桑宝旭,帕孜来.马合木提.基于小波包能量熵和BP神经网络的孤岛检测法[J].电测与仪表,2022,59(2):63-67. Sang Baoxu,Pazilai Mahemuti.Island detection based on wavelet packet energy entropy and BP neural network[J].Electrical Measurement & Instrumentation,2022,59(2):63-67.
基于小波包能量熵和BP神经网络的孤岛检测法
Island detection based on wavelet packet energy entropy and BP neural network
Unplanned island detection will cause serious impact on the power grid and personal injury, finishing the island detection must be accurate and rapid. Aiming at the current island detection technology based on signal processing, this paper come out with the new island detection method with wavelet packet energy entropy and BP neural network. The reconstructed sequences are got by wavelet packet transform reconstructed common point voltages and the output current of an inverter, then make entropy operation on the sequences, which can get a more stable and representative eigenvector.In this way, we can distinguish the energy distribution before and after island occurrence more effectively.Finally, Use the BP neural network to judge the island for realizing the island detection. In addition, the MATLAB/Simulink simulation shows that the method is effective,stable and fast,and there is no need to introduce disturbances so will cause no influence on the power quality and will narrow the non-detection zone as well.