Research of Model Reference Attack Angle Control Based on BP Natural Network

摘要

In this paper, the well-known design framework of model reference adaptive control is adopted to construct the adaptive attack angle controller of aircraft, where all the parameters of PID controller are adjusted by BP neural network. By using the reference model output and the actual object output as training signals, all the weights of the three-layer BP neural network are updated. The simulation results present that, the parameters of the PID controller can be adjusted autonomously by applying the BP neural network to the attack angle control system of the aircraft, which shows the excellent approximation property of the BP neural network. At the same time, the control scheme improves the performance indices of the aircraft attitude control system and also enhances the intelligent level of engineering design.