面向能量差异混合信号的单通道盲源分离算法

doi:10.12305/j.issn.1001-506X.2023.10.35

摘要/Abstract

摘要：

针对不同源信号存在能量差异时的单通道盲源分离(single-channel blind source separation, SCBSS)问题, 提出一种面向能量差异混合信号的单通道盲源分离算法。首先, 针对能量差异信号的分解问题, 提出一种改进的变分模态分解算法, 设置谱相关系数和中心频率的双重门限, 明确该模态分量的来源, 对来自同一源信号的模态分量进行合并得到源信号对应的分量；然后, 将得到的信号分量与混合信号共同构成多通道信号; 最后利用多通道盲分离算法对源信号进行分离。仿真结果表明, 当信噪比满足一定条件时, 该算法能够有效地从频谱混叠的混合信号中分离出存在能量差异的多路源信号。

关键词: 单通道盲源分离, 能量差异, 变分模态分解

Abstract:

In order to solve the problem of single-channel blind source separation (SCBSS) when the different source signals have different energy, a single-channel blind source separation algorithm for mixed signals with different energy is proposed. Aiming at the decomposition problem of energy difference signal, an improved variational mode decomposition algorithm is proposed, which set the double threshold of spectral correlation coefficient and center frequency, identify the source of the modal component, and combine the modal components from the same source signal to obtain the corresponding component of the source signal. Secondly, the signal component and the mixed signal are combined to form the multi-channel signal. Finally, the multi-channel blind separation algorithm is used to separate the source signal. The simulation results show that when the signal-noise ratio meets certain conditions, the proposed algorithm can effectively separate the multi-channel signals with energy difference from the spectrum aliasing mixed signals.

Key words: single channel blind source separation (SCBSS), energy difference, variational mode decomposition

中图分类号:

TN911

付卫红, 周雨菲, 赵文胜. 面向能量差异混合信号的单通道盲源分离算法[J]. 系统工程与电子技术, 2023, 45(10): 3302-3311.

Weihong FU, Yufei ZHOU, Wensheng ZHAO. Single-channel blind source separation algorithm for energy differential mixed signals[J]. Systems Engineering and Electronics, 2023, 45(10): 3302-3311.

图/表 12

图1

表1

表2

表3

图2

表4

图3

图4

图5

图6

图7

图8

参考文献 31

1	HERAULT J, JUTTEN C. Space or time adaptive signal processing by neural network models[C]//Proc. of the AIP Confe-rence Proceedings, 1986: 206-211.
2	BELOUCHRANI A , ABED-MERAIM K , CARDOSO J F , et al. A blind source separation technique using second-order statistics[J]. IEEE Trans.on Signal Processing, 1997, 45 (2): 434- 444. doi: 10.1109/78.554307
3	BAI X W , FU W H , ZHOU C H , et al. Mixing matrix estimation algorithm for time-varying radar signals in a dynamic system under UBSS model[J]. Circuits, Systems, and Signal Processing, 2021, 40 (6): 3075- 3098. doi: 10.1007/s00034-020-01614-4
4	WEI L L , LIU Y S , CHENG D F . A novel partial discharge ultra-high frequency signal de-noising method based on a single channel blind source separation algorithm[J]. Electronics Newsweekly, 2018, 11 (3): 509- 516.
5	HOPGOOD J R , RAYNER P J . Single channel nonstationary stochastic signal separation using linear time-varying filters[J]. IEEE Trans.on Signal Processing, 2003, 51 (7): 1739- 1752. doi: 10.1109/TSP.2003.812837
6	DAVIES M E , JAMES C J . Source separation using single channel ICA[J]. Signal Processing, 2007, 87 (8): 1819- 1832. doi: 10.1016/j.sigpro.2007.01.011
7	ZHU H , ZHANG S N , ZHAO H C . Single-channel source se-paration of multi-component radar signal with the same genera-lized period using ICA[J]. Circuits, Systems, and Signal Processing, 2016, 35 (1): 353- 363. doi: 10.1007/s00034-015-0061-1
8	ALI S , KHAN N A , HANEEF M , et al. Blind source separation schemes for mono-sensor and multi-sensor systems with application to signal detection[J]. Circuits, Systems, and Signal Processing, 2017, 36 (11): 4615- 4636. doi: 10.1007/s00034-017-0533-6
9	ZHAO M C , YAO X J , WANG J , et al. Single-channel blind source separation of spatial aliasing signal based on Stacked-TCN[J]. Sensors (Basel), 2021, 21 (14): 4844. doi: 10.3390/s21144844
10	OLIVEIRA D R D , LIMA M A A , SILVA L R M , et al. Se-cond order blind identification algorithm with exact model order estimation for harmonic and interharmonic decomposition with reduced complexity[J]. International Journal of Electrical Power and Energy Systems, 2021, 125, 106415. doi: 10.1016/j.ijepes.2020.106415
11	PANG L H , DENG X R . A SCBSS methodology for time-frequency overlapped signals using non-negative matrix factorization[J]. International Journal of Electronics, 2016, 104 (4): 624- 634.
12	HUANG N E , SHEN Z , LONG S R , et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 1998, 454 (1971): 903- 995. doi: 10.1098/rspa.1998.0193
13	GAO B , WOO W L , DLAY S S . Single-channel source separation using EMD-subband variable regularized sparse features[J]. IEEE Trans.on Audio, Speech, and Language Processing, 2011, 19 (4): 961- 976. doi: 10.1109/TASL.2010.2072500
14	PRASANNA KUMAR M K , KUMARASWAMY R . Single-channel speech separation using combined EMD and speech-specific information[J]. International Journal of Speech Technology, 2017, 20 (4): 1037- 1047. doi: 10.1007/s10772-017-9468-3
15	YUE G , LI X , CHEN S Y , et al. An automatic ocular artifacts removal approach for multi-channel EEG data based on NMF and EMD[J]. Journal of Neural Engineering, 2021, 18 (5): 6012- 6017.
16	WU Z , HUANG N E . Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1 (1): 1- 41. doi: 10.1142/S1793536909000047
17	SHANG H K , LO K L , LI F . Partial discharge feature extraction based on ensemble empirical mode decomposition and sample entropy[J]. Entropy, 2017, 19 (9): 439- 456. doi: 10.3390/e19090439
18	SONG H L , DONG H B , YUAN Z W , et al. An EEMD-based electromagnetic induction method for nondestructive testing of buried metal conductors[J]. IEEE Access, 2019, 7 (1): 142261- 142271.
19	LIU X L , WANG H , HUANG Y M . A SCBSS signal de-noising method of integrating EEMD and ESMD for dynamic deflection of bridges using GBSAR[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14, 2845- 2856. doi: 10.1109/JSTARS.2021.3061543
20	ZHAO L H , HONG G , WANG Z L , et al. Research on fault vibration signal features of GIS disconnector based on EEMD and kurtosis criterion[J]. IEEJ Trans.on Electrical and Electronic Engineering, 2021, 16 (5): 677- 686. doi: 10.1002/tee.23347
21	DRAGOMIRETSKIY K , ZOSSO D . Variational mode decomposition[J]. IEEE Trans.on Signal Processing, 2013, 62 (3): 531- 544.
22	ZHANG Y N , QI S B , ZHOU L . Single channel blind source separation for wind turbine aeroacoustics signals based on variational mode decomposition[J]. IEEE Access, 2018, 6 (1): 73952- 73964.
23	BHATTACHARJEE A , FATTAH S A , ZHU W P , et al. VMD-RiM: Rician modeling of temporal feature variation extracted from variational mode decomposed EEGs signal for automatic sleep apnea detection[J]. IEEE Access, 2018, 6 (1): 77440- 77453.
24	WANG R , XU L , LIU F K . Bearing fault diagnosis based on improved VMD and DCNN[J]. Journal of Vibro-engineering, 2020, 22 (5): 1055- 1068. doi: 10.21595/jve.2020.21187
25	PANG L H , TANG B . Wavelet FastICA based separation method for single-channel and time-frequency overlapped signal in electromagnetic surveillance[J]. International Journal of Information and Communication Technology, 2017, 11 (2): 187- 201. doi: 10.1504/IJICT.2017.086248
26	ZHAO Z J , HUANG Y B . Single-channel blind-source separation algorithm based on wavelet packet decomposition[J]. Communications Technology, 2017, 50 (3): 425- 429. doi: 10.3969/j.issn.1002-0802.2017.03.007
27	CHEN C, LU Z F, GUO Z F, et al. Deep learning based single-channel blind separation of co-frequency modulated signals[C]// Proc. of the International Conference on Communications and Networking, 2019: 607-618.
28	LUO Y, CHEN Z, YOSHIOKA T. Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation[C]//Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2020: 46-50.
29	WU S Y , GAO Y . Single-channel blind separation combined with deep recurrent neural network[J]. Radio Engineering, 2021, 51 (7): 563- 567. doi: 10.3969/j.issn.1003-3106.2021.07.008
30	GUO Y M , PENG H , YANG Y . Blind separation algorithm for non-cooperative PCMA signal based on feedforward neural network[J]. Tien Tzu Hsueh Pao/acta Electronica Sinica, 2019, 47 (2): 302- 307.
31	CARDOSO J F , LAHELD B H . Equivariant adaptive source separation[J]. IEEE Trans.on Signal Processing, 1996, 44 (12): 3017- 3030. doi: 10.1109/78.553476

源信号s_i(t)	幅度	滚降系数$\tilde{\alpha}$	低通采样频率F_s₁/MHz	符号速率R_b/(bit/s)	载频f_i/MHz
s₁(t)	1	0.5	20	200×10³	5
s₂(t)	3	0.5	20	200×10³	5.2

上边频f_l/MHz	下边频f_r/MHz	分界频率f_m/MHz	f_l到f_m之间频谱平均值${\bar F}$₁	f_m到f_r之间频谱平均值${\bar F}$₂	能量比$L=\frac{\bar{F}_2}{\bar{F}_1}$	能量较大信号频率范围Δf_max/MHz	能量较小信号频率范围Δf_min/MHz
4.89	5.32	5.11	63.56	180.62	3	[5.11, 5.32]	[4.89, 5.11]

参数	1	2	3	4
谱相关系数ρ_i	0.094 0	0.363 2	0.396 9	0.362 2
中心频率f_{c_i}′/MHz	4.99	5.14	5.20	5.26

信号类型	源信号s₁(t)	源信号s₂(t)
估计信号y₁(t)	0.838 5	0.047 8
估计信号y₂(t)	0.030 5	0.947 1

[1]	王磊, 张志勇, 胥辉旗, 曾维贵, 曹司磊. 基于VMD分解和多域联合分布的雷达辐射源识别[J]. 系统工程与电子技术, 2023, 45(8): 2479-2488.
[2]	彭正红, 杨德贵, 王行, 王浩, 朱政亮. 基于趋势估计的微多普勒分离与特征提取算法[J]. 系统工程与电子技术, 2021, 43(12): 3452-3461.
[3]	李亚兰, 金炜东, 葛鹏. 基于VMD和特征融合的辐射源信号识别[J]. 系统工程与电子技术, 2020, 42(7): 1499-1503.
[4]	方章闻, 张金艺, 李科, 姜玉稀. 小样本条件下的通信辐射源半监督特征提取[J]. 系统工程与电子技术, 2020, 42(10): 2381-2389.