• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2021 Fiscal Year Final Research Report

Machine learning-based turbulent combustion modelling

Research Project

  • PDF
Project/Area Number 19K14903
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 19020:Thermal engineering-related
Research InstitutionTokyo Institute of Technology

Principal Investigator

Minamoto Yuki  東京工業大学, 工学院, 助教 (70769687)

Project Period (FY) 2019-04-01 – 2022-03-31
Keywords乱流燃焼 / 乱流燃焼モデル / 直接数値計算 / 機械学習 / LES / RANS
Outline of Final Research Achievements

Turbulent combustion models were developed by using machine learning techniques which may be applied to various combustion conditions such as premixed and MILD combustion. For these purposes, physics-guided loss function was proposed to consider mass and atomic conservations. Also a conventional modelling framework was incorporated with machine learning to achieve robust modelling.

Free Research Field

熱工学

Academic Significance and Societal Importance of the Research Achievements

希薄予混合燃焼やMILD燃焼技術などを用いた次世代低環境負荷燃焼では、乱流特性時間が火炎特性時間に比べて局所的に短くなる場合があり、乱流燃焼条件は局所的に大きく異なる。このような特性を持つ低環境負荷燃焼器を低コストで開発するには数値熱流体解析による予測が必要であるが、そのような燃焼場の予測を可能とする乱流燃焼モデル開発は困難である。本研究では、高精度数値熱流体解析の実現に寄与する乱流燃焼モデルを機械学習により開発した。

URL: 

Published: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi