Transient power quality disturbance identification method based on SSAE and SDP transform

To solve the power supply quality problem caused by transient power quality disturbance, how to identify various power quality disturbances efficiently and accurately has become an urgent problem. In this paper, a transient power quality disturbance identification method based on stacked sparse auto-encoder and symmetrized dot pattern is proposed. In this method, the original time-frequency disturbance signal is transformed into polar coordinate domain through symmetric point mode, and the visualization of disturbance signal is realized and the corresponding disturbance map is generated; then, various disturbance maps are input into stacked sparse auto-encoder for identification and classification; finally, it is compared with common transient power quality disturbance identification methods. The results show that: the proposed transient power quality disturbance identification method based on stacked sparse auto-encoder and symmetrized dot pattern can identify and classify the transient disturbance efficiently and accurately; at the same time, the framework of the proposed method is clear and has good convergence and generalization ability, which is suiTable for the fast and accurate identification of power system power quality transient disturbance.