The invention discloses a design method for optimizing the plane shape of a blade of a special unmanned aerial vehicle based on machine learning. The method comprises the following steps: step 1, establishing a database of machine learning; 2, establishing a machine learning model; and step 3, carrying out optimal design on the optimal blade. According to the method, an airfoil mechanical parameter data set generated through NACA airfoil library and CFD computational fluid mechanics simulation is adopted, a machine learning method is adopted to train the data set, and a proper machine learning method is selected to predict and optimize parameters through evaluation of a training result, so that the accuracy of the airfoil mechanical parameter data set is improved. And an optimization result and a prediction result are verified through an experiment mode, so that the experiment cost is saved to a great extent, and the calculation efficiency is improved.
本发明公开了一种基于机器学习的特种无人机桨叶平面形状优化的设计方法,所述方法包括如下步骤:步骤1:建立机器学习的数据库;步骤2:建立机器学习的模型;步骤3:最优桨叶优化设计。本发明通过NACA翼型库和CFD计算流体力学仿真所生成的翼型力学参数数据集,采用机器学习的方法对数据集进行训练,通过对训练结果的评估,选择合适的机器学习方法对参数进行预测和优化,并通过实验的方式对优化结果和预测结果进行验证,很大程度上节约了实验成本并且提高了计算效率。
Design method for optimizing plane shape of paddle of special unmanned aerial vehicle based on machine learning
基于机器学习的特种无人机桨叶平面形状优化的设计方法
2023-12-29
Patent
Elektronische Ressource
Chinesisch
IPC: | G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B64C AEROPLANES , Flugzeuge / B64F GROUND OR AIRCRAFT-CARRIER-DECK INSTALLATIONS SPECIALLY ADAPTED FOR USE IN CONNECTION WITH AIRCRAFT , Boden- oder Flugzeugträgerdeckeinrichtungen besonders ausgebildet für die Verwendung in Verbindung mit Luftfahrzeugen |
Novel unmanned aerial vehicle paddle protection cover
Europäisches Patentamt | 2020
|