论文部分内容阅读
基于南航NH-2风洞中某飞机模型大迎角大振幅单自由度偏航、滚转及偏航-滚转耦合的谐波、阶跃运动实验数据,应用径向基神经网络,研究人工神经网络描述非线性非定常气动力特性的能力。研究结果表明,所建立的径向基神经网络模型的预测结果与训练数据和验证数据都符合得很好,说明神经网络建模方法可以有效地对高度非线性的气动力进行建模。研究还表明,用神经网络建立模型时所需要的风洞实验数据可以减少,从而提高风洞实验效率、减少风洞实验的时间和成本。
Based on the experimental data of harmonic and step motion of yaw, roll and yaw-roll coupling with large amplitude single degree of freedom at a high angle of attack of an aircraft model in NH-2 wind tunnel of China Southern Airlines, the radial basis function neural network Neural networks describe the ability of nonlinear unsteady aerodynamic properties. The results show that the prediction results of the RBF neural network model are in good agreement with the training data and the verification data, which shows that the neural network modeling method can effectively model highly nonlinear aerodynamics. The research also shows that the wind tunnel experiment data needed to model the neural network can be reduced, so as to improve the efficiency of wind tunnel experiment and reduce the time and cost of wind tunnel experiment.