基于深度学习的空中目标威胁评估技术研究  

Research on Air Target Threat Assessment Technology Based on Deep Learning

作　　者：江达伟 董阳阳 张立东 路宵 董春曦[1] Jiang Dawei;Dong Yangyang;Zhang Lidong;Lu Xiao;Dong Chunxi(School of Electronic Engineering,Xidian University,Xi'an 710071,China;PLA 93209 Troops,Beijing 100085,China)

机构地区：[1]西安电子科技大学电子工程学院,陕西西安710071 [2]中国人民解放军93209部队,北京100085

出　　处：《系统仿真学报》2025年第3期791-802,共12页Journal of System Simulation

摘　　要：为了实现对空中作战目标的有效评估,提出了一种基于深度学习的空中目标威胁评估方法。根据空中目标的威胁特性,从平台层和设备层2个角度出发,对电子对抗作战所面对的空中目标的威胁属性进行了分析,构建了空中目标威胁评估指标体系,并建立了空中目标威胁评估指标数据集。以卷积神经网络为基础,引入残差结构对该网络进行优化,建立了威胁评估模型,利用构建的指标数据集进行训练,得出空中目标的威胁排序。仿真实验表明:威胁评估方法准确率高,鲁棒性强,具有较好的适用性和有效性,为威胁评估提供了一种新思路。In order to realize the effective assessment of air combat targets,a deep learning-based air target threat assessment method is proposed.According to threat characteristics of the air target,the threat attributes of air target faced by electronic countermeasure operation are analyzed from the two perspectives of platform layer and equipment layer,the air target threat assessment index system is constructed,and the air target threat assessment index data set is established.Based on convolutional neural network,a residual structure is introduced to optimize the network,a threat assessment model is established,and the threat ranking of air targets is obtained by using the constructed index data set for training.Through simulation and experimental results,it is verified that the proposed threat assessment method has high accuracy,strong robustness,good applicability and effectiveness,which provides a new idea for threat assessment.

关 键 词：电子对抗 威胁评估 深度学习 残差网络 残差卷积自编码器 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]