Data-driven Fault Detection

Data-Driven Fault Detection is a fault detection approach that belongs to the class of diagnostic methods relying on empirical data rather than explicit physical models, distinguished by its use of statistical, machine learning, or pattern recognition techniques to identify anomalies or faults directly from observed system data.

522

Publications

31K

Citations

1.7K

Authors

560

Institutions

Publications per year

2017–2026

374

Authors

1.7K

  1. SX
    Steven X. Ding

    University of Duisburg-Essen, Germany

    21 publications · 3K citations

    17

    h-index

  2. SY
    Shen Yin

    Harbin Institute of Technology, China

    16 publications · 2.6K citations

    13

    h-index

  3. HC
    Hongtian Chen

    University of Alberta, Canada

    12 publications · 1.2K citations

    12

    h-index

  4. LL
    Linlin Li

    University of Science and Technology Beijing, China

    10 publications · 425 citations

    10

    h-index

  5. HL
    Hao Luo

    Harbin Institute of Technology, China

    9 publications · 280 citations

    9

    h-index

1–5 of 1.7K

Venues

  1. IEEE Transactions on Industrial Informatics

    19 publications · 2.3K citations

    19

    h-index

  2. IEEE Transactions on Industrial Electronics

    17 publications · 3.4K citations

    17

    h-index

  3. IEEE Access

    20 publications · 833 citations

    17

    h-index

  4. 15

    h-index

  5. Energies

    10 publications · 337 citations

    10

    h-index

1–5