摘要
提出一种新型神经元网络结构及其学习算法。这种改进型神经网络(MNN)由两个子神经网络综合构成:线性神经网络(LNN)和递归神经网络(DRNN)。该MNN网络能用于在线学习对象的动态特性,从而提供一种能提高整个控制系统性能的自适应控制实现策略。仿真结果表明所提出的新型神经元网络是有效的。
In this paper, a novel modified neural network and the corresponding algorithm are presented. The novel modified neural network (MNN) described here is composed of two sub -nets: linear neural net-work(LNN) and diagonal recurrent neural network(DRNN). The MNN can be used for on -line learning of the plant's dynamic characteristics and provide a kind of adaptive control strategy which can improve the whole control system's performance. The simulation results show that the proposed MNN is effective and prospective in practical application.
出处
《控制与决策》
EI
CSCD
北大核心
1997年第A00期467-471,共5页
Control and Decision
关键词
神经元网络
学习算法
直流调速系统
neural network, learning algorithm, DC drive control system
