Target recognition is an important link in the chain of information processing for air -defense. Yet ,there is not any ripe theory for air target type recognition. On the foundation of BP a1gorithm , a target recognition method based on neural network is applied to the specific major air - raid aircraft type. Following that the model is simu1ated by the tools of neural network provided by MATLAB. The result of simulation implies that the method is reasonable and workable. And the method presents a great significence in improving the accuracy in the information processing.