Adaptive neural fixed-time control for high-order nonlinear systems with sensor faults and input dead-zone and saturation

This paper presents a fixed-time adaptive fault-tolerant control strategy for high-order nonlinear systems affected by sensor faults, input dead- zone, and saturation nonlinearities. To handle the unknown nonlinearities, radial basis function neural networks (RBFNNs) are employed. The method of adding a power integrator is introduced to address challenges arising from high-order system dynamics. Moreover, a smooth nonaffine function is designed to approximate the nonsmooth characteristics of input dead-zone and saturation effects, which is then transformed into an affine structure using the mean value theorem. A fixed-time adaptive control law is developed based on neural network approximation by integrating the backstepping technique with the Lyapunov stability theory. The proposed scheme guarantees that all signals within the closed-loop system remain bounded, and the system output converges to a small region around zero within a fixed time. The effectiveness and practicality of the proposed control approach are validated through two simulation examples.