ive of

Abstract—A novel method for ferroresonance detection is presented in this paper. Using this method ferroresonance can be discriminate from other transients such as capacitor switching, load switching, transformer switching. Wavelet transform is used for decomposition of signals and Multi Layer Perceptron (MLP) neural network used for classification. Ferroresonance data and other transients are obtained by simulation using EMTP program. Results show that the MLPNN trained with the Levenberg–Marquardt algorithm is effective for discriminating Ferroresonance from other transients. Index Terms—MLP neural network, ferroresonance, EMTP program, wavelet transform, Levenberg–Marquardt algorithm. I