A Decision Tree and S-Transform Based Approach for Power Quality Disturbances Classification

Abstract

In this paper, it is presented an automated classification based on S-transform as feature extraction tool and Decision Tree as algorithm classifier. The signals generated according to mathematical models, including complex disturbances, have been used to design and test this approach, where noise is added to the signals from 40dB to 20dB. Finally, several disturbances, simple and complex, have been considered to test the implemented system. Evaluation results verifying the accuracy of the proposed method are presented.