文献类型：期刊文献

中文题名：应用聚类和模糊神经网络方法设计模糊规则库

英文题名：Clustering and fuzzy neural network for fuzzy rule sets modeling

作者：王秀娟[1];侍洪波[1]

机构：[1]华东理工大学工程自动化研究中心,上海200237

年份：2003

卷号：34

期号：4

起止页码：360

中文期刊名：中南工业大学学报

外文期刊名：Journal of Central South University of Technology(Natural Science)

收录：北大核心:【北大核心2000】；CSCD:【CSCD2011_2012】；

语种：中文

中文关键词：聚类;模糊神经网络;模糊规则库

外文关键词：clustering; fuzzy neural network; fuzzy rule sets

摘要：基于聚类技术和模糊神经网络提出一种新的自动生成模糊系统规则库的设计方法.采用结构辨识和参数辨识相结合的方法,构造模糊系统完善的模糊规则库.用此设计方法对函数逼近问题进行仿真,结果表明该方法具有规则数目少、学习速度快、建模精度高等特点.
Based on the clustering arithmetic and fuzzy neural network, a new approach, which is composed of structure identification and parameter identification, is proposed for designing the fuzzy system. In the process of structure identification, a clustering method is used to extract the number of fuzzy rules; in the process of parameter identification, the RBF network is used to obtain more precise parameter of the fuzzy system. Stimulated results of function approximation problems show that the proposed method can provide optimal model structure and parameters for fuzzy modeling and possesses high learning efficiency.