一种确定增升装置形态参数的方法以及计算设备
By combining a performance prediction model with machine learning methods that include low-precision and high-precision prediction branches, the problem of insufficient aerodynamic performance prediction accuracy of lift enhancement devices for distributed propulsion aircraft is solved, and accurate optimization of the morphological parameters of the lift enhancement devices is achieved at a lower cost.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TIANMUSHAN LABORATORY
- Filing Date
- 2026-04-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately optimize lift enhancement devices for distributed propulsion aircraft within acceptable computational and time cost limits, especially due to insufficient aerodynamic performance prediction accuracy caused by the complexity of three-dimensional slipstream effects.
A performance prediction model is adopted, which uses a machine learning method that combines low-precision and high-precision prediction branches. By constructing a training sample set and training the model with a sample set, the morphological parameters of the lifting device are obtained, including the feature extraction module and the output layer, thereby reducing computational and time costs.
With lower computational and time costs, accurate prediction of the aerodynamic performance of the lift enhancement device was achieved, the optimal morphological parameters were determined, and the computational burden of 3D simulation was reduced.
Smart Images
Figure CN122020865B_ABST