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

Low‐Probability‐Of‐Intercept Point Beam Design for Frequency Diverse Array‐Multiple‐Input Multiple‐Output Radio Detectors Based on Adaptive Weight‐Deep Deterministic Policy Gradient Reinforcement Learning

Jinwei Jia, Min Gao, Yuying Liang, Yuanwei Yin, Zhuangzhi Han

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

DOI: 10.1049/rsn2.70184 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Radar, Sonar & Navigation, online erschienen am 17.06.2026. Verfasst von Jinwei Jia und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Radio detectors are widely used in the aerospace field, but they are subject to numerous electronic interferences, especially information interference, which is commonly seen in increasingly complex electromagnetic environments in modern times. Thus, improving information interference resistance is key to ensuring the accurate detection and damage control for radio detectors in such complex electromagnetic environments. Given that jammers intercept the radio detector signal first and then forward the interference, this study focuses on the design of low‐probability‐of‐intercept (LPI) point beams for the radio detector. We construct a new evaluation model to verify the spatial LPI performance. Frequency diverse array‐multiple‐input multiple‐output (FDA‐MIMO) beams are employed and key factors influencing beam convergence are determined. A novel FDA‐MIMO LPI spot beam design technique based on the adaptive weight‐deep deterministic policy gradient (AW‐DDPG) algorithm is proposed. A two‐stage adaptive weight multi‐dimensional reward function is designed for the AW‐DDPG algorithm, with the array element frequency offset as the optimization objective. Leveraging the Actor‐Critic framework, the gradient ascent method is used to maximise the reward, thereby deriving the array element frequency offset with better beam convergence performance in the current environment. Meanwhile, the AW‐DDPG algorithm applies to LPI point beam design across various radio detector fall angles, overcoming the technical bottleneck that the formula method for the array element frequency offset only applies when the radio detector's fall angle is close to vertical. Simulation shows that with the array element frequency offset optimised by the proposed AW‐DDPG algorithm, the FDA‐MIMO beam exhibits a half‐power beam width of 1 m in the distance dimension and 9.9° in the angular dimension. The beam convergence and LPI performance with the proposed method are significantly better than other classical frequency offset calculation methods. Thus, the proposed algorithm represents a new method for array element frequency offset optimization and LPI point beam design, effectively improving the radio detector's LPI performance.

Zitieren

APA

Jia, J., Gao, M., Liang, Y., Yin, Y., & Han, Z. (2026). Low‐Probability‐Of‐Intercept Point Beam Design for Frequency Diverse Array‐Multiple‐Input Multiple‐Output Radio Detectors Based on Adaptive Weight‐Deep Deterministic Policy Gradient Reinforcement Learning. IET Radar, Sonar & Navigation, 20(1). https://doi.org/10.1049/rsn2.70184

Vancouver

Jia J, Gao M, Liang Y, Yin Y, Han Z. Low‐Probability‐Of‐Intercept Point Beam Design for Frequency Diverse Array‐Multiple‐Input Multiple‐Output Radio Detectors Based on Adaptive Weight‐Deep Deterministic Policy Gradient Reinforcement Learning. IET Radar, Sonar & Navigation. 2026;20(1). doi:10.1049/rsn2.70184

BibTeX
@article{Jia2026,
  author = {Jia, Jinwei and Gao, Min and Liang, Yuying and Yin, Yuanwei and Han, Zhuangzhi},
  title = {Low‐Probability‐Of‐Intercept Point Beam Design for Frequency Diverse Array‐Multiple‐Input Multiple‐Output Radio Detectors Based on Adaptive Weight‐Deep Deterministic Policy Gradient Reinforcement Learning},
  journal = {IET Radar, Sonar & Navigation},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/rsn2.70184}
}
Kostenlos starten →