In order to better explore the convenience and efficiency of effectiveness evaluation method, the effectiveness evaluation method of neural network is used to evaluate the combat effectiveness of fighter in over-the-horizon air combat. The actual training results are used to make sample set labels to fully tap the law of the data itself. Aiming at the problems of slow convergence speed and gradient explosion of BP neural network, the method of deep belief network (DBN) is used to evaluate the combat effectiveness of fighter aircraft. The results show that the method can greatly avoid the subjective error, and the evaluation results verified the effectiveness and accuracy of the DBN model.