A Real-Time Power Quality Disturbances Classification Using Hybrid Method Based on S-Transform and Dynamics

摘要: This paper proposes a real-time power quality disturbances (PQDs) classification by using hybrid method (HM) based on S-transform (ST) and dynamics (Dyn). Classification accuracy run time are mainly considered in our work. The HM firstly uses Dyn to identify the location of signal components frequency spectrum yielded Fourier transform, inverse transform only some components. Then features from ST, selected, decision tree is used classify types PQD. In order reduce influence Heisenberg' s uncertainty, we proposed that different windowed Gaussian windows, which brings better adaption flexibility. By HM, application has been greatly reduced with satisfactory accuracy. Finally, DSP-FPGA hardware platform adopted test correctness under real standard signals. Field tests have also presented. Both simulations experiments validate feasibility new method.