系统工程与电子技术 ›› 2023, Vol. 45 ›› Issue (1): 9-14.doi: 10.12305/j.issn.1001-506X.2023.01.02

• 电子技术 • 上一篇    

基于神经网络和散射中心模型的目标参数提取

罗宇航1, 陈彦锡1, 郭琨毅1, 盛新庆1, 马静2,*   

  1. 1. 北京理工大学信息与电子学院应用电磁研究所, 北京 100081
    2. 北京仿真中心, 北京 100854
  • 收稿日期:2021-09-26 出版日期:2023-01-01 发布日期:2023-01-03
  • 通讯作者: 马静
  • 作者简介:罗宇航(1997—), 男, 硕士研究生, 主要研究方向为散射中心参数化建模
    陈彦锡(1994—), 男, 博士研究生, 主要研究方向为雷达目标特性
    郭琨毅(1976—), 女, 教授, 博士, 主要研究方向为雷达目标特性、散射中心参数化建模
    盛新庆(1968—), 男, 讲席教授, 博士, 主要研究方向为计算电磁学、目标电磁特性与隐身设计、复杂电磁环境仿真
    马静(1982—), 女, 研究员, 博士, 主要研究方向为射频仿真

Target parameter extraction based on neural network and scattering center model

Yuhang LUO1, Yanxi CHEN1, Kunyi GUO1, Xinqing SHENG1, Jing MA2,*   

  1. 1. Institute of Applied Electromagnetics, School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
    2. Beijing Simulation Center, Beijing 100854, China
  • Received:2021-09-26 Online:2023-01-01 Published:2023-01-03
  • Contact: Jing MA

摘要:

从雷达回波中获取目标几何参数信息往往存在高计算成本、非线性等困难。该文基于卷积神经网络和前馈神经网络, 提出了一种依据散射中心时频像特征的目标类型自动识别和目标几何参数自动提取方法。由于构建一个神经网络需要大量的训练数据样本, 而扩展目标的散射场计算又非常耗时, 利用基于已知目标已建立的散射中心模型, 快速生成大样本训练数据, 有效解决了训练样本难以获得的问题。以弹头类目标为例给出了数值实验结果, 证实了所提方法的有效性。

关键词: 神经网络, 散射中心, 时频特征, 参数提取

Abstract:

Target geometry extraction from radar echoes are often subject to high computational cost, non-linearity, and other difficulties. In this paper, based on convolutional neural network and back propagation neural network, a method is proposed to automatically identify the target pattern and extract the target geometry parameters from the time-frequency image characteristics of scattering center. Since the construction of a neural network requires a large number of training data samples, and the computation of the scattering field of the extended target is very time-consuming, the scattering center model established based on the known target is used in this paper to quickly generate large sample training data, which effectively solves the problem of obtaining training samples. Taking warhead targets as an example, the neural networks are established, and the effectiveness of the proposed method is verified by numerical experiment results.

Key words: neural network, scattering center, time-frequency characteristics, parameter extraction

中图分类号: