Fault prediction system of airplane steer surface based on neural network model

In the airplane steering surface fault diagnosis system, timely and accurate forecast of failure is of great significance to improve the safety of the airplane. According to the design requirements of the airplane steering surface fault forecast system, the neural network fault forecast model and training algorithm were established. The three-tier model BP network model was applied in the fault forecast model. The evaluation function of the forecast accuracy was proposed. Finally, in order to validate the effectiveness of the method described, combining with the wind tunnel test data, forecast and analysis upon a kind of airplane steering surface failure mode of rudder block were done. Compared to the traditional method of ARMA, the result shows that the neural network model is of effectiveness and superiority.