High-Accuracy Prediction of Modal Emissions Using a Data-Driven Model
データ駆動型モデルによるモーダルEMの高精度予測
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20266257
- Paper/Info type
- Proceedings (Autumn)
No.146-26
- Pages
- 1-5(Total 5 p)
- Date of publication
- Oct 2026
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2026 JSAE Annual Congress (Autumn)
Detailed Information
| Author(J) | 1) 酒井 康平, 2) 荒木 崇至, 3) 長野 高皓, 4) 河野 通治 |
|---|---|
| Author(E) | 1) Kohei Sakai, 2) Takashi Araki, 3) Takaaki Nagano, 4) Michiharu Kawano |
| Affiliation(J) | 1) マツダ, 2) マツダ, 3) マツダ, 4) マツダ |
| Affiliation(E) | 1) Mazda, 2) Mazda, 3) Mazda, 4) Mazda |
| Abstract(J) | 自動車開発において，排出ガス（EM）規制強化に伴う車両全体での機能配分の需要に対し，高速かつ高精度な机上でのEM予測技術の構築が求められる．それに対し本研究では，定常性能マップと過渡補正AIを組みあわせたデータ駆動型モデルを提案し，仕様変更を伴う新機種でのモーダルEM予測技術を構築した． Translation |
| Abstract(E) | In automotive development, increasingly stringent emission (EM) regulations require effective allocation of functions at the vehicle level, driving the need for fast and accurate model-based emission prediction technologies. To address this challenge, this study proposes a data-driven model that combines steady-state performance maps with AI-based transient correction. Using this approach, a modal emission prediction method applicable to new vehicle configurations with specification changes is developed. The proposed method enables efficient and reliable emission prediction, supporting model-based development in early-stage vehicle design. |
