Power Quality monitoring using wavelet transform and Artificial Neural Networks

With an increasing usage of sensitive electronic equipments, power quality has become a major concern now. One critical aspect of power quality studies is the ability to perform automatic power quality data analysis and categorization. This paper presents an approach that is able to provide the detection and time location as well as the identification of power quality problems. The method is developed by using the discrete wavelet transform (DWT) analysis. The given signal is decomposed through wavelet transform. Later, using the wavelet coefficients, feature extraction is done and an artificial neural network is developed to classify the power quality disturbances. The training and testing data required to develop the ANN model is generated through simulation. In this paper, it is demonstrated that each power quality disturbance has unique deviations from the pure sinusoidal waveform and this is adopted to provide a reliable classification of the type of disturbance.