Development of High-Speed Prediction System Using Surrogate Models for Motor Cooling CAE
モータ冷却CAEの高速化技術開発
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20266207
- Paper/Info type
- Proceedings (Autumn)
No.135-26
- Pages
- 1-2(Total 2 p)
- Date of publication
- Oct 2026
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2026 JSAE Annual Congress (Autumn)
Detailed Information
| Author(J) | 1) 中野 慎太郎 |
|---|---|
| Author(E) | 1) Shintaro Nakano |
| Affiliation(J) | 1) トヨタ自動車 |
| Affiliation(E) | 1) Toyota Motor |
| Abstract(J) | 電動車駆動用モータ開発では冷却性能予測としてCAEを活用して効率的な開発を実施している．CAEは計算に数日を要し更なる効率化として，本研究は粒子法による3次元モータ冷却CAEを対象に，サロゲートモデルによる計算高速化を行った．CAE結果を直交格子上に変換した前処理と，GCNNを用いて冷媒粒子挙動を予測し，濡れ面積を算出する手法を構築．その結果，粒子法解析と比較して計算時間を1分程度に短縮しつつ，濡れ面積予測精度MAPE5％を達成． Translation |
| Abstract(E) | This paper proposes a method for accelerating particle-based motor cooling CAE using a surrogate model. The method consists of a preprocessing step that converts CAE results to a Cartesian grid, followed by prediction of particle behavior using a geodesic convolutional neural network (GCNN) and subsequent calculation of the wetted area. The results show that the computation time is reduced to approximately one minute compared with conventional particle-based analysis, while achieving a wetted-area prediction accuracy with a mean absolute percentage error (MAPE) of 5%. |
