摘要
在导弹设计研发的初始阶段,需要精确获取导弹不同气动外形对应的气动参数。然而,获取导弹气动参数的传统方法存在价格昂贵、过程耗时等缺陷。为此,本文进行了基于神经网络的导弹气动参数预测研究,构建了利用思维进化算法优化的BP神经网络模型。建模结果表明,利用该方法进行导弹气动参数的预测是可行且有效的,在样本所确定的参数范围内,对导弹的气动参数拟合能力较强,具有较好的泛化能力。
In the initial stage of missile design and development,it is necessary to accurately obtain the aerodynamic parameters corresponding to different aerodynamic shapes of missile.However,the traditional methods of obtaining the aerodynamic parameters of missile are defective in that the price is expensive and the process is time consuming.In this paper,the neural network-based prediction of aerodynamic parameters of missiles is carried out,and a BP neural network model optimized by mind evolutionary algorithm is constructed.The modeling results show that it is feasible and effective to use this method to predict the aerodynamic parameters of missile.Within the range of parameters determined by the sample,the fitting ability of aerodynamic parameters of missile is strong and has better generalization ability.
作者
原智杰
张公平
崔茅
唐炜
Yuan Zhijie;Zhang Gongping;Cui Mao;Tang Wei(School of Automation,Northwestern Polytechnical University,Xi’an 710129,China;China Airborne Missile Academy,Luoyang 471009,China;Aviation Key Laboratory of Science and Technology on Airborne Guided Weapons,Luoyang 471009,China)
出处
《航空兵器》
CSCD
北大核心
2020年第5期28-32,共5页
Aero Weaponry
基金
国家自然科学基金项目(61573289)
航空科学基金项目(20170153002)
陕西省自然科学基础研究计划项目(2019JM-042)。
关键词
气动参数
气动布局
气动建模
参数预测
BP神经网络
思维进化算法
导弹
aerodynamic parameter
aerodynamic configuration
aerodynamic modeling
parameter prediction
BP neural network
mind evolutionary algorithm
missile
