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

Prediction of thickness undulations in coating of liquid films by means of physics-informed machine learning

Research Project

Project/Area Number 19K04175
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 19010:Fluid engineering-related
Research InstitutionTokyo City University

Principal Investigator

Shiratori Suguru  東京都市大学, 理工学部, 准教授 (10803447)

Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2021: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2020: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2019: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Keywords液膜流れ / 物理法則の機械学習 / 膜厚ムラ / データ同化 / 自動微分 / 物性値予測 / Neural Network / Physics-Informed NN / 塗膜の膜厚ムラ / 機械学習
Outline of Research at the Start

半導体デバイス、MEMS、ディスプレイのカラーフィルタ等の製法では機能性の液膜を基板に塗布する工程があるが、様々な物理要因によって種々の膜厚ムラが発生し、最終製品の寸法精度が低下してしまう課題がある。この膜厚ムラの発生を回避・抑制できるような最適塗布条件を数値シミュレーションによって探索したいが、従来の方法では①時間発展計算に時間を要すること、②計算に必要な塗膜の物性値の測定・入手が困難なこと、が障壁となっていた。
本研究では①支配方程式を教師とした機械学習を導入して高速に膜厚ムラを予測する枠組みを構築し、②塗膜の物性値をデータ同化の方法によって推定できるようにすることで上記の課題の解決を目指す。

Outline of Final Research Achievements

This research applied Physics-Informed Neural Network (PINN), to efficiently predict various film thickness irregularities that occur in the liquid film coating process in microfabrication technologies such as semiconductor device and various color filter manufacturing methods. The effectiveness of PINN was investigated by applying it to the partial differential equation of liquid film flow, which includes a fourth-order spatial derivative and a fourth-order nonlinearity, for which was not validated. We found that for proper learning, it is effective to (1) densely place the spatio-temporal residual points where the solution changes rapidly, (2) use double precision floating-point operation, and (3) reduce the number of automatic differentiation operations by introducing intermediate variables and reducing the highest order of derivatives in the partial differential equation.

Academic Significance and Societal Importance of the Research Achievements

液膜に生じる膜厚ムラを予測するシミュレーション方法として、従来の有限差分法等の計算法では時間発展計算に長時間を要するため、膜厚ムラを回避・抑制するための最適塗布条件の探索に供するのは非現実的状況にあった。本研究で有効性を検証したPhysics-informed neural networkは一度学習計算を終えれば、任意の時刻と位置における膜厚を即時に計算することができるため、最適塗布条件への活用が現実的になると期待される。

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (15 results)

All 2022 2021 2020 2019

All Journal Article (4 results) (of which Peer Reviewed: 4 results,  Open Access: 2 results) Presentation (11 results) (of which Int'l Joint Research: 2 results)

  • [Journal Article] Physics‐informed neural network applied to surface‐tension‐driven liquid film flows2022

    • Author(s)
      Nakamura Yo、Shiratori Suguru、Takagi Ryota、Sutoh Michihiro、Sugihara Iori、Nagano Hideaki、Shimano Kenjiro
    • Journal Title

      International Journal for Numerical Methods in Fluids

      Volume: early view Issue: 9 Pages: 1359-1378

    • DOI

      10.1002/fld.5093

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Efficient Implementation of Two-Phase Flow Solver Based on THINC/SW and S-CLSVOF on Unstructured Meshes2021

    • Author(s)
      Suguru SHIRATORI, Takuro USUI, Shiho KOYAMA, Shumpei OZAWA, Hideaki NAGANO, Kenjiro SHIMANO
    • Journal Title

      International journal of microgravity science and application

      Volume: 38 Issue: 3 Pages: 380301

    • DOI

      10.15011/jasma.38.380301

    • NAID

      130008070032

    • ISSN
      2188-9783
    • Year and Date
      2021-07-31
    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Spatio-temporal thickness variation and transient Marangoni number in striations during spin coating2020

    • Author(s)
      Shiratori Suguru、Kato Daiki、Sugasawa Kyosuke、Nagano Hideaki、Shimano Kenjiro
    • Journal Title

      International Journal of Heat and Mass Transfer

      Volume: 154 Pages: 119678-119678

    • DOI

      10.1016/j.ijheatmasstransfer.2020.119678

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] Semi-analytical solution for deformation of elastic/viscoelastic two-layered films pressed on partially-opened substrate2020

    • Author(s)
      Shiratori Suguru、Nagano Hideaki、Shimano Kenjiro
    • Journal Title

      International Journal of Solids and Structures

      Volume: 191-192 Pages: 588-600

    • DOI

      10.1016/j.ijsolstr.2019.12.013

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Presentation] Physics-Informed Neural Networkにおける活性化関数の種別の影響2022

    • Author(s)
      杉原 伊織,白鳥 英,永野 秀明,島野 健仁郎
    • Organizer
      流体力学会年会2022
    • Related Report
      2022 Annual Research Report
  • [Presentation] Modeling of liquid film flow during spin-coating; Marangoni-Benard instability in parallel basic flow2021

    • Author(s)
      Kohei Ono, Suguru Shiratori, Kenjiro Shimano, Hideaki Nagano
    • Organizer
      8th International Conference on Heat Transfer and Fluid Flow (HTFF’21)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Physics-Informed Neural Network with Variable Initial Conditions2021

    • Author(s)
      Yo Nakamura, Suguru Shiratori, Hideaki Nagano, Kenjiro Shimano
    • Organizer
      8th International Conference on Heat Transfer and Fluid Flow (HTFF’21)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Physics-Informed Neural Networkにおける転移学習の効果2021

    • Author(s)
      中村 耀、白鳥 英、周藤 道宏、永野 秀明、島野 健仁郎
    • Organizer
      日本流体力学会年会2021
    • Related Report
      2021 Research-status Report
  • [Presentation] スピンコート中の液膜流れの3次元非定常数値シミュレーション2021

    • Author(s)
      小野 航平、白鳥 英、永野 秀明、島野 健仁郎
    • Organizer
      第35回 数値流体力学シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] Physics-Informed Neural Networkを用いた高速なデータ同化法2020

    • Author(s)
      白鳥 英、武田 唯、中村 耀、山口 郁斗、永野 秀明、島野 健仁郎
    • Organizer
      日本流体力学会年会2020
    • Related Report
      2020 Research-status Report
  • [Presentation] 平行流中のMarangoni-Benard不安定性:スピンコート中の液膜内流れのモデリング2020

    • Author(s)
      野 航平、白鳥 英、永野 秀明、島野 健仁郎
    • Organizer
      日本流体力学会年会2020
    • Related Report
      2020 Research-status Report
  • [Presentation] 初期条件を可変とするPhysics-Informed Neural Network2020

    • Author(s)
      中村 耀、白鳥 英、永野 秀明、島野 健仁郎
    • Organizer
      日本流体力学会年会2020
    • Related Report
      2020 Research-status Report
  • [Presentation] 液膜流れの方程式に対するPhysics-Informed Machine Learningの有効性2019

    • Author(s)
      白鳥 英、高木 遼太、中村 耀、永野 秀明、島野 健仁郎
    • Organizer
      日本流体力学会 年会2019
    • Related Report
      2019 Research-status Report
  • [Presentation] スピンコート中の液膜に発生する放射状スジムラ:膜厚分布の時系列変化の測定2019

    • Author(s)
      白鳥 英、加藤 大輝、島野 健仁郎、永野 秀明
    • Organizer
      日本流体力学会 年会2019
    • Related Report
      2019 Research-status Report
  • [Presentation] 液膜のスピンコートにおける放射状スジムラの形成過程:膜厚分布の時系列変化2019

    • Author(s)
      白鳥 英、加藤 大輝、島野 健仁郎、永野 秀明
    • Organizer
      日本マイクログラビティ応用学会 第31回学術講演会
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi