EUVIMEDEUVIMED entdecken
Crossref

Burial Depth Estimation for Partially Embedded Rocks Using Scanning Laser Doppler Vibrometry and Neural Networks

Yiyan Ruan, Erik Komendera

IEEE Sensors Journal · 2026-11 · 26 (21) · 33392-33402

DOI: 10.1109/jsen.2026.3733381 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, 2026-11. Verfasst von Yiyan Ruan und 1 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Estimating the burial depth of partially embedded rocks is a key capability for energy-limited robotic excavation, where unnecessary digging or repeated probing can be prohibitively costly. This article presents a geometry-informed, vibration-based pipeline that combines impulse excitation, scanning laser Doppler vibrometry (LDV), and exposed geometry to estimate burial depth with a neural network. Unlike spring–mass inversions, which require rock mass and soil stiffness, the proposed estimator uses no measured mass, assumed density, or independently measured soil parameters as model inputs. A multilayer perceptron (MLP) maps 11 measurable features, including resonance parameters, half-power damping ratio, and spatial vibration decay, to burial depth. Under strict leave-one-rock-out (LORO) cross-validation with nested hyperparameter selection, it achieves 25.1% mean absolute percentage error (MAPE) and 0.94 cm root-mean-squared error (RMSE) on 18 near-uniform-density (1.92–2.03 g/cm3) concrete blocks spanning 204 measurements in one controlled sand condition. The mean signed error is $+{0}.{01}$ cm, the absolute error is roughly 1 cm across the 1–8.4 cm depth range, and the largest observed error across the 20 seeded nested cross-validation runs is 3.0 cm. The estimator also outperforms a calibrated closed-form inversion supplied with the true rock mass (45.9% MAPE). To the authors’ knowledge, this is the first mass-agnostic, data-driven burial-depth estimator evaluated under cross-specimen LORO validation.

Zitieren

APA

Ruan, Y., & Komendera, E. (2026). Burial Depth Estimation for Partially Embedded Rocks Using Scanning Laser Doppler Vibrometry and Neural Networks. IEEE Sensors Journal, 26(21), 33392-33402. https://doi.org/10.1109/jsen.2026.3733381

Vancouver

Ruan Y, Komendera E. Burial Depth Estimation for Partially Embedded Rocks Using Scanning Laser Doppler Vibrometry and Neural Networks. IEEE Sensors Journal. 2026;26(21):33392-33402. doi:10.1109/jsen.2026.3733381

BibTeX
@article{Ruan2026,
  author = {Ruan, Yiyan and Komendera, Erik},
  title = {Burial Depth Estimation for Partially Embedded Rocks Using Scanning Laser Doppler Vibrometry and Neural Networks},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {33392--33402},
  doi = {10.1109/jsen.2026.3733381}
}
Kostenlos starten →