不确定对象的自学习模糊神经网络控制方法  

A Self learning Fuzzy Neural Network Control of Uncertain Objects

作　　者：陈善本[1] 吴林[1] 李友善[2] 

机构地区：[1]哈尔滨工业大学材料学院 [2]河北机电学院自动化系

出　　处：《模糊系统与数学》1997年第2期63-69,共7页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金

摘　　要：本文对具有不确定性控制对象提出了一种自学习模糊神经网络控制方法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的建模，实现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实验。A self learning fuzzy neural network control approach to the controlled objects with uncertainties 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.The results of experiment and simulation on the dynamic process of welding current top bead width in the pulse TIG welding show that the self learning fuzy neural network control scheme presented in this paper is effective.

关 键 词：不确定对象 自学习神经网络 模糊控制 鲁棒控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]