Indirect Neural-Enhanced Integral Sliding Mode Control for Finite-Time Fault-Tolerant Attitude Tracking of Spacecraft

In this article, a neural integral sliding mode control strategy is presented for the finite-time fault-tolerant attitude tracking of rigid spacecraft subject to unknown inertia and disturbances. First, an controller was developed by originally constructing novel surface avoid singularity problem. Then, network (NN) embedded into compensate lumped uncertainty replace robust switching term. way, chattering phenomenon significantly suppressed. Particularly, mechanism indirect approximation introduced through inequality relaxation. Benefiting from design, only single learning parameter required be adjusted online, computation burden proposed extremely reduced. The stability argument showed that could guarantee angular velocity errors were regulated minor residual sets around zero in finite time. It noteworthy not strongly against disturbances, but also highly insensitive actuator faults. Finally, effectiveness advantages validated using simulations comparisons.