Abstract:Accurate determination of the severity of secondary equipment defects in power grid can provide an important basis for the operation and maintenance of equipment.Therefore,in this paper,to address problems such as large quantity of defective data features,and the great difficulty of using error-prone human judgment as an evaluation parameter,a defect classification method based on XGBoost (eXtreme Gradient Boosting) is proposed to improve the accuracy of defect classification of secondary equipment.First,a series of pre-processing work,such as removing outliers and coding,is performed on the secondary equipment historical defect data,and the characteristics highly correlated with equipment defects are extracted to establish the feature index set.Subsequently,the XGBoost model is trained and optimized using historical defect data.Finally,the trained classification model is used to realize the accurate classification of secondary equipment defects.Based on the secondary equipment defective data of a power plant,simulation results are presented to illustrate the effectiveness of the proposed algorithm and are compared with those of traditional classifiers (decision tree,logistic regression,etc.).Simulation results show that XGBoost can accurately determine the defect degree of secondary equipment,to assist the maintenance and management of equipment.