Skip to Main Content
For the classification and recognition of power quality disturbances, a method based on principle of maximum information entropy is proposed in this paper. The corn of it is that, using S-transform to establish standard mode time-frequency matrix of various disturbances and obtaining information entropy of standard disturbances by probability density distribution of matrix amplitude. The correct classification has been realized by approaching degree of disturbance signal's information entropy with the standard disturbances' entropy. The simulation results show that the approach has better anti interference performance and in the condition of low SNR, classification results are also acceptable.