Research on identification algorithm of voltage sag type based on Adaboost-BP

Accurate identification of sag type is the basis of effective governance sag problem. This paper proposes a method for identifying voltage sag types based on Adaboost-BP. The Adaboost-BP classification model is a weighted combination of multiple weak classifiers to classify three types of sags: short circuit, induction motor starting, and transformer switching. Combined with the judgment result of the number of sag phases, the identification of the final sag type is realized. The results of the calculation examples show that the algorithm proposed in this paper can achieve more than 90% accuracy for each type of sag, and its performance is superior to the existing algorithms.