EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Anomaly detection in industrial control networks based on deep reinforcement learning and data reconstruction

Hanjun Gao, Jiaqi Sun, Wei Feng, Xiaoxuan Fan, Wei Xiang, Shenghao Liu, Xianjun Deng

Digital Communications and Networks · 2026-09 · 12 (9) · 1461-1469

DOI: 10.1016/j.dcan.2026.07.010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital Communications and Networks, 2026-09. Verfasst von Hanjun Gao und 6 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Chongqing Municipal Education Commission, Chongqing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • National Natural Science Foundation of China
  • Chongqing Municipal Education Commission
  • Chongqing Natural Science Foundation
  • Hubei Province Natural Science Foundation

Zitieren

APA

Gao, H., Sun, J., Feng, W., Fan, X., Xiang, W., Liu, S., & Deng, X. (2026). Anomaly detection in industrial control networks based on deep reinforcement learning and data reconstruction. Digital Communications and Networks, 12(9), 1461-1469. https://doi.org/10.1016/j.dcan.2026.07.010

Vancouver

Gao H, Sun J, Feng W, Fan X, Xiang W, Liu S, et al. Anomaly detection in industrial control networks based on deep reinforcement learning and data reconstruction. Digital Communications and Networks. 2026;12(9):1461-1469. doi:10.1016/j.dcan.2026.07.010

BibTeX
@article{Gao2026,
  author = {Gao, Hanjun and Sun, Jiaqi and Feng, Wei and Fan, Xiaoxuan and Xiang, Wei and Liu, Shenghao and Deng, Xianjun},
  title = {Anomaly detection in industrial control networks based on deep reinforcement learning and data reconstruction},
  journal = {Digital Communications and Networks},
  year = {2026},
  volume = {12},
  number = {9},
  pages = {1461--1469},
  doi = {10.1016/j.dcan.2026.07.010}
}
Kostenlos starten →