Abstract: In this study,a method of sensor status self-confirmation is proposed,taking the wind turbine airborne anemometer as an example. A group of wind turbines is selected by a dynamic time warping algorithm,following the correlation of wind speed of multiple wind turbines. The prediction model of the wind turbine group anemometer based on an auto-association neural network is constructed.The model is trained by the sparrow search optimization algorithm with normal historical data,and the state of the anemometer is determined according to the relationship between the actual value and the predicted value. The simulation experiment proves that the method can identify the abnormal state of anemometer simulation. Finally,the actual wind speed of the wind farm is detected. The results show that this method can reliably identify the state of the anemometer and acquire the self-confirmation of the state of the anemometer of the wind turbine.