Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Research for Radar Signal Classification Model Using Deep Learning Technique

딥 러닝 기법을 이용한 레이더 신호 분류 모델 연구

  • Kim, Yongjun (Electronic Warfare R&D, LIG NEX1 Co., Ltd.) ;
  • Yu, Kihun (Electronic Warfare R&D, LIG NEX1 Co., Ltd.) ;
  • Han, Jinwoo (Electronic Warfare R&D, LIG NEX1 Co., Ltd.)
  • 김용준 (LIG넥스원(주) 전자전연구소) ;
  • 유기훈 (LIG넥스원(주) 전자전연구소) ;
  • 한진우 (LIG넥스원(주) 전자전연구소)
  • Received : 2018.10.16
  • Accepted : 2019.02.25
  • Published : 2019.04.05
Download PDF
⟨ Previous Next ⟩

Abstract

Classification of radar signals in the field of electronic warfare is a problem of discriminating threat types by analyzing enemy threat radar signals such as aircraft, radar, and missile received through electronic warfare equipment. Recent radar systems have adopted a variety of modulation schemes that are different from those used in conventional systems, and are often difficult to analyze using existing algorithms. Also, it is necessary to design a robust algorithm for the signal received in the real environment due to the environmental influence and the measurement error due to the characteristics of the hardware. In this paper, we propose a radar signal classification method which are not affected by radar signal modulation methods and noise generation by using deep learning techniques.

Keywords

GSGGBW_2019_v22n2_170_f0001.png 이미지

Fig. 1. Frequency modulation type

GSGGBW_2019_v22n2_170_f0002.png 이미지

Fig. 2. PRI modulation type

GSGGBW_2019_v22n2_170_f0003.png 이미지

Fig. 3. Conventional radar signal classification

GSGGBW_2019_v22n2_170_f0004.png 이미지

Fig. 4. CNN-based classification model

GSGGBW_2019_v22n2_170_f0005.png 이미지

Fig. 5. RNN-based classification model

GSGGBW_2019_v22n2_170_f0006.png 이미지

Fig. 6. Distribution of training data Freq/PRI

GSGGBW_2019_v22n2_170_f0007.png 이미지

Fig. 7. Distribution of training data Freq/PRI modulation type

GSGGBW_2019_v22n2_170_f0008.png 이미지

Fig. 8. Comparison of before and after application of frequency error

GSGGBW_2019_v22n2_170_f0009.png 이미지

Fig. 9. Comparison of before and after application of pulse missing

GSGGBW_2019_v22n2_170_f0010.png 이미지

Fig. 10. Change in cost value by model

GSGGBW_2019_v22n2_170_f0011.png 이미지

Fig. 11. Comparison of No. 56~58 PRI characteristic

GSGGBW_2019_v22n2_170_f0012.png 이미지

Fig. 12. Comparison of No. 32, 33 frequency characteristic

Table 1. Details of PDW

GSGGBW_2019_v22n2_170_t0001.png 이미지

Table 2. Computer resource and library list

GSGGBW_2019_v22n2_170_t0002.png 이미지

Table 3. Classification accuracy by model

GSGGBW_2019_v22n2_170_t0003.png 이미지

References

  1. Richard G. Wiley, "ELINT The Intercception and Analysis of Radar Signals," Artech House, Norwood, MA, pp. 385-388, 2006.
  2. D. Curtis Schleher, "Electronic Warfare in the Information Age," Artech House, Norwood, MA, pp. 336-345, 1999.
  3. James A. Anderson, et al., “Radar Signal Categorization Using a Neural Network,” Proceedings of the IEEE, Vol. 78, No. 10, pp. 1646-1657, 1990. https://doi.org/10.1109/5.58358
  4. Nedyalko Petrov et al., "Radar Emitter Signals Recognition and Classification with Feedforward Networks," Procedia Computer Science 22, pp. 1192-1200, 2013. https://doi.org/10.1016/j.procs.2013.09.206
  5. Chih-Min Lin, et al., “A Self-Organizing Interval Type-2 Fuzzy Neural Network for Radar Emitter Identification,” International Journal of Fuzzy Systems, Vol. 16, No. 1, pp. 20-30, 2014.
  6. Ching-Sung Shieh, et al., "A Vector Neural Network for Emitter Identification," IEEE Transactions of Antennas and Propagation, Vol. 50, No. 8, pp. 1120-1127, 2002. https://doi.org/10.1109/TAP.2002.801387
  7. Dongqing Zhou, et al., "A Novel Radar Signal Recognition Method Based On a Deep Restricted Boltzmann Machine," Engineering Review, Vol. 37, Issue 2, pp. 165-171, 2017.
  8. Xavier Glorot, et al., "Understanding the Difficulty of Training Deep Feedforward Neural Networks," International Conference on Artificial Intelligence and Statistics PMLR 9, pp. 249-256, 2010.