基于参数单点模糊化方法的模糊系统及其逼近能力  

Fuzzy Systems and Their Approximation Capability Based on Parameter Singleton Fuzzifier Methods

作　　者：袁学海[1] 李洪兴[1] 孙凯彪[1] 

机构地区：[1]大连理工大学控制科学与工程学院,辽宁大连116024

出　　处：《电子学报》2011年第10期2372-2377,共6页Acta Electronica Sinica

基　　金：国家自然科学基金(No.90818025;No.61074044)

摘　　要：本文研究了单输入-单输出模糊系统的构造和所构造的模糊系统的逼近能力.首先,在模糊系统的构造中,引入了对输入变量进行参数单点模糊化的方法.应用这种方法,当推理前件和后件都取为具有二相性的三角波时,对六类(41个)模糊蕴涵算子构造的模糊系统进行了研究.其次,对所构造的模糊系统的逼近能力做了研究,给出了它们的余项表达式和余项估计公式.The aim of this paper is to study the construction of fuzzy systems and their approximation capability.Firstly,a new fuzzifier method called parameter singleton fuzzifier is introduced.By the use of the new fuzzifier method,the construction of fuzzy systems based on six classes of fuzzy implication operators is studied when the antecedent part and consequent part of the fuzzy inference are chosen as triangular membership functions with two-phase.Secondly,the approximation capability of the fuzzy systems is discussed and their approximate error formulas and the error estimate formulas are built.

关 键 词：模糊控制 模糊蕴涵算子 模糊系统 泛逼近性 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]