Wakao, Noboru Murata, Yoshifumi Okamoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The finite element analysis (FEA) of magnetic field generally requires a lot of calculation time. Especially, design optimization methods such as the level-set method with FEA result in large computational effort to find better solution. In this paper, we propose a novel method of precisely and quickly reproducing the conventional optimization steps by means of Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM). The developed method enables us to implement high speed search of solution, which means the possibility of effective optimization with various initial conditions for better solution. Finally, we evaluate calculation time and computational accuracy of the proposed method by using a magnetic circuit design model.

Original languageEnglish
Title of host publicationCOMPUMAG 2019 - 22nd International Conference on the Computation of Electromagnetic Fields
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728155920
DOIs
Publication statusPublished - 2019 Jul
Event22nd International Conference on the Computation of Electromagnetic Fields, COMPUMAG 2019 - Paris, France
Duration: 2019 Jul 152019 Jul 19

Publication series

NameCOMPUMAG 2019 - 22nd International Conference on the Computation of Electromagnetic Fields

Conference

Conference22nd International Conference on the Computation of Electromagnetic Fields, COMPUMAG 2019
CountryFrance
CityParis
Period19/7/1519/7/19

Keywords

  • Design optimization
  • convolutional neural network
  • level set method
  • long short-term memory
  • magnetic circuit

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Computational Mathematics
  • Radiation

Fingerprint Dive into the research topics of 'Development of Encoder-Decoder Predicting Search Process of Level-set Method in Magnetic Circuit Design'. Together they form a unique fingerprint.

  • Cite this

    Kawamata, R., Wakao, S., Murata, N., & Okamoto, Y. (2019). Development of Encoder-Decoder Predicting Search Process of Level-set Method in Magnetic Circuit Design. In COMPUMAG 2019 - 22nd International Conference on the Computation of Electromagnetic Fields [9032835] (COMPUMAG 2019 - 22nd International Conference on the Computation of Electromagnetic Fields). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/COMPUMAG45669.2019.9032835