基于阵列的神经网络水声通信信号多参数联合估计算法

成乐; 刘悦; 胡正良; 朱宏娜; 罗斌

doi:10.11959/j.issn.1000-436x.2025017

您当前的位置：

首页 >

文章列表页 >

基于阵列的神经网络水声通信信号多参数联合估计算法

学术论文 | 更新时间：2025-02-13

- 基于阵列的神经网络水声通信信号多参数联合估计算法
- Array-based neural network algorithm for multi-parameter joint estimation of underwater acoustic communication signals
- 通信学报 2025年46卷第1期页码：67-78
- 作者机构：
  
  1.西南交通大学信息科学与技术学院，四川成都 610031
  2.国防科技大学气象海洋学院，湖南长沙 410073
- 作者简介：
  
  [ "成乐（1996- ），男，湖南怀化人，西南交通大学博士生，主要研究方向为通信信号检测、阵列信号处理、神经网络等。" ]
  [ "刘悦（1991- ），男，湖北荆门人，国防科技大学博士生，主要研究方向为光纤传感、阵列信号处理等。" ]
  [ "胡正良（1975- ），男，湖南长沙人，国防科技大学教授、硕士生导师，主要研究方向为光纤传感、声信号处理等。" ]
  [ "朱宏娜（1979- ），女，山东烟台人，西南交通大学教授、博士生导师，主要研究方向为光纤通信、机器学习及智能信息处理等。" ]
  罗斌（1968- ），男，四川成都人，西南交通大学教授、博士生导师，主要研究方向为光纤通信、光电子技术等。
- 基金信息：
  
  国家重点研发计划基金资助项目(2021YFC3101402;SQ2021YFF0500035)
- DOI：10.11959/j.issn.1000-436x.2025017
  中图分类号： TN911.7
- 收稿：2024-09-03，
  
  修回：2024-12-30，
  
  纸质出版：2025-01-25
- 稿件说明：
移动端阅览
成乐,刘悦,胡正良等.基于阵列的神经网络水声通信信号多参数联合估计算法[J].通信学报,2025,46(01):67-78.

CHENG Le,LIU Yue,HU Zhengliang,et al.Array-based neural network algorithm for multi-parameter joint estimation of underwater acoustic communication signals[J].Journal on Communications,2025,46(01):67-78.
成乐,刘悦,胡正良等.基于阵列的神经网络水声通信信号多参数联合估计算法[J].通信学报,2025,46(01):67-78. DOI： 10.11959/j.issn.1000-436x.2025017.

CHENG Le,LIU Yue,HU Zhengliang,et al.Array-based neural network algorithm for multi-parameter joint estimation of underwater acoustic communication signals[J].Journal on Communications,2025,46(01):67-78. DOI： 10.11959/j.issn.1000-436x.2025017.

摘要

针对水声信道复杂多变且衰减严重等问题，为提升非合作条件下水声通信信号的检测概率并扩大感知范围，设计了一种新型基于阵列多通道时频谱输入的神经网络多参数联合估计算法。该算法通过引入载波频率标签分配策略，将载波频率作为区分不同信号的关键物理特征，有效避免了频带外信号和噪声的干扰；利用端到端的多任务学习，能够同时完成信号检测、调制模式识别，以及对信号个数、载波频率、带宽和波达方向的联合估计，从而避免了传统算法中需要先进行波束成形再进行检测识别的复杂流程。仿真实验结果表明，在阵列阵元位置失配和信号被噪声掩蔽的情况下，所提算法仍能实现准确的信号估计。进一步的湖上实验验证了所提算法的实用性和泛化能力。

Abstract

To address the challenges posed by complex and highly variable underwater acoustic channel (UWAC) with severe attenuation

a novel neural network algorithm was proposed for multi-parameter joint estimation. Multi-channel spectrograms derived from array signals were utilized by the algorithm to improve the detection probability of UWAC signals under non-cooperative conditions and extend the sensing range. A carrier frequency label assignment strategy was designed

in which carrier frequency served as the key physical feature to distinguish different signals

thereby effectively mitigating interference from out-of-band signals and noise. End-to-end multi-task learning was adopted to simultaneously perform signal detection

modulation recognition

and joint estimation of the number of signal sources

carrier frequency

bandwidth

and direction of arrival

eliminating the complex beamforming process typically required in traditional methods before detection and recognition. Simulation results confirm that accurate signal estimation is reliably achieved even in the presence of array element position mismatches and when signals are obscured by noise. Lake experiments further demonstrate the practicality and generalization capability of the proposed algorithm.

关键词

Keywords

references

KULIN M , KAZAZ T , MOERMAN I , et al . End-to-end learning from spectrum data: a deep learning approach for wireless signal identification in spectrum monitoring applications [J ] . IEEE Access , 2018 , 6 : 18484 - 18501 .

KAPOOR S , SINGH G . Non-cooperative spectrum sensing: a hybrid model approach [C ] // Proceedings of the 2011 International Conference on Devices and Communications (ICDeCom) . Piscataway : IEEE Press , 2011 : 1 - 5 .

BARTLETT M S . Properties of sufficiency and statistical tests [J ] . Proceedings of the Royal Society Series A-Mathematical and Physical Sciences , 1937 , 160 ( 901 ): 268 - 282 .

CAPON J . High-resolution frequency-wavenumber spectrum analysis [J ] . Proceedings of the IEEE , 1969 , 57 ( 8 ): 1408 - 1418 .

SCHMIDT R . Multiple emitter location and signal parameter estimation [J ] . IEEE Transactions on Antennas and Propagation , 1986 , 34 ( 3 ): 276 - 280 .

周鑫 , 何晓新 , 郑昌文 . 基于图像深度学习的无线电信号识别 [J ] . 通信学报 , 2019 , 40 ( 7 ): 114 - 125 .

ZHOU X , HE X X , ZHENG C W . Radio signal recognition based on image deep learning [J ] . Journal on Communications , 2019 , 40 ( 7 ): 114 - 125 .

LI W H , WANG K R , YOU L , et al . A new deep learning framework for HF signal detection in wideband spectrogram [J ] . IEEE Signal Processing Letters , 2022 , 29 : 1342 - 1346 .

CHENG L , ZHU H N , HU Z L , et al . A sequence-to-sequence model for online signal detection and format recognition [J ] . IEEE Signal Processing Letters , 2024 , 31 : 994 - 998 .

ZHENG S L , YANG Z , SHEN W G , et al . Deep learning-based DOA estimation [J ] . IEEE Transactions on Cognitive Communications and Networking , 2024 , 10 ( 3 ): 819 - 835 .

PAPAGEORGIOU G K , SELLATHURAI M , ELDAR Y C . Deep networks for direction-of-arrival estimation in low SNR [J ] . IEEE Transactions on Signal Processing , 2021 , 69 : 3714 - 3729 .

WANG J J , QUAN T Q , JIAO L L , et al . DOA estimation of underwater acoustic array signal based on wavelet transform with double branch convolutional neural network [J ] . IEEE Transactions on Vehicular Technology , 2023 , 72 ( 5 ): 5962 - 5972 .

WU L L , HUANG Z T . Coherent SVR learning for wideband direction-of-arrival estimation [J ] . IEEE Signal Processing Letters , 2019 , 26 ( 4 ): 642 - 646 .

NIE W H , ZHANG X W , XU J , et al . Adaptive direction-of-arrival estimation using deep neural network in marine acoustic environment [J ] . IEEE Sensors Journal , 2023 , 23 ( 13 ): 15093 - 15105 .

CHENG L , LIU Y , ZHANG B B , et al . Direction of arrival joint prediction of underwater acoustic communication signals using faster R-CNN and frequency–azimuth spectrum [J ] . Remote Sensing , 2024 , 16 ( 14 ): 2563 .

NGUYEN T N T , WATCHARASUPAT K N , NGUYEN N K , et al . SALSA: spatial cue-augmented log-spectrogram features for polyphonic sound event localization and detection [J ] . IEEE/ACM Transactions on Audio , Speech and Language Processing, 2022 , 30 : 1749 - 1762 .

ADAVANNE S , POLITIS A , NIKUNEN J , et al . Sound event localization and detection of overlapping sources using convolutional recurrent neural networks [J ] . IEEE Journal of Selected Topics in Signal Processing , 2019 , 13 ( 1 ): 34 - 48 .

SCHYMURA C , BÖNNINGHOFF B , OCHIAI T , et al . PILOT: introducing transformers for probabilistic sound event localization [C ] // Proceedings of the 2021 Conference of the International Speech Communication Association . Piscataway : IEEE Press , 2021 : 2117 - 2121 .

CHAKRABARTY S , HABETS E A P . Multi-speaker DOA estimation using deep convolutional networks trained with noise signals [J ] . IEEE Journal of Selected Topics in Signal Processing , 2019 , 13 ( 1 ): 8 - 21 .

SUNDAR H , WANG W R , SUN M , et al . Raw waveform based end-to-end deep convolutional network for spatial localization of multiple acoustic sources [C ] // Proceedings of the ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE Press , 2020 : 4642 - 4646 .

HE Y , TRIGONI N , MARKHAM A . SoundDet: polyphonic moving sound event detection and localization from raw waveform [C ] // Proceedings of the 2021 International Conference on Machine Learning (ICLM) . Piscataway : IEEE Press , 2021 : 4160 - 4170 .

CHAKRABARTY S , HABETS E A P . Broadband DOA estimation using convolutional neural networks trained with noise signals [C ] // Proceedings of the 2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) . Piscataway : IEEE Press , 2017 : 136 - 140 .

DIAZ-GUERRA D , MIGUEL A , BELTRAN J R . Robust sound source tracking using SRP-PHAT and 3D convolutional neural networks [J ] . IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2020 , 29 : 300 - 311 .

COMANDUCCI L , BORRA F , BESTAGINI P , et al . Source localization using distributed microphones in reverberant environments based on deep learning and ray space transform [J ] . IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2020 , 28 : 2238 - 2251 .

VERA-DIAZ J M , PIZARRO D , MACIAS-GUARASA J . Towards domain independence in CNN-based acoustic localization using deep cross correlations [C ] // Proceedings of the 2020 28th European Signal Processing Conference (EUSIPCO) . Piscataway : IEEE Press , 2021 : 226 - 230 .

CONG J Y , WANG X P , HUANG M X , et al . Robust DOA estimation method for MIMO radar via deep neural networks [J ] . IEEE Sensors Journal , 2021 , 21 ( 6 ): 7498 - 7507 .

MERKOFER J P , REVACH G , SHLEZINGER N , et al . DA-MUSIC: data-driven DoA estimation via deep augmented MUSIC algorithm [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 2 ): 2771 - 2785 .

GUO Y , ZHANG Z , HUANG Y Z . Dual class token vision transformer for direction of arrival estimation in low SNR [J ] . IEEE Signal Processing Letters , 2023 , 31 : 76 - 80 .

OCHIAI T , DELCROIX M , NAKATANI T , et al . Mask-based neural beamforming for moving speakers with self-attention-based tracking [J ] . IEEE/ACM Transactions on Audio, Speech, and Language Processing , 2023 , 31 : 835 - 848 .

LIU Y , CHENG L , ZOU Y C , et al . Thin fiber-optic hydrophone towed array for autonomous underwater vehicle [J ] . IEEE Sensors Journal , 2024 , 24 ( 9 ): 15125 - 15132 .

浏览量

1655

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于子张量重构的宽带信号DOA估计

基于mRMR-GA的太赫兹信道场景识别研究

基于神经网络的恶意DNS流量检测方法

基于可见光和射频融合的通信定位一体化系统

基于特征依赖图的源代码漏洞检测方法