Automatic Classification of Power Quality disturbances Using S-transform and MLP neural network

The paper presents an S-Transform based multilayer perceptron neural network (MLP) classifier for the identification of power quality (PQ) disturbances.The proposed method is used to extract the three input features (Standard deviation, peak value and variances) from the distorted voltage waveforms simulated using parametric equations. The features extracted through S-transform are trained by a MLP neural network for the automatic classification of PQ disturbances. MLP neural classifier has been implemented and tested for nine types of power quality disturbances. The results clearly show that the proposed method has the ability to identify and characterize PQ disturbances. The performance of the proposed technique is compared with the kalman based MLP neural network.