JFET_V2_N4_RP5 Slim Frikha Mohamed Djemel Nabil Derbel Journal on Future Engineering and Technology 2230 – 7184 2 4 68 74 Adaptive control, neural networks, sliding mode control, observers, stability This paper proposes an observer based indirect adaptive sliding mode controller with neural networks for a certain class of unknown nonlinear dynamic systems. For these systems not all the state variables are available for measurements. To design the proposed controller, we first construct neural network models to describe system nonlinear dynamics. Then, an observer is employed to estimate the tracking error vector, and a neuro-sliding mode controller is developed to achieve the tracking performances. Adaptive laws are proposed to adjust parameters of neural models. The stability of the overall control system is analyzed based on the Lyapunov method. Simulation results illustrate the design procedures and show the tracking performance of the proposed controller in the presence of external disturbances. May - July 2007 Copyright © 2007 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=808