Neural-network-based adaptive finite-time output constraint control for rigid spacecrafts

This article proposes a neural-network-based adaptive finite-time output constraint control scheme for attitude stabilization of rigid spacecrafts. First, a novel singularity-free terminal sliding mode variable is constructed and an auxiliary function is developed in the controller design to avoid the singularity problem. Then, an adaptive neural control law is designed to approximate the lumped uncertainty of spacecraft system including inertia uncertainties and external disturbances. Furthermore, a novel finite-time prescribed performance function is constructed for characterizing the convergence rate and steady state of the spacecraft attitude, such that the attitude can be maintained within a prescribed small region in finite time. Finally, the finite-time stability of the whole closed-loop system is analyzed by rigorous theoretical proofs, and comparative simulations are given to show the effectiveness and superiority of the proposed scheme.