Proposal and Feasibility Study of New Combustion Analysis Method Based on Heat Release Rate Prediction Using Machine Learning
機械学習による熱発生率予測を基とした新燃焼解析手法の提案
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20265089
- Paper/Info type
- Proceedings (Spring)
No.20-26
- Pages
- 1-6(Total 6 p)
- Date of publication
- May 2026
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2026 JSAE Annual Congress (Spring)
Detailed Information
| Author(J) | 1) 良知 聖淳, 2) 長沼 要 |
|---|---|
| Author(E) | 1) Shojun Rachi, 2) Kaname Naganuma |
| Affiliation(J) | 1) 金沢工業大学大学院, 2) 金沢工業大学大学院 |
| Affiliation(E) | 1) Kanazawa Institute of Technology, 2) Kanazawa Institute of Technology |
| Abstract(J) | 筆者らが過去に提唱した新たな燃焼解析コンセプトを，最新の機械学習アプローチにより再構築する．本研究では，実験で得られた熱発生率に対してWiebe関数の係数導出に機械学習に用いられるアルゴリズムを適用し，筒内圧力履歴の予測を試み，高精度なエンジン諸性能予測へ発展できる可能性を得た． Translation |
| Abstract(E) | The original combustion analysis concept previously proposed by the authors is reconstructed using recent machine learning techniques. Machine learning–based algorithms are applied to optimize the Wiebe function coefficients to fit the experimentally derived heat release rate, enabling the prediction of in-cylinder pressure profiles and demonstrating the potential for highly accurate engine performance prediction. |
