Abstract: With the popularization of intelligent substation, the safe operation of power system puts forward higher requirements for the secondary maintenance of substation. In order to solve the problem of misoperation in the process of state transition of secondary equipment, a new anti-misoperation method of secondary system is proposed. First and second equipment status values are obtained through the measuring device to construct the initial sample data set. In order to obtain the required feature vector set of the model, PCA method is adopted to achieve data dimensionality reduction, and the feature vector set is classified by decision tree for secondary operations. SVM training and testing are carried out on the classified sample set to realize the misjudgment prevention of secondary equipment operation. Finally, an anti-error model is constructed, and the simulation test is carried out with the historical operating data to verify the effectiveness of the proposed method.