Design of Smart Control System of Wing Anti-icing

Abstract

A self-adaptive neural network-based control method in aircraft anti-ice systems is introduced. To get better accuracy and stability in wing anti-ice system control, a self-adaptive PID control is applied to drive the heater groups distributed around the wing and powered by remote power distribution units. Unlike the traditional system, the type of heater command is substituted from constant frequency to vary the frequency, and the control signals are given by PID controller whose three parameters propagation, integral and derivative, are given by backpropagation neural networks. Furthermore, in the tuning process, the plant’s predictive output is used to modify the weights of neural networks. The plant’s output will also be predicted by BP neural networks, and it is a nonlinear prediction that improves the predictive accuracy. The implementation and simulation program was written by MATLAB/Simulink.