Recognition of dynamically varying PRI modulation via deep learning and recurrence plot

doi:10.23919/JSEE.2022.000071

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (4): 815-826.doi: 10.23919/JSEE.2022.000071

收稿日期:2021-03-12 出版日期:2023-08-18 发布日期:2023-08-28

Recognition of dynamically varying PRI modulation via deep learning and recurrence plot

Pengcheng WANG(), Weisong LIU(), Zheng LIU()

¹ College of Electronic Science and Technology, National University of Defense Technology, Changsha 410000, China

Received:2021-03-12 Online:2023-08-18 Published:2023-08-28
Contact: Zheng LIU E-mail:wangpencheng19@163.com;liuweisong15@nudt.edu.cn;liuzheng@nudt.edu.cn
About author:
WANG Pengcheng was born in 1998. He received his B.S. degree in the College of Communication Engineering from Jilin University in 2019. He is currently working toward his M.S. degree in the College of Communication Engineering, Jilin University, Jilin, China and the State Key Laboratory of Complex Electromagnetic Environment Effects of Electronic Information System, National University of Defense Technology, Changsha. His current research interests include data mining and radar signal processing. E-mail: wangpencheng19@163.com

LIU Weisong was born in 1993. He received his M.S. degree in information and communication engineering in 2015, from the College of Electronic Science and Engineering, National University of Defense Technology, Changsha, China. He is currently pursuing his Ph.D. degree in information and communication engineering with the State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology. His research interests include radar and communication signal processing, and deep learning. E-mail: liuweisong15@nudt.edu.cn

LIU Zheng was born in 1978. He received his Ph.D. degree from National University of Defense Technology in 2012, and now is a researcher and Ph.D. supervisor of the State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology. His research direction is intelligent electronic reconnaissance system and technology. E-mail: liuzheng@nudt.edu.cn
Supported by:
This work was supported by the National Defense Science and Technology Outstanding Youth Science Fund Project (2018-JCJQ-ZQ-023) and the Hunan Provincial Natural Science Foundation of Innovation Research Group Project (2019JJ10004).

摘要/Abstract

Abstract:

Recognition of pulse repetition interval (PRI) modulation is a fundamental task in the interpretation of radar intentions. However, the existing PRI modulation recognition methods mainly focus on single-label classification of PRI sequences. The prerequisite for the effectiveness of these methods is that the PRI sequences are perfectly divided according to different modulation types before identification, while the actual situation is that radar pulses reach the receiver continuously, and there is no completely reliable method to achieve this division in the case of non-cooperative reception. Based on the above actual needs, this paper implements an algorithm based on the recurrence plot technique and the multi-target detection model, which does not need to divide the PRI sequence in advance. Compared with the sliding window method, it can more effectively realize the recognition of the dynamically varying PRI modulation.

Key words: you look only once (YOLO), pulse repetition interval(PRI) modulation, recurrence plot

. [J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 815-826.

Pengcheng WANG, Weisong LIU, Zheng LIU. Recognition of dynamically varying PRI modulation via deep learning and recurrence plot[J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 815-826.

图/表 14

参考文献 32

1	NISHIGUCHI K, KOBAYASHI M Improved algorithm for estimating pulse repetition intervals. IEEE Trans. on Aerospace and Electronic Systems, 2000, 36 (2): 407- 421. doi: 10.1109/7.845217
2	GENCOL K, KARA A, AT N Improvements on deinterleaving of radar pulses in dynamically varying signal environments. Digital Signal Processing, 2017, 69, 86- 93. doi: 10.1016/j.dsp.2017.06.010
3	GENCOL K, AT N, KARA A A wavelet-based feature set for recognizing pulse repetition interval modulation patterns. Turkish Journal of Electrical Engineering & Computer Sciences, 2016, 24 (4): 3078- 3090.
4	KAUPPI J P, MARTIKAINEN K, RUOTSALAINEN U Hierarchical classification of dynamically varying radar pulse repetition interval modulation patterns. Neural Networks, 2010, 23 (10): 1226- 1237. doi: 10.1016/j.neunet.2010.06.008
5	SHI R, WU C Review on technology research about radar pulse signal deinterleaving based on PRI information. Telecommunication Engineering, 2020, 60 (1): 112- 120.
6	TORUN O, KOCAMIS M B, ABACI H, et al Deinterleaving of radar signals with stagger PRI and dwell-switch PRI types. Proc. of the IEEE 25th Signal Processing and Communications Applications Conference, 2017, 1- 4.
7	HASANI H, KHOSRAVI M R Pulse deinterleaving based on fusing PDWs and PRI extraction process for radar-assisted edge devices considering computational costs. EURASIP Journal on Wireless Communications and Networking, 2021, (1): 1- 14.
8	GUAN Y F, ZHANG G Y A radar emitter recognition method based on the PRI switching rules. Fire Control and Command Control, 2015, 40 (3): 79- 82.
9	LIU Z M Recognition of multifunction radars via hierarchically mining and exploiting pulse group patterns. IEEE Trans. on Aerospace and Electronic Systems, 2020, 56 (6): 4659- 4672. doi: 10.1109/TAES.2020.2999163
10	RICHARD G, WILEY E. The interception and analysis of radar signals. Boston: Artech House, 2006.
11	RAY P S A novel pulse TOA analysis technique for radar identification. IEEE Trans. on Aerospace and Electronic Systems, 1998, 34 (3): 716- 721. doi: 10.1109/7.705881
12	WANG J P, CHU C Q Approach to radar pulse repetition intervals modulation recognition based on Bayesian networks. Electronic Information Warfare Technology, 2007, 22 (2): 14- 17.
13	TAO R H, LI H S A novel algorithm of radar signal recognition based on histogram and wavelet networks. Chinese Journal of Radio Science, 2005, 20 (6): 784- 788.
14	KAUPPI J P, MARTIKAINEN K S An efficient set of features for pulse repetition interval modulation recognition. Proc. of the IET International Conference on Radar Systems, 2007.
15	MAHDAVI A, PEZESHK A M A robust method for PRI modulation recognition. Proc. of the IEEE 10th International Conference on Signal Processing, 2010, 1873- 1876.
16	LIU Y C, ZHANG Q Y An improved algorithm for PRI modulation recognition. Proc. of the IEEE International Conference on Signal Processing, Communications and Computing, 2017.
17	LI X Q, HUANG Z T, WANG F H, et al Toward convolutional neural networks on pulse repetition interval modulation recognition. IEEE Communications Letters, 2018, 22 (11): 2286- 2289. doi: 10.1109/LCOMM.2018.2864725
18	NUHOĞLU M A Classification of radar signal features in electronic warfare with convolutional long-short time memory. Proc. of the IEEE 26th Signal Processing and Communications Applications Conference, 2018.
19	ZHANG J Y, SU S Y A method for the modulation pattern recognition of radar PRI based on fully convolutional neural network. Electronic Warfare Technology, 2020, 35 (3): 40- 45.
20	LI X, LIU Z, HUANG Z T Attention-based radar PRI modulation recognition with recurrent neural networks. IEEE Access, 2020, 8, 57426- 57436. doi: 10.1109/ACCESS.2020.2982654
21	WEI S Q, QU Q Z, WU Y T, et al PRI modulation recognition based on squeeze-and-excitation networks. IEEE Communications Letters, 2020, 24 (5): 1047- 1051. doi: 10.1109/LCOMM.2020.2970397
22	ECKMANN J P, KAMPHORST S O, RUELLE D Recurrence plots of dynamical systems. World Scientific Series on Nonlinear Science Series A, 1995, 16, 441- 446.
23	ZOLOTOVA N V, PONYAVIN D I Phase asynchrony of the north-south sunspot activity. Astronomy & Astrophysics, 2006, 449 (1): L1- L4.
24	MARWAN N, TRAUTH M H, VUILLE M, et al Comparing modern and Pleistocene ENSO-like influences in NW Argentina using nonlinear time series analysis methods. Climate Dynamics, 2003, 21 (3/4): 317- 326. doi: 10.1007/s00382-003-0335-3
25	NICHOLS J M, TRICKEY S T, SEAVER M Damage detection using multivariate recurrence quantification analysis. Mechanical Systems and Signal Processing, 2006, 20 (2): 421- 437. doi: 10.1016/j.ymssp.2004.08.007
26	REDMON J, DIVVALA S, GIRSHICK R, et al You only look once: unified, real-time object detection. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, 779- 788.
27	REDMON J, FARHADI A. YOLO9000: better, faster, stronger. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263−7271.
28	REDMON J, FARHADI A. Yolov3: an incremental improvement. arXiv preprint arXiv: 1804.02767, 2018.
29	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv: 2004.10934, 2020.
30	LI H, DENG L B, YANG C, et al Enhanced YOLO v3 tiny network for real-time ship detection from visual image. IEEE Access, 2021, 9, 16692- 16706. doi: 10.1109/ACCESS.2021.3053956
31	XU Q W, LIN R Z, YUE H, et al Research on small target detection in driving scenarios based on improved yolo network. IEEE Access, 2020, 8, 27574- 27583. doi: 10.1109/ACCESS.2020.2966328
32	CHEN H P, HE Z T, SHI B W, et al Research on recognition method of electrical components based on YOLO V3. IEEE Access, 2019, 7, 157818- 157829. doi: 10.1109/ACCESS.2019.2950053

Method	Parameter
Method	Deviation of the average PRI	Number of bursts	Length of the burst in pulse	Number of periods	PRI	Missing pulse rate	Spurious pulse rate	Measure noisy standard deviation/μs
Jitter	5%−40%	−	−	−	100−200	0%−50%	0%−40%	0−3
Sliding	1:10	−	−	3−10
Sine	5%−20%	−	−	3−10
DAS	−	2−8	20−200	−
Stagger	−	2−64	−	20−40

Parameter	Method
Parameter	SL-CNN	SL-LSTM	RP-YOLOv3	RP-YOLOv4
Training time/s	1446	1143	15116	12809
Training round	100	85	85	80

Parameter	Method
Parameter	SL-CNN	SL-LSTM	RP-YOLOv3	RP-YOLOv4
Single sample processing time/s	0.08	0.95	0.18	0.13

Recognition of dynamically varying PRI modulation via deep learning and recurrence plot

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 32

相关文章 0

编辑推荐

Metrics

本文评价

Scene	Measuring noise/μs	Spurious pulse/%	Missing pulse/%
1	0.0	0	0
2	0.3	5	4
3	0.6	10	8
4	0.9	15	12
5	1.2	20	16
6	1.5	25	20
7	1.8	30	24
8	2.1	35	28
9	2.4	40	32
10	2.7	45	36
11	3.0	50	40