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

Fundamental study on structural damage detection applying machine learning methods to sensor data

Research Project

Project/Area Number 19K04583
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 22020:Structure engineering and earthquake engineering-related
Research InstitutionTokai University

Principal Investigator

Mikami Atsushi  東海大学, 建築都市学部, 教授 (10262122)

Project Period (FY) 2019-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2021: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2019: ¥260,000 (Direct Cost: ¥200,000、Indirect Cost: ¥60,000)
Keywords損傷検知 / 機械学習 / センサーデータ / オートエンコーダ / 振動実験 / 時系列データ / 構造物の損傷検知
Outline of Research at the Start

高度経済成長期に建設された膨大な数のインフラが老朽化を迎えているが,技術者不足により点検が進んでいない.1つの改善策は,低価格化が進んでいるセンサーを構造物に設置して得られるデータの分析から,自動的に損傷を検知する方法を補助的に用いることである.本研究はセンサーデータに機械学習の方法を適用することで構造物の損傷検知を自動化し,インフラ点検技術者不足の問題に寄与することを最終目標としているが,特に,損傷検知手法の適切な選択や損傷検知能力向上のためのデータ処理の手法を検討し,実用化につなげるものである.

Outline of Final Research Achievements

Assuming that structural response data (vibration data) is obtained by instrumented sensors, it is possible to automatically and immediately detect damage to structures by applying autoencoders as a machine learning method.
Specifically, damage to the structure was simulated by reducing stiffness, and an attempt was made to detect responses with damage from learning responses without damage. As a further application, it was shown that it is possible to obtain criteria for determining whether a structure should be immediately taken out of service by having a structure equipped with a strong motion seismometer learn the response to small and medium earthquake motions that occur sometimes, and then applying an autoencoder to the nonlinear response of the structure when a large earthquake occurs.

Academic Significance and Societal Importance of the Research Achievements

構造物の損傷検知の必要性は,インフラメンテナンスのように,損傷が徐々に進行する場合と,例えば,地震などの災害時のように急激に進行する場合が考えられるが,いずれの場合においても対応する技術者が不足する今日の状況の中,本研究成果を適用することで,自動,かつ,即時に損傷検知が可能となる.本研究は構造物の損傷を検知し,次の詳細検査段階へと進めるための1次スクリーニング手法として有益であると考えられ,これにより,技術者不足の問題の解消につながることが期待される.

Report

(6 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (9 results)

All 2024 2023 2022 2021 2019

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

  • [Journal Article] IMMEDIATE DAMAGE DETECTION OF INSTRUMENTED STRUCTURE BY A LARGE EARTHQUAKE BASED ON MACHINE LEARNING OF LINEAR RESPONSES CAUSED BY SMALL AND MEDIUM EARTHQUAKES2023

    • Author(s)
      三神 厚
    • Journal Title

      Japanese Journal of JSCE

      Volume: 79 Issue: 13 Pages: n/a

    • DOI

      10.2208/jscejj.22-13013

    • ISSN
      2436-6021
    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Fundamental Study on Damage Detection of Civil Structures Modeled as MDOF System Based on Machine Learning2023

    • Author(s)
      Atsushi Mikami
    • Journal Title

      STRUCTURAL HEALTH MONITORING 2023 Designing SHM for Sustainability, Maintainability and Reliability

      Volume: 1 Pages: 1489-1496

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 中小地震による構造物の応答の機械学習に基づく大地震時の即時損傷検知の試み2022

    • Author(s)
      三神厚
    • Journal Title

      第42回地震工学研究発表会講演論文集

      Volume: 1

    • Related Report
      2022 Research-status Report
  • [Journal Article] 構造物の非線形地震応答に対するオートエンコーダの適用2021

    • Author(s)
      三神厚
    • Journal Title

      第41回地震工学研究発表会講演論文集

      Volume: 1

    • Related Report
      2021 Research-status Report
  • [Journal Article] 時刻歴応答にオートエンコーダを適用した構造物の損傷検知に関する基礎的検討2019

    • Author(s)
      三神厚
    • Journal Title

      第39回地震工学研究発表会講演論文集

      Volume: 39

    • Related Report
      2019 Research-status Report
  • [Presentation] 振動実験データに機械学習を適用した構造物の損傷検知の試み2024

    • Author(s)
      三神 厚
    • Organizer
      土木学会関東支部第51回関東支部技術研究発表会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Fundamental Study on Damage Detection of Civil Structures Modeled as MDOF System Based on Machine Learning2023

    • Author(s)
      Atsushi Mikami
    • Organizer
      14th International Workshop on Structural Health Monitoring
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 地殻変動データに機械学習の方法を適用した火山噴火予兆検知の試み2022

    • Author(s)
      三神厚,神山眞
    • Organizer
      令和4年度 土木学会全国大会第77回年次学術講演会
    • Related Report
      2022 Research-status Report
  • [Presentation] 異常検知や予測の問題における時系列信号のノイズの影響や標準化の効果に関する基礎的検討2022

    • Author(s)
      三神厚
    • Organizer
      第49回土木学会関東支部技術研究発表会
    • Related Report
      2021 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi