模型误差影响下基于CNN+BiLSTM神经网络的非圆信号目标直接跟踪算法

尹洁昕; 王鼎; 杨欣; 杨宾

doi:10.12263/DZXB.20230525

您当前的位置：

首页 >

文章列表页 >

模型误差影响下基于CNN+BiLSTM神经网络的非圆信号目标直接跟踪算法

学术论文 | 更新时间：2025-12-08

- 模型误差影响下基于CNN+BiLSTM神经网络的非圆信号目标直接跟踪算法
- Direct Tracking for a Non-Circular Source Based on CNN+BiLSTM Neural Network in the Presence of Modeling Errors
- 电子学报 2024年52卷第4期页码：1315-1329
- 作者机构：
  
  1.中国人民解放军战略支援部队信息工程大学信息系统工程学院,河南郑州 450001
  2.国家数字交换系统工程技术研究中心,河南郑州 450002
  3.郑州大学计算机与人工智能学院,河南郑州 450001
- 作者简介：
  
  [ "尹洁昕女，1989年8月出生于河南省郑州市.现为中国人民解放军战略支援部队信息工程大学信息系统工程学院副教授、硕士生导师.主要研究方向为无线信号定位、阵列信号处理. E-mail: Cindyin0807@163.com" ]
  [ "王鼎男，1982年10月出生于安徽省芜湖市.现为中国人民解放军战略支援部队信息工程大学信息系统工程学院副教授、博士生导师.主要研究方向为无线信号定位、阵列信号处理. E-mail: wang_ding814@aliyun.com" ]
  [ "杨欣女，1980年3月出生于河北省遵化市.现为郑州大学计算机与人工智能学院副教授、硕士生导师.主要研究方向数据科学和人工智能. E-mail: 416469463@qq.com" ]
  [ "杨宾男，1974年11月出生于江西省南昌市.现为中国人民解放军战略支援部队信息工程大学信息系统工程学院教授、博士生导师.主要研究方向为无线电频谱监测." ]
- 基金信息：
  
  国家自然科学基金(61901526;62171469;62071029);军事科技领域青年人才托举工程(2022-JCJQ-QT-028);全军共用信息系统装备预先研究专用技术项目(315087701)
- DOI：10.12263/DZXB.20230525
  中图分类号： TN911.7
- 收稿：2023-06-08，
  
  修回：2024-01-01，
  
  纸质出版：2024-04-25
- 稿件说明：
移动端阅览
尹洁昕,王鼎,杨欣,等.模型误差影响下基于CNN+BiLSTM神经网络的非圆信号目标直接跟踪算法[J].电子学报,2024,52(04):1315-1329.

YIN Jie-xin, WANG Ding, YANG Xin, et al.Direct Tracking for a Non-Circular Source Based on CNN+BiLSTM Neural Network in the Presence of Modeling Errors[J].Acta Electronica Sinica, 2024, 52(04): 1315-1329.
尹洁昕,王鼎,杨欣,等.模型误差影响下基于CNN+BiLSTM神经网络的非圆信号目标直接跟踪算法[J].电子学报,2024,52(04):1315-1329. DOI：10.12263/DZXB.20230525

YIN Jie-xin, WANG Ding, YANG Xin, et al.Direct Tracking for a Non-Circular Source Based on CNN+BiLSTM Neural Network in the Presence of Modeling Errors[J].Acta Electronica Sinica, 2024, 52(04): 1315-1329. DOI：10.12263/DZXB.20230525

摘要

针对运动观测阵列状态误差与接收频率抖动同时影响下的非圆信号无源跟踪问题，提出了一种基于卷积神经网络（Convolutional Neural Network，CNN）+双向长短时记忆网络（Bi-directional Long Short-Term Memory，BiLSTM）的直接跟踪算法.该算法首先利用多运动观测阵列信号各频带间的相关性与辐射源信号的非圆特性，建立模型误差影响下的扩展多站观测矢量；接着利用多个观测时隙内扩展多站观测矢量的信号子空间构造空时特征输入序列；然后设计基于CNN与BiLSTM混合神经网络的直接跟踪模型，通过训练实现对非圆目标的轨迹矢量直接估计.本文算法是从原始数据信号子空间中估计轨迹矢量的直接跟踪模式，相比传统“观测参数估计+滤波轨迹跟踪”的两步估计模式，具有更高的估计精度.由于本文算法在神经网络训练过程中学习到模型误差的信息，因此能够实现对多种误差的校正.仿真结果表明，本文算法较传统两步跟踪算法与现有直接跟踪算法均具有更高的轨迹估计精度，能够明显提升模型误差影响下多站协同跟踪的鲁棒性.

Abstract

In order to track a non-circular source target under the influence of both the state errors of moving observer arrays and frequency jitter deviations

this paper proposes a direct tracking algorithm based on the CNN (Convolutional Neural Network) + BiLSTM (Bi-directional Long Short-Term Memory) neural network. The proposed algorithm first exploits the correlation between the received array signals of multiple moving observers in various frequency bands and the non-circular property of the radiation source signals. Therefore

an extended multi-station observation vector is established in the presence of modeling errors. Then

the non-circular signal subspaces of the extended multi-station observation vectors within multiple observing timeslots are used to form the spatiotemporal feature input sequence. Subsequently

the direct tracking model for a non-circular source target based on CNN and BiLSTM neural network is designed. After training this neural network

the trajectory vector for a non-circular source target in several timeslots can be directly determined. Because the proposed algorithm estimates the target trajectory vector directly from the subspaces of the original array signals

it has higher estimation accuracy compared to the traditional two-step tracking methods which extract measurement parameters and then estimate the trajectory from them. As the information of modeling errors can be learned from training the neural network

this algorithm can achieve the calibration for modeling errors. The simulation results show that the proposed algorithm has higher trajectory estimation accuracy compared to the traditional two-step tracking algorithm and existing direct tracking algorithm. It significantly improves the robustness of multi-station collaborative tracking under the influence of modeling errors.

关键词

Keywords

references

黄亮 , 刘忠 , 石章松 , 等 . 无人机系统纯方位定位技术及应用 [M ] . 北京 : 国防工业出版社 , 2015 .

王鼎 , 吴瑛 , 张莉 , 等 . 无线电测向与定位理论及方法 [M ] . 北京 : 国防工业出版社 , 2016 .

朱建丰 , 陈玥 , 郝本建 , 等 . 基于合成孔径阵列的雷达辐射源被动定位技术研究 [J ] . 电子学报 , 2017 , 45 ( 10 ): 2332 - 2336 .

ZHU J F , CHEN Y , HAO B J , et al . Passive radar source localization using synthetic aperture antenna array [J ] . Acta Electronica Sinica , 2017 , 45 ( 10 ): 2332 - 2336 . (in Chinese)

王鼎 , 尹洁昕 , 张欣光 , 等 . 一种基于加权多维标度分析的多个非相关源TDOA/FDOA协同定位方法 [J ] . 航空学报 , 2023 , 44 ( 7 ): 222 - 245 .

WANG D , YIN J X , ZHANG X G , et al . A TDOA/FDOA cooperative localization method for multiple disjoint sources based on weighted multidimensional scaling analysis [J ] . Acta Aeronautica et Astronautica Sinica , 2023 , 44 ( 7 ): 222 - 245 . (in Chinese)

徐美玲 . 无人机速度与姿态角瞬态控制技术研究 [D ] . 成都 : 电子科技大学 , 2014 .

XU M L . The Transient Control Research on the UAV Speed and Attitude Angle [D ] . Chengdu : University of Electronic Science and Technology of China , 2014 . (in Chinese)

WANG D , YIN J X , CHEN X , et al . Direct position determination of multiple constant modulus sources based on direction of arrival and Doppler frequency shift [J ] . Circuits, Systems and Signal Processing , 2020 , 39 ( 1 ): 268 - 306 .

HO K C , XU W . An accurate algebraic solution for moving source location using TDOA and FDOA measurements [J ] . IEEE Transactions on Signal Processing , 2004 , 52 ( 9 ): 2453 - 2463 .

LIU Z X , HU D X , ZHAO Y J , et al . Computationally efficient TDOA, FDOA and differential Doppler rate estimation algorithm for passive emitter localization [J ] . Digital Signal Processing , 2020 , 96 : 102598 .

YU H G , HUANG G M , GAO J , et al . An efficient constrained weighted least squares algorithm for moving source location using TDOA and FDOA measurements [J ] . IEEE Transactions on Wireless Communications , 2012 , 11 ( 3 ): 44 - 47 .

YU H G , HUANG G M , GAO J . Practical constrained least-square algorithm for moving source location using TDOA and FDOA measurements [J ] . Journal of Systems Engineering and Electronics , 2012 , 23 ( 4 ): 488 - 494 .

YI Q F , GUO F C , MENG X W , et al . Constrained location algorithms based on total least squares method using TDOA and FDOA measurements [C ] // 2012 IET International Conference on Automatic Control and Artificial Intelligence . London : IET , 2012 : 2587 - 2590 .

ZHANG F R , SUN Y M , WAN Q . Calibrating the error from sensor position uncertainty in TDOA-AOA localization [J ] . Signal Processing , 2020 , 166 : 1 - 16 .

CHEN X , WANG D , YIN J X , et al . Bias reduction for TDOA localization in the presence of receiver position errors and synchronization clock bias [J ] . EURASIP Journal on Advances in Signal Processing , 2019 , 7 : 1 - 26 .

孙霆 , 董春曦 . 传感器参数误差下的运动目标TDOA/FDOA无源定位算法 [J ] . 航空学报 , 2020 , 41 ( 2 ): 257 - 266 .

SUN T , DONG C X . TDOA/FDOA passive localization algorithm for moving target with sensor parameter errors [J ] . Acta Aeronautica et Astronautica Sinica , 2020 , 41 ( 2 ): 257 - 266 . (in Chinese)

WANG D , YIN J X , TANG T , et al . Quadratic constrained weighted least-squares method for TDOA source localization in the presence of clock synchronization bias Analysis and solution [J ] . Digital Signal Processing , 2018 , 82 ( 11 ): 237 - 257 .

TIAN Z W , LIU W F , RU X F . Multi-target localization and tracking using TDOA and AOA measurements based on Gibbs-GLMB filtering [J ] . Sensors , 2019 , 19 ( 24 ): 5437 .

JING T , TIAN W , HUANG G M . TDOA-based adaptive observer trajectory optimization algorithm for tracking in passive coherent location system [J ] . The Journal of Engineering , 2019 ( 20 ): 6863 - 6867 .

AMAR A , WEISS A J . Localization of narrowband radio emitters based on Doppler frequency shifts [J ] . IEEE Transactions on Signal Processing , 2008 , 56 ( 11 ): 5500 - 5508 .

MA F H , LIU Z M , GUO F C . Direct position determination in asynchronous sensor networks [J ] . IEEE Transactions on Vehicular Technology , 2019 , 68 ( 9 ): 8790 - 8803 .

KULIKOV G Y , KULIKOVA M V . Accurate continuous-discrete unscented Kalman filtering for estimation of nonlinear continuous-time stochastic models in radar tracking [J ] . Signal Processing , 2017 , 139 : 25 - 35 .

KULIKOV G Y , KULIKOVA M V . Estimation of maneuvering target in the presence of non-Gaussian noise: A coordinated turn case study [J ] . Signal Processing , 2018 , 145 : 241 - 257 .

SIDI A Y , WEISS A J . Delay and Doppler induced direct tracking by particle filter [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2014 , 50 ( 1 ): 559 - 572 .

逯志宇 , 巴斌 , 任衍青 , 等 . 基于进化粒子滤波的数据域直接跟踪方法 [J ] . 系统工程与电子技术 , 2018 , 40 ( 5 ): 968 - 975 .

LU Z Y , BA B , REN Y Q , et al . Direct trajectory determination algorithm based on evolutionary particle filter [J ] . Systems Engineering and Electronics , 2018 , 40 ( 5 ): 968 - 975 . (in Chinese)

YIN J X , WANG D , WU Y , et al . ML-based single-step estimation of the locations of strictly noncircular sources [J ] . Digital Signal Processing , 2017 , 69 : 224 - 236 .

YIN J X , WANG D , NIE F Q , et al . Single‐step geolocation for a non-circular source in the presence of satellite orbit perturbations [J ] . IET Signal Processing , 2022 , 16 ( 2 ): 170 - 200 .

WANG D , YIN J X , CHEN X , et al . Direct position determination of multiple constant modulus sources based on direction of arrival and Doppler frequency shift [J ] . Circuits Systems and Signal Processing . 2020 , 39 ( 1 ): 268 - 306 .

BIALER O , RAPHAELI D , WEISS A J . Robust time-of-arrival estimation in multipath channels with OFDM signals [C ] // 2017 25th European Signal Processing Conference . Piscataway : IEEE , 2017 : 2724 - 2728 .

XIE J , WANG L , ZHANG W , et al . Direction finding algorithm for noncircular signals in the presence of unknown mutual coupling [C ] // 2018 USNC-URSI Radio Science Meeting . Piscataway : IEEE , 2018 : 47 - 48 .

LI Z , SHEN J , ZHAI H , et al . 3-D Localization for Near-Field and Strictly Noncircular Sources Via Centro-Symmetric Cross array [J ] . IEEE Sensors Journal , 2021 , 21 ( 6 ): 8432 - 8440 .

余婉婷 . 基于深度学习的机动目标轨迹跟踪关键技术研究 [D ] . 郑州 : 战略支援部队信息工程大学 , 2022 .

YU W T . Research on Key Technologies of Maneuvering Target Trajectory Tracking Based on Deep Learning [D ] . Zhengzhou : PLA Strategic Support Force Information Engineering University , 2022 . (in Chinese)

PICINBONO B . On circularity [J ] . IEEE Transactions on Signal Processing , 1994 . 24 ( 12 ): 3473 - 3482 .

ABEIDA H . Imagerie D'Antenne Pour Signaux Non Circulaires: Bornes de Performance et Algorithms [D ] . Orsay : Université Paris VI , 2006 .

ABEIDA H , J-P DELMAS . MUSIC-like estimation of direction of arrival for noncircular sources [J ] . IEEE Transactions on Signal Processing , 2006 , 54 ( 7 ): 2678 - 2690 .

ABEIDA H , J-P DELMAS . Statistical performance of MUSIC-like algorithms in resolving noncircular sources [J ] . IEEE Transactions on Signal Processing , 2008 , 56 ( 9 ): 4317 - 4329 .

张小飞 , 曾浩威 , 郑旺 , 等 . 多阵列中非圆信号借助于降维搜索和子空间数据融合的直接定位算法 [J ] . 数据采集与处理 , 2020 , 35 ( 6 ): 1022 - 1032 .

ZHANG X F , ZENG H W , ZHENG W , et al . Direct position determination of non-circular signals with multiple arrays by exploiting reduced-dimension finding and subspace data fusion [J ] . Journal of Data Acquisition and Processing , 2020 , 35 ( 6 ): 1022 - 1032 . (in Chinese)

逯志宇 , 王建辉 , 秦天柱 , 等 . 基于对称旋转不变性的非圆相干分布源直接定位算法 [J ] . 电子与信息学报 , 2019 , 41 ( 3 ): 537 - 543 .

LU Z Y , WANG J H , QIN T Z , et al . Direct position determination for coherently distributed noncircular source based on symmetric shift invariance [J ] . Journal of Electronics & Information Technology , 2019 , 41 ( 3 ): 537 - 543 . (in Chinese)

王永良 , 陈辉 , 彭应宁 . 空间谱估计理论与算法 [M ] . 北京 : 清华大学出版社 , 2005 .

吴瑛 , 张莉 , 张冬玲 . 数字信号处理 [M ] . 第二版 . 西安 : 西安电子科技大学出版社 , 2017 .

TIRER T , WEISS A J . High resolution localization of narrowband radio emitters based on Doppler frequency shifts [J ] . Signal Processing , 2017 , 141 : 288 - 298 .

CHEN Y , SUN J , LIN Y , et al . Hybrid N-inception-LSTM-based aircraft coordinate prediction method for secure air traffic [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 3 ): 2773 - 2783 .

CHEN X , WANG D , YIN J X , et al . A direct position-determination approach for multiple sources based on neural network computation [J ] . Sensors , 2018 , 18 ( 6 ): 1925 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于非一般类算子融合方法及硬件架构设计

共享超分的双分支遥感图像时空融合网络

基于轻量级全连接张量映射网络的高光谱图像分类方法

Cross-CNN：基于CNN和Transformer混合模型的动画跨帧线稿着色算法

基于边缘辅助和多尺度Transformer的无参考屏幕内容图像质量评估