Application of Conditional Variational Auto-Encoder to Magnetic Circuit Design with Magnetic Field Computation

Ryota Kawamata, Shinji Wakao, Noboru Murata

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

Abstract

In the design optimization of electric machine, we ordinarily derive the objective physical quantities, e.g., the shape of the investigated model as design variables, by using numerical method such as the finite element method with the analysis conditions. In recent years, the representation learning using Deep Learning much attracts attention because it can acquire the features of data as a distributed representation and reproduce corresponding data. In this paper, utilizing machine learning technology, we propose an application of Conditional Variational Auto-Encoder (CVAE) to reproduce the more adequate shape of magnetic materials, i.e., design variables, corresponding to the intended magnetic energy, i.e., objective function values.

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

  • conditional variational auto-encoder
  • Design optimization
  • magnetic circuit
  • representation learning

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Application of Conditional Variational Auto-Encoder to Magnetic Circuit Design with Magnetic Field Computation'. Together they form a unique fingerprint.

  • Cite this

    Kawamata, R., Wakao, S., & Murata, N. (2019). Application of Conditional Variational Auto-Encoder to Magnetic Circuit Design with Magnetic Field Computation. In COMPUMAG 2019 - 22nd International Conference on the Computation of Electromagnetic Fields [9032766] (COMPUMAG 2019 - 22nd International Conference on the Computation of Electromagnetic Fields). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/COMPUMAG45669.2019.9032766