A dynamic defuzzification method for interval Type-2 Fuzzy Logic Controllers

Cenk Ulu*, Müjde Güzelkaya, Ibrahim Eksin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

15 Citations (Scopus)

Abstract

In Type-2 Fuzzy Logic Systems (T2FLS), the output of a type-2 fuzzy inference engine needs to be type-reduced in order to obtain crisp output in defuzzification process. The type reduced set is an interval type-1 set determined by the left and right end points. In conventional defuzzification method, the defuzzified crisp output is obtained by averaging these left and right end points of the type reduced set. With this defuzzification method, the capability of the T2FLS cannot be utilized effectively. Type-2 Fuzzy Logic Controllers (T2FLCs) is very effective in various control applications. In this study, a new defuzzification method which uses a linear combination of the left and right end points of the type reduced set is proposed for T2FLCs. This linear combination is formed using the current system error and change of error. In this manner, it has been possible to enhance the performance of the T2FLC. To demonstrate the effectiveness of the proposed defuzzification method, various simulations are presented.

Original languageEnglish
Title of host publication2011 IEEE International Conference on Mechatronics, ICM 2011 - Proceedings
Pages318-323
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 IEEE International Conference on Mechatronics, ICM 2011 - Istanbul, Turkey
Duration: 13 Apr 201115 Apr 2011

Publication series

Name2011 IEEE International Conference on Mechatronics, ICM 2011 - Proceedings

Conference

Conference2011 IEEE International Conference on Mechatronics, ICM 2011
Country/TerritoryTurkey
CityIstanbul
Period13/04/1115/04/11

Keywords

  • Defuzzification
  • Fuzzy Logic Systems
  • Robustness
  • System Dynamics
  • Type-2 Fuzzy Logic Controllers
  • Type-Reduction

Fingerprint

Dive into the research topics of 'A dynamic defuzzification method for interval Type-2 Fuzzy Logic Controllers'. Together they form a unique fingerprint.

Cite this