Abstract
Accurately quantifying the maneuver time uncertainty and impulsive maneuver deviation of spacecraft is an effective means to ensure the smooth progress of rendezvous, docking, and orbit determination missions. A method for quantification and propagation of uncertainty in maneuver time is presented. This method uses deep neural networks to sample the maneuvering time deviation in response to the strong coupling between maneuvering time and spacecraft state, as well as the strong nonlinearity of orbital dynamics. First, a maneuver time uncertainty quantification and propagation model is proposed, followed by an analysis of the efficiency and effectiveness of different sampling strategies. Subsequently, combined with the conclusions drawn from the analysis of the sampling strategies, an optimized sampling model is developed to address the issue of accuracy in the quantification of maneuver uncertainty. Finally, a deep neural network is trained as a surrogate model to instantaneously map process parameters to the sampling strategies. This replaces the costly online optimization process, enabling rapid and high-fidelity uncertainty quantification and propagation. Simulation results demonstrate that the proposed method can effectively quantify both the uncertainty of the maneuver time and the maneuver deviation.
Funding Information
  • National Key Laboratory of Space Intelligent Control Laboratory (HTKJ2025KL502010)
  • National Key Laboratory of Space Intelligent Control Laboratory (HTKJ2024KL502001)

This publication has 35 references indexed in Scilit: