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

Machine learning-based turbulent combustion modelling

Research Project

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
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2021: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2019: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Keywords乱流燃焼 / 乱流燃焼モデル / 直接数値計算 / 機械学習 / LES / RANS / 反応性乱流 / 乱流 / 数値計算 / モデル / 深層学習 / モデル開発 / 高Ka
Outline of Research at the Start

次世代高効率・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単一の乱流燃焼モデル開発は困難である.また,低環境負荷燃焼場で起こり得る火炎同士の干渉による燃焼速度の変化や自着火,消炎などの複数の局所現象が複合的に混在する燃焼場を予測可能な乱流燃焼モデルは存在しない.本研究では,複合的乱流燃焼場におけるこれらの局所現象を解明し,解明された洞察に基づき構築された学習データを用いて,複合的乱流燃焼場を連続的に記述するような機械学習支援型の乱流燃焼モデルを開発することを目的とする.

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.

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。

Report

(4 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (14 results)

All 2022 2021 2020 2019

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 4 results) Presentation (8 results) (of which Int'l Joint Research: 2 results) Book (1 results)

  • [Journal Article] Effect of flame-flame interaction on scalar PDF in turbulent premixed flames2022

    • Author(s)
      Yuki Minamoto, Kherlen Jigjid, Rentaro Igari, Mamoru Tanahashi
    • Journal Title

      Combustion and Flame

      Volume: 00 Pages: 111660-111660

    • DOI

      10.1016/j.combustflame.2021.111660

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Species reaction rate modelling based on physics-guided machine learning2022

    • Author(s)
      Ryota Nakazawa, Yuki Minamoto, Nakamasa Inoue, Mamoru Tanahashi
    • Journal Title

      Combustion and Flame

      Volume: 235 Pages: 111696-111696

    • DOI

      10.1016/j.combustflame.2021.111696

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Data driven analysis and prediction of MILD combustion mode2021

    • Author(s)
      Jigjid, Kherlen Tamaoki, Chitoshi Minamoto, Yuki Nakazawa, Ryota Inoue, Nakamasa Tanahashi, Mamoru
    • Journal Title

      Combustion and Flame

      Volume: 223 Pages: 474-485

    • DOI

      10.1016/j.combustflame.2020.10.025

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Corrigendum to "Data driven analysis and prediction of MILD combustion mode" [Combust. Flame 223 (2021) 474-485]2021

    • Author(s)
      Jigjid, Kherlen Tamaoki, Chitoshi Minamoto, Yuki Nakazawa, Ryota Inoue, Nakamasa Tanahashi, Mamoru
    • Journal Title

      Combustion and Flame

      Volume: 227 Pages: 481-482

    • DOI

      10.1016/j.combustflame.2021.01.017

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Identification of combustion mode under MILD conditions using Chemical Explosive Mode Analysis2021

    • Author(s)
      Doan, N. A.K. Bansude, S. Osawa, K. Minamoto, Y. Lu, T. Chen, J. H. Swaminathan, N.
    • Journal Title

      Proceedings of the Combustion Institute

      Volume: 38 Issue: 4 Pages: 5415-5422

    • DOI

      10.1016/j.proci.2020.06.293

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Presentation] 乱流予混合火炎における火炎干渉とスカラー分布の関係2022

    • Author(s)
      ジグジッド・ヘルレン,源 勇気,店橋 護
    • Organizer
      第58回日本伝熱シンポジウム
    • Related Report
      2021 Annual Research Report
  • [Presentation] Neural Network Aided Sub-Grid Scale Reaction Rate Model for MILD Combustion2022

    • Author(s)
      ジグジッド・ヘルレン,源 勇気,店橋 護
    • Organizer
      第59回燃焼シンポジウム
    • Related Report
      2021 Annual Research Report
  • [Presentation] データ指向型手法によるMILD燃焼モードの解明とモデル開発2020

    • Author(s)
      源 勇気, ジグジッド ヘルレン, 玉置 千智, 店橋 護
    • Organizer
      第58回燃焼シンポジウム
    • Related Report
      2020 Research-status Report
  • [Presentation] 複合的燃焼場における局所燃焼モードのデータ指向型解析2020

    • Author(s)
      ジグジッド・ヘルレン, 源 勇気, 玉置 千智, 店橋 護
    • Organizer
      日本機械学会熱工学コンファレンス2020
    • Related Report
      2020 Research-status Report
  • [Presentation] Fundamental Analysis of Turbulent Combustion Modelling with Deep Learning2019

    • Author(s)
      Ryota Nakazawa, Yuki Minamoto, Masayasu Shimura, Mamoru Tanahashi
    • Organizer
      The Second Pacific Rim Thermal Engineering Conference
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Analysis for Deep Learning Based Turbulent Combustion Modelling2019

    • Author(s)
      Ryota Nakazawa, Yuki Minamoto, Masayasu Shimura, Mamoru Tanahashi
    • Organizer
      7th Asian Symposium on Computational Heat Transfer and Fluid Flow
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] 深層学習を応用したレイノルズ平均反応速度モデル2019

    • Author(s)
      中澤 凌太, 源 勇気, 志村 祐康, 店橋 護
    • Organizer
      第57回燃焼シンポジウム
    • Related Report
      2019 Research-status Report
  • [Presentation] 深層学習を活用した乱流燃焼モデルの開発2019

    • Author(s)
      中澤 凌太, 源 勇気, 志村 祐康, 店橋 護
    • Organizer
      第56回日本伝熱シンポジウム
    • Related Report
      2019 Research-status Report
  • [Book] MILD Combustion, In N. Swaminathan, X.-S. Bai, N. E. L. Haugen, C. Fureby, G. Brethouwer, ed., Advanced Turbulent Combustion Physics and Applications2021

    • Author(s)
      Y. Minamoto, N. A. K. Doan, N. Swaminathan
    • Total Pages
      31
    • Publisher
      Cambridge University Press
    • ISBN
      9781108497961
    • Related Report
      2020 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi