EUVIMEDEUVIMED entdecken
Crossref

Depth estimation of weak narrowband sources using a hybrid interference-deep learning method

Tong WANG, Lin SU, Pengchao LIU, Qunyan REN, Xinyi GUO, Tao HU, Li MA

Chinese Journal of Acoustics · 2026

DOI: 10.3724/0217-9776.3025004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chinese Journal of Acoustics, 2026. Verfasst von Tong WANG und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interference-structure-based passive source localization provides computational efficiency and physical interpretability but suffers performance degradation for weak acoustic targets, where low signal-to-noise ratios (SNRs) obscure the observable interference patterns necessary for reliable depth estimation. Narrowband time-window limitations and environmental mismatches further introduce blind zones and nonlinear distortions between the source depth and the measured interference structure. To mitigate these effects, this study proposes a hybrid depth estimation method that integrates arrival-angle interference features with a deep learning (DL) framework based on a residual network. Sound intensity in the beam domain is employed to exploit multidimensional and nonlinear relationships in the acoustic field, thereby enhancing robustness under weak target and low SNR conditions. Simulation and sea experiment results demonstrate that the proposed method achieves improved depth estimation accuracy compared with conventional interference-based techniques. The findings indicate that the hybrid interference-DL approach effectively extends the applicability of interference-structure-based localization to weak acoustic targets.

Zitieren

APA

WANG, T., SU, L., LIU, P., REN, Q., GUO, X., HU, T., & MA, L. (2026). Depth estimation of weak narrowband sources using a hybrid interference-deep learning method. Chinese Journal of Acoustics. https://doi.org/10.3724/0217-9776.3025004

Vancouver

WANG T, SU L, LIU P, REN Q, GUO X, HU T, et al. Depth estimation of weak narrowband sources using a hybrid interference-deep learning method. Chinese Journal of Acoustics. 2026. doi:10.3724/0217-9776.3025004

BibTeX
@article{WANG2026,
  author = {WANG, Tong and SU, Lin and LIU, Pengchao and REN, Qunyan and GUO, Xinyi and HU, Tao and MA, Li},
  title = {Depth estimation of weak narrowband sources using a hybrid interference-deep learning method},
  journal = {Chinese Journal of Acoustics},
  year = {2026},
  doi = {10.3724/0217-9776.3025004}
}
Kostenlos starten →