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

Development of computational techniques for inverse problems and optimizations of sheet metal forming using machine learning

Research Project

Project/Area Number 20H02476
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 26050:Material processing and microstructure control-related
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), 教授 (50542198)

Co-Investigator(Kenkyū-buntansha) 桑原 利彦  東京農工大学, 工学(系)研究科(研究院), 卓越教授 (60195609)
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, 主幹研究員 (20535992)
箱山 智之  岐阜大学, 工学部, 助教 (20799720)
Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥17,680,000 (Direct Cost: ¥13,600,000、Indirect Cost: ¥4,080,000)
Fiscal Year 2022: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2021: ¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Fiscal Year 2020: ¥6,890,000 (Direct Cost: ¥5,300,000、Indirect Cost: ¥1,590,000)
Keywordsデータ同化 / 材料モデリング / ベイズ最適化 / 深層学習 / アルミニウム合金 / 材料設計 / 逆問題 / 板材成形 / 機械学習 / 最適化 / フェーズフィールド法 / 結晶塑性有限要素法 / 結晶塑性
Outline of Research at the Start

本研究では, フェーズフィールド法による材料組織予測と多岐にわたる機械学習方法(深層学習・転移学習・敵対的生成ネットワーク・データ同化・ベイズ最適化)を駆使し, アルミニウム合金板の内部組織情報から機械的特性や成形加工性を順推定するのみならず, その逆推定, さらには内部組織の最適化を可能とする計算技術を開発する.

Outline of Final Research Achievements

In order to improve the accuracy of numerical simulation of sheet metal forming process, material models that accurately describe the plastic deformation of sheet metal have been identified based on multiaxial-stress test data. However, the conventional method requires special testing equipments and advanced experimental skills. In order to solve this issue, this study employs various data scientific methods, in particular, deep learning, Bayesian optimization, and data assimilation in addition to the sheet metal forming simulation using the finite element method. We developed several numerical calculation techniques that enable us to perform not only quantitative forward estimation of mechanical properties and formability of sheet metal from microstructural information, but also inverse estimation and optimization of microstructure.

Academic Significance and Societal Importance of the Research Achievements

金属板材をプレス成形加工する技術は、日本の主要製造業を支える重要技術である。しかし、国際競争の激化と少子高齢化のために、プレス成形加工に関する研究開発は一層の効率化・省人化が求められており、各種の機械学習方法、最適化理論、逆解析手法を駆使した技術が必要とされる。本研究では、深層学習やデータ同化を用いて、金属板材内部の微細組織情報から機械的特性や成形加工性を定量的に順推定するのみならず、その逆推定や最適化も可能とする数値計算技術を開発した。これは、金属板材の変形を再現するデジタルツインの構築であり、所望のプレス加工を実現するためのプレス成形加工条件の設計や新しい材料の設計に応用できる基礎となる。

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • Research Products

    (23 results)

All 2023 2022 2021 2020 Other

All Int'l Joint Research (2 results) Journal Article (6 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 4 results,  Open Access: 1 results) Presentation (12 results) (of which Int'l Joint Research: 6 results,  Invited: 1 results) Remarks (3 results)

  • [Int'l Joint Research] KU Leuven(ベルギー)

    • Related Report
      2022 Annual Research Report
  • [Int'l Joint Research] KU Leuven(ベルギー)

    • Related Report
      2021 Annual Research Report
  • [Journal Article] データ同化によるフェーズフィールドシミュレーションの進展2023

    • Author(s)
      山中 晃徳
    • Journal Title

      計算工学

      Volume: 28 Pages: 7-10

    • Related Report
      2022 Annual Research Report
  • [Journal Article] 非逐次データ同化の塑性加工分野への応用2023

    • Author(s)
      山中 晃徳
    • Journal Title

      ぷらすとす

      Volume: 65

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Bayesian texture optimization using deep neural network-based numerical material test2022

    • Author(s)
      Ryunosuke Kamijyo, Akimitsu Ishii, Sam Coppieters, and Akinori Yamanaka
    • Journal Title

      International Journal of Mechanical Sciences

      Volume: 223 Pages: 107285-107285

    • DOI

      10.1016/j.ijmecsci.2022.107285

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Data Scientific Application to Numerical Material Test for Sheet Metals2022

    • Author(s)
      山中晃徳
    • Journal Title

      PLASTOS

      Volume: 5 Issue: 52 Pages: 203-207

    • DOI

      10.32277/plastos.5.52_203

    • ISSN
      2433-8826
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Quantitative three-dimensional phase-field modeling of dendritic solidification coupled with local ensemble transform Kalman filter2021

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

      Computational Materials Science

      Volume: 190 Pages: 110296-110296

    • DOI

      10.1016/j.commatsci.2021.110296

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Deep neural network approach to estimate biaxial stress-strain curves of sheet metals2020

    • Author(s)
      Yamanaka Akinori, Kamijyo Ryunosuke, Koenuma Kohta, Watanabe Ikumu, and Kuwabara Toshihiko
    • Journal Title

      Materials & Design

      Volume: 195 Pages: 108970-108970

    • DOI

      10.1016/j.matdes.2020.108970

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] Bayesian data assimilation for inverse material modelling using 3D-digital image correlation measurement2022

    • Author(s)
      Sae Sueki, Akimitsu Ishii, Akinori Yamanaka
    • Organizer
      JSME International Conference on Materials and Processing 2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Material Model Calibration using 3D-DIC measurement and Bayesian Data Assimilation2022

    • Author(s)
      Sae Sueki, Akimitsu Ishii, Eisuke Miyoshi, Akinori Yamanaka
    • Organizer
      The World Congress on Computational Mechanics & 8th Asian Pacific Congress on Computational Mechanics 2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Calibration of Material Model for Sheet Metalls Using Digital Image Correlation and Bayesian Data Assimilation2022

    • Author(s)
      Michihiko Suda, Ryunosuke Kamijyo, Akimitsu Ishii, Akinori Yamanaka
    • Organizer
      The World Congress on Computational Mechanics & 8th Asian Pacific Congress on Computational Mechanics 2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Phase-field simulation of ternary alloy solidification in forced convection with local ensemble transform kalman filter2022

    • Author(s)
      Kawasaki Masahiro, Akinori Yamanaka, Eisuke Miyoshi
    • Organizer
      The World Congress on Computational Mechanics & 8th Asian Pacific Congress on Computational Mechanics 2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 金属板材成形シミュレーションへの非逐次データ同化の適用2022

    • Author(s)
      須田充彦, 上條龍之介, 石井秋光, 山中晃徳
    • Organizer
      日本塑性加工学会 2022年度塑性加工春季講演会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 金属板材成形のための非逐次データ同化を用いた材料モデリング2022

    • Author(s)
      山中晃徳, 須田充彦,石井秋光
    • Organizer
      日本塑性加工学会 第73回塑性加工連合講演会
    • Related Report
      2022 Annual Research Report
  • [Presentation] フェーズフィールドモデリングおよび有限要素解析へのデータ科学的手法の応用2022

    • Author(s)
      山中晃徳
    • Organizer
      日本鉄鋼協会第155回圧延理論部会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] Estimation of biaxial stress-strain curves for aluminum alloy sheets using deep neural network2021

    • Author(s)
      Akinori Yamanaka, Kohta Koenuma, Ryunosuke Kamijyo, Ikumu Watanabe and Toshihiko Kuwabara
    • Organizer
      25th International Congress of Theoretical and Applied Mechanics (ICTAM2020+1)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 畳み込みニューラルネットワークを用いたアルミニウム合金板材の二軸引張変形挙動の推定2021

    • Author(s)
      上條龍之介, 山中晃徳, 渡邊育夢, 桑原利彦
    • Organizer
      日本塑性加工学会 2021年度塑性加工春季講演会
    • Related Report
      2021 Annual Research Report
  • [Presentation] ニューラルネットワークと最適化理論を用いたアルミニウム合金板の成形性向上のための集合組織最適化2021

    • Author(s)
      上條龍之介, 石井秋光, 山中晃徳
    • Organizer
      日本塑性加工学会 第72回塑性加工連合講演会
    • Related Report
      2021 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フェーズフィールドシミュレーションのデータ同化:数値実験による検証2021

    • Author(s)
      川嵜真広, 山中晃徳, 高橋和希, 三好英輔
    • Organizer
      第35回数値流体力学シンポジウム
    • Related Report
      2021 Annual Research Report
  • [Presentation] Estimation of biaxial tensile deformation behavior of aluminum alloy sheet using deep learning2021

    • Author(s)
      Ryunosuke Kamijyo, Akinori Yamanaka, Kohta Koenuma, Ikumu Watanabe and Toshihiko Kuwabara
    • Organizer
      14th World Congress in Computational Mechanics (WCCM)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Remarks] 東京農工大学山中研究室

    • URL

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

    • Related Report
      2022 Annual Research Report 2021 Annual Research Report 2020 Annual Research Report
  • [Remarks] 深層学習を用いた数値材料試験(DNN-NMT)

    • URL

      https://github.com/Yamanaka-Lab-TUAT/DNN-NMT

    • Related Report
      2021 Annual Research Report
  • [Remarks] DNN-NMTとベイズ最適化を用いた最適化ツール(BayesTexOpt)

    • URL

      https://github.com/Yamanaka-Lab-TUAT/BayesTexOpt

    • Related Report
      2021 Annual Research Report

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi