【摘要】 载机投放炸弹或发射导弹的机弹分离过程对于飞行安全和任务完成具有重要意义。为了从有限的试验或计算数据中尽可能全面、细致地预测分离轨迹,根据某型飞机投弹的计算流体力学模拟结果,基于误差反向传播(BP)神经网络方法,研究确定了模型的隐藏层层数、隐藏层神经元数目和训练函数,建立了分离过程中导弹的空气动力学性能预测模型。经与风洞试验结果对比验证,本文基于BP神经网络的机弹分离轨迹预测方法可行,为类似问题的研究提供参考思路。更多还原

【Abstract】 The process of separating bombs or missiles from the carrier aircraft is of great significance to flight safety and mission completion. In order to predict the separation trajectory as comprehensively as possible from the limited experimental or calculation data, an aerodynamic performance prediction model based on error Back-Propagation(BP)neural network is established according to the computational fluid dynamics simulation results of a certain type of aircraft bombing. The selection of the number of hidden layers, the number of hidden layer nodes and the training function are studied. Compared with the results of wind tunnel tests, the store separation trajectory prediction method based on BP neural network in this paper is feasible and can provide reference ideas for the study of similar problems.更多还原