Development of Aerodynamic Noise Prediction System Using Generative AI by Flow of Vehicle Shape
生成AIを用いた車体形状流れに起因する空力騒音予測システムの開発
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20264548
- Paper/Info type
- Journal of Society of Automotive Engineers of Japan
Vol.80 No.9
- Pages
- 32-37(Total 6 p)
- Date of publication
- Sep 2026
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | AIを活用した振動・騒音設計技術 Translation |
|---|---|
| Category(E) | AI-based Noise and Vibration Design Technology |
| Author(J) | 1) 伊藤 祐太, 2) 新谷 浩平, 3) 森國 洋平, 4) 菅井 友駿, 5) 安岡 志朗 |
| Author(E) | 1) Yuta Ito, 2) Kohei Shintani, 3) Yohei Morikuni, 4) Tomotaka Sugai, 5) Shiro Yasuoka |
| Affiliation(J) | 1) トヨタ自動車, 2) Toyota Research Institute, 3) トヨタ自動車, 4) トヨタ自動車, 5) トヨタ自動車 |
| Abstract(J) | 車体形状に起因する空力騒音の予測時間短縮を目的に、IDS結果を教師データとした生成AIモデルを構築した。VAEによる形状特徴量抽出と回帰モデルによりIDS分布を高精度に推定し、計算時間を大幅に削減できることを数値検証で確認した。 Translation |
| Abstract(E) | Aerodynamic noise is one of the important factors in vehicle product value, and it needs to be optimized during the exterior design phase of the vehicle. Aerodynamic noise refers to the phenomenon where sound waves induced by turbulent flow around a vehicle, propagate and transmit inside the cabin and affects the passengers. In this paper, a prediction method for exterior wind noise based on combination of generative AI is proposed to solve the simulation time problem and its effectiveness is confirmed by numerical validation results. |