FNN-based Robust Adaptive Tracking Control for a Class of Uncertain Nonlinear Systems

An FNN (fuzzy neural network)-based robust adaptive controller is presented for a class of perturbed uncertain nonlinear system with unknown virtual control gain functions (UVCGF). The FNN is used to approximate unstructured uncertain functions. The proposed algorithm, which combined Nussbaum gain with the decoupled backstepping techniques, does not require a priori knowledge of the signs of the UVCGF, and circumvents the controller-singularity problem gracefully. It proved that the tracking error can be driven to a small residual set while keeping all signals in the closed loop semi-globally uniformly ultimately bounded (SGUUB). Numerical simulation results are presented to validate the effectiveness