A Parallel Robust Model Reference Control Method Based on Neural Network

Aiming to the control feature of large ship, a neural network parallel self-learning robust model reference control method of ship course is presented. The problems of model online identification and controller online design in traditional adaptive control is solved by this compounded control structure using the self-learning and nonlinear map capability of neural network, so that the high precision output track control of uncertain nonlinear large ship can be realized. Furthermore, a robust feedback controller is imported to ensure closed-loop stability in the initial learning stages of NN model and improve the NN control´s real-time ability. Simulation results show that the method had perfect control effect.