LI Fengjun, WANG Zixin, SUN Qian, PENG Lei, MIAO Shihong. A Model for Mining Association of Equipment Faults in Distribution Network Considering Meteorological Factors[J]. Modern Electric Power, 2023, 40(4): 605-613. DOI: 10.19725/j.cnki.1007-2322.2021.0376
Citation: LI Fengjun, WANG Zixin, SUN Qian, PENG Lei, MIAO Shihong. A Model for Mining Association of Equipment Faults in Distribution Network Considering Meteorological Factors[J]. Modern Electric Power, 2023, 40(4): 605-613. DOI: 10.19725/j.cnki.1007-2322.2021.0376

A Model for Mining Association of Equipment Faults in Distribution Network Considering Meteorological Factors

  • The structure of the power grid is becoming more and more complex, and the cost of fault monitoring and prevention will increase. The frequent occurrence of strong convective weather makes equipment failures more closely related to external conditions. Therefore, it is of great significance for the safe and stable operation of the power system to excavate the correlation between the fault equipment and the fault factors, and to focus on the monitoring and prevention of the equipment with high correlation degree. Based on the fuzzy frequent item mining algorithm, a distribution network equipment fault association mining model that considers meteorological factors was proposed. The model first extracts fault characteristic data from a multivariate information database, uses the Relief-F algorithm to eliminate redundant features that are less relevant, and builds a fault associated characteristic database containing meteorological factors through data preprocessing and data integration. Secondly, based on the fault correlation feature database, the fuzzy set theory was introduced, and the method of fault factor and fault equipment association model construction was proposed based on the fuzzy frequent item set mining algorithm. Finally, an example was analyzed based on the fault correlation model, and the results verify the correctness and effectiveness of the proposed method.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return