Reduced Order Modeling of CFD Model using Machine Learning and an Application for Heat Damage Evaluation
熱害検討のための機械学習を用いたCFDモデルの低次元化とその応用
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20226285
- Paper/Info type
- Proceedings (Autumn)
No.143-22
- Pages
- 1-6(Total 6 p)
- Date of publication
- Oct 2022
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2022 JSAE Annual Congress (Autumn)
Detailed Information
Author(J) | 1) 河合 悠奈, 2) 新谷 浩平, 3) 菅井 友駿, 4) 笹川 崇 |
---|---|
Author(E) | 1) Haruna Kawai, 2) Kohei Shintani, 3) Tomotaka Sugai, 4) Takashi Sasagawa |
Affiliation(J) | 1) トヨタ自動車, 2) トヨタ自動車, 3) トヨタ自動車, 4) 豊田中央研究所 |
Affiliation(E) | 1) Toyota Motor, 2) Toyota Motor, 3) Toyota Motor, 4) Toyota Central R&D Labs. |
Abstract(J) | 自動車メーカーは,近年の激しい市場変化の中,よりアジャイルな開発体制を構築する必要がある.これに対しCFDは多くの時間を要するため,より簡易的な手法が求められる.本研究では,熱害を題材とし,テンソル分解を用いたモデルの低次元化を行った.さらに,これを応用してCFDに代わるAIを作成し,その有効性を検証した. Translation |
Abstract(E) | In recent years, automakers have become required to build more agile development system for drastic changes in market needs. However, CFD takes a lot of time, so we need the simpler method instead. In this study, we reduced the dimension of the CFD model using tensor decomposition for heat damage evaluation as an example. Additionally, by applying this method, we built the AI model to replace CFD and verified its effectiveness. |