摘要
基于大量测试或仿真得到的近场弹目交会回波数据,提出了数据驱动的近场弹目交会回波建模方法。分析近场交会回波包络的峰值特征,建立以峰值幅度、位置和个数为特征参数的点散射源模型。采用基于支持向量机的统计学习方法,对大量近场交会回波包络的峰值特征参数进行训练学习,分别建立回波峰值幅度、位置和个数的支持向量回归模型。对上万条仿真点目标近场交会回波进行支持向量学习,结果表明,高斯核函数的支持向量回归模型能够实现高精度的目标回波峰值特征参数建模。
A data driven echo modeling approach for the near-field engagement is proposed based on a large number of measured or simulated echo data.The echo envelope of near-field engagement can be characterized by peak features,whose is represent by apoint scattering model with its peak amplitude,position and order parameters.The statistical learning method based on support vector machine(SVM)is applied to train peak features from a large amount of echo envelopes,and then the support vector regression(SVR)models for peak amplitude,position and order are obtained,represtively.The experiment of ten thousand simuluated echoes from point target near-field engagement indicates that the SVR with the Gaussian kernel can model peak features of target echoes accurately.
作者
李永晨
廖意
王晓冰
魏飞鸣
LI Yong-chen;LIAO Yi;WANG Xiao-bing;WEI Fei-ming(Science and Technology on Electromagnetic Scattering Laboratory,Shanghai 200438,China;School of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China)
出处
《制导与引信》
2021年第3期50-54,60,共6页
Guidance & Fuze
基金
国家自然科学基金(62001296)。
关键词
近场
数据建模
支持向量机
弹目交会
near-field
data modeling
support vector machine
missile target engagement
