Stability analysis of recurrent type-2 TSK fuzzy systems with nonlinear consequent part. Issue 1 (January 2017)

• Record Type: Journal Article
• Authors: Tavoosi, Jafar; Suratgar, Amir; Menhaj, Mohammad
• Is Part Of: Neural computing & applications. Volume 28:Issue 1(2017)
• Page Start: 47
• Page End: 56
• Publication Date: 2017-01
• Subjects: Recurrent type-2 fuzzy -- Stability analysis -- Nonlinear consequent; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-2036-3
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract A necessary condition for stability of a class of recurrent type-2 TSK fuzzy systems is presented. In this system, the antecedent part is indeed represented by interval Gaussian type-2 fuzzy set, and the consequent part is an ordinary nonlinear function of the system's inputs. In the proposed method, at first a type-2 fuzzy model is established, and then an LMI-based stability analysis of the model is fully discussed. Two first-order systems (one stable and one unstable) and two second-order systems (one stable and one unstable) are then considered as proper case studies. The simulation results easily approve the effectiveness of the proposed method.