Classification and Recognition of Ferroresonance Based on Improved Elman-Adaboost

Abstract

Abstract Aiming at the problem that the fault suppression effect is not obvious due to the unclear type of ferroresonance, an improved Elman-Adaboost method for classification and identification of ferroresonance was proposed. Firstly, the characteristic values of different types of ferroresonance overvoltage were extracted, and then a classifier was added to the traditional Elman-Adaboost model to automatically find the optimal hidden layer, and the corresponding weighted parameters were added and adjusted when the training set was recognized correctly. Finally, by constructing a two-stage improved Elman-Adaboost model to test different types of ferroresonance samples and comparing with other methods, the accuracy of the proposed method is verified. The results show that the proposed method can effectively identify the type of ferroresonance in power systems, and the identification accuracy is greatly improved. It has potential application value in the identification and suppression of ferroresonance faults.