EUVIMEDEUVIMED entdecken
Crossref

Pipeline event recognition in distributed optical fiber acoustic sensing systems based on FMD

JunJie Zhang, Yong Kong, Yuhao Liu, Xiaofan Tong, Xin Tang

Optica Applicata · 30.05.2026 · 56 (1) · 19-34

DOI: 10.37190/oa/208835 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optica Applicata, online erschienen am 30.05.2026. Verfasst von JunJie Zhang und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To enhance the early warning rate of pipeline leak events and reduce the false alarm rate in Φ-OTDR-based DAS systems, this paper proposes a new method based on FMD. The introduced vibration event types include not only pipeline leaks but also hammer strikes, steel pipe hits, and noise. A 160-meter pipeline setup was constructed, and the sensing optical fiber wound around it was monitored to collect 2240 samples. The results after denoising demonstrate the effectiveness of the proposed denoising method. Subsequently, features were extracted using overlapping frames, dimensionality reduction was performed with t-SNE, and after training with NRBO-XGBoost, the leak event recognition rate reached 99.74%, the average classification accuracy reached 98.71%, and the false alarm rate was reduced to 0.19%.

Zitieren

APA

Zhang, J., Kong, Y., Liu, Y., Tong, X., & Tang, X. (2026). Pipeline event recognition in distributed optical fiber acoustic sensing systems based on FMD. Optica Applicata, 56(1), 19-34. https://doi.org/10.37190/oa/208835

Vancouver

Zhang J, Kong Y, Liu Y, Tong X, Tang X. Pipeline event recognition in distributed optical fiber acoustic sensing systems based on FMD. Optica Applicata. 2026;56(1):19-34. doi:10.37190/oa/208835

BibTeX
@article{Zhang2026,
  author = {Zhang, JunJie and Kong, Yong and Liu, Yuhao and Tong, Xiaofan and Tang, Xin},
  title = {Pipeline event recognition in distributed optical fiber acoustic sensing systems based on FMD},
  journal = {Optica Applicata},
  year = {2026},
  volume = {56},
  number = {1},
  pages = {19--34},
  doi = {10.37190/oa/208835}
}
Kostenlos starten →