DefinePK

Abstract

This paper aims to develop a new technique for the classification of various power quality disturbances using Kalman filter and Multi-layer perceptron (MLP) neural network. Kalman filter is adopted to extract the three types of input features (standard deviation, peak value and variances) from the power quality disturbance waveforms simulated on a Matlab test system. The extracted features are given as inputs to the neural network. MLP based neural network has been used for disturbance classification and the neural network has been trained using 1800 number of test data at the rate of 200 samples for each class of disturbance. The algorithm has been tested with 1800 number of test data and the outcomes are recorded.