基于竞争神经网络的雷达杂波抑制方法  被引量:3

Radar clutter suppression method based on competitive neural network

在线阅读下载全文

作  者:施端阳 林强[1] 胡冰[1] 马艳艳 SHI Duan-yang;LIN Qiang;HU Bing;MA Yan-yan(Air Force Early Warning Academy,Wuhan 430019, China;Unit No. 95174,Wuhan 430040, China)

机构地区:[1]空军预警学院,武汉430019 [2]95174部队,武汉430040

出  处:《海军工程大学学报》2022年第1期67-74,共8页Journal of Naval University of Engineering

基  金:军事类研究生资助课题(JY2020B150);空军预警学院“双重”教研创新项目。

摘  要:为鉴别杂波点迹和目标点迹,消除杂波对雷达性能的影响,提出了一种基于竞争神经网络的雷达杂波抑制方法。首先,选取雷达点迹形成过程中能够反映目标点迹和杂波点迹差异化的特征,作为神经网络输入数据;然后,根据输入输出的数据维度设计竞争神经网络分类器,并对其进行训练;最后,利用训练好的神经网络分类器对雷达点迹进行聚类,对识别为杂波的点迹进行滤除,达到抑制杂波的目的。对雷达实测数据的测试结果证明:所提出的无监督学习方法的杂波抑制效果优于传统的有监督学习BP神经网络算法,能够实现点迹类别未知情况下的雷达点迹鉴别和杂波抑制功能。In order to identify the clutter and target trace and eliminate the influence of clutter on radar performance,a method of radar clutter suppression based on competitive neural network was proposed.Firstly,the feature reflecting the difference between target and clutter in the process of radar trace formation was selected as the input data of neural network.Secondly,the competitive neural network classifier was designed and trained according to the data dimension of input and output.Finally,the trained neural network classifier was used to cluster the radar trace and filter the trace identified as clutter so as to achieve the purpose of clutter suppression.The test of radar measured data proves that the clutter suppression effect of the proposed unsupervised learning method is better than that of the traditional supervised learning BP neural network algorithm in that it can realize the radar point trace identification and clutter suppression function when the point trace category is unknown.

关 键 词:雷达 竞争神经网络 无监督学习 杂波抑制 

分 类 号:TN957[电子电信—信号与信息处理]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象