2022年9月
Prediction of Current-Dependent Motor Torque Characteristics Using Deep Learning for Topology Optimization
IEEE Transactions on Magnetics
- ,
- ,
- ,
- ,
- ,
- 巻
- 58
- 号
- 9
- 開始ページ
- 1
- 終了ページ
- 4
- 記述言語
- 掲載種別
- 研究論文(学術雑誌)
- DOI
- 10.1109/tmag.2022.3167254
- 出版者・発行元
- Institute of Electrical and Electronics Engineers (IEEE)
In this study, we propose a fast topology optimization method based on a deep neural network (DNN) that predicts the currentdependent motor torque characteristics using its cross-sectional image. The trained DNN is shown to provide the current condition that provides the maximum torque under the assumed motor control method. The proposed method helps perform topology optimization with a reduced number of field computations while maintaining a high search capability.
- リンク情報
-
- DOI
- https://doi.org/10.1109/tmag.2022.3167254
- URL
- http://xplorestaging.ieee.org/ielx7/20/9868170/09756554.pdf?arnumber=9756554
- Scopus
- https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85128335295&origin=inward
- Scopus Citedby
- https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85128335295&origin=inward
- ID情報
-
- DOI : 10.1109/tmag.2022.3167254
- ISSN : 0018-9464
- eISSN : 1941-0069
- SCOPUS ID : 85128335295