Detection of power quality disturbances using wavelet transform and artificial neural network

Detection of Power Quality (PQ) is an essential service which many utilities perform for their industrial and large commercial customers. Poor PQ affect the load connected to the supply. It shortens the life of load and can damage the load. It is a difficult task to detect and classify electrical problems which can cause PQ problems. Various types of PQ disturbances are defined in IEEE standards 1159-2009 in terms of their frequency, magnitude and duration. In this paper, a new approach has been shown to detect, localize, and investigate the feasibility of classifying various types of power quality disturbances. Voltage sag, swell, transient and harmonics are the main PQ problems shown in the paper. The approach is based on wavelet transform analysis, particularly the discrete wavelet transform. The key idea is to decompose a given disturbance signal using DWT which represent a smoothed version and a detailed version of the original signal. These decomposed signals are used to extract features using many mathematical operations like peak, variance, mean deviation and skewness. These features are used as classifier which is fed to ANN to classify the PQ disturbances.