Command-filter-based fast finite-time composite adaptive neural control for nonlinear systems with input dead-zone

In this paper, a command-filter-based fast finite-time composite adaptive control scheme is proposed for nonlinear systems with input dead-zone. The neural networks (NNs) are used to approximate the unknown functions of the controlled systems. The series-parallel nonsmooth estimation models are used to predict the errors. In addition, the tracking error and prediction errors are anastomosed to update the weights of the NNs. To solve the problem of "explosion of complexity," the command-filter technology is adopted. Combining the Lyapunov stability theory and the adaptive backstepping algorithm, a composite adaptive backstepping control scheme is proposed. The proposed scheme dissolves the singularity problem which may emerge in the design process and the neural networks approximation performances can be realized as well. Meanwhile, the proposed scheme guarantees the tracking error converges into a small neighborhood of zero in fast finite-time and the boundedness of all the closed-loop signals. Finally, the simulation example is provided to verify the effectiveness of the proposed scheme.