Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
402572 | Knowledge-Based Systems | 2010 | 8 Pages |
A novel neural fuzzy (NF) mapping framework is developed in this paper to convert linear systems and a class of nonlinear systems from the crisp-domain to a NF representation. The resulting neural fuzzy system (NFS) is guaranteed to be functionally identical to the original system. Therefore, the proposed mapping technique provides a well-defined prototype for one type of NFS design. The resulting fuzzy reasoning representation facilitates the investigation in linguistic terms into the system operations, whereas the system performance can be further improved by properly incorporating expertise knowledge or by online/offline training via this NF structure. The developed technique is to extend our previously-developed techniques to NF modeling/mapping applications and its effectiveness is demonstrated by simulations using a flexible-link robot.