The Research For Non-minimum Phase Control System Based On Neural Network

In the control engineering, the non-minimum phase system is very common and more restive, for non-minimum phase system with overshoot and undershoot phenomena often occur because of the right-half plane zeros and poles. It is a difficult task to eliminate the phenomena by using traditional linear control techniques. How to bring advantages of neural network control strategy into full play and to improve the performance is focused in this paper. Firstly, the application of non-minimum phase control system based on GA-BP neural network and RBF neural network are discussed in detail. Secondly, the application of multi-variable control system based on neural network, it prepared for the research of multi-variable non-minimum phase control system based on neural network. The simulation results show that the designed system can get better control results, can eliminate undershoot and reduce overshoot, and make system effective in robustness and anti-jamming, meanwhile prove the superiority of this controller to the PID controller.