To investigate the control problem of chaotic motion in spacecraft system caused by the coupled effect of liquid fuel sloshing and small periodic disturbance inside or outside spacecraft, the H∞ control strategy based on neural network disturbance observer is presented, which makes liquid spacecraft disengage chaos and liquid fuel sloshing which are inhibited. Disturbance observer is designed to track and compensate the coupled disturbance caused by liquid sloshing, parameter uncertainty, and external disturbance based on the nonlinear approximation capability of neural network. Taking into account the problems of observation error and model inaccuracy, the H∞ control strategy can be applied to improve the robustness of the control system. Compared with the existing common control algorithm, the proposed strategy proves to be valid and better at adaptability and robustness by simulations.