Education, Science, Technology, Innovation and Life
Open Access
Sign In

Parametric Transfer-Based DQN for Multi-Function Radar Jamming Decision Method

Download as PDF

DOI: 10.23977/acss.2024.080701 | Downloads: 14 | Views: 317

Author(s)

Lihui Huang 1, Changhua Hu 1

Affiliation(s)

1 Missile Engineering Institute, Rocket Force University of Engineering, Xi'an, China

Corresponding Author

Lihui Huang

ABSTRACT

With the continuous development of multi-function radar technology, the number of radar tasks the seeker can perform is increasing. This has led to the environment state transitioning from a small space to an ample space, facing more complex radar jamming decision problems. Traditional reinforcement learning algorithms have insufficient processing capacity and limited learning ability, thus we adopted a deep reinforcement learning algorithm, combining its powerful perception and processing capabilities to improve the jamming effect further. At the same time, to solve the problem of low computational efficiency for deep reinforcement learning, the transfer learning algorithm is introduced by migrating the parameters of deep learning networks from other tasks to the radar seeker jamming decision, further improving the learning rate.

KEYWORDS

Multifunctional Radar; Jamming Decision-Making; DQN

CITE THIS PAPER

Lihui Huang, Changhua Hu, Parametric Transfer-Based DQN for Multi-Function Radar Jamming Decision Method. Advances in Computer, Signals and Systems (2024) Vol. 8: 1-11. DOI: http://dx.doi.org/10.23977/acss.2024.080701.

REFERENCES

[1] REICH G M, ANTONIOU M, BAKER C J. Memory-enhanced cognitive radar for autonomous navigation[J]. IET RADAR SONAR AND NAVIGATION, 2020, 14(9): 1287-1296. DOI: 10.1049/iet-rsn.2019.0409
[2] GURBUZ S Z, GRIFFITHS H D, CHARLISH A, et al. An overview of cognitive radar: Past, present, and future[J]. IEEE Aerospace and Electronic Systems Magazine, 2019, 34(12): 6-18. DOI: 10.1109/MAES.2019.2953762.
[3] LIANG Y C, CHEN K C, LI G Y, et al. Cognitive radio networking and communications: an overview[J]. IEEE Transactions on Vehicular Technology, 2011, 60(7): 3386-3407. DOI: 10.1109/TVT.2011.2158673.
[4] Y. F. Li, "Research on interference decision technology based on deep reinforcement learning," M.S. thesis, Xi'an Univ. Electron. Sci. Technol., Xi'an, China, 2020.
[5] L. Yuqian, ''Radar cognitive behavior identification and interference decision optimization,” M.S. thesis, Xi'an Univ. Electron. Sci. Technol., Xi'an, China, 2019.
[6] B. Siwei, "Based on Neural Network Effectiveness Evaluation of Radar Jamming," M.S. thesis, Xi'an Univ. Electron. Sci. Technol., Xi'an, China, 2020.
[7] Z. Baikai and Z. Weigang, "Multi-function radar cognitive jamming decision-making method based on Q-learning," Telecommun. Technol., vol. 60, no. 2, pp. 129–136, 2020.
[8] B. K. Zhang and W. G. Zhu, "A DQN cognitive interference decision method for multifunctional radars," Syst. Eng. Electron. Technol., vol. 42, no. 4, pp. 819–825, 2020. 
[9] QIANG X, WEIGANG Z, XIN J. Research on method of intelligent radar confrontation based on reinforcement learning[C]//2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA). 2017: 471-475. DOI: 10.1109/CIAPP.2017.8167262.
[10] M. Shaoqing, "Research on intelligent jamming decision method based on reinforcement learning," Harbin Inst. Technol., 2021, doi: 10.27061/d.cnki.ghgdu.2021.003754.
[11] WEINBERG G V. Geometric mean switching constant false alarm rate detector[J]. DIGITAL SIGNAL PROCESSING, 2017, 69: 1-10. DOI: 10.1016/j.dsp.2017.06.015.
[12] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540): 529-533.
[13] LI G, WANG Z, GAO J, et al. Performance assessment of cross office building energy prediction in the same region using the domain adversarial transfer learning strategy[J]. Applied Thermal Engineering, 2024, 241: 122357. 

Downloads: 27683
Visits: 469034

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.