EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UNet-INSN: Self-Supervised Algorithm for Impulsive Noise Suppression in Power Line Communication

Enguo Zhu, Yi Ren, Ran Li, Shuiqing Ouyang, Yang Ma, Ximin Yang, Guojin Liu

Applied Sciences · 19.08.2025 · 15 (16) · 9101

DOI: 10.3390/app15169101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.08.2025. Verfasst von Enguo Zhu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2024 State Grid Corporation of China Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Impulsive noise suppression plays a crucial role in enhancing the reliability of power line communication (PLC). In view of the rapid advancement of deep learning methodologies, recently, studies on deep learning-based impulsive noise suppression have garnered extensive attention. Nevertheless, on one hand, the training of deep learning-based impulsive noise suppression models relies on a large number of labeled data, whose acquisition incurs high costs. On the other hand, the currently proposed models struggle to adapt to the dynamic variations in impulsive noise distributions. To address these two issues, in this paper, a UNet-based self-supervised learning model for impulsive noise suppression (UNet-INSN) is proposed. Firstly, by using the designed global mask mapper, UNet-INSN can utilize the entire noisy signal for model training, resolving the information loss issue caused by partial signal masking in traditional mask-driven algorithms. Secondly, a reproducibility loss function is introduced to effectively prevent the model from degenerating into an identity mapping, thereby enhancing the denoising performance of UNet-INSN. Simulation results show that the required SNRs for the proposed algorithm to achieve a bit error rate of 10−6 under ideal and non-ideal conditions are 12 dB and 26 dB, respectively, significantly outperforming comparison methods. Moreover, it still exhibits excellent robustness and generalization capabilities when the impulsive noise distribution changes dynamically.

Förderung

  • 2024 State Grid Corporation of China Science and Technology Program

Zitieren

APA

Zhu, E., Ren, Y., Li, R., Ouyang, S., Ma, Y., Yang, X., & Liu, G. (2025). UNet-INSN: Self-Supervised Algorithm for Impulsive Noise Suppression in Power Line Communication. Applied Sciences, 15(16), 9101. https://doi.org/10.3390/app15169101

Vancouver

Zhu E, Ren Y, Li R, Ouyang S, Ma Y, Yang X, et al. UNet-INSN: Self-Supervised Algorithm for Impulsive Noise Suppression in Power Line Communication. Applied Sciences. 2025;15(16):9101. doi:10.3390/app15169101

BibTeX
@article{Zhu2025,
  author = {Zhu, Enguo and Ren, Yi and Li, Ran and Ouyang, Shuiqing and Ma, Yang and Yang, Ximin and Liu, Guojin},
  title = {UNet-INSN: Self-Supervised Algorithm for Impulsive Noise Suppression in Power Line Communication},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {16},
  pages = {9101},
  doi = {10.3390/app15169101}
}
Kostenlos starten →