摘要
提出一种新的神经网络枛类模糊神经网络,并以基于多项式系的类模糊神经网络为例作了 讨论。该网络具有隐层少,运算简单和函数逼近能力强的特点。就一类非线性系统的在线控制,给出了类模糊神经网络控制的选择记忆算法,并证明了这种算法的收敛性,使一类非线性系统的在线控制问题得以初步解决。
A new neural networkquasi-fuzzy neural network is proposed and discussion is carried out with the quasi-fuzzy neural network based on polynomial series as an example. The network has the advantages of less hidden layers, simple operation and powerful function approximation capacity. The memory-selected algorithm for quasi-fuzzy neural network is given so far as the on-line control of the nonlinear system. The convergence of the algorithm is demonstrated and thus the on-line control problem for the nonlinear system has been initially solved.
出处
《光电工程》
CAS
CSCD
北大核心
2002年第5期1-4,11,共5页
Opto-Electronic Engineering
基金
国家863高技术项目资助
