A novel fuzzy system with dynamic rule base
Document Type
Article
Publication Date
10-1-2005
Publication Title
IEEE Transactions on Fuzzy Systems
Volume
13
Issue
5
First Page
569
Keywords
Function approximation, Fuzzy system, Fuzzy theory
Last Page
582
Abstract
A new fuzzy system containing a dynamic rule base is proposed in this paper. The novelty of the proposed system is in the dynamic nature of its rule base which has a fixed number of rules and allows the fuzzy sets to dynamically change or move with the inputs. The number of the rules in the proposed system can be small, and chosen by the designer. The focus of this article is mainly on the approximation capability of this fuzzy system. The proposed system is capable of approximating any continuous function on an arbitrarily large compact domain. Moreover, it can even approximate any uniformly continuous function on infinite domains. This paper addresses existence conditions, and as well provides constructive sufficient conditions so that the new fuzzy system can approximate any continuous function with bounded partial derivatives. Finally, an example is given to show how the proposed fuzzy system can be effectively used for system modeling and control. © 2005 IEEE.
DOI
10.1109/TFUZZ.2005.856566
ISSN
10636706
Recommended Citation
Chen, Weitian and Saif, Mehrdad. (2005). A novel fuzzy system with dynamic rule base. IEEE Transactions on Fuzzy Systems, 13 (5), 569-582.
https://scholar.uwindsor.ca/electricalengpub/401