EUVIMEDEUVIMED entdecken
Crossref

Physically constrained neural network for predicting blast-induced ground vibration

Shuangshuang Ge, Wei Gao, Peiyuan Li, Shuo Yuan, Jingwen Zhu

Journal of Vibration and Control · 19.11.2026

DOI: 10.1177/10775463261506937 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Vibration and Control, online erschienen am 19.11.2026. Verfasst von Shuangshuang Ge und 4 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ground vibration from blasting, measured by peak particle velocity (PPV), threatens urban areas. To address this, physically constrained neural network (PCNN) is proposed for accurate PPV prediction, integrating physical relationships into data-driven learning processes. The core innovation lies in the design of the loss function, which combines data-driven loss with physical loss derived from dimensional analysis. Tested on 152 datasets from Tonglvshan open-pit mine, the PCNN achieves R 2 = 0.925, RMSE = 0.407, and MAE = 0.309, outperforming traditional models. The results highlight the value of embedding physical constraints for accurate PPV prediction, offering a high-precision method that merges data-driven modeling with physical knowledge.

Zitieren

APA

Ge, S., Gao, W., Li, P., Yuan, S., & Zhu, J. (2026). Physically constrained neural network for predicting blast-induced ground vibration. Journal of Vibration and Control. https://doi.org/10.1177/10775463261506937

Vancouver

Ge S, Gao W, Li P, Yuan S, Zhu J. Physically constrained neural network for predicting blast-induced ground vibration. Journal of Vibration and Control. 2026. doi:10.1177/10775463261506937

BibTeX
@article{Ge2026,
  author = {Ge, Shuangshuang and Gao, Wei and Li, Peiyuan and Yuan, Shuo and Zhu, Jingwen},
  title = {Physically constrained neural network for predicting blast-induced ground vibration},
  journal = {Journal of Vibration and Control},
  year = {2026},
  doi = {10.1177/10775463261506937}
}
Kostenlos starten →