留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于SABA优化的Volterra级数空战目标机动轨迹预测

李战武 彭明毓 高春庆 杨爱武 徐安 方诚喆

李战武,彭明毓,高春庆,等. 基于SABA优化的Volterra级数空战目标机动轨迹预测[J]. 北京航空航天大学学报,2023,49(3):503-513 doi: 10.13700/j.bh.1001-5965.2021.0287
引用本文: 李战武,彭明毓,高春庆,等. 基于SABA优化的Volterra级数空战目标机动轨迹预测[J]. 北京航空航天大学学报,2023,49(3):503-513 doi: 10.13700/j.bh.1001-5965.2021.0287
LI Z W,PENG M Y,GAO C Q,et al. Air combat maneuver trajectory prediction of target based on Volterra series optimized by SABA algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,49(3):503-513 (in Chinese) doi: 10.13700/j.bh.1001-5965.2021.0287
Citation: LI Z W,PENG M Y,GAO C Q,et al. Air combat maneuver trajectory prediction of target based on Volterra series optimized by SABA algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics,2023,49(3):503-513 (in Chinese) doi: 10.13700/j.bh.1001-5965.2021.0287

基于SABA优化的Volterra级数空战目标机动轨迹预测

doi: 10.13700/j.bh.1001-5965.2021.0287
详细信息
    作者简介:

    李战武等:基于SABA优化的Volterra级数空战目标机动轨迹预测 7

    通讯作者:

    E-mail:afeulzw@189.cn

  • 中图分类号: V19

Air combat maneuver trajectory prediction of target based on Volterra series optimized by SABA algorithm

More Information
  • 摘要:

    目标机动轨迹预测是空战态势感知和目标威胁评估的重要前提。针对传统目标机动轨迹预测模型复杂度大、预测精度低等问题,通过分析并结合目标机动轨迹时序数据所具备的混沌特性,引入Volterra泛函级数模型进行目标机动轨迹预测。为解决Volterra泛函级数模型中存在高阶核函数难以求解的问题,利用变异机制和自适应步长控制机制改进蝙蝠算法的寻优能力,进而构建了一种基于自适应蝙蝠算法(SABA)优化的Volterra泛函级数目标机动轨迹预测模型,并利用优化后不同阶数的Volterra泛函级数模型对目标未来机动轨迹进行预测。仿真实验中,通过与其他优化算法改进的Volterra泛函级数模型的预测精度对比,验证了所提预测模型的可行性,同时也说明了二阶Volterra泛函级数模型更加适用于目标机动轨迹预测。

     

  • 图 1  基于SABA算法优化的Volterra泛函级数目标机动轨迹预测流程

    Figure 1.  Flow chart of target maneuver trajectory prediction based on Volterra functional series optimized by SABA algorithm

    图 2  基于二、三阶Volterra模型目标空间预测结果对比

    Figure 2.  Comparison of target space prediction results based on second-order and third-order Volterra models

    图 3  不同智能算法优化预测模型的空间适应度函数值比较

    Figure 3.  Comparison of spatial fitness function values of prediction models optimized by different intelligent algorithms

    图 4  不同智能算法优化预测模型的运行时间对比

    Figure 4.  Comparison of running time of prediction models optimized by several intelligent algorithms

    表  1  不同预测模型进行2步预测的性能对比

    Table  1.   Performance comparison of two-step prediction with different prediction models

    算法阶数MadMseMapeCor
    BA-Volterra二阶21.91376.563 3×1020.00090.9983
    BA-Volterra三阶30.50211.460 4×1030.00120.9976
    SABA-Volterra二阶15.43372.424 6×1020.00060.9987
    SABA-Volterra三阶25.18748.296 9×1020.00100.9978
    ACO-Volterra二阶24.43208.006 2×1020.00100.9979
    ACO-Volterra三阶112.59011.684 0×1040.00430.9891
    GA-Volterra二阶35.42521.355 7×1030.00140.9975
    GA-Volterra三阶202.45835.289 1×1040.00800.9836
    BPNN83.79949.162 4×1030.00330.9971
    下载: 导出CSV

    表  2  不同预测模型进行4步预测的性能对比

    Table  2.   Performance comparison of four-step prediction with different prediction models

    算法阶数MadMseMapeCor
    BA-Volterra二阶85.60528.851 1×1030.00330.9899
    BA-Volterra三阶134.29222.223 0×1040.00530.9886
    SABA-Volterra二阶27.90751.269 8×1030.00110.9982
    SABA-Volterra三阶27.95971.104 6×1030.00110.9983
    ACO-Volterra二阶30.59991.143 9×1030.00130.9978
    ACO-Volterra三阶114.26221.695 3×1040.00450.9890
    GA-Volterra二阶53.71303.015 4×1030.00210.9970
    GA-Volterra三阶210.48225.956 8×1040.00820.9834
    BPNN221.76367.253 6×1040.00870.9830
    下载: 导出CSV

    表  3  不同预测模型进行8步预测的性能对比

    Table  3.   Performance comparison of eight-step prediction with different prediction models

    算法阶数MadMseMapeCor
    BA-Volterra二阶108.00241.475 9×1040.00420.9887
    BA-Volterra三阶125.67331.900 8×1040.00490.9888
    SABA-Volterra二阶39.52751.589 9×1030.00150.9976
    SABA-Volterra三阶71.76246.519 5×1030.00280.9968
    ACO-Volterra二阶294.70231.395 2×1050.01140.9811
    ACO-Volterra三阶545.39523.806 3×1050.02120.9689
    GA-Volterra二阶100.65321.049 8×1040.00390.9890
    GA-Volterra三阶430.59772.278 4×1050.01670.9753
    BPNN369.86971.923 3×1050.01440.9773
    下载: 导出CSV
  • [1] 寇英信, 李战武, 陈哨东, 等. 火控系统在航空作战中的作用——作战飞机之“魂”[J]. 电光与控制, 2013, 20(12): 1-5.

    KOU Y X, LI Z W, CHEN S D, et al. The important role of fire control system in air combat—Soul of fighters[J]. Electronics Optics & Control, 2013, 20(12): 1-5(in Chinese).
    [2] 姜佰辰, 关键, 周伟, 等. 基于多项式卡尔曼滤波的船舶轨迹预测算法[J]. 信号处理, 2019, 35(5): 741-746.

    JIANG B C, GUAN J, ZHOU W, et al. Vessel trajectory prediction algorithm based on polynomial fitting Kalman filtering[J]. Journal of Signal Processing, 2019, 35(5): 741-746(in Chinese).
    [3] 赵帅兵, 唐诚, 梁山, 等. 基于改进卡尔曼滤波的控制河段船舶航迹预测[J]. 计算机应用, 2012, 32(11): 3247-3250.

    ZHAO S B, TANG C, LIANG S, et al. Track prediction of vessel in controlled waterway based on improved Kalman filter[J]. Journal of Computer Applications, 2012, 32(11): 3247-3250(in Chinese).
    [4] 乔少杰, 韩楠, 朱新文, 等. 基于卡尔曼滤波的动态轨迹预测算法[J]. 电子学报, 2018, 46(2): 418-423.

    QIAO S J, HAN N, ZHU X W, et al. A dynamic trajectory prediction algorithm based on Kalman filter[J]. Acta Electronica Sinica, 2018, 46(2): 418-423(in Chinese).
    [5] 翟岱亮, 雷虎民, 李炯, 等. 基于自适应IMM的高超声速飞行器轨迹预测[J]. 航空学报, 2016, 37(11): 3466-3475.

    ZHAI D L, LEI H M, LI J, et al. Trajectory prediction of hypersonic vehicle based on adaptive IMM[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(11): 3466-3475(in Chinese).
    [6] 杨彬, 贺正洪. 一种GRNN神经网络的高超声速飞行器轨迹预测方法[J]. 计算机应用与软件, 2015, 32(7): 239-243.

    YANG B, HE Z H. Hypersonic vehicle track prediction based on GRNN[J]. Computer Applications and Software, 2015, 32(7): 239-243(in Chinese).
    [7] 谭伟, 陆百川, 黄美灵. 神经网络结合遗传算法用于航迹预测[J]. 重庆交通大学学报, 2010, 291(1): 147-150.

    TAN W, LU B C, HUANG M L. Track prediction based on neural networks and genetic algorithm[J]. Journal of Chongqing Jiaotong University, 2010, 291(1): 147-150(in Chinese).
    [8] 甘旭升, 端木京顺, 孟月波, 等. 基于粒子群优化的WNN飞行数据气动力建模[J]. 航空学报, 2012, 33(7): 1209-1217.

    GAN X S, DUANGMU J S, MENG Y B, et al. Aerodynamic modeling from flight data based on WNN optimized by particle swarm[J]. Acta Aeronautica et Astronautica Sinica, 2012, 33(7): 1209-1217(in Chinese).
    [9] SLATTERY R, ZHAO Y. Trajectory synthesis for air traffic automation[J]. Journal of Guidance, Control, and Dynamic, 1997, 20(2): 232-238. doi: 10.2514/2.4056
    [10] 张家良, 曹建福, 高峰. 大型装备传动系统非线性频谱特征提取与故障诊断[J]. 控制与决策, 2012, 27(1): 135-138.

    ZHANG J L, CAO J F, GAO F. Feature extraction and fault diagnosis of large-scale equipment transmission system based on nonlinear frequency spectrum[J]. Control and Decision, 2012, 27(1): 135-138(in Chinese).
    [11] 张华君. 基于递推批量最小二乘的Volterra级数辨识方法[J]. 小型微型计算机, 2004, 25(12): 2282-2285.

    ZHANG H J. Volterra series identification method based on recursive least square algorithm[J]. Mini-Micro Systems, 2004, 25(12): 2282-2285(in Chinese).
    [12] 孔祥玉, 韩崇昭, 马红光, 等. 基于Volterra级数的全解耦RLS自适应辨识算法[J]. 系统仿真学报, 2004, 16(4): 807-809.

    KONG X Y, HAN C Z, MA H G, et al. Fully decoupled RLS adaptive identification algorithm based on Volterra series[J]. Journal of System Simulation, 2004, 16(4): 807-809(in Chinese).
    [13] 孔祥玉, 韩崇昭, 马红光, 等. 一种总体最小二乘算法及在Volterra滤波器中的应用[J]. 西安交通大学学报, 2004, 38(4): 339-342.

    KONG X Y, HAN C Z, MA H G, et al. Total least square algorithm and its application to Volterra filter[J]. Journal of Xi’an Jiao Tong University, 2004, 38(4): 339-342(in Chinese).
    [14] 唐浩, 屈梁生, 温广瑞. 基于Volterra级数的转子故障诊断研究[J]. 中国机械工程, 2009, 20(4): 447-454.

    TANG H, QU L S, WEN G R. Fault diagnosis for rotor system based on Volterra series[J]. China Mechanical Engineering, 2009, 20(4): 447-454(in Chinese).
    [15] ABBAS H M, BAYOUMI M M. Volterra system identification using adaptive genetic algorithms[J]. Applied Soft Computing, 2005, 5(1): 75-86.
    [16] 李志农, 唐高松, 肖尧先, 等. 基于自适应蚁群优化的Volterra核辨识算法研究[J]. 振动与冲击, 2011, 30(10): 35-38.

    LI Z N, TANG G S, XIAO Y X, et al. Volterra series identification method based on adaptive ant colony optimizations[J]. Journal of Vibration and Shock, 2011, 30(10): 35-38(in Chinese).
    [17] 李志农, 蒋静, 陈金刚, 等. 基于量子粒子群优化的Volterra核辨识算法研究[J]. 振动与冲击, 2013, 32(3): 60-63.

    LI Z N, JIANG J, CHEN J G, et al. Volterra series identification method based on quantum particle swarm optimization[J]. Journal of Vibration and Shock, 2013, 32(3): 60-63(in Chinese).
    [18] 李志农, 蒋静, 冯辅周, 等. 基于量子粒子群优化Volterra时域核辨识的隐Markov模型识别方法[J]. 仪器仪表学报, 2011, 32(12): 2693-2698.

    LI Z N, JIANG J, FENG F Z, et al. Hidden Markov model recognition method based on Volterra kernel identified with particle swarm optimization[J]. Chinese Journal of Scientific Instrument, 2011, 32(12): 2693-2698(in Chinese).
    [19] YANG X. A new metaheuristic bat-inspired algorithm[C]//Nature Inspired Cooperative Strategies for Optimization. Berlin: Springer, 2010, 284: 65-74.
    [20] 吕石磊, 黄永霖, 陈海强, 等. 基于自适应步长的改进蝙蝠算法[J]. 控制与决策, 2018, 33(3): 557-567.

    LV S L, HUANG Y L, CHEN H Q, et al. Improved bat algorithm using self-adaptive step[J]. Control and Decision, 2018, 33(3): 557-567(in Chinese).
    [21] FISTER I, FISTER D, YANG X S. A hybrid bat algorithm[J]. Elektrotehniski Vestnik, 2013, 80(1): 1-7.
    [22] TAN L, JIANG J. Adaptive second-order Volterra filtered-XRLS algorithms with sequential and partial updates for non-linear active noise control[C]//Proceedings of 4th IEEE Conference on Industrial Electronics and Applications. Piscataway: IEEE Press, 2009: 1625-1630.
    [23] CHENG C M, PENG Z K, ZHANG W M, et al. Volterra-series-based nonlinear system modeling and its engineering applications: A state-of-the-art review[J]. Mechanical Systems and Signal Processing, 2017, 87: 340-364.
    [24] 卫晓娟, 丁旺才, 李宁洲, 等. 基于改进粒子群算法的Volterra模型参数辨识[J]. 振动与冲击, 2015, 34(21): 105-112.

    WEI X J, DING W C, LI N Z, et al. Parametric identification of nonlinear Volterra model based on improved PSO algorithm[J]. Journal of Vibration and Shock, 2015, 34(21): 105-112(in Chinese).
    [25] SONG J, MENG D, WANG Y. Analysis of chaotic behavior based on phase space reconstruction methods[C]//Proceedings of the IEEE 6th International Symposium on Computational Intelligence and Design. Piscataway: IEEE Press, 2014: 414-417.
    [26] 陆振波, 蔡志明, 姜可宇. 基于改进的C-C方法的相空间重构参数选择[J]. 系统仿真学报, 2007, 19(11): 2527-2529. doi: 10.3969/j.issn.1004-731X.2007.11.036

    LU Z B, CAI Z M, JIANG K Y. Determination of embedding parameters for phase space reconstruction based on improved C-C methods[J]. Journal of System Simulation, 2007, 19(11): 2527-2529(in Chinese). doi: 10.3969/j.issn.1004-731X.2007.11.036
    [27] 赵玮, 王强, 何晓晖, 等. 基于BA优化核参数的非线性Volterra滤波方法研究[J]. 仪表技术与传感器, 2019(6): 77-81. doi: 10.3969/j.issn.1002-1841.2019.06.018

    ZHAO W, WANG Q, HE X H, et al. Research on nonlinear Volterra filter method with kernel parameters optimized based on BA[J]. Instrument Technique and Sensor, 2019(6): 77-81(in Chinese). doi: 10.3969/j.issn.1002-1841.2019.06.018
    [28] 姜学鹏, 洪贝. 基于AP的Volterra级数自适应多重回归及其多步预测应用[J]. 系统工程与电子技术, 2014, 36(12): 2652-2655.

    JIANG X P, HONG B. Multi-step predicting model based on multi-recursive AP algorithm of Volterra series[J]. Systems Engineering and Electronics, 2014, 36(12): 2652-2655(in Chinese).
    [29] 韩敏. 混沌时间序列预测理论与方法[M]. 北京: 中国水利水电出版社, 2007: 24-30.

    HAN M. Theory and method of chaotic time series prediction[M]. Beijing: China Water Resources and Hydropower Press, 2007: 24-30(in Chinese).
    [30] 张家树, 肖先赐. 混沌时间序列的自适应高阶非线性滤波预测[J]. 物理学报, 2000, 49(7): 1222-1226. doi: 10.7498/aps.49.1221

    ZHANG J S, XIAO X C. Prediction of chaotic time series by using adaptive higher-order nonlinear Fourier infrared filters[J]. Acta Physica Sinica, 2000, 49(7): 1222-1226(in Chinese). doi: 10.7498/aps.49.1221
  • 加载中
图(4) / 表(3)
计量
  • 文章访问数:  451
  • HTML全文浏览量:  108
  • PDF下载量:  110
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-06-01
  • 录用日期:  2021-09-03
  • 网络出版日期:  2021-09-13
  • 整期出版日期:  2023-03-30

目录

    /

    返回文章
    返回
    常见问答