Radial Basis Function Neural Network-based Control for Uncertain Nonlinear Systems with Unknown Dead-Zone Input

In this work, an adaptive dynamic surface control scheme is studied for a class of nonlinear systems with unknown functions and unknown non-symmetric dead-zone nonlinearity. The unknown asymmetric dead-zone is described as a combination of a linear term and a disturbance-like term. Radial basis function neural networks (RBFNNs) are used in the online approximation of unknown functions and disturbance- like term of the dead-zone model and adaptive laws are designed to adjust the weights of network. Using the RBFNN-based model, the dead-zone model and the dynamic surface control (DSC) technique, the adaptive control scheme is developed for uncertain nonlinear systems with dead-zone nonlinearity. The proposed scheme eliminates the explosion of complexity problem and presents a singular-free adaptive DSC control scheme. Also, it does not require any knowledge about unknown terms and the dead-zone nonlinearity. Simulation results are provided to demonstrate the performance and effectiveness of the proposed approach.