Application of neuro-fuzzy control for satellite AOCS

The attitude control of a future satellite is facing the challenge of its uncertain model because of flexural bodies coupling to the center body. This paper proposes a neuro-fuzzy approach to control the uncertain dynamics and disturbance. The flexible model of solar array is extended to the satellite attitude equation. To overcome the variation of internal parameters and external disturbances, three adaptive neuro-fuzzy controllers are applied to realize the attitude and orbit control system (AOCS) on the base of Proportional-Integral-Differential (PID) controllers. A least square estimation method is combined with gradient descent learning in order to optimize the learning error universally during train procedure. Simulation results show the neuro-fuzzy controllers have good performance to abate influence from disturbance, fadeless vibration and the change of the satellite´s inertia parameters.