This paper is concerned with nonlinear time delays systems with unmodeled dynamics. Based on the radial basis functions(RBF), an dynamic surface control(DSC) is presented. By putting forward to a dynamic signal to dominating the dynamic disturbance,this approach combines with mean value theorem and uses radial basis function(RBF) to approximate unknown continuous functions. Furthermore,dynamic surface control(DSC)is introduced to avoid the issue that the vitual control is needed to be derivated repeatly in every step of the back-stepping design. It is that coming up with the Lyapunov-Krasovskii functionals and hyperbolic tangent function smartly o?set the unknown time delays functions and overcomes the problem that the circular construction of controller in the design of adaptive neural control for pure-feedback nonlinear systems. Compared with the systems of the existing literature, the proposed system model is more universal. With this proposed method, the number of adaptive parameters required is reduced significantly.The closed-loop control system is shown to be semi-globally uniformly ultimately bounded through theoretical analysis. The tracking error converges to a residual set. Simulation studies are given to demonstrate the e?ectiveness of the proposed design scheme. |