基于灰色神经网络的小型无人机目标威胁评估  

Small UAV Target Threat Assessment Based on Grey Neural Network

作　　者：朱婧 徐好 蒲桃园 杨雯霞 ZHU Jing;XU Hao;PU Taoyuan;YANG Wenxia(Sichuan Jiuzhou Falcon Technologies Co.LTD.,Mianyang 621000,China)

机构地区：[1]四川九洲防控科技有限责任公司,四川绵阳621000

出　　处：《火力与指挥控制》2025年第3期201-208,共8页Fire Control & Command Control

摘　　要：针对以四旋翼无人机为代表的“低慢小”目标威胁评估问题,提出了一种基于灰色神经网络的小型无人机目标威胁评估方法。该方法通过建立灰色神经网络模型,将灰色关联和BP神经网络的优势相结合,在提高目标威胁评估结果可靠性的同时,还弥补了单一灰色关联在时间维度上的信息缺失。实验结果表明,该方法的威胁评估效果明显优于单一灰色关联法,且具有较强的自适应学习能力,可以准确地实现低空领域小型无人机目标的威胁估计。Aiming at the problem of“low,slow,and small”target threat assessment represented by quadcopter unmanned aerial vehicles(UAVs),a gray neural network-based target threat assessment method for small UAVs is proposed.The method combines the advantages of gray correlation and back propagation(BP)neural network by establishing a gray neural network model,which improves the reliability of the target threat assessment results and makes up for the lack of information on single gray correlation in the time dimension.The experimental results show that the threat assessment effect of the method is obviously better than that of the single gray correlation method,and it has a stronger adaptive learning ability,which can accurately realize the threat estimation of small UAV targets in the lowaltitude domain.

关 键 词：低慢小目标 小型无人机目标 威胁评估 灰色神经网络 

分 类 号：E917[军事] TP18[自动化与计算机技术—控制理论与控制工程]