Abstract: In this paper，a direct adaptive neural network controller is proposed arming at the unknown functions and uncertain disturbance of a class of nonlinear systems.The Radial Basis Function （RBF） neural network is used as approximation model for the unknown functions due to their nicer approximation capabilities，and nonlinear damping terms is used to counteract the disturbances.The proposed method’s advantages are simple structure，brief algorithm，nicer stability and convergence with conditions.Simulation results are presented to verify the effectiveness of the approach.