EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Intelligent Radar Jamming Decision‐Making Method Based on Rainbow DQN and Bayesian Inference

Ji‐Chao Tang, Chuan He, Wen‐Shen Peng, Jun‐Wei Wang, Xu‐Sheng Niu

IET Radar, Sonar & Navigation · 2026-01 · 20 (1)

DOI: 10.1049/rsn2.70198 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Radar, Sonar & Navigation, online erschienen am 22.07.2026. Verfasst von Ji‐Chao Tang und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The development of intelligent jamming decision‐making technology has significantly enhanced the performance of jammers in combat scenarios. However, existing decision‐making algorithms often exhibit poor adaptability to complex electromagnetic environments, limited decision dimensions and challenges in making effective decisions under conditions of uncertainty. To address these issues, this paper proposes a radar intelligent jamming decision‐making algorithm based on Rainbow DQN and Bayesian inference. By constructing a 30‐dimensional state space, the proposed method achieves multidimensional information fusion that encompasses radar operating parameters, detection performance, jamming status, electromagnetic environment and tactical situation. It employs distributed Q‐learning and duelling network architectures to mitigate the deficiencies of traditional DQN in value estimation and exploration efficiency. Furthermore, by utilising NoisyNets to enhance the exploration mechanism and integrating them with a Bayesian inference environment model, the algorithm significantly improves decision‐making robustness under uncertainty. Compared to mainstream models, such as deep Q‐network (DQN), rainbow DQN, proximal policy optimisation (PPO) and deep deterministic policy gradient (DDPG), the proposed method increases convergence speed by approximately 1.5 times and improves the jamming success rate by 22.3%. Experimental results demonstrate that this method can adaptively learn various jamming strategies and achieve a beneficial balance between jamming effectiveness and resource consumption, showcasing significant advantages in decision quality and adaptability compared to traditional methods.

Zitieren

APA

Tang, J., He, C., Peng, W., Wang, J., & Niu, X. (2026). Intelligent Radar Jamming Decision‐Making Method Based on Rainbow DQN and Bayesian Inference. IET Radar, Sonar & Navigation, 20(1). https://doi.org/10.1049/rsn2.70198

Vancouver

Tang J, He C, Peng W, Wang J, Niu X. Intelligent Radar Jamming Decision‐Making Method Based on Rainbow DQN and Bayesian Inference. IET Radar, Sonar & Navigation. 2026;20(1). doi:10.1049/rsn2.70198

BibTeX
@article{Tang2026,
  author = {Tang, Ji‐Chao and He, Chuan and Peng, Wen‐Shen and Wang, Jun‐Wei and Niu, Xu‐Sheng},
  title = {Intelligent Radar Jamming Decision‐Making Method Based on Rainbow DQN and Bayesian Inference},
  journal = {IET Radar, Sonar & Navigation},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/rsn2.70198}
}
Kostenlos starten →