Power system fault detection classification based on PCA and PNN

This paper presents a new approach for power system fault classification based on principal component analysis (PCA) and probabilistic neural network (PNN).the work presented in this paper is focused on identification of simple power system faults. The new model mainly includes three steps. Firstly wavelet transform is used to analyze power system fault signals, and distinguishing features are extracted from the result of wavelet transform. Secondly, principal-component analysis (PCA) is used to reduce the dimensionality of data set, mean while extract principal-components to describe nonstationary signals of the power system. Finally, use the principal-components as the input vectors of probabilistic neural network and classify the power system faults. The simulation results show the validity and efficiency of the proposed model.