Fuzzy recognition system for power quality events using spline wavelet

In this paper we present a new approach to detect, localize and classify the power quality events. It is a two-stage method in which a spline wavelet transform is used to generate a set of optimal feature vector in the first stage. In second stage, a fuzzy logic-based pattern recognition system is used to classify the various disturbance wave form generated due to power quality violations. The disturbance frequency components are accurately extracted by using spline wavelet. Using this feature power frequency and low frequency disturbances are accurately classified. The instant of occurrence and duration of the power disturbance events are also calculated using spline wavelet.