一种基于模糊聚类的模糊辨识方法  

A FUZZY IDENTIFICATION METHOD BASED ON FUZZY CLUSTERING

作　　者：张椿玲[1] 黄景廉[1] 曾贤强[1] 

机构地区：[1]西北民族大学电气工程学院,甘肃兰州730030

出　　处：《计算机应用与软件》2012年第2期216-217,253,共3页Computer Applications and Software

摘　　要：介绍一种基于模糊聚类的模糊辨识方法。首先利用含有聚类准则函数的模糊聚类方法来确定模糊规则数和模型前提参数,然后利用最小二乘法来辨识模型的结论参数,最后采用梯度下降法来调整模型的参数。该方法应用于Box-Jenkins数据仿真实例,仿真结果表明该方法简单有效。This paper introduces a method of fuzzy identification based on fuzzy clustering.In the method,a fuzzy clustering technique associated with clustering criterion function is used to determine the number of fuzzy rules and the parameters in antecedent part of the model first,and then the parameters in consequent part of the model are identified by means of least square algorithm,at last the gradient descent algorithm is used to adjust the parameters of fuzzy model.This method has been successfully applied to identifying the simulation instance of Box-Jenkins data set,and the results demonstrate its simplicity and effectiveness.

关 键 词：模糊模型辨识 模糊聚类 最小二乘估计 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]