一种基于无人机桨叶力矩的风场反演系统及方法
By installing torque sensors at the root of UAV propellers and constructing a nonlinear mapping model between torque and wind speed, and combining this with graph neural networks for wind field inversion, the problems of large weight and high power consumption of UAV meteorological detection equipment have been solved, enabling efficient and accurate detection of low-altitude wind fields.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING INST OF TECH
- Filing Date
- 2025-09-26
- Publication Date
- 2026-07-17
AI Technical Summary
Existing drone-based meteorological detection equipment is expensive, heavy, and consumes a lot of power, making it impossible to deploy on small drones and hindering the achievement of lightweight, low-cost, high-precision, and real-time accurate detection of low-altitude wind fields.
By installing torque sensors at the root of the drone propellers, the changes in the torque on the propellers are measured in real time. A nonlinear mapping model between torque and wind speed is constructed, and wind field inversion is performed using graph neural networks and Transformer modules to output wind field evolution data.
It enables real-time monitoring and inversion of low-altitude wind fields, improving the efficiency and accuracy of wind field information acquisition. The system is compact, lightweight, and easy to integrate into small UAVs, featuring fast data acquisition speed and low system equipment cost.
Smart Images
Figure CN121142087B_ABST