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

Inverse analysis of the butterfly effect in dendrite precipitates using machine learning

Research Project

Project/Area Number 19K22117
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 28:Nano/micro science and related fields
Research InstitutionTokyo University of Science

Principal Investigator

Kotsugi Masato  東京理科大学, 基礎工学部材料工学科, 准教授 (60397990)

Co-Investigator(Kenkyū-buntansha) 橋爪 洋一郎  東京理科大学, 理学部第一部応用物理学科, 講師 (50711610)
Project Period (FY) 2019-06-28 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥6,500,000 (Direct Cost: ¥5,000,000、Indirect Cost: ¥1,500,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2019: ¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Keywordsパーシステントホモロジー / 機械学習 / 金属組織 / デンドライト組織 / フェーズフィールド法 / スピノーダル分解 / 光電子顕微鏡
Outline of Research at the Start

本研究は二次電池の安全性向上を目標に、表面科学と情報科学を融合し、これまで困難であった電極の劣化原因の逆解析技術の実現に挑戦する。電極表面に形成されるデンドライト組織のフラクタル構造に着目し、(1)パーシステントホモロジーを用いた特徴量抽出と、(2)多様体による機械学習を行い、析出現象の初期物性値を推定する枠組みを構築する。組織構造と物性値の関係性を特徴量空間を介して接続し、電極表面におけるバタフライ効果を記述する。

Outline of Final Research Achievements

We developed an automated analysis method for predicting physical property parameters from image data of dendrite precipitates and spinodal decomposition using the topological concept of "persistent homology," First, image data of dendrite precipitates and spinodal decomposition were generated using the phase-field method. Next, persistent homology was used to extract the features of the shape of microstructures. Then, principal component analysis was used for dimensionality reduction, and the changes in the data were visualized in low-dimensional space. The results suggest that it is possible to estimate various physical property parameters such as development time, anisotropy parameter, gradient energy coefficient, and total energy in metallographic formation.

Academic Significance and Societal Importance of the Research Achievements

パーシステントホモロジーと呼ばれる位相幾何学の概念と教師無し機械学習を組み合わせて、デンドライト組織などの複雑な金属組織から、自動的に物性パラメータ(発展時間、異方性パラメータ、勾配エネルギー係数、全エネルギー)を逆解析するための枠組みを新しく開発した。

Report

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

    (17 results)

All 2020 2019

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (16 results) (of which Int'l Joint Research: 5 results,  Invited: 9 results)

  • [Journal Article] Visualization of Topological Defect in Labyrinth Magnetic Domain by Using Persistent Homology2019

    • Author(s)
      YAMADA T.、SUZUKI Y.、MITSUMATA C.、ONO K.、UENO T.、OBAYASHI I.、HIRAOKA Y.、KOTSUGI M.
    • Journal Title

      Vacuum and Surface Science

      Volume: 62 Issue: 3 Pages: 153-160

    • DOI

      10.1380/vss.62.153

    • NAID

      130007609737

    • ISSN
      2433-5835, 2433-5843
    • Year and Date
      2019-03-10
    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] 自由エネルギーモデリングに基づく材料機能-微細組織の自動解析2020

    • Author(s)
      小嗣真人
    • Organizer
      日本学術振興会, R026先端計測技術の将来設計委員会
    • Related Report
      2020 Annual Research Report
    • Invited
  • [Presentation] 機能の解釈に踏み込む新しいAI顕微解析手法の提案2020

    • Author(s)
      小嗣真人
    • Organizer
      日本学術振興会 先端AI計測委員会
    • Related Report
      2020 Annual Research Report
    • Invited
  • [Presentation] 擬自由エネルギーを用いた多様な安定相の探索:微細組織構造の情報解析2020

    • Author(s)
      小嗣真人
    • Organizer
      日本応用物理学会
    • Related Report
      2020 Annual Research Report
    • Invited
  • [Presentation] Topological data analysis of magnetic domain structure for the interpretation of microscopic image data2020

    • Author(s)
      小嗣真人
    • Organizer
      IMR+MAX IV 2020 international workshop
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] Visualization of free energy landscape in spinodal decomposition using persistenthomology combined with unsupervised machine learning2020

    • Author(s)
      Alexandre Lira Foggiatto, Hirotaka Aoki, Sotaro Kunii, MasatoKotsugi
    • Organizer
      日本応用物理学会
    • Related Report
      2019 Research-status Report
  • [Presentation] パーシステントホモロジーを用いた軟磁性材料の保磁力解析2020

    • Author(s)
      國井創大郎, Alexandre Lira Foggiatto,木村恵太,三俣千春,小嗣真人
    • Organizer
      日本応用物理学会
    • Related Report
      2019 Research-status Report
  • [Presentation] 強磁性形状記憶合金の金属・磁区構造シミュレーションとトポロジカルデータ解析2020

    • Author(s)
      仙井遼平, Alexandre Lira Foggiatto, 小嗣真人
    • Organizer
      日本応用物理学会
    • Related Report
      2019 Research-status Report
  • [Presentation] Topological data analysis of magnetic domain structure for the interpretation of microscopic image data2020

    • Author(s)
      M. Kotsugi
    • Organizer
      IMR+MAX IV 2020 international workshop
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] 機械学習を用いた磁区構造からの情報抽出:擬自由エネルギーによる多様な安定相の探索2020

    • Author(s)
      M. Kotsugi
    • Organizer
      日本応用物理学会
    • Related Report
      2019 Research-status Report
    • Invited
  • [Presentation] 位相的データ解析によるネオジム磁石の磁区構造からの特徴量抽出2019

    • Author(s)
      寺嶋悠貴, 山田拓洋, 大林一平,赤木和人,平岡裕章,小嗣真人
    • Organizer
      日本磁気学会
    • Related Report
      2019 Research-status Report
  • [Presentation] パーシステントホモロジーを用いたスピノーダル分解における特徴抽出2019

    • Author(s)
      青木 宏賢, 沖 直人, 山田拓洋, 大林一平, 赤木和人, 平岡裕章, 小嗣真人
    • Organizer
      日本応用物理学会
    • Related Report
      2019 Research-status Report
  • [Presentation] Topological data analysis of microscopic image data2019

    • Author(s)
      M. Kotsugi, T. Yamada, Y. Suzuki, C. Mitsumata, K. Ono, T. Ueno, I. Obayashi, K. Akagi, Y. Hiraoka
    • Organizer
      12th International Symposium on Atomic Level Characterizations for New Materials and Devices '19 (ALC19)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Topological data analysis of the magnetic domain for the automated visualization of the origin of coercivity2019

    • Author(s)
      M. Kotsugi, T. Yamada, Y. Suzuki, C. Mitsumata, K. Ono, T. Ueno, I. Obayashi, K. Akagi, Y. Hiraoka
    • Organizer
      Materials Research Meeting 2019 (MRM2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Automated visualization of the origin of the coercivity by using persistent homology2019

    • Author(s)
      M. Kotsugi, T. Yamada , Y. Suzuki , C. Mitsumata , K. Ono , T. Ueno , I. Obayashi , K. Akagi , Y. Hiraoka
    • Organizer
      Annual Conference on Magnetism and Magnetic Materials (MMM2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] データサイエンスによる大規模計測データからの知識抽出2019

    • Author(s)
      M. Kotsugi
    • Organizer
      日本科学機器協会講演会
    • Related Report
      2019 Research-status Report
    • Invited
  • [Presentation] トポロジカルデータ解析による磁区構造からの特徴抽出2019

    • Author(s)
      M. Kotsugi
    • Organizer
      日本磁気学会223回研究会
    • Related Report
      2019 Research-status Report
    • Invited

URL: 

Published: 2019-07-04   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi