Skip to Main Content
In order to solve the detection and classification of power quality disturbances, a new approach combining S-transform and decision tree is proposed. First, some disturbances are decomposed through S-transform time-frequency analysis, three feature functions are defined, then feature components are extracted, and decision rules are found, finally the decision tree approach for disturbances classification is presented. The simulation results show that the method could detect and classify the power quality disturbances effectively and has high classification correct ratio even though in noise condition. The reasons are also analyzed in this paper.