基于雷达RCS序列HMM目标识别分类算法研究  

Research on HMM Target Recognition and Classification Algorithm Based on Radar RCS Sequence

在线阅读下载全文

作  者:陆渊章[1] 吉训生[2] LU Yuanzhang;JI Xunsheng(Department qf Microelectronics,Jiangsu Vocational College of Information Technology,Wuxi Jiangsu 214153,China;School of Internet of Things Engineering,Jiangnan University,Wuxi Jiangsu 214000,China)

机构地区:[1]江苏信息职业技术学院微电子学院,江苏无锡214153 [2]江南大学物联网工程学院,江苏无锡214000

出  处:《电子器件》2022年第5期1089-1093,共5页Chinese Journal of Electron Devices

基  金:国家自然科学基金面上项目(61973140);江苏高校自然科学研究面上项目(16KJB510008);江苏省高职院校教师专业带头人高端研修项目。

摘  要:针对隐性马尔可夫模型(Hidden markov model, HMM)识别低频隐身目标参数建模固有问题,提出了基于雷达散射面积(Radar Cross Section, RCS)序列改进HMM目标识别分类算法。构建RCS观测序列的全局概率函数,提取序列变化特征,使模型的状态数能自动适应待建模信号结构的复杂性,并采用隐性马尔科夫模型表征雷达目标RCS变化特征,实现雷达目标的识别分类。仿真结果表明该算法可提高低频隐身目标识别的可靠性,信噪比和识别分类效果得到显著提升。Aiming at the inherent problem of parameter modeling of hidden Markov model(HMM)for identifying low-frequency stealth targets, an improved HMM target recognition and classification algorithm based on radar cross section(RCS)sequence is proposed. The global probability function of RCS observation sequence is constructd, and the variation characteristics of the sequence is extracted, so that the state number of the model can automatically adapt to the complexity of the signal structure to be modeled. Hidden Markov model is used to characterize the RCS variation characteristics of radar targets, so as to realize the recognition and classification of radar targets. Simulation results show that the reliability of low-frequency stealth target recognition is improved, and the signal-to-noise ratio and recognition and classification effect are significantly improved by using the proposed algorithm.

关 键 词:雷达散射截面 隐性马尔可夫模型 全局概率函数 状态转移概率 

分 类 号:TN911.7[电子电信—通信与信息系统] TN957.51[电子电信—信息与通信工程]

 

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