An Adaptive Learning Method for the Generation of Fuzzy Inference System from Data  

作　　者：ZHANG Li-Quan SHAO Cheng 

机构地区：[1]Institute of Advanced Control Technology, Dalian University of Technology, Dalian 116024, P.R. China [2]College of Electric and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, P.R. China

出　　处：《自动化学报》2008年第1期80-87,共8页Acta Automatica Sinica

基　　金：Supported by National Basic Research Program of China(973 Program)(2007CB714006)

摘　　要：Designing a fuzzy inference system(FIS)from data can be divided into two main phases:structure identification and parameter optimization.First,starting from a simple initial topology,the membership functions and system rules are defined as specific structures.Second,to speed up the convergence of the learning algorithm and lighten the oscillation,an improved descent method for FIS generation is developed.Furthermore, the convergence and the oscillation of the algorithm are system- atically analyzed.Third,using the information obtained from the previous phase,it can be decided in which region of the in- put space the density of fuzzy rules should be enhanced and for which variable the number of fuzzy sets that used to partition the domain must be increased.Consequently,this produces a new and more appropriate structure.Finally,the proposed method is applied to the problem of nonlinear function approximation.Designing a fuzzy inference system （FIS） from data can be divided into two main phases： structure identification and parameter optimization. First, starting from a simple initial topology, the membership functions and system rules are defined as specific structures. Second, to speed up the convergence of the learning algorithm and lighten the oscillation, an improved descent method for FIS generation is developed. Furthermore, the convergence and the oscillation of the algorithm are systematically analyzed. Third, using the information obtained from the previous phase, it can be decided in which region of the input space the density of fuzzy rules should be enhanced and for which variable the number of fuzzy sets that used to partition the domain must be increased. Consequently, this produces a new and more appropriate structure. Finally, the proposed method is applied to the problem of nonlinear function approximation.

关 键 词：自适应学习 模糊推论系统 数据处理 非线性函数逼近 梯度演化 信度 

分 类 号：TP273.22[自动化与计算机技术—检测技术与自动化装置]