乱流に対するデータ駆動型アプローチの可能性と限界
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20244755
- Paper/Info type
- Forum Text (Online)
No.24-W4
- Pages
- 1-45(Total 45 p)
- Date of publication
- Jan 2025
- Publisher
- JSAE
- Language
- Japanese
- Event
- JSAE Forum 2024 (Winter)
Detailed Information
| Category(J) | PPT資料 Translation |
|---|---|
| Category(E) | PPT slides |
| Author(J) | 1) 塚原 隆裕 |
| Author(E) | 1) Takahiro Tsukahara |
| Affiliation(J) | 1) 東京理科大学 |
| Affiliation(E) | 1) Tokyo University of Science |
| Abstract(J) | 乱流は自然現象予測や，産業機器の高度化に不可欠であり，未解明の物理現象です．その解明や予測において，数値計算に続き，今後は機械学習を活用したデータ駆動型アプローチが鍵となります．本講演では，乱流中の物質拡散推定や粘弾性流体乱流の予測の研究を紹介し，その可能性と限界について論じます． Translation |
| Abstract(E) | Turbulence is a complex physical phenomenon crucial for predicting natural events and advancing practical applications. While CFD simulations have driven progress, data-driven approaches using machine learning are emerging as a key tool for further understanding and prediction. This lecture explores recent research on scalar diffusion source estimation in turbulence and viscoelastic fluid turbulence prediction, highlighting their potential and limitations. |
