Neural network-based adaptive fixed-time control for nonlinear systems with actuator faults, unmodeled dynamics, and input dead-zone

This work presents an adaptive fixed-time control scheme for nonstrict-feedback nonlinear systems, taking into account the presence of actuator faults, input dead-zone, unmodeled dynamics, and external disturbances. Radial basis function neural networks (RBFNNs) are employed to approximate the unknown nonlinearities, and a dynamic auxiliary signal is incorporated to handle the effects of unmodeled dynamics. By combining the backstepping design with Lyapunov stability theory, the proposed adaptive fixed-time controller guarantees that all closed-loop signals remain bounded and that the system output tracks the desired trajectory within a fixed duration. Importantly, the settling time is determined solely by the selected controller parameters and is independent of the initial system states. The proposed control approach is validated and its practicality is illustrated using both a numerical simulation and a pendulum system example.