摘要
本文介绍通过利用神经网络计算算法怎样将神经网络两个重要的计算特点用于自适应控制。以单自由度机械手为例,对神经形态控制方法和模型参考自适应控制方法进行比较,对很大规模的系统,利用神经网络作为自适应控制提供定速,比传统的方法优越。
This paper presents how two important computional features of neural networks can be used for adaptive control through the use of neural network computional algorithms.The neuromorphic control approach is compared to model reference adaptive control on a specific example, e. g. a single-degree-of-freedom manipulator.The utilization of neural networks foradaptive control offers definite speed advantages over traditional approaches for very large scale systems.
出处
《控制与决策》
EI
CSCD
北大核心
1991年第6期418-422,共5页
Control and Decision
