DESIGN OF TAKAGI-SUGENO-KANG TYPE INTERVAL TYPE-2 FUZZY LOGIC SYSTEMS BASED ON ENHANCED OPPOSITE DIRECTION SEARCHING ALGORITHMS

摘要

Interval type-2 fuzzy logic systems (IT2 FLSs) have drawn great attention in recent years. Compared with the centroid type-reduction (TR), the center-of-sets (COS) TR is more applicable for applications of IT2 FLSs. The comparison between Karnik-Mendel (KM) algorithms and other types of algorithms for performing the COS TR is still an open question. This paper introduces the blocks fuzzy reasoning, COS TR and defuzzification of IT2 FLSs, and designs a type of Takagi-Sugeno-Kang (TSK) type IT2 FLSs on the basis of enhanced opposite direction searching (EODS) algorithms. Six computer simulation examples are provided to show the performances of EODS algorithms. While computing the output of IT2 FLSs, the EODS algorithms can obtain much faster computational speeds compared with the most popular Karnik-Mendel (KM) algorithms, which may provide the potential value for designing and applying T2 FLSs.