Hybrid wind power plant fault characteristic grouping method based on BP neural network

The invention discloses a hybrid wind power plant grouping method based on a BP neural network. The method comprises the following steps: firstly, defining factors influencing the short-circuit current difference change of different types of generator groups in a wind power plant, characterizing a control protection sequential switching mode of the doubly-fed and permanent magnet direct-driven wind generator group from a mathematical perspective, and providing a classification method considering the control protection sequential switching mode; performing normalization processing on the type identification S of n units in the hybrid wind power plant, the input wind speed v and the terminal voltage drop degree gamma of each unit during fault, and training the BP neural network; inputting the feature vectors of the parameters of each unit into the trained BP neural network, and dividing the units in the same mode into units in the same group according to the recognition result of the unit group mode in the wind