针对一类不确定离散非线性系统, 提出了一种神经网络预测控制算法. 考虑系统中的不确定项, 建立神经网络辨识模型作为预测模型. 为减少重构误差 对系统的影响使用了反馈校正技术. 为提高控制性能引入了一种动态补偿器来镇 定跟踪误差系统. 所提出的控制算法保证了闭环系统的所有信号都是有界的. 最后, 针对AUV中的路径跟踪问题对所提出的控制算法进行仿真应用, 仿真结果说明了算法的有效性.

A neural-network predictive control algorithm is proposed for a class of uncertain discrete-time nonlinear systems. Considering the uncertainties in the system, the prediction model is the identification model of the neural network. The feedback correction is used to reduce the influence of reconstruction error of the system. In order to improve the control performance, a dynamic compensator to stabilize the tracking error system is introduced. The proposed control algorithm guarantees the boundedness of all the closed loop signals. Finally, an example of tracking problem for an automatical underwater vehicle (AUV) is given to show the effectiveness of the proposed control algorithm.