A Two-Stage Artificial Neural Network Classifier to Discriminate Three-Phase Unbalanced Voltage Sag Types.

This paper presents an efficient two-stage classifier based on artificial neural network (ANN) concept to discriminate different types of three-phase unbalanced voltage sags at the location of power quality monitoring. In the first stage, the general type of unbalanced voltage sag (C and D) in terms of number of phases undergoing voltage drop is detected. In the next stage, the symmetrical phase is identified. Different classification approaches such as six-phase (SP), symmetrical components (SC) and three-phase three-angle (TPTA) algorithms have been previously developed to characterize and discriminate six types of unbalanced voltage sags, but they are not fully reliable because of possible incorrect results reported. The proposed classifier is widely tested and compared with three aforementioned algorithms to validate its reliability and efficiency. It is concluded that the learning intelligence of the proposed classifier is its strong point to be superior to those classifiers exclusively employing mathematical operations. [ABSTRACT FROM AUTHOR]