Classification of Power Quality Disturbance Using Segmented and Modified S-Transform and DCNN-MSVM Hybrid Model

In this paper, a novel approach to classify the signals of power quality (PQ) disturbance is proposed based on segmented and modified S-transform (SMST), deep convolutional neural network (DCNN), multiclass support vector machine (MSVM). The idea frequency segmentation with different adjustable parameters was used in Gaussian window function. accurate time-frequency localization efficient feature extraction PQ disturbances then could be achieved. Firstly, SMST analyze obtained two-dimensional (2D) contour maps high resolution. Then, DCNN employed automatically extract features from 2D maps. Finally, MSVM classifier developed for classification single complex disturbance. order demonstrate effectiveness robustness model, eight thirteen waveforms were considered without noise level, respectively. Extensive simulations performed compared other existing methods. simulation results show that method has better performance than several state-of-the-art algorithms classifying under level.