A Distribution Network Equipment Fault Correlation Mining Model Based on the FFI-Miner Algorithm

With the continuous development of the distribution network, its structure becomes increasingly complex, and the requirements for reliability rise accordingly. Meteorological conditions are one of the primary factors affecting the reliability of the distribution network. Therefore, investigating the correlation under extreme climatic conditions and implementing targeted improvements based on the findings is beneficial for the safe and stable operation of the distribution network. This paper proposes a “Meteorology-Equipment” fault correlation mining model for the distribution network. Firstly, the EWM-AHP algorithm is used to select the most relevant correlation factors and build a fault correlation feature database. Secondly, fuzzy set theory and the FFI-Miner algorithm are introduced, and membership functions for various meteorological factors are established, proposing a method for constructing the fault correlation model. Finally, a case study using data from a specific area of the State Grid is conducted, and the results validate the correctness and effectiveness of the proposed method.