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

Study on Adaptive Fault Diagnosis for Reducing Fault Diagnosis Time

Research Project

Project/Area Number 19K11877
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60040:Computer system-related
Research InstitutionEhime University

Principal Investigator

higami Yoshinobu  愛媛大学, 理工学研究科(工学系), 教授 (40304654)

Co-Investigator(Kenkyū-buntansha) 稲元 勉  愛媛大学, 理工学研究科(工学系), 講師 (10379513)
高橋 寛  愛媛大学, 理工学研究科(工学系), 教授 (80226878)
王 森レイ  愛媛大学, 理工学研究科(工学系), 講師 (90735581)
Project Period (FY) 2019-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Keywords故障診断 / テスト容易化設計 / 故障辞書 / 機械学習 / テストポイント / 出力圧縮 / ニューラルネットワーク / テストパターン / 組込み自己テスト / LSIテスト / アダプティブ故障診断 / LSIの故障診断 / フィールドテスト / テストパターン生成 / 出力応答圧縮
Outline of Research at the Start

本研究では,出力応答に応じてテストパターンを印加するようなアダプティブ故障診断を想定し,故障診断時間が短縮する手法を開発する.開発する手法は,アダプティブ故障診断におけるテストパターン選択法,出力応答を比較する時間を短縮するための出力応答圧縮法,故障位置を1か所に絞り込むためのテストパターン生成法である.

Outline of Final Research Achievements

In this study, we have developed fault diagnosis methods, which deduce fault sites in Large-Scale Integrated Circuits (LSIs). The methods include compaction of fault dictionary, test point insertion and machine learning based diagnosis methods. Fault dictionary stores output responses of faulty circuits. By using a fault dictionary, fault diagnosis time becomes short, but it requires large amount of memory requirement. The developed method compacts fault dictionary and results in reduction of memory requirement. Also test insertion method enhances the ability of fault diagnosis, and machine learning based method reduces fault diagnosis time without using a fault dictionary.

Academic Significance and Societal Importance of the Research Achievements

LSIの故障診断の結果は、2通りの活用法がある。1つは、故障診断位置や原因を解析することで、LSI設計・製造上の問題を発見し、それを改善することで歩留まり向上を実現することができる。もう1つは、実稼働中のシステムにおいて、故障位置から故障の影響する外部出力を推定することによって、故障影響のない外部出力のみを用いてシステムを稼働させることができる。これによって、故障が発見されても、システムを停止させることなく、縮小した機能でシステムを稼働させることができる。以上のように、本研究は、LSIの生産性向上、コンピュータシステム信頼性向上などに貢献する。

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

    (18 results)

All 2023 2022 2021 2020 2019 Other

All Int'l Joint Research (5 results) Journal Article (11 results) (of which Int'l Joint Research: 5 results,  Peer Reviewed: 10 results,  Open Access: 1 results) Presentation (2 results)

  • [Int'l Joint Research] ウィスコンシン大学 マディソン校(米国)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] University of Wisconsin - Madison(米国)

    • Related Report
      2022 Research-status Report
  • [Int'l Joint Research] University of Wisconsin - Madison(米国)

    • Related Report
      2021 Research-status Report
  • [Int'l Joint Research] University of Wisconsin - Madison(米国)

    • Related Report
      2020 Research-status Report
  • [Int'l Joint Research] University of Wisconsin - Madison(米国)

    • Related Report
      2019 Research-status Report
  • [Journal Article] Improving of Fault Diagnosis Ability by Test Point Insertion and Output Compaction2023

    • Author(s)
      Higami Yoshinobu、Inamoto Tsutomu、Wang Senling、Takahashi Hiroshi、Saluja Kewal K.
    • Journal Title

      Proc. in 2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC)

      Volume: - Pages: 1-6

    • DOI

      10.1109/itc-cscc58803.2023.10212844

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Machine Learning Based Fault Diagnosis for Stuck-at Faults and Bridging Faults2022

    • Author(s)
      Yoshinobu Higami, Takaya Yamauchi, Tsutomu Inamoto, Senling Wang, Hiroshi Takahashi, Kewal K. Saluja
    • Journal Title

      Proceedings of International Technical Conference on Circuits/Systems, Computers and Communications

      Volume: - Pages: 477-480

    • DOI

      10.1109/itc-cscc55581.2022.9894966

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Preliminary Study on Noise-Resilient Artificial Neural Networks for On-Chip Test Generation2022

    • Author(s)
      Tsutomu Inamoto, Tomoki Nishino, Senling Wang, Yoshinobu Higami and Hiroshi Takahashi
    • Journal Title

      Proceedings of IEEE 11th Global Conference on Consumer Electronics

      Volume: - Pages: 561-565

    • DOI

      10.1109/gcce56475.2022.10014218

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Journal Article] Compaction of Fault Dictionary without Degrading Diagnosis Ability,2021

    • Author(s)
      Yoshinobu Higami, Tomokazu Nakamura, Tsutomu Inamoto, Senling Wang, Hiroshi Takahashi, Kewal K. Saluja
    • Journal Title

      Proceedings of International Technical Conference on Circuits/Systems, Computers and Communications

      Volume: - Pages: 51-54

    • DOI

      10.1109/itc-cscc52171.2021.9501474

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Preliminary Evaluation of Artificial Neural Networks as Test Pattern Generators for BIST2021

    • Author(s)
      Tsutomu Inamoto, Kazuki Ohtomo, and Yoshinobu Higami
    • Journal Title

      Proceedings of International Technical Conference on Circuits/Systems, Computers and Communications

      Volume: - Pages: 307-310

    • DOI

      10.1109/itc-cscc52171.2021.9501263

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Formulation of a Test Pattern Measure that Counts Distinguished Fault-Pairs for Circuit Fault Diagnosis2020

    • Author(s)
      Tsutomu Inamoto and Yoshinobu Higami
    • Journal Title

      IEICE Trans. on Fundamentals

      Volume: E103-A Pages: 1456-1463

    • NAID

      130007948287

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Reduction of Fault Dictionary Size by Optimizing the Order of Test Patterns Application2020

    • Author(s)
      Yoshinobu Higami, Tsutomu Inamoto, Senling Wang, Hiroshi Takahashi, Kewal K. Saluja
    • Journal Title

      Proc. Int. Technical Conf. on Circuits/Systems, Computers and Communications

      Volume: - Pages: 131-136

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Regeneration of Test Patterns for BIST by Using Artificial Neural Networks2020

    • Author(s)
      Tsutomu Inamoto, Yoshinobu Higami
    • Journal Title

      Proc. Int. Technical Conf. on Circuits/Systems, Computers and Communications

      Volume: - Pages: 137-140

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Compact Dictionaries for Reducing Compute Time in Adaptive Diagnosis2019

    • Author(s)
      Yoshinobu Higami, Tomokazu Nakamura, Tsutomu Inamoto, Senling Wang, Hiroshi Takahashi, Kewal K Saluja
    • Journal Title

      Proceedings Internationa Technical Conference on Circuits/Systems, Computers and Communications

      Volume: - Pages: 525-528

    • DOI

      10.1109/itc-cscc.2019.8793429

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Application of Convolutional Neural Networks to RegenerateDeterministic Test Pattern for BIST2019

    • Author(s)
      Tsutomu Inamoto and Yoshinobu Higami
    • Journal Title

      Proceedings Internationa Technical Conference on Circuits/Systems, Computers and Communications

      Volume: - Pages: 523-524

    • DOI

      10.1109/itc-cscc.2019.8793374

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] 畳み込みニューラルネットワークを用いたテストパターンの再生2019

    • Author(s)
      稲元 勉, 樋上 喜信
    • Journal Title

      第32回 回路とシステムワークショップ (KWS 32) 論文集

      Volume: - Pages: 234-239

    • NAID

      40021991413

    • Related Report
      2019 Research-status Report
  • [Presentation] 圧縮優先度の近似的計算による故障辞書の圧縮処理時間の短縮2022

    • Author(s)
      濱野郁也,稲元勉,樋上喜信
    • Organizer
      令和4年度電気・電子・情報関係学会四国支部連合大会
    • Related Report
      2022 Research-status Report
  • [Presentation] 機械学習を用いた複数故障モデルの故障診断2021

    • Author(s)
      山内崇矢,稲元勉,王森レイ,樋上喜信,高橋寛
    • Organizer
      令和3年度電気・電子・情報関係学会四国支部連合大会
    • 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