基于矩阵QR分解的模糊模型结构分析与简化  

Analysis and Simplification for Fuzzy Model Structure Based on Matrix QR Decomposition

作　　者：刘士荣[1] 俞金寿[2] 

机构地区：[1]宁波大学自动化与计算机技术系,315211 [2]华东理工大学

出　　处：《控制与决策》1999年第A11期589-592,共4页Control and Decision

基　　金：国家自然科学基金;工业控制技术国家重点实验室开放课题基金

摘　　要：研究用矩阵ＱＲ分解分析一类模糊模型的结构，用模糊统计信息判据指导规则的精简，用Ｒ矩阵的主对角线元素分布与模糊规则的关系确定重要规则、冗余或不重要规则，实现模糊模型结构优化。该方法已成功地应用于Ｍａｃｋｅｙ－Analyzing model structure for a class of fuzzy models with matrix QR decomposition and guiding fuzzy rule simplification using fuzzy statistical information criteria are presented. According to the relation between the fuzzy rules and the value distribution of the primary diagonal elements in the matrix R, the more important rules and unimportant or redundant rules in the model can be determined respectively, and then an optimal fuzzy model can be constructed. The method has been applied successfully in Mackey-Glass chaotic system modeling.

关 键 词：模糊模型 QR分解 矩阵 结构分析 系统辨识 

分 类 号：O235[理学—运筹学与控制论]