Recurrent-fuzzy-neural system-based adaptive controller for nonlinear uncertain systems

Tzu Wei Hu, Ching Hung Lee

Research output: Contribution to journalConference articlepeer-review

Abstract

This paper aims to treat the adaptive control of nonlinear system with un-model uncertainty and bounded disturbance by using a novel recurrent fuzzy neural system. The used recurrent interval type-2 fuzzy neural network with asymmetric membership functions (RT2FNN-A) combines the interval asymmetric type-2 fuzzy sets and fuzzy logic system and implements in a five-layer neural network structure which contains four layer forward network and a feedback layer. The RT2FNN-A is modified to provide memory elements for capturing the system's dynamic information and has the properties of high approximation accuracy and small network structure (fewer rules and tuning parameters) from the simulation results. Based on the Lyapunov theorem, adaptive updat laws of RT2FNN-A derived and the stability of closed-loop system is guaranteed for control of the nonlinear uncertain systems. Simulation result is also introduced to show the performance and effectiveness of RT2FNN-A system.

Original languageEnglish
Pages (from-to)7-12
Number of pages6
JournalLecture Notes in Engineering and Computer Science
Volume2209
Issue numberJanuary
StatePublished - 2014
EventInternational MultiConference of Engineers and Computer Scientists, IMECS 2014 - Kowloon, Hong Kong
Duration: 12 Mar 201414 Mar 2014

Keywords

  • Interval type-2 fuzzy system
  • Nonlinear control
  • Recurrent
  • Uncertainty

Fingerprint Dive into the research topics of 'Recurrent-fuzzy-neural system-based adaptive controller for nonlinear uncertain systems'. Together they form a unique fingerprint.

Cite this