Project/Area Number |
18K18840
|
Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
Allocation Type | Multi-year Fund |
Review Section |
Medium-sized Section 21:Electrical and electronic engineering and related fields
|
Research Institution | Hokkaido University |
Principal Investigator |
|
Project Period (FY) |
2018-06-29 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2018: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
|
Keywords | トポロジー最適化 / 深層学習 / 遺伝的アルゴリズム / 電磁界解析 / モータ / 最適設計 / IPMモータ / 転移学習 / 永久磁石モータ / IPMモータ― / 共進化 |
Outline of Final Research Achievements |
In the design of electric apparatus such as traction electric motors for EVs, we need to find the optimal machine structure that gives excellent performance satisfying the constraints. The topology optimization, which searches for the optimal structure by freely deformation allowing generation and annihilation of holes, is fairly suitable for such complicated design problems. This method, however, has difficulties for real uses due to large number of electromagnetic field computations during the optimization process. In this study, I have shown that the computing time can drastically be reduced by the deep learning which predicts the machine characteristics. This method can be applied not only to the design of electric apparatus but also to that of other devices and systems.
|
Academic Significance and Societal Importance of the Research Achievements |
深層学習は画像認識や音声認識など様々な分野に応用されている.しかし最適設計など設計・開発への応用は多くなかった.本研究では,深層学習によりトポロジー最適化が高速化できることを初めて示した.高速化により,製品の性能が向上できるのみならず,深層学習に与える学習データも豊富に取得できる.さらに得られたデータにより深層学習機の推定精度が向上する.このように,両者が共進化できることを明らかにした.
|