Résumé: In this paper, an Adaptive Neural Network Sliding-Mode Controller (ANNSMC) design approach is proposed. We present a novel adaptive method for a Neural Network (NN) system to approximate unknown non-linear continuous functions. The proposed scheme combines the benefits of the adaptive control, NN and Sliding-Mode Control (SMC) manner without precise system model information. It has online adjusting ability to cope with the unknown parametric and external disturbance by tuning the control parameters. The proposed ANNSMC approximator is then applied in the control of a seesaw system. Simulation results of the seesaw system show that the proposed controller is feasible and effective.

Langue: Anglais