Sliding mode control using RBF neural network for spacecraft attitude tracking

In order to avoid inherent chattering of sliding mode control, a radial basis function neural network based sliding mode control is presented. By using four reaction wheels and Modified Rodrigues Parameters for attitude tracking representation, the tracking dynamic has been considered, and inertia matrix uncertainty, actuators uncertainty and external disturbances has been considered in the model. Divide the controller into two parts, one is the traditional sliding mode control, and the other part is neural network to estimating the system's uncertainties. The Lyapunov stability theory has been used to achieve a stable closed loop system. Simulation results illustrate the performance of the proposed algorithm. The controller successfully deals with unknown misalignments of the axis directions of the actuators, inertia matrix uncertainty and external disturbance torques.