一种空间光学载荷承力结构的智能优化及微振动抑制方法
By combining a cascaded neural network surrogate model and a multi-objective genetic algorithm, the problem of synergistic optimization of micro-vibration suppression and optical imaging performance of space optical payloads was solved, achieving efficient and accurate structural parameter optimization, and improving the imaging quality and lightweight design of space optical payloads.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI JIAOTONG UNIV
- Filing Date
- 2025-12-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to effectively suppress micro-vibrations of space optical payloads under constraints of limited weight and volume. Traditional methods lead to increased structural mass and installation complexity, and lack synergistic optimization of optical imaging performance. Existing neural networks have low prediction accuracy and poor interpretability, making it difficult to achieve multi-objective optimization.
A cascaded neural network surrogate model combined with a multi-objective genetic algorithm is adopted. By establishing a mathematical model for optimizing the structural parameters of the optical load, the cascaded neural network model is trained and iteratively optimized using a multi-objective genetic algorithm. Taking into account performance indicators such as load mass, structural fundamental frequency and image point offset, the Pareto optimal solution set is output.
It achieves efficient optimization of space optical payload structure under multiple constraints and objectives, reduces computational load, improves image shift prediction accuracy and model interpretability, and enhances the synergistic optimization effect of optical imaging performance and structural lightweighting.
Smart Images
Figure CN121683530B_ABST