一种基于模板匹配的蜂窝结构板撞击定位方法及装置
By combining template matching and neural networks, the problem of accurate impact positioning of cellular structure panels under extreme high and low temperatures was solved, realizing accurate impact positioning of spacecraft cellular structure panels and improving signal quality and positioning accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AEROSPACE DONGFANGHONG SATELLITE
- Filing Date
- 2025-08-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately monitor multi-point strain and pressure parameters of spacecraft honeycomb structure panels under extreme high and low temperatures, especially given the inhomogeneity within the honeycomb structure, making precise impact positioning difficult.
A template matching-based approach is adopted. By collecting FBG sensor signals after a simulated impact on a cellular structure panel, a feature library is established, signal feature extraction and template matching are performed, and combined with a neural network method, feature comparison and weighted averaging of real-time impact signals are realized to determine the global impact location.
It achieves precise impact positioning of cellular structure panels, improves signal quality and positioning accuracy, and can adapt to sensor failure and structural changes in complex environments, thereby improving positioning coverage and accuracy.
Smart Images
Figure CN121144864B_ABST