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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.