Pushpa Publishing House

Journal Menu

Content

Volume 4 (2009)

Volume 3 (2009)

Volume 2 (2008)

Volume 1 (2008)

	Volume 1, Issue 2 Pg 87 - 178 (May 2008)
	Volume 1, Issue 1 Pg 1 - 86 (February 2008)

Far East Journal of Experimental and Theoretical Artificial Intelligence

Far East Journal of Experimental and Theoretical Artificial Intelligence
Volume 1, Issue 1, Pages 5 - 22 (February 2008)

RECURRENT FUZZY NEURAL CONTROLLER DESIGN FOR NONLINEAR SYSTEMS USING ELECTROMAGNETISM-LIKE ALGORITHM
Ching-Hung Lee (Taiwan) and Fu-Kai Chang (Taiwan)

Abstract:
This paper presents a recurrent fuzzy neural network (RFNN) controller design for nonlinear systems using electromagnetism-like (EM) algorithm, called RFNN-EM. EM algorithm is a population-based meta-heuristic originated from the electromagnetism theory in physics. RFNN-EM system simulates the attraction and repulsion of charged particles by considering each RFNN parameter vector as an electrical charge. It consists of initialization, local search, total force calculation, and movement. RFNN-EM is used to develop the direct adaptive control scheme (on-line) and direct inverse control scheme (off-line) for nonlinear systems. RFNN-EM has advantages of multiple search, global optimization, and faster convergence. Simulation results are presented to illustrate the effectiveness of RFNN-EM for nonlinear system control.

Keywords and phrases: electromagnetism-like algorithm, neural fuzzy system, nonlinear control, adaptive control, direct inverse control.

Communicated by Shun-Feng Su

Number of Downloads: 174 | Number of Views: 749