A Modified Neural-Network based Predictive Control for Nonlinear Systems

摘要：

In this paper an improved neural-network (NN) based predictive control strategy for nonlinear systems is presented.Two nonlinear systems are considered,and each of them is estimated by a neural network.Control signals are generated by minimizing an objective function which considers both the cumulative differences between a setpoint and the output of the neuro model and the control signal changes.The standard backpropagation (BP) algorithm is used to train the weights of the neural network (NN).Moreover,simulation results on two typical nonlinear plants are given to illustrate the effectiveness of the proposed control strategy.

关键词： neural- network (NN) nonlinear systems backpropagation (BP) algorithm predictive control.

作者: Qinglin Sun Na Dong Zengqiang Chen Zhuzhi Yuan

作者单位: Department of Automation,Nankai Unversity,Tianjin,China

会议类型: 国际会议

会议名称: International Conference on Modelling,Identification and Control(模拟、鉴定、控制国际会议)

会议地点: 上海

会议语种:英文

在线出版日期: 2008-06-29（万方平台首次上网日期，不代表论文的发表时间）