Method of Equipment Fault Diagnosis Based on Frequent Itemsets Mining

With the construction of new power systems, the grid structure is becoming increasingly complex, and the potential factors that cause power grid faults are also increasing. In this paper, frequent itemset mining is used to deeply mine the association relationship between equipment faults, so as to predict the occurrence of equipment faults and improve the stability of power grid operation. Firstly, the correlation feature of equipment faults is to be selected, at the same time, the method of mutual information is used to filter out the main features. Then, the potential correlation relationship between the fault equipment is evaluated and analyzed by establishing a model. Finally, through the correlation analysis of actual data, the results show that this method performs better compared with other algorithms at the respect of the training time and accuracy, which can be used to predict and guide the fault correlation analysis of power grid equipment.