Data-driven Fault Isolation

Data-Driven Fault Isolation is a fault isolation method that relies on empirical data and statistical or machine learning techniques to identify the root cause of system failures, distinguished from model-based or rule-based approaches by its dependence on observed operational data rather than predefined system models or expert-defined logic.

58

Publications

2.5K

Citations

170

Authors

97

Institutions

Publications per year

2017–2026

29

Authors

170

  1. CS
    Chaitanya Sankavaram

    General Motors (United States), United States

    3 publications · 119 citations

    3

    h-index

  2. SX
    Steven X. Ding

    University of Duisburg-Essen, Germany

    3 publications · 401 citations

    3

    h-index

  3. JF
    James F. Davis

    University of California, Los Angeles, United States

    3 publications · 68 citations

    3

    h-index

  4. KR
    Krishna R. Pattipati

    University of Connecticut, United States

    3 publications · 119 citations

    3

    h-index

  5. BJ
    Benjamin J. Ohran

    University of California, Los Angeles, United States

    3 publications · 68 citations

    3

    h-index

1–5 of 170

Venues

  1. IFAC Proceedings Volumes

    4 publications · 131 citations

    4

    h-index

  2. ISA Transactions

    2 publications · 116 citations

    2

    h-index

  3. IEEE Transactions on Industrial Electronics

    2 publications · 105 citations

    2

    h-index

  4. Mechanical Systems and Signal Processing

    MSSP · 2 publications · 130 citations

    2

    h-index

  5. IEEE Transactions on Smart Grid

    2 publications · 80 citations

    2

    h-index

1–5