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

Study on transfer learning and explainability of data-driven health monitoring

Research Project

Project/Area Number 19K12094
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionThe University of Tokyo

Principal Investigator

Yairi Takehisa  東京大学, 先端科学技術研究センター, 教授 (90313189)

Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2019: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywordsデータ駆動型健全性管理 / 機械学習 / 動的システム学習 / 異常検知 / 健全性監視 / 転移学習 / 教師なし学習 / システム同定 / 生成モデル / 予防保全 / 人工知能
Outline of Research at the Start

近年、過去の膨大なデータからシステムの挙動モデルを統計的に学習して監視に利用するデータ駆動型の健全性監視法が注目を集めているが、2つの未解決問題が存在する。第1に、現実の人工システムでは事前に十分な量のデータを用意することがしばしば困難であることである。第2に、人工システムの監視において深層学習等の機械学習では説明性が十分でない点である。本研究では、データ駆動健全性監視のための転移学習法を開発すること、および、工学者・専門家にとって解釈性の高い潜在変数-状態空間モデルと最新の機械学習手法との融合を図ることでデータ駆動健全性監視の説明性を実現することでこれらの課題を解決する。

Outline of Final Research Achievements

This study tackled two issues associated with data-driven health monitoring methods for artificial systems. The first issue is the difficulty or high cost of obtaining a sufficient amount and quality of training data in real-world artificial systems. The second issue is the lack of explanatory power in data-driven models obtained through machine learning, as they diverge from the domain knowledge of the target artificial system, making them less practical. In this study, we addressed these two problems by integrating interpretable latent variable-state space models, which are highly interpretable for engineers and experts, with state-of-the-art machine learning techniques. This integration enabled us to reduce the required amount of training data through the utilization of domain knowledge and improve the explanatory power of data-driven health monitoring.

Academic Significance and Societal Importance of the Research Achievements

人工知能・機械学習はインフラや生産システムなどが安全かつ効率的に運用されているかどうかを監視する目的においても大いに期待されているが、学習に膨大な訓練データが必要であること、および、モデルがブラックボックスになり説明性に欠けることが大きな懸念事項である。本研究は、最新の機械学習と伝統的な状態空間・潜在空間モデルを統合して動的なシステムのモデルを学習する方法を開発することによって、これらの問題の解決に貢献した。

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

    (10 results)

All 2022 2021 2020 2019

All Journal Article (5 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 5 results,  Open Access: 1 results) Presentation (5 results) (of which Int'l Joint Research: 3 results,  Invited: 1 results)

  • [Journal Article] Residual reinforcement learning for logistics cart transportation2022

    • Author(s)
      Matsuo Ryosuke、Yasuda Shinya、Kumagai Taichi、Sato Natsuhiko、Yoshida Hiroshi、Yairi Takehisa
    • Journal Title

      Advanced Robotics

      Volume: 36 Issue: 8 Pages: 404-421

    • DOI

      10.1080/01691864.2022.2046504

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Human Language Explanation for a Decision Making Agent via Automated Rationale Generation2022

    • Author(s)
      Phong Nguyen X.、Tran Tho H.、Pham Nguyen B.、Do Dung N.、Yairi Takehisa
    • Journal Title

      IEEE Access

      Volume: 10 Pages: 110727-110741

    • DOI

      10.1109/access.2022.3214323

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Estimating Aerodynamic Coefficients from Uncertain Data of D-SEND Aircraft with Gaussian Process Regression2020

    • Author(s)
      KARINO Hidekazu、YAIRI Takehisa、NINOMIYA Tetsujiro、HORI Koichi
    • Journal Title

      TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES

      Volume: 63 Issue: 6 Pages: 257-264

    • DOI

      10.2322/tjsass.63.257

    • NAID

      130007935581

    • ISSN
      0549-3811, 2189-4205
    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Visual localization for asteroid touchdown operation based on local image features2020

    • Author(s)
      Anzai Yoshiyuki、Yairi Takehisa、Takeishi Naoya、Tsuda Yuichi、Ogawa Naoko
    • Journal Title

      Astrodynamics

      Volume: 4 Issue: 2 Pages: 149-161

    • DOI

      10.1007/s42064-020-0075-8

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Unsupervised anomaly detection in unmanned aerial vehicles2019

    • Author(s)
      Khan Samir、Liew Chun Fui、Yairi Takehisa、McWilliam Richard
    • Journal Title

      Applied Soft Computing

      Volume: 83 Pages: 105650-105650

    • DOI

      10.1016/j.asoc.2019.105650

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] 変分オートエンコーダによる物体画像列からの姿勢推定2022

    • Author(s)
      二木浩司, 矢入健久
    • Organizer
      第65回自動制御連合講演会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Dictionary Learning on Satellite Housekeeping Data: Profiling, Imputation, Novelty Detection2022

    • Author(s)
      Ryosuke TANIDA, Chun Fui LIEW, Takehisa YAIRI and Yusuke FUKUSHIMA
    • Organizer
      33rd International Symposium on Space Technology and Science
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] 動的システム学習の概要と研究動向2021

    • Author(s)
      矢入健久
    • Organizer
      第8回 制御部門マルチシンポジウム(MSCS2021) OS「データサイエンス×システム同定による制御技術の新たな発展」
    • Related Report
      2020 Research-status Report
    • Invited
  • [Presentation] Diagnosing intermittent faults through non-linear analysis2020

    • Author(s)
      Khan, S., Yairi T
    • Organizer
      21st IFAC World Congress 2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Neural Gray-Box Identification of Nonlinear Partial Differential Equations2019

    • Author(s)
      Riku Sasaki, Naoya Takeishi, Takehisa Yairi, and Koichi Hori
    • Organizer
      16th Pacific Rim International Conference on Artificial Intelligence
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi