摘要
本文对具有时滞的不确定性控制对象提出了一种神经网络时滞补偿模糊自学习控制方法．模糊控制器采用误差、误差变化及误差加速度的加权和的解析描述形式，利用人工神经网络直接对过程建模，实现对时滞补偿预报以及对模糊加权因子的自学习优化调整．将上述方法用于焊接熔池动态过程控制试验，结果表明本文提出的自学习神经网络时滞补偿模糊控制方案有效．
A self-learning neural network time lag compensation and fuzzy control approach to the controlled uncertain objects with time lag is presented in this paper. Using artificial neural networks for modelling the objects,the fuzzy controllor described in the analysis formula with control error,error change and error accelation is real-timely regulated by self-learning weight factors and the time lag compensation and prediction of the systems is realized. The results of experiment on the dynamic Process of weld pool in the pulse TIG welding show that the self-learning neural network time lag compensation and fuzzy control scheme presented in this paper is effective.
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
1996年第3期347-355,共9页
Control Theory & Applications
基金
国家自然科学基金
关键词
神经网络
模糊控制
不确定系统
数学模型
Uncertain objects
time lag compensation
neural networks
self-learning fuzzy control
