Satellite multi-pulse orbit transfer strategy optimization method
By modeling the satellite orbit change process as a Markov decision process and using deep reinforcement learning algorithms to optimize the satellite orbit change strategy, the problems of high computational complexity and difficulty in meeting high precision and timeliness in existing technologies are solved. The optimal balance between time and fuel consumption is achieved, making it suitable for complex satellite orbit optimization tasks.
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA ACADEMY OF SPACE TECHNOLOGY
- Filing Date
- 2025-12-09
- Publication Date
- 2026-06-26
AI Technical Summary
Existing satellite orbit change strategies suffer from high computational complexity and are prone to deviating from the actual optimal solution when dealing with complex orbit change tasks involving multiple pulses, multiple layers, and multiple constraints, making it difficult to meet the requirements of high-precision and high-timeliness satellite missions.
The satellite's pulse orbit change process is modeled as a Markov decision process. A deep reinforcement learning algorithm is used to jointly optimize the orbit change timing and pulse velocity increment. By constructing a state space, action space, and reward function, a satellite orbit change strategy is generated, and the optimal action is executed during on-orbit operation.
It achieves an optimal balance between time and fuel consumption, avoids local optima, has rapid decision-making capabilities, adapts to uncertainties and unexpected situations in orbital dynamics, and is suitable for solving high-dimensional and nonlinear problems.
Smart Images

Figure CN122284281A_ABST