AUTOMATED CLASSIFICATION OF POWER QUALITY DISTURBANCES USING SIGNAL PROCESSING TECHNIQUES AND NEURAL NETWORKS

摘要: OF THESIS AUTOMATED CLASSIFICATION POWER QUALITY DISTURBANCES USING SIGNAL PROCESSING TECHNIQUES AND NEURAL NETWORKS This thesis focuses on simulating, detecting, localizing and classifying the power quality disturbances using advanced signal processing techniques neural networks. Primarily discrete wavelet Fourier transforms are used for feature extraction, classification is achieved by network algorithms. The proposed vector consists of a combination features computed multi resolution analysis transform. vectors exploit benefits having both time frequency domain information simultaneously. Two different algorithms based Feed forward adaptive resonance theory networks classification. demonstrates that methodology achieves good computational error efficiency rate.