Principal component analysis and identification of power quality disturbance signal phase space reconstructed images

This paper investigates a combination of phase space reconstruction and principal component analysis (PCA) methods for classifying six types of power quality disturbances: voltage sag, voltage swell, voltage spikes, voltage interruption, harmonics and fluctuation signals. Phase space reconstruction method is introduced to construct the disturbance signal, and translate them into images. From the perspective of image processing, the principle of PCA in the face and fingerprint image recognition applications is used to extract features of different quality disturbance phase space reconstruction trajectories, and the corresponding power quality disturbance signals are classified. This method can avoid obtaining the difficulties of stable feature extraction which results of the complexity of the disturbance signal, and the training time is short, less training samples is needed to identify, the process results can be visualized to facilitate the analysis and so on. Simulation results show that it can better identify the power quality disturbance. It is a novel disturbance signal detection and classification methods.