Predicting Vehicle Aerodynamics Using a Machine Learning Model Based on Physics
物理法則に立脚した機械学習モデルによる自動車空力特性の予測
- Delivery
- Available on the other site
- Click here to order.
- Publication code
- 20244093
- Paper/Info type
- JSAE Transaction
Vol.55 No.2
- Pages
- 387-392(Total 6 p)
- Date of publication
- Mar 2024
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | 論文 Translation |
|---|---|
| Category(E) | Paper |
| Author(J) | 1) 堀江 正信, 2) 足立 大樹, 3) 谷村 慈則 |
| Author(E) | 1) Masanobu Horie, 2) Daiki Adachi, 3) Yoshinori Tanimura |
| Affiliation(J) | 1) RICOS, 2) RICOS, 3) RICOS |
| Abstract(J) | 本研究では、物理法則に基づく既存の機械学習モデルを用いて、自動車の空気抵抗係数を予測する機械学習モデルを構築する。DrivAer モデルの形状をさまざまに変更して作成したデータセットでは、空気抵抗係数の誤差 0.0025 という非常に高い予測精度が得られた。 Translation |
| Abstract(E) | In this research, we construct a machine learning model that can predict the drag coefficient based on an existing physics-based machine learning model. The base model can predict velocity and pressure fields accurately thanks to the physical knowledge embedded. Our novelty is to add a model that computes the drag coefficient inside it rather than postprocessing for more accurate results. Also, we generated a dataset using aerodynamic simulation with various shapes generated based on the DrivAer model. The model shows high accuracy with an error of 0.0025 in the drag coefficient for the considered dataset. |
