The invention discloses an XGBoost-based electric power secondary equipment defect degree evaluation method, which comprises the following steps of: firstly, acquiring and arranging related defect data of electric power system secondary equipment, and performing a series of preprocessing work such as duplicate removal, abnormal value filtration, missing value removal and the like on the acquired historical defect data of the electric power system secondary equipment; then carrying out association rule mining on the processed data based on an Apriori algorithm; screening out features having strong association rules with the defect degree of the secondary equipment of the power system to establish a feature index set, performing feature and label coding on index data, and after data grouping, performing training and parameter optimization on an XGBoost model by utilizing data of a training set and a test set respectively; and finally, achieving accurate classification of the defects of the secondary equipment of the power system by using the trained classification model. Maintenance personnel can be well assisted in maintenance and management of the equipment.