基于反向传播神经网络的海杂波参数估计

doi:10.3969/j.issn.1000-1093.2019.12.011

摘要/Abstract

摘要： 研究分析海杂波、评估弹载导引头在不同海况下的打击精度具有重大意义。针对传统统计方法的海杂波参数估计易存在脱离实况海杂波物理特征的问题，提出基于反向传播（BP）神经网络的参数估计法。利用海杂波幅度分布特性和时间相关性，建立基于K分布的时间与空间相关海杂波模型；重点分析形状参数、尺度参数、杂波速度均方根、平均多普勒频移4个模型参数对海杂波混沌特性、分形特性的影响，总结出模型参数与物理特征之间的定性关系；利用BP神经网络充分挖掘参数与物理特征间的定量关系，并对混沌特性、分形特性进行预测，决定系数为0.985、0.952. 以实测海杂波数据为例，比较BP神经网络、最大似然估计和矩估计法的模型参数，验证了该方法可以较好地贴近真实海杂波的物理特征。

关键词: 海杂波, 反向传播神经网络, 物理特性, 参数估计

Abstract: Sea clutter is studied and analyzed for evaluating the accuracy of missile-borne synthetic aperture radar under different sea conditions. A parameter estimation method based on BP neural network is proposed to solve the problem that the sea clutter parameter estimation based on traditional statistical methods is prone to be divorced from the actual sea clutter. The amplitude distribution characteristics and temporal correlation of sea clutter are used to establish a K-distribution-based sea clutter model. The influences of four model parameters, such as shape, scale, mean square root of clutter speed, and mean Doppler shift, on sea clutter chaos and fractal characteristics are analyzed, and the qualitative relationship among model parameters and physical characteristics is summarized. On this basis, BP neural network is used to fully explore the quantitative relationship among parameters and physical characteristics, and predict the chaos characteristics and fractal characteristics. The determinate coefficients are 0.985 and 0.952. The model parameters of BP neural network, maximum likelihood estimation and moment estimation method are compared by taking the measured sea clutter data as an example. The results show that the proposed model can be well close to the physical characteristics of actual sea clutter. Key

Key words: seaclutter, BPneuralnetwork, physicalcharacteristic, parameterestimation

中图分类号:

TN957.52⁺4

何耀民，何华锋，徐永壮，苏敬，王依繁. 基于反向传播神经网络的海杂波参数估计[J]. 兵工学报, 2019, 40(12): 2473-2481.

HE Yaomin, HE Huafeng, XU Yongzhuang, SU Jing, WANG Yifan. Sea Clutter Parameter Estimation Based on BP Neural Network[J]. Acta Armamentarii, 2019, 40(12): 2473-2481.

参考文献

［1］ CONTE E, LONGO M.Characterization of radar clutter as a spherically invariant random process [J].IEE Proceedings，1987, 134(2): 191-197.
[2］ MARIER L J. Correlated K-distributed clutter generation for radar detection and track [J].IEEE Transactions on Aerospace and Electronic Systems, 1995, 31(2): 568-580.
[3］ RITCHIE M A,WOODBRIDGE K,STOVE A G.Analysis of sea clutter distribution variation with Doppler using the compound K-distribution [C]∥Proceedings of the 2010 IEEE Radar Conference.Arlington，VA，US:IEEE, 2010:495-499.
[4］ WATTS S. Modeling and simulation of coherent sea clutter [J]. IEEE Transactions on Aerospace and Electronic Systems, 2012, 48(4): 3303-3317.
[5］ WATTS S, ROSENBERG L, BOCQUET S, et al. Doppler spectra of medium grazing angle sea clutter; part 1: characterization [J]. IET Radar, Sonar & Navigation, 2016, 10(1):24-31.
[6］ WATTS S, ROSENBERG L, BOCQUET S, et al.Doppler spectra of medium grazing angle sea clutter; part 2:model assessment and simulation[J].IET Radar, Sonar & Navigation, 2016, 10(1): 32-42.
[7］ WEINBERG G V.Coherent multi-look radar detection for targets in KK-distributed clutter[M]∥PALANISAMY C.Digital Communication.Rijeka，Croatia：InTech，2012:161-175.
[8］ WEINBERG G V.Constant false alarm rate detectors for Pareto clutter models [J]. IET Radar, Sonar & Navigation, 2013, 7(2): 153-163.
[9］ HAYKIN S, LEUNG S. Is there a radar clutter attractor？[J].Applied Physics Letters,1990, 56(6): 592-595.
[10］ LEUNG H, LO T.Chaotic radar signal processing over the sea[J].IEEE Journal of Oceanic Engineering,1993, 18(3):287-295.
[11］崔万照, 朱长纯, 保文星, 等.混沌时间序列的支持向量机预测[J].物理学报, 2004,53 (10): 3303-3311.
CUI W Z, ZHU C C, BAO W X, et al. Prediction of the chaotic time series using support vector machines[J].Acta Physica Sinica, 2004, 53(10): 3303-3311.(in Chinese)
[12］ UNSWOORTH C P,COWPER M R,MCLAU-GHLIN S,et al.Re-examining the nature of radar sea clutter [J]. IEE Proceedings-Radar, Sonar and Navigation, 2002, 149(3): 105-112.
[13］ HU J, GAO J B, POSNER F L, et al.Target detection within sea clutter: a comparative study by fractal scaling analyses[J]. Fractals，2006, 14(3):187-204.
[14］ SONG R, GUO H D, LIU G. Improved Goldstein SAR interferogram filter based on empirical mode decomposition[J].IEEE Geoscience and Remote Sensing Letters, 2014, 11(2): 399-403.
[15］ XIN Z H, LIAO G S, YANG Z W, et al. A deterministic sea-clutter space-time model based on physical sea surface[J].IEEE Transactions on Geoscience and Remote Sensing,2016, 54(11): 6659-6673.
[16］ DU G. Detection of sea-surface radar targets based on fractal model[J]. Electronics Letters, 2004,40(14): 906-914.
[17］行鸿彦，龚平，徐伟.海杂波背景下小目标检测的分形方法[J].物理学报,2012,61(16): 70-79.
XING H Y, GONG P, XU W.Small target detection in the background of sea clutter using fractal method[J].Acta Physica Sinica, 2012, 61(16): 70-79. (in Chinese)
[18］行鸿彦，张强，徐伟.混沌海杂波背景下的微弱信号检测混合算法[J].物理学报, 2015, 64(4): 040506.
XING H Y, ZHANG Q, XU W.Hybrid algorithm for weak signal detection in chaotic sea clutter[J].Acta Physica Sinica,2015, 64(4): 040506.(in Chinese)
[19］李正周，曹雷，邵万兴, 等.基于空时混沌分析的海面小弱目标检测[J].光学精密工程, 2018, 26(1): 193-199.
LI Z Z, CAO L, SHAO W X, et al. Detection of small target in sea clutter based on spatio-temporal chaos analysis[J].Optics and Precision Engineering,2018,26(1):193-199. (in Chinese)
[20］刘宁波，关键，黄勇, 等.海杂波的分段分数布朗运动模型[J].物理学报,2012,61(19)：37-45.
LIU N B, GUAN J, HUANG Y, et al. Piecewise fractional Brownian motion for modeling sea clutter[J].Acta Physica Sinica, 2012, 61(19): 37-45. (in Chinese)
[21］刘宁波,丁昊,田永华,等.基于组合分形分析特征的海杂波中目标检测方法[J].航空兵器, 2018(2): 38-42.
LIU N B, DING H, TIAN Y H, et al. Target detection method in sea clutter based on combined fractal characteristics [J]. Aero Weaponry, 2018(2): 38-42. (in Chinese)
[22］ WARD K D. Compound representation of high resolution sea clutter [J]. Electronic Letter, 1981, 7(16):561-563.
[23］ OLIVER C J, TOUGH R J A. On the simulation of correlated K-distributed random clutter [J].Journal of Modern Optics, 1986, 33(3):223-250.
[24］ WARD K D, BAKER C J, WATTS S. Maritime surveillance radar [J]. IEEE Proceedings F - Radar and Signal Processing, 1990, 137(2): 51-62.
[25］ GRASSBERGER P, PROCACCIS I. Measuring the strangeness of strange attractor [J]. Physica D: Nonlinear Phenomena, 1983,54(9):189-208.
[26］ KANTELHARDT J W, ZACHIEGNER S A, KOSCIELNY B E, et al. Multi-fractal detrended fluctuation analysis of nonstationary time series [J]. Physica A, 2002, 316(1): 87-114.
［27］易怀军，刘宁，张相炎，等.基于优化的非等间隔灰色理论和BP神经网络的身管磨损量预测［J］.兵工学报，2016，37(12): 2220-2225.
YI H J，LIU N，ZHANG X Y，et al.Prediction of gun barrel wear based on improved non-equal interval grey model and BP neural network［J］.Acta Armamentarii，2016，37(12):2220-2225.(in Chinese)
[28］ DING S F, SU C Y, YU J Z. An optimizing BP neural network algorithm based on genetic algorithm [J]. Artificial Intelligence Review, 2011, 36(2): 153-162.
[29］ GUO H J, BING S, YU Q L. On the application of improved back propagation neural network in real-time forecast[C]∥Proceedings of the 3rd International Conference on Natural Computation.Haikou，China: IEEE, 2007: 541-542.
[30］ LONG J Q, LAN F C, CHEN J Q. Mechanical properties prediction of the mechanical clinching joints based on genetic algorithm and BP neural network[J].Chinese Journal of Mechanical Engineering, 2009, 22(1): 36-41.
[31］ CAO J X, LU J P. Genetic algorithm-Bayes BP neural network fitting titration of organic acids in molasses [J].Chinese Journal of Analytica Chemistry, 2011, 39(5):743-747.
[32］刘恒燕, 熊伟, 宋杰, 等. 大入射余角海杂波特性分析[J]. 电光与控制, 2019,41(1):1-7.
LIU H Y, XIONG W, SONG J, et al. Sea clutter correlation analysis and amplitude fitting for large incidence angle[J]. Electronics Optics & Control, 2019, 41(1):1-7. (in Chinese)
[33］ JOUGHIN I R, PERCIVAL D B, WINEBREN-NER D P. Maximum likelihood estimation of K-distribution parameters for SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002,31(5): 989-999.
[34］ ISKANDER D R, ZOUBIR A M. Estimating the parameters of the K-distribution using higher order and fractional moments[J].IEEE Transactions on Aerospace and Electronic Systems, 2002, 35(4): 1453-1457.

第40卷
第12期2019 年12月兵工学报ACTA
ARMAMENTARIIVol.40No.12Dec.2019

[1]	闫晓鹏, 王珂, 刘强, 郝新红, 于洪海. 基于Duffing振子参数估计的伪码调相引信干扰信号设计[J]. 兵工学报, 2022, 43(4): 729-736.
[2]	马剑飞，颜冰，林春生. 基于正交基函数的矢量磁梯度异常探测[J]. 兵工学报, 2021, 42(11): 2433-2443.
[3]	何耀民，何华锋，徐永壮，王依繁，苏敬. 基于多特征量的海杂波参数估计[J]. 兵工学报, 2020, 41(3): 517-525.
[4]	赵星宇，白春华，姚箭，孙彬峰. 燃料空气炸药爆轰产物JWL状态方程参数计算[J]. 兵工学报, 2020, 41(10): 1921-1929.
[5]	曹伟浩，姚直象，夏文杰，闫肃. 基于插值短时分数阶傅里叶变换-变权拟合的线性调频信号参数估计[J]. 兵工学报, 2020, 41(1): 86-94.
[6]	柯肇捷，周文雅. 基于灰自助和未确知有理数的小样本试验数据估计[J]. 兵工学报, 2019, 40(4): 874-879.
[7]	毛辉煌，谢文冲，徐鹏，刘畅. 基于概率定义扩展样本的机载雷达空间和时间相关海杂波数据仿真方法[J]. 兵工学报, 2019, 40(3): 530-538.
[8]	李文军，王潇楠，郑永军. 热电偶分数阶传递函数阶次和参数估计[J]. 兵工学报, 2018, 39(9): 1820-1828.
[9]	李海洋，谢里阳，李铭，李强，钟海. 一种新的无失效数据可靠性评估方法研究[J]. 兵工学报, 2018, 39(8): 1622-1631.
[10]	高玉波，张伟, 李达诚，宜晨虹, 汤铁钢. 基于反向传播神经网络的陶瓷损伤参数反演分析[J]. 兵工学报, 2018, 39(1): 146-152.
[11]	黄大荣, 陈长沙，孙国玺，赵玲，米波. 复杂装备轴承多重故障的线性判别分析与反向传播神经网络协作诊断方法[J]. 兵工学报, 2017, 38(8): 1649-1657.
[12]	熊光明，鲁浩，郭孔辉，陈慧岩. 基于滑动参数实时估计的履带车辆运行轨迹预测方法研究[J]. 兵工学报, 2017, 38(3): 600-607.
[13]	萧辉，杨国来，孙全兆. 火炮多柔体动力学结构优化研究[J]. 兵工学报, 2017, 38(1): 27-34.
[14]	王谦，侯宏，尹韶平，陈志菲. 水下高速直线运动目标的双参考源航迹估计方法研究[J]. 兵工学报, 2016, 37(4): 677-683.
[15]	赵建忠，欧阳中辉，张磊，赵建印. 基于多智能体遗传算法优化的航空电子设备状态组合预测[J]. 兵工学报, 2016, 37(4): 727-734.