气动目标多频点调制谱融合增强识别方法

doi:10.12305/j.issn.1001-506X.2023.07.14

摘要/Abstract

摘要：

预警雷达探测过程中气动目标微动回波能量弱导致识别性能不稳定。针对该问题, 提出一种基于稀疏约束非负矩阵分解(sparse constrained non-negative matrix factorization, SCNMF)和集成极限学习机(integrated extreme learning machine, IELM)的多频点调制谱融合增强识别方法。通过分析微动部件回波特性, 对多频点频域幅度谱进行SCNMF处理实现像素级融合得到特征增强后的稀疏调制谱, 并将其作为样本输入IELM, 实现气动目标类型识别。仿真和实测数据表明, 本文方法能够有效融合多频点微动特征, 具有抗噪能力强、所需训练样本少和识别性能稳健等优势。

关键词: 调制谱, 气动目标, 稀疏约束非负矩阵分解, 集成极限学习机

Abstract:

To solve the problem of unstable recognition performance caused by weak energy of aircraft fretting echo in early warning radar detection process, a multi-frequency modulation spectrum fusion and enhanced recognition method combining sparse constrained non-negative matrix factorization (SCNMF) and integrated extreme learning machine (IELM) is proposed.By analyzing the echo frequency domain characteristics of the micro-motion parts, SCNMF is performed on the modulation spectrum of multi-frequency to achieve pixel-level fusion and obtain the enhanced sparse modulation spectrum, which is input into IELM as a sample to achieve pneumatic target classification. Simulation and measured data verify that the proposed method can effectively integrate multi-frequency micro-motion features, and has the advantages of strong anti-noise ability, fewer training samples and robust recognition performance.

Key words: modulation spectrum, pneumatic target, sparse constrained non-negative matrix factorization, integrated extreme learning machine (IELM)

中图分类号:

TN95

赵庆媛, 赵志强, 叶春茂, 鲁耀兵. 气动目标多频点调制谱融合增强识别方法[J]. 系统工程与电子技术, 2023, 45(7): 2043-2050.

Qingyuan ZHAO, Zhiqiang ZHAO, Chunmao YE, Yaobing LU. Multi-frequency modulation spectrum fusion enhanced recognition method for pneumatic targets[J]. Systems Engineering and Electronics, 2023, 45(7): 2043-2050.

图/表 10

图1

图2

表1

图3

图4

表2

图5

图6

表3

图7

参考文献 32

1	CHEN V C , LI F , HO S S , et al. Micro-Doppler effect in radar: phenomenon model and simulation study[J]. IEEE Trans.on Aerospace and Electronic Systems, 2006, 42 (1): 2- 21.
2	XIA S Q , ZHANG C W , CAI W Y , et al. Aircraft target classification method for conventional narrowband radar based on micro-Doppler effect[J]. Mathematical Problems in Engineering, 2022, 2022, 3154854.
3	唐明磊, 张文鹏, 姜卫东, 等. 基于多分辨率显著性滤波的微动信号增强方法[J]. 系统工程与电子技术, 2022, 44 (4): 1148- 1157.
	TANG M L , ZHANG W P , JIANG W D , et al. Micro-motion signal enhancement method based on multi-resolution saliency filtering[J]. Systems Engineering and Eletronics, 2022, 44 (4): 1148- 1157.
4	ZHANG Y D, XIANG X, LI Y, et al. Enhanced micro-Doppler feature analysis for drone detection[C]//Proc. of the IEEE Radar Conference, 2021.
5	黄璟, 肖志河, 任红梅. 窄带相参雷达调制谱超分辨处理方法[J]. 系统工程与电子技术, 2010, 32 (9): 1894- 1897.
	HUANG J , XIAO Z H , REN H M . Super-resolution processing of coherent narrowband radar for modulation spectrum[J]. Systems Engineering and Electronics, 2010, 32 (9): 1894- 1897.
6	RITCHIE M , FIORANELLI F . Multistatic micro-Doppler radar feature extraction for classification of unloaded/loaded micro-drones[J]. IET Radar, Sonar & Navigation, 2017, 11 (1): 116- 124.
7	CHEN Z X , LI G , FIORANELLI F , et al. Personnel recognition and gait classification based on multistatic micro-Doppler signatures using deep convolutional neural networks[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (5): 669- 673. doi: 10.1109/LGRS.2018.2806940
8	章鹏飞, 李刚, 霍超颖, 等. 基于双雷达微动特征融合的无人机分类识别[J]. 雷达学报, 2018, 7 (5): 557- 564.
	ZHANG P F , LI G , HUO C Y , et al. Classification of drones based on micro-Doppler radar signatures using dual radar sensors[J]. Journal of Radars, 2018, 7 (5): 557- 564.
9	CAI H , LIU B , XIAO Y S , et al. Semi-supervised multi-view clustering based on orthonormality-constrained nonnegative matrix factorization[J]. Information Sciences, 2020, 536 (10): 171- 184.
10	ELOSUA-BAYES M , NIETO P , MEREU E , et al. SPOTlight: seeded NMF regression to deconvolute spatial transcriptomics spots with single-cell transcriptomes[J]. Nucleic Acids Research, 2021, 49 (9): e50. doi: 10.1093/nar/gkab043
11	LEPLAT V , GILLIS N , ANG A . Blind audio source separation with minimum-volume beta-divergence NMF[J]. IEEE Trans.on Signal Processing, 2020, 68, 3400- 3410. doi: 10.1109/TSP.2020.2991801
12	LEE S , PANG H S . Feature extraction based on the non-negative matrix factorization of convolutional neural networks for monitoring domestic activity with acoustic signals[J]. IEEE Access, 2020, 8, 122384- 122395.
13	韦娟, 杨皇卫, 宁方立. 基于NMF与CNN联合优化的声学场景分类[J]. 系统工程与电子技术, 2022, 44 (5): 1433- 1438.
	WEI J , YANG H W , NING F L . Acoustic scene classification based on joint optimization of NMF and CNN[J]. Systems Engineering and Electronics, 2022, 44 (5): 1433- 1438.
14	LEE D D , SEUNG H S . Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401 (6755): 788- 791.
15	LEE D D, SEUNG H S. Algorithms for non-negative matrix factorization[C]//Proc. of the Conference on Advances in Neural Information Processing Systems, 2001: 556-562.
16	LIN C J . Projected gradient methods for nonnegative matrix factorization[J]. Neural Computation, 2007, 19 (10): 2756- 2779.
17	CAI D, HE X F, WU X Y, et al. Non-negative matrix factori-zation on manifold[C]//Proc. of the 8th IEEE International Conference on Data Mining, 2008: 63-72.
18	LIU W X, ZHENG N N, LU X F. Non-negative matrix factori -zation for visual coding[C]//Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003, 3: 293-296.
19	HOYER P O . Nonnegative matrix factorization with sparseness constraints[J]. Journal of Machine Learning Research, 2004, 5 (9): 1457- 1469.
20	QIAN Y T , JIA S , ZHOU J , et al. Hyperspectral unmixing via L_1/2 sparsity constrained nonnegative matrix factorization[J]. IEEE Trans.on Geoscience and Remote Sensing, 2011, 49 (11): 4282- 4297.
21	许然, 李亚超, 邢孟道. 利用稀疏非负矩阵分解的大转角SAR成像方法[J]. 西安电子科技大学学报, 2014, 41 (3): 49- 55.
	XU R , LI Y C , XING M D . Wide angle SAR imaging via sparse non-negative matrix factorization[J]. Journal of Xidian University, 2014, 41 (3): 49- 55.
22	HUANG G B , ZHU Q Y , SIEW C K . Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70 (1/3): 489- 501.
23	WANG J , LU S Y , WANG S H , et al. A review on extreme learning machine[J]. Multimedia Tools and Applications, 2022, 81, 41611- 41660.
24	AFZA F , SHARIF M , KHAN M A , et al. Multiclass skin lesion classification using hybrid deep features selection and extreme learning machine[J]. Sensors, 2022, 22 (3): 799.
25	MANOHARAN J S . Study of variants of extreme learning machine (ELM) brands and its performance measure on classification algorithm[J]. Journal of Soft Computing Paradigm, 2021, 3 (2): 83- 95.
26	AL-DHIEF F T , BAKI M M , LATIFFL N , et al. Voice pathology detection and classification by adopting online sequential extreme learning machine[J]. IEEE Access, 2021, 9, 77293- 77306.
27	KHAN M A, KADRY S, PARWEKAR P, et al. Human gait analysis for osteoarthritis prediction: a framework of deep learning and kernel extreme learning machine[J/OL]. Complex & Intelligent Systems, 2021.http://link.springer.com/artide/10.1007/s40747-020-00244-2.[2022-08-11].
28	BHATTI Y K , JAMIL A , NIDA N , et al. Facial expression recognition of instructor using deep features and extreme learning machine[J]. Computational Intelligence and Neuroscience, 2021, 2021, 5570870.
29	HU T , KHISHE M , MOHAMMADI M , et al. Realtime COVID-19 diagnosis from X-Ray images using deep CNN and extreme learning machines stabilized by chimp optimization algorithm[J]. Biomedical Signal Processing and Control, 2021, 68, 102764.
30	NAHIDUZZAMAN M , GONI M O F , ANOWER M S , et al. A novel method for multivariant pneumonia classification based on hybrid CNN-PCA based feature extraction using extreme learning machine with CXR images[J]. IEEE Access, 2021, 9, 147512- 147526.
31	LADDADA S , SI-CHAIB M O , BENKEDJOUH T , et al. Tool wear condition monitoring based on wavelet transform and improved extreme learning machine[J]. Journal of Mechanical Engineering Science, 2020, 234 (5): 1057- 1068.
32	TSAO J , STEINBERG B D . Reduction of sidelobe and speckle artifacts in microwave imaging: the CLEAN technique[J]. IEEE Trans.on Antennas and Propagation, 1988, 36 (4): 543- 556.

参数	目标
参数	目标1	目标2	目标3
桨叶数	3	4	38
L₁/m	0	0	0.38
L₂/m	5.345	1.8	0.6
w_r/rps	7~8	18~21	55~60

序号	方法	准确率
序号	方法	最小	最大	平均
1	单频点+BP	72.5	79.0	76.6
2	GLRT+BP	75.4	86.7	81.4
3	SCNMF+BP	82.0	90.5	85.4
4	单频点+PCA+SVM^[8]	75.0	80.5	77.7
5	GLRT++PCA+SVM^[8]	76.8	89.1	82.3
6	SCNMF+PCA+SVM^[8]	85.5	93.0	87.9
7	单频点+ELM	70.0	83.5	82.4
8	GLRT+ELM	72.3	90.4	86.4
9	SCNMF+ELM	80.5	96.5	90.6
10	单频点+IELM	81.5.0	84.0	83.1
11	GLRT+IELM	85.9	91.5	87.6
12	SCNMF+IELM	90.5	96.5	93.2

方法	平均准确率
方法6	85.2
方法10	79.3
方法11	80.9
方法12	89.6

[1]	赵庆媛, 赵志强, 叶春茂, 鲁耀兵. 基于自注意力的双波段预警雷达微动融合识别[J]. 系统工程与电子技术, 2023, 45(3): 708-716.
[2]	赵庆媛, 赵志强, 叶春茂, 鲁耀兵. 基于调制谱超分辨重构的微多普勒参数估计[J]. 系统工程与电子技术, 2023, 45(2): 407-415.
[3]	黄璟，肖志河，任红梅. 窄带相参雷达调制谱超分辨处理方法[J]. Journal of Systems Engineering and Electronics, 2010, 32(9): 1894-1897.