Nonlinear control of benchmark problems using TSK-type fuzzy neural network

Ching Hung Lee*, Wei Yu Lai

*Corresponding author for this work

Research output: Contribution to journalArticle

4 Scopus citations

Abstract

This paper proposes a TSK-type fuzzy neural network system (TFNN) for identifying and controlling nonlinear control benchmark problem system. It is available for nonlinear dynamic system with uncertainties. The TFNN system can construct and learn its knowledge base from the input-output training data firstly. Thus, a nonlinear system can be represented by several if-then rules with Gaussian membership functions and TSK-type consequent parts. Based on the learned TFNN system, a robust fuzzy controller is proposed, which combines linear matrix inequality-based fuzzy controller and fuzzy sliding model controller. Rigorous proof of asymptotic stability for the closed-loop system is presented via Lyapunov stability theorem. Several examples are presented to illustrate the effectiveness of our approach.

Original languageEnglish
Pages (from-to)83-94
Number of pages12
JournalNeural Computing and Applications
Volume23
Issue numberSUPPL1
DOIs
StatePublished - 2013

Keywords

  • Back-propagation algorithm
  • Fuzzy neural network
  • Nonlinear control
  • TSK-type fuzzy systems

Fingerprint Dive into the research topics of 'Nonlinear control of benchmark problems using TSK-type fuzzy neural network'. Together they form a unique fingerprint.

  • Cite this