摘要
针对一类具有特殊模型的非线性系统本文提出了一种新型神经网络预测控制算法。该算法利用线性系统预测控制技术和神经网络的非线性映射及并行处理能力来求实际控制量 ,避免了解非线性方程和非线性预测控制所需的在线数值寻优计算 ,减少了计算量和计算时间。
A novel neural network predictive control algorithm is proposed for a class of nonlinear system with special model.In the method the control variable is obtained by employing the results of linear predictive control and the abilities of nonlinear projection and parallel processing of neural network.The algorithm doesn't need solve nonlinear equation and on_line numerical optimizing in general nonlinear predictive control,which greatly decreases computing consumption.The validity of the proposed algorithm is demonstrated by the simulation results.
出处
《自动化技术与应用》
2003年第4期5-7,共3页
Techniques of Automation and Applications
基金
国家高技术研究发展计划 (863计划 )经费资助
课题编号 :2 0 0 1AA41 31 1 0
