Surrogate Model Development for Prediction of Car Aerodynamics Using Machine Learning
機械学習を用いた自動車空力性能を予測するためのサロゲートモデル開発
- Delivery
- Available on the other site
- Click here to order.
- Publication code
- 20214248
- Paper/Info type
- JSAE Transaction
Vol.52 No.3
- Pages
- 621-626(Total 6 p)
- Date of publication
- May 2021
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
Category(J) | 研究論文 Translation |
---|---|
Category(E) | ResearchPaper |
Author(J) | 1) 赤坂 啓, 2) 陳 放歌, 3) 寺口 剛仁 |
Author(E) | 1) Kei Akasaka, 2) Fangge Chen, 3) Takehito Teraguchi |
Affiliation(J) | 1) 日産自動車, 2) 日産自動車, 3) 日産自動車 |
Abstract(J) | 機械学習を用いて自動車形状とCFD結果(空気抵抗係数、圧力分布、流速分布)の関係を学習することで、CFDを代替するサロゲートモデルを開発した。本論文では、開発したサロゲートモデルの概要および学習に使用したデータセット、予測精度を示し、提案手法の有用性について述べる。 Translation |
Abstract(E) | In the evaluation of car aerodynamics, Computational Fluid Dynamics (CFD) are frequently used as well as a wind-tunnel. However, the CFD simulations consume a lot of cost and time. In this study, a surrogate model using the machine learning was developed to reduce cost and time of CFD. In the proposed model, the relation between car shapes and CFD results was learned for rapid prediction of pressure, velocity and coefficient of drag for aerodynamics. In this paper, we introduce the proposed model, the training dataset, the accuracy and the computational time. |