Deinterleaving of radar pulse based on implicit feature

doi:10.23919/JSEE.2023.000032

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (6): 1537-1549.doi: 10.23919/JSEE.2023.000032

• DEFENCE ELECTRONICS TECHNOLOGY • Previous Articles Next Articles

Deinterleaving of radar pulse based on implicit feature

Qiang GUO¹(), Long TENG¹(), Xinliang WU²(), Liangang QI¹^,*(), Wenming SONG²()

¹ College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
² China National Aeronautical Radio Electronics Research Institute, Shanghai 200030, China

Received:2021-11-10 Accepted:2022-10-08 Online:2023-12-18 Published:2023-12-29
Contact: Liangang QI E-mail:guoqiang@hrbeu.edu.cn;tenglong@hrbeu.edu.cn;wuxinliang51@163.com;qiliangang@hrbeu.edu.cn;fate1530@126.com
About author:
GUO Qiang was born in 1972. He received his B.S., M.S., and Ph.D. degrees in information and communication engineering from Harbin Engineering University, China, in 1994, 2003, and 2007 respectively. In 2009, he received the National 100 Excellent Doctoral Degree Dissertation Candidate Nomination. He is currently a full professor with the College of Information and Communication Engineering. He is a review expert of the Science and Technology Commission of the Military Commission, the Degree and Postgraduate Education Center of the Ministry of Education, the National Natural Science Foundation of China, and the National Science and Technology Award. His research interests include electronic countermeasure, machine learning, radar signals sorting, and recognition. E-mail: guoqiang@hrbeu.edu.cn

TENG Long was born in 1994. He received his B.E. degree in electronic information engineering from Shaanxi University of Technology, Shaanxi, China, in 2016. He is pursuing his Ph.D. degree in information and communication engineering, Harbin Engineering University. His research interests include radar signals sorting, deep learning, and information fusion. E-mail: tenglong@hrbeu.edu.cn

WU Xinliang was born in 1982. He received his B.E. degree in detection guidance and control technology from Northwestern Polytechnical University, Shaanxi, China, in 2003. He received his M.S. degree from Nanjing University of Aeronautics and Astronautics, Nanjing, China, in 2013. His research interests include avionics integrated technology, information fusion and image processing. E-mail: wuxinliang51@163.com

QI Liangang was born in 1990. He received his B.S. and Ph.D. degrees in information and communication engineering from Harbin Engineering University, China, in 2013 and 2018, respectively. He has been a lecturer with Harbin Engineering University since 2018. His research interests include electronic countermeasure, machine learning, radar target recognition, and radar signal processing. E-mail: qiliangang@hrbeu.edu.cn

SONG Wenming was born in 1988. He received his B.S. and M.S. degrees in information and communication engineering from Harbin Engineering University, China, in 2011 and 2014 respectively. His research interests include avionics integrated technology, information fusion, radar signals sorting and deep learning. E-mail: fate1530@126.com
Supported by:
This work was supported by the National Major Research & Development project of China (2018YFE0206500), the National Natural Science Foundation of China (62071140), the Program of China International Scientific and Technological Cooperation (2015DFR10220), and the Technology Foundation for Basic Enhancement Plan (2021-JCJQ-JJ-0301).

Abstract

Abstract:

In the complex countermeasure environment, the pulse description words (PDWs) of the same type of multi-function radar emitters are similar in multiple dimensions. Therefore, it is difficult for conventional methods to deinterleave such emitters. In order to solve this problem, a pulse deinterleaving method based on implicit features is proposed in this paper. The proposed method introduces long short-term memory (LSTM) neural networks and statistical analysis to mine new features from similar PDW features, that is, the variation law (implicit features) of pulse sequences of different radiation sources over time. The multi-function radar emitter is deinterleaved based on the pulse sequence variation law. Statistical results show that the proposed method not only achieves satisfactory performance, but also has good robustness.

Key words: multi-functional radars of the same type, pulse deinterleaving, pulse amplitude, implicit feature, long short-term memory (LSTM) neural networks

Qiang GUO, Long TENG, Xinliang WU, Liangang QI, Wenming SONG. Deinterleaving of radar pulse based on implicit feature[J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1537-1549.

Figures/Tables 18

Fig 1

Fig 2

Fig 3

Fig 4

Table 1

Fig 5

Fig 6

Fig 7

Fig 8

Fig 9

Fig 10

Table 2

Table 3

Table 4

Fig 11

Table 5

Table 6

Fig 12

References 32

1	MARDIA H K New techniques for the deinterleaving of repetitive sequences. IEE Proceedings F, 1989, 136 (4): 149- 154.
2	MILOJEVIC D J, POPOVIC B M Improved algorithm for the deinterleaving of radar pulses. IEE Proceedings F, 1992, 139 (1): 98- 104.
3	AN Q Y, LI Y H, YANG J W, et al Research on radar pulse signal sorting based on improved SDIF algorithm. Fire Control and Command Control, 2018, 43 (7): 42- 46.
4	NELSON D Special purpose correlation functions for improved signal detection and parameter estimation. Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 1993, 4, 73- 76.
5	LIU Y C, ZHANG Q Y Improved method for deinterleaving radar signals and estimating PRI values. IET Radar, Sonar & Navigation, 2018, 12 (5): 506- 514. doi: 10.1049/iet-rsn.2017.0516
6	GE Z P, SUN X, REN W J, et al Improved algorithm of radar pulse repetition interval deinterleaving based on pulse correlation. IEEE Access, 2019, 7, 30126- 30134. doi: 10.1109/ACCESS.2019.2901013
7	YANG M S, TIAN Y C Bias-correction fuzzy clustering algorithms. Information Sciences, 2015, 309, 138- 162. doi: 10.1016/j.ins.2015.03.006
8	GUO Q, WANG C H, GUO L M, et al Application of segment clustering in radar signal sorting. Journal of Beijing University of Posts and Telecommunications, 2008, 31 (2): 132- 136.
9	GUO Q, WANG C H, LI Z Support vector clustering and type-entropy based radar signal sorting method. Journal of Xi’an Jiaotong University, 2010, 44 (8): 63- 67.
10	GUO Q, NAN P L, WAN J. Signal classification method based on data mining for multi-mode radar. Journal of Systems Engineering and Electronics, 2016, 27(5): 1010–1017.
11	ZHANG Y X, GUO W P, KANG K, et al Radar signal sorting method based on data field combined PRI transform and clustering. Systems Engineering and Electronics, 2019, 41 (7): 1509- 1515.
12	LIU Z M, YU P S Classification, denoising, and deinterleaving of pulse streams with recurrent neural networks. IEEE Trans. on Aerospace and Electronic Systems, 2019, 55 (4): 1624- 1639. doi: 10.1109/TAES.2018.2874139
13	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
14	SGAMBATO P, BOTTA N, CELENTANO S, et al System manager for AESA radar systems. Proc. of the IEEE Radar Conference, 2015, 1734- 1738.
15	LIU S T, LEI Z S, GE Y, et al Automatic radar antenna scan type recognition based on limited penetrable visibility graph. Journal of Systems Engineering and Electronics, 2021, 32 (2): 437- 446. doi: 10.23919/JSEE.2021.000037
16	SHI Z X, GU H, ZHU S L Analysis and feature extraction of amplitude information in full pulse data. Command Control and Simulation, 2009, 31 (3): 43- 45.
17	GUO Q. Signal sorting methods for unknown radar emitters in complex environments. Harbin: Harbin Engineering University, 2007. (in Chinese)
18	BARSHAN B, ERAVCI B Automatic radar antenna scan type recognition in electronic warfare. IEEE Trans. on Aerospace and Electronic Systems, 2012, 48 (4): 2908- 2931. doi: 10.1109/TAES.2012.6324669
19	AYAZGOK S, ERDEM C, OZTURK M T, et al Automatic antenna scan type classification for next-generation electronic warfare receivers. IET Radar, Sonar & Navigation, 2018, 12 (4): 466- 474. doi: 10.1049/iet-rsn.2017.0354
20	GUO Q, TENG L, QI L G, et al A novel radar signals sorting method based trajectory features. IEEE Access, 2019, 7, 171235- 171245. doi: 10.1109/ACCESS.2019.2955819
21	AN H, YANG L, WANG X M. Modeling and simulation of rardar and electronic warfare systems. Beijing: National Defense Industry Press, 2017. (in Chinese)
22	HU L Z. Radar reconnaissance receiver design. Beijing: National Defense Industry Press, 2000.
23	CHEN T, WANG T H, GUO L M Sequence searching methods of radar signal pulses based on PRI transform algorithm. Systems Engineering and Electronics, 2017, 39 (6): 1261- 1267.
24	WILLIAMS D E, HINTON G E Learning representations by back-propagating errors. Nature, 1986, 323 (6088): 533- 538. doi: 10.1038/323533a0
25	SILVER D, HUANG A, MADDISON C J, et al Mastering the game of go with deep neural networks and tree search. Nature, 2016, 4529 (7587): 484- 489.
26	SILVER D, SCHRITTWIESER J, SIMONYAN K, et al Mastering the game of go without human knowledge. Nature, 2017, 550 (7676): 354- 359. doi: 10.1038/nature24270
27	LECUN Y, BENGIO Y, HINTON G Deep learning. Nature, 2015, 521 (7553): 436- 444. doi: 10.1038/nature14539
28	SCHMIDHUBER J Deep learning in neural networks: an overview. Neural Networks, 2015, 61, 85- 117. doi: 10.1016/j.neunet.2014.09.003
29	HOCHREITER S, SCHMIDHUBER J Long short-term memory. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
30	ZHANG Z J, ZHENG L N, WENG J, et al A new varying-parameter recurrent neural-network for online solution of time-varying sylvester equation. IEEE Trans. on Cybernetics, 2018, 48 (11): 3135- 3148. doi: 10.1109/TCYB.2017.2760883
31	BEN-HUR A, HORN D, SIEGELMANN H T, et al. A support vector method for hierarchical clustering. Advances in Neural Information Processing Systems. 2001, 31: 367–373.
32	BEN-HUR A, HORN D, SIEGELMANN H T, et al Support vector clustering. Journal of Machine Learning Research, 2001, 2, 125- 137.

Item	Formula
Centroid	Equations (9) and (10)
PA difference between centroid pulses	$\left\| {{{\rm{PA}}_{{{\rm{FR}}_{m + 1} } } } - {{\rm{PA}}_{{{\rm{FR}}_m} } } } \right\|$
TOA difference between centroid pulses	${{\rm{TOA}}_{{{\rm{FR}}_{m + 1} } } } - {{\rm{TOA}}_{{{\rm{FR}}_m} } }$
Peak of PA envelope	${{\rm{PA}}_{{{\rm{FR}}_{m - 1} } } } < {{\rm{PA}}_{{{\rm{FR}}_m} } } < {{\rm{PA}}_{{{\rm{FR}}_{m + 1} } } }$
Implicit feature	LSTM

Item	Value
Functional state	Track and search (TAS)
Transmitters power/W	12
Maximum gain/dB	38
First sidelobe level/dB	−34
Average sidelobe level/dB	−44
3 dB beam width (azimuth)	2°
3 dB beam width (elevation)	2°
Antenna scanning rate/(°/s)	50
Azimuth scanning/(°)	±15
Elevation scanning/(°)	±4
RF/MHz	[9400,9800], pseudo-random agility
PRI/μs	[30,50], group stagger
DOA/(°)	36
PW/ns	1 300

Parameter	Unit	Method
Input layer	1	−
LSTM layer	128	−
Fully connected layer	256	−
Output layer	1	−
Optimization	−	Adam
Loss function	−	Root mean square error (RMSE)

Parameter	Unit	Method
Input layer	4	−
LSTM layer	256	−
LSTM layer	256	−
Fully connected layer	512	−
Output layer	1	−
Optimization	−	Adam
Loss function	−	RMSE

Criterion	Results in [20]	DNN	SVR	Improved method
Number of total pulses	584873	584873	584873	584873
Number of correct pulses	478101	502371	503565	555759
Number of false pulses	106772	82502	81308	29114
Accuracy/%	81.74	85.90	86.10	95.02
Computation time/s	29.97	40.78	38.85	43.49

Deinterleaving of radar pulse based on implicit feature

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 18

References 32

Related Articles 1

Recommended Articles

Metrics

Comments

Scenario	Missing	Jitter PRI	Noise	Probabilities of correct deinterleaving
1	20	20	10	92.67
2	40	40	10	92.37
3	50	50	10	91.86
4	50	50	20	90.04
5	50	50	30	87.36
6	50	50	40	85.89
7	50	50	50	83.43