基于非监督贝叶斯学习雷达性能指标动态评估

doi:10.3969/j.issn.1001-506X.2021.01.10

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (1): 74-82.doi: 10.3969/j.issn.1001-506X.2021.01.10

基于非监督贝叶斯学习雷达性能指标动态评估

杨磊¹(), 毛欣瑶¹(), 杨晓炜²(), 张海^2,*(), 杨菲²(), 孙麟²()

1. 中国民航大学天津市智能信号与图像处理重点实验室, 天津 300300
2. 中国工程物理研究院电子工程研究所, 四川绵阳 621999

收稿日期:2020-04-20 出版日期:2020-12-25 发布日期:2020-12-30
通讯作者: 张海 E-mail:yanglei840626@163.com;mxy75897427@163.com;yangxwh@126.com;e2zhanghai@aliyun.com;13535738@qq.com;sunlin@mail.ustc.mail.cn
作者简介:杨磊(1984-),男,副教授,博士,主要研究方向为高分辨SAR成像及机器学习理论应用。E-mail:yanglei840626@163.com|毛欣瑶(1993-),女,硕士研究生,主要研究方向为机器学习理论应用。E-mail:mxy75897427@163.com|杨晓炜(1988-),男,助理研究员,硕士,主要研究方向为信号仿真与评估。E-mail:yangxwh@126.com|杨菲(1981-),女,副研究员,硕士,主要研究方向为雷达回波模拟。E-mail:13535738@qq.com|孙麟(1990-),男,助理研究员,博士,主要研究方向为雷达信号处理及压缩感知。E-mail:sunlin@mail.ustc.mail.cn
基金资助:
国家自然科学基金(61601470);天津市自然科学基金(16JCYBJC41200)

Dynamic evaluation of radar performance index based on unsupervised Bayesian learning

Lei YANG¹(), Xinyao MAO¹(), Xiaowei YANG²(), Hai ZHANG^2,*(), Fei YANG²(), Lin SUN²()

1. Tianjin Key Laboratory for Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, China
2. Institute of Electronic Engineering, China Academy of Engineering Physics, Mianyang 621999, China

Received:2020-04-20 Online:2020-12-25 Published:2020-12-30
Contact: Hai ZHANG E-mail:yanglei840626@163.com;mxy75897427@163.com;yangxwh@126.com;e2zhanghai@aliyun.com;13535738@qq.com;sunlin@mail.ustc.mail.cn

摘要/Abstract

摘要：

针对传统雷达性能指标评估方法相对“机械”、缺乏理论约束,需要多次重复实验,导致评估效率较低,评估成本较高等问题,提出基于非监督贝叶斯学习方法的雷达性能指标动态评估算法,在一定雷达探测目标先验假设下,结合典型回波观测数据模型,建立雷达性能指标后验概率模型。考虑到先验知识与观测数据可能存在的非共轭特性,针对先验概率模型建立分层贝叶斯模型,从而保证雷达性能指标后验概率密度函数的可解性。此外,为了保证后验概率密度函数的闭合解析解,应用变分贝叶斯期望最大化(variational Bayesian expectation maximization, VB-EM)方法,基于高斯-赛德尔迭代策略分别计算性能指标及其超参数的后验概率密度函数。最终,利用后验概率密度函数计算结果,可获得相应性能指标解析估计值及其置信区间和置信度,从而实现对指标动态变化的解析指示。相比传统蒙特卡罗评估方法,所提方法仅需一次实验数据便可获得定量的、解析的指标评估结果,可以大大缩减评估成本,提升评估效率,同时可对指标动态变化给出定量指示。应用仿真数据对雷达定位、测高精度以及目标检测概率指标进行了验证,相比传统方法,评估处理增益获得了有效提升。

关键词: 非监督学习, 贝叶斯学习, 动态评估, 雷达性能指标

Abstract:

In view of conventional evaluation method of radar performance index is relatively tedious and lack of theoretical bounds, which requires enough repeated experiments. This results in low efficiency and high cost of implementation. A fully dynamic evaluation algorithm for the radar performance index is proposed based on the unsupervised Bayesian statistical learning method. Combined with typical observed data model, the posterior probability model of radar performance index is established under a certain prior assumption of radar target. Considering the possible non-conjugated characteristic of prior and observation data, a hierarchical Bayesian model for the prior probability model is introduced, which guarantees the solvability of the intended posterior probability function for the radar performance index. In addition, to ensure closed form solutions of the posterior probability function, the method of variational Bayesian expectation maximization (VB-EM) is utilized, so that the posterior probability function of the performance index and the hyper-parameters can be calculated through Gauss-Seidel iterative strategy. Finlly, the analytical estimates of corresponding performance indexs, and their confidential interval and confidential degree can be acquired by using the results of posterior probability function, which can realize the analytical indication of the dynamic change of index. Compared with the traditional Monte Carlo evaluations, the proposed method can obtain quantitative and analytical index evaluation results with single piece of experimental data, which can greatly reduce the evaluation cost and improve the evaluation efficiency. At the same time, it can give a quantitative indication of the dynamic changes of the index. The simulation data is applied to verify the accuracy of radar positioning and height measurement as well as target detection probability index. Compared with the traditional methods, the gain of the evaluation can be improved in a great extent.

Key words: unsupervised learning, Bayesian learning, dynamic evaluation, radar performance index

中图分类号:

TN957

杨磊, 毛欣瑶, 杨晓炜, 张海, 杨菲, 孙麟. 基于非监督贝叶斯学习雷达性能指标动态评估[J]. 系统工程与电子技术, 2021, 43(1): 74-82.

Lei YANG, Xinyao MAO, Xiaowei YANG, Hai ZHANG, Fei YANG, Lin SUN. Dynamic evaluation of radar performance index based on unsupervised Bayesian learning[J]. Systems Engineering and Electronics, 2021, 43(1): 74-82.

图/表 7

图1

图2

图3

图4

图5

图6

图7

参考文献 23

1	葛江涛, 和伟, 侯道琪. 基于改进型t对比较法的雷达性能指标对比分析[J]. 电子信息对抗技术, 2015, (5): 61- 64.
	GE J T , HE W , HOU D Q . The contrastive analysis of radar properties indicators based on the improved t-pairs comparative method[J]. Electronic Information Warfare Technology, 2015, (5): 61- 64.
2	任明秋, 蔡金燕, 朱元清, 等. 基于RS-ANFIS的雷达抗干扰性能评估方法[J]. 系统工程理论与实践, 2013, 33 (10): 255- 261.
	REN M Q , CAI J Y , ZHU Y Q , et al. Evaluation approach for radar ECCM capability based on RS-ANFIS[J]. Systems Engineering-Theory & Practice, 2013, 33 (10): 255- 261.
3	WALTER J C , BARKEMA G T . An introduction to Monte Carlo methods[J]. Physica A Statistical Mechanics & Its Applications, 2015, 418, 78- 87.
4	HABRICH T, WAGNER C, HELLINGRATH B. Qualitative assessment of machine learning techniques in the context of fault diagnostics[C]//Proc.of the International Conference on Business Information Systems, 2018.
5	黄慧萍, 肖世德, 梁红琴. 基于AHP和攻防树的SCADA系统安全脆弱性评估[J]. 控制工程, 2018, 25 (6): 1091- 1097.
	HUANG H P , XIAO S D , LIANG H Q . Vulnerability assessment of cyber security for SCADA systems based on AHP and attack defense tree[J]. Control Engineering of China, 2018, 25 (6): 1091- 1097.
6	胡玉伟, 马萍, 杨明, 等. 一种时频结合分析的仿真结果动态一致性检验方法[J]. 系统工程与电子技术, 2013, 35 (3): 643- 649.
	HU Y W , MA P , YANG M , et al. Dynamic consistency test method combining time domain with frequency domain for simulation results[J]. Systems Engineering and Electronics, 2013, 35 (3): 643- 649.
7	MARTENS J , PUT F , KERRE E . A fuzzy set theoretic approach to validate simulation models[J]. ACM Trans.on modeling and Computer Simulation, 2006, 16 (4): 375- 398.
8	YANG L , LI P C , ZHANG S , et al. Cooperative multitask learning for sparsity-driven SAR imagery and nonsystematic error autocalibration[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 58 (7): 5132- 5143.
9	LAMPROPOULOS G A , DROSOPOULOS A . High resolution radar clutter statistics[J]. IEEE Trans.on Aerospace and Electronic Systems, 1999, 35 (1): 43- 60.
10	WANG L , ZHAO L F , BI G A , et al. Hierarchical sparse signal recovery by variational Bayesian inference[J]. IEEE Signal Processing Letters, 2014, 21 (1): 110- 113.
11	ZHAO L F , WANG L , BI G A , et al. An autofocus technique for high-resolution inverse synthetic aperture radar imagery[J]. IEEE Trans.on Geoscience and Remote Sensing, 2014, 52 (10): 6392- 6403.
12	YANG H Z , CHEN C Z , CHEN S Y , et al. Non-common band SAR interferometry via compressive sensing[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 58 (6): 4436- 4453.
13	BABACAN S D , MOLINA R , KATSAGGE-LOS A K . Bayesian compressive sensing using laplace priors[J]. IEEE Trans.on Image Processing, 2010, 19 (1): 53- 63.
14	YANG L , ZHAO L F , BI G A , et al. SAR ground moving target imaging algorithm based on parametric and dynamic sparse Bayesian learning[J]. IEEE Trans.on Geoence and Remote Sensing, 2016, 54 (4): 2254- 2267.
15	MÍDL V , QUINN A . The variational Bayes method in signal processing[M]. Berlin: Springer, 2006.
16	WANG L , ZHAO L F , BI G A , et al. Enhanced ISAR imaging by exploiting the continuity of the target scene[J]. IEEE Trans.on Geoscience and Remote Sensing, 2014, 52 (9): 5736- 5750.
17	TZIKAS D G , LIKAS A C , GALATSANOS N P . The variational approximation for Bayesian inference[J]. IEEE Signal Processing Magazine, 2008, 25 (6): 131- 146.
18	OLIVIER C , AURÉLIEN G , ODALRIC-AMBRYM M , et al. Kullback-Leibler upper confidence bounds for optimal sequential allocation[J]. The Annals of Stats, 2012, 41 (3): 1516- 1541.
19	NOH M , LEE Y , PARK H . Low complexity LMMSE channel estimation for OFDM[J]. IEEE Proceedings Communications, 2006, 153 (5): 645- 650.
20	张忠, 方可, 杨明. 基于群组AHP的复杂仿真系统可信度评估方法[J]. 系统工程与电子技术, 2011, 33 (11): 2569- 2572.
	ZHANG Z , FANG K , YANG M . Method for complex simulation credibility evaluation based on group AH[J]. Systems Engineering and Electronics, 2011, 33 (11): 2569- 2572.
21	LIU W, ZHANG R, HE Z, et al. Study on simulation credibility control of command system[C]//Proc.of the International Symposium on Computational Intelligence & Design, 2017.
22	陈维义, 程晗, 刘国强, 等. 考虑仿真可信度的舰炮射击精度贝叶斯估计[J]. 系统工程与电子技术, 2018, 40 (11): 211- 217.
	CHEN W Y , CHENG H , LIU G Q , et al. Bayesian estimation for naval gun's firing accuracy considering reliability of simulation[J]. Systems Engineering and Electronics, 2018, 40 (11): 211- 217.
23	杨小军, 徐忠富, 张星, 等. 仿真模型可信度评估研究综述及难点分析[J]. 计算机科学, 2019, 46 (S1): 23- 29.
	YANG X J , XU Z F , ZHANG X , et al. Overview and difficulties analysis on credibility assessment of simulation models[J]. Computer Science, 2019, 46 (S1): 23- 29.

[1]	徐安林, 张毓, 周峰. 基于Beta过程的高分辨ISAR成像[J]. 系统工程与电子技术, 2022, 44(6): 1873-1879.
[2]	张俊, 张新禹, 姜卫东, 刘永祥, 黎湘. 基于广义近似消息传递的快速DOA估计方法[J]. 系统工程与电子技术, 2022, 44(10): 2995-3002.
[3]	李冬霞, 陈秋雨, 王磊, 刘海涛. 基于BSBL-BO算法的DME脉冲干扰抑制方法[J]. 系统工程与电子技术, 2021, 43(9): 2649-2656.
[4]	沈笑云, 廖仙华, 孙卫天, 夏亚波, 杨磊. 可变先验贝叶斯学习稀疏SAR成像[J]. 系统工程与电子技术, 2021, 43(7): 1781-1790.
[5]	袁骏, 肖卉, 蔡志明, 奚畅. 基于稀疏贝叶斯学习的拖曳线列阵空间谱估计[J]. 系统工程与电子技术, 2019, 41(6): 1202-1209.
[6]	张永顺, 朱卫纲, 贾鑫, 王满喜. 基于块稀疏贝叶斯学习的直扩通信窄带干扰检测与参数估计[J]. 系统工程与电子技术, 2019, 41(4): 889-897.
[7]	冯明月, 何明浩, 郁春来, 曲智国. 基于双平行互质阵列的二维高精度DOA估计[J]. 系统工程与电子技术, 2017, 39(5): 977-983.

基于非监督贝叶斯学习雷达性能指标动态评估

Dynamic evaluation of radar performance index based on unsupervised Bayesian learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 23

相关文章 7

编辑推荐

Metrics

本文评价