摘要
为了实现快速控制,用两层线性神经网络构造预测器,估计未来p步的输出值,用两层非线性神经网络组成控制器,实现对下一步控制的优化.仿真结果显示:该方法是可行的,且具有结构简单、运算量小、速度快的特点.
In order to realize fast control, a predictor is constructed using two layers of linear neural networks to predict the future p step output, and a controller is composed using two layers of nonlinear neural network to optimize the next control volume. The simulation results show that this method is feasible, and it is characterized by its simple structure, small calculating amount and fast speed.
出处
《华南理工大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2000年第2期87-92,共6页
Journal of South China University of Technology(Natural Science Edition)
关键词
神经网络
单值预测控制
连接权系数
predictive neural network
control neural network
single predictive control
connecting weight coefficients
