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

Improvement of sheet metal forming simulation using precise multiracial material tests and machine learning

Research Project

Project/Area Number 17H03425
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Material processing/Microstructural control engineering
Research InstitutionTokyo University of Agriculture and Technology

Principal Investigator

Yamanaka Akinori  東京農工大学, 工学(系)研究科(研究院), 准教授 (50542198)

Co-Investigator(Kenkyū-buntansha) 渡邊 育夢  国立研究開発法人物質・材料研究機構, 構造材料研究拠点, 主任研究員 (20535992)
桑原 利彦  東京農工大学, 工学(系)研究科(研究院), 卓越教授 (60195609)
Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥17,810,000 (Direct Cost: ¥13,700,000、Indirect Cost: ¥4,110,000)
Fiscal Year 2019: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2018: ¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Fiscal Year 2017: ¥7,020,000 (Direct Cost: ¥5,400,000、Indirect Cost: ¥1,620,000)
Keywords機械学習 / 結晶塑性 / アルミニウム合金 / ニューラルネットワーク / データ同化 / フェーズフィールド法 / 深層学習 / 結晶塑性有限要素法 / 集合組織 / 結晶塑性解析 / 多軸材料試験 / 成形シミュレーション / 板材成形 / 有限要素法 / 数値材料試験 / 二軸引張試験
Outline of Final Research Achievements

Calibration of yield functions and those parameters (material models) by multiaxial stress tests are important for performing accurate sheet metal forming simulation. However, the multiaxial stress tests needs special experimental apparatus. We have developed the deep learning-based material modelling methodology which estimated the biaxial stress-strain curves and the plastic work contour from crystallographic textured data of aluminum alloy sheets. We demonstrated that the trained neural network developed in this study successfully estimated the biaxial stress-strain curves from an image data of (111) pole figure within a few seconds. A web application was developed based on the trained neural network.

Academic Significance and Societal Importance of the Research Achievements

本研究の成果を公開し, 一般に利用できる環境を構築することを目指して, ①アルミニウム合金の擬似集合組織の生成と②極点図による可視化, ③訓練済みDNNを用いた応力-ひずみ曲線の推定, ④等塑性仕事面の可視化を可能とするWebアプリケーションを開発した. このアプリケーションでは, 上記①~④の全てをWebブラウザ上で実行可能であり, 多軸応力試験機や結晶塑性有限要素法のソースコードを所有しない場合でも, 材料モデリングに必要な情報を得ることが可能となり, 成形シミュレーションの高度化に寄与すると考える.

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Annual Research Report
  • 2017 Annual Research Report
  • Research Products

    (26 results)

All 2020 2019 2018 2017 Other

All Journal Article (2 results) (of which Peer Reviewed: 2 results,  Open Access: 1 results) Presentation (21 results) (of which Int'l Joint Research: 7 results) Remarks (3 results)

  • [Journal Article] Estimation of Texture-dependent Stress-Strain Curve and <i>r</i>-value of Aluminum Alloy Sheet Using Deep Learning2020

    • Author(s)
      肥沼康太, 山中晃徳, 渡邊育夢, 桑原利彦
    • Journal Title

      Journal of the Japan Society for Technology of Plasticity

      Volume: 61 Issue: 709 Pages: 48-55

    • DOI

      10.9773/sosei.61.48

    • NAID

      130007801669

    • ISSN
      0038-1586, 1882-0166
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Data Assimilation for Three-dimensional Phase-field Simulation of Dendritic Solidification using the Local Ensemble Transform Kalman Filter2020

    • Author(s)
      Akinori Yamanaka, Kazuki Takahashi
    • Journal Title

      Materials Today Communications

      Volume: not decided

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] Data Assimilation for Three-dimensional Phase-field Simulation of Binary Alloy Solidification2019

    • Author(s)
      Kazuki Takahashi, Akinori Yamanaka
    • Organizer
      Asian Pacific Congress on Computatioanl Mechanics (APCOM2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Bayesian Data Assimilation Solver for Phase-field Models with Python2019

    • Author(s)
      Akinori Yamanaka, Yuri Maeda
    • Organizer
      Asian Pacific Congress on Computatioanl Mechanics (APCOM2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Ensemble-based data assimilation method for phase-field simulation of binary alloy solidification2019

    • Author(s)
      Akinori Yamanaka, Kazuki Takahashi
    • Organizer
      The 4th International Symposium on Phase-Field Modelling in Materials Science (PF19)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] EnKF-based data assimilation for multi-phase-field simulation of grain growth2019

    • Author(s)
      Akinori Yamanaka, Yuri Maeda and Kengo Sasaki
    • Organizer
      International Conference on Computational & Experimental Engineering and Sciences (ICCES 2019)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 機械学習と結晶塑性有限要素法を用いたアルミニウム合金板材の変形挙動推定2019

    • Author(s)
      山中晃徳, 肥沼康太, 上條龍之介, 渡邊育夢, 桑原利彦
    • Organizer
      軽金属学会第137回秋期大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 結晶塑性有限要素法に基づく数値二軸引張試験と深層学習による材料モデリング2019

    • Author(s)
      山中晃徳、上條龍之介、肥沼康太、桑原利彦
    • Organizer
      日本塑性加工学会 第70回塑性加工連合講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 敵対的生成ネットワークを用いたアルミニウム合金の集合組織の逆推定2019

    • Author(s)
      肥沼康太、山中晃徳、上條龍之介、桑原利彦
    • Organizer
      日本塑性加工学会 第70回塑性加工連合講演会 講演論文集
    • Related Report
      2019 Annual Research Report
  • [Presentation] フェーズフィールドモデルに用いる逐次データ同化手法の推定精度評価2019

    • Author(s)
      前田悠里、庄司香織、山中晃徳
    • Organizer
      日本機械学会 第32回計算力学講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 深層学習による集合組織に依存したアルミニウム合金板材の変形特性の高速推定2019

    • Author(s)
      上條龍之介、肥沼康太、庄司香織、山中晃徳
    • Organizer
      日本機械学会 第32回計算力学講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] アルミニウム合金のミクロ組織設計に資する条件付き敵対的生成ネットワークの構築2019

    • Author(s)
      肥沼康太、上條龍之介、庄司香織、山中晃徳
    • Organizer
      日本機械学会 第32回計算力学講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 局所アンサンブル変換カルマンフィルタを用いた合金凝固シミュレーションのデータ同化2019

    • Author(s)
      高橋和希、庄司香織、山中晃徳
    • Organizer
      日本機械学会 第32回計算力学講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] 合金凝固のフェーズフィールドシミュレーションへの局所アンサンブル変換カルマンフィルタの適用2019

    • Author(s)
      高橋和希、山中晃徳
    • Organizer
      第65回理論応用力学講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Prediction of biaxial tensile deformation behavior of aluminum alloy using crystal plasticity finite element method and machine learning2019

    • Author(s)
      Kohta Koenuma, Akinori Yamanaka and Toshihiko Kuwabara
    • Organizer
      2019 TMS Annual Meeting & Exhibition
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 結晶塑性有限要素法と深層学習による金属板材の二軸応力ひずみ曲線の推定2019

    • Author(s)
      肥沼康太、山中晃徳、桑原利彦
    • Organizer
      日本塑性加工学会 2019年度塑性加工春季講演大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] データ同化による異方性降伏関数の逆問題推定2019

    • Author(s)
      山中晃徳、肥沼康太
    • Organizer
      日本塑性加工学会 2019年度塑性加工春季講演大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 深層学習を用いたアルミニウム合金板材の二軸引張変形の推定2019

    • Author(s)
      肥沼康太、山中晃徳、桑原利彦
    • Organizer
      軽金属学会第136回春期大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] データ同化によるアルミニウム合金の異方性降伏関数の推定2019

    • Author(s)
      山中晃徳、桑原利彦、佐々木健吾
    • Organizer
      軽金属学会第136回春期大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] Prediction of Biaxial Tensile Deformation Behavior of Aluminum Alloy Sheets using Crystal Plasticity Finite Element Method and Machine Learning2018

    • Author(s)
      Kota Koenuma, Akinori Yamanaka, Ikumu Watanabe, Toshihiko Kuwabara
    • Organizer
      The 9th International Conference on Multiscale Materials Modeling (MMM2018)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Estimation of Grain Boundary Anisotropy using Multi-phase-field Model based on the Ensemble Kalman Filter2018

    • Author(s)
      Akinori Yamanaka, Yuri Maeda, Kengo Sasaki
    • Organizer
      The 9th International Conference on Multiscale Materials Modeling (MMM2018)
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 結晶塑性FFT法による静的再結晶シミュレーション2017

    • Author(s)
      前田悠里, 山中晃徳
    • Organizer
      第22回計算工学講演会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 結晶塑性有限要素法によるアルミニウム合金板の数値材料試験と成形シミュレーションへの応用2017

    • Author(s)
      山中晃徳
    • Organizer
      軽金属学会 第104回シンポジウム「アルミニウム合金板材の成形シミュレーション高精度化技術」
    • Related Report
      2017 Annual Research Report
  • [Remarks] 東京農工大学 山中研究室

    • URL

      http://web.tuat.ac.jp/~yamanaka/index.html

    • Related Report
      2019 Annual Research Report
  • [Remarks] 東京農工大学 山中研究室

    • URL

      http://web.tuat.ac.jp/~yamanaka/index.html

    • Related Report
      2018 Annual Research Report
  • [Remarks] 東京農工大学 山中研究室

    • URL

      http://web.tuat.ac.jp/~yamanaka/publications.html

    • Related Report
      2017 Annual Research Report

URL: 

Published: 2017-04-28   Modified: 2021-12-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi