EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Study on While-Drilling Prediction of Rock Mechanical Parameters Based on the CNN-LSTM-MoE Hybrid Deep Learning Model

Sheng Li, Yiteng Wang, Baijun Li, Rui Xu, Fengyi Sun, Xiaolong Ma

Applied Sciences · 12.05.2026 · 16 (10) · 4795

DOI: 10.3390/app16104795 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 12.05.2026. Verfasst von Sheng Li und 5 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Strategic Priority Research Program of the Chinese Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate and efficient acquisition of rock mechanical properties is critical for ensuring the safety and efficiency of underground engineering construction. Traditional laboratory tests are characterized by long cycles, high costs, and an inability to reflect in situ mechanical properties, while existing deep learning models based on while-drilling data suffer from poor noise robustness, insufficient deep feature extraction, and low accuracy in synchronous multi-parameter prediction. To address these limitations, this paper proposes a hybrid deep learning model (CNN-LSTM-MoE) combining a convolutional neural network (CNN), a long short-term memory network (LSTM), and a mixture of experts (MoE) system. The model enables intelligent prediction of elastic modulus, Poisson’s ratio, and yield stress from while-drilling parameters. The proposed model integrates CNN’s local feature extraction capability, LSTM’s temporal dependency modeling capability, and the multi-expert dynamic fusion mechanism of MoE. Furthermore, it incorporates physical constraints from rock fragmentation mechanics and an adaptive multi-objective loss weight optimization strategy to comprehensively enhance the multi-parameter synchronous prediction performance. Experimental results demonstrate that the proposed model achieves coefficients of determination (R2) of 0.8965 for elastic modulus, 0.9193 for Poisson’s ratio, and 0.9813 for yield stress on the laboratory validation dataset, with a mean squared error (mse) of 4.0720. Its prediction performance significantly outperforms benchmark models such as TCN and Transformer time-series architectures. Ablation studies further validate the critical role of the integrated LSTM and MoE modules in improving model accuracy, with the MoE module contributing an average R2 improvement of approximately 24%. This study not only provides an effective method for high-precision acquisition of rock mechanical parameters while drilling, but also offers a feasible solution based on numerical simulation for data augmentation to address the common issue of scarce labeled data in deep learning applications within engineering fields.

Förderung

  • Strategic Priority Research Program of the Chinese Academy of Sciences

Zitieren

APA

Li, S., Wang, Y., Li, B., Xu, R., Sun, F., & Ma, X. (2026). Study on While-Drilling Prediction of Rock Mechanical Parameters Based on the CNN-LSTM-MoE Hybrid Deep Learning Model. Applied Sciences, 16(10), 4795. https://doi.org/10.3390/app16104795

Vancouver

Li S, Wang Y, Li B, Xu R, Sun F, Ma X. Study on While-Drilling Prediction of Rock Mechanical Parameters Based on the CNN-LSTM-MoE Hybrid Deep Learning Model. Applied Sciences. 2026;16(10):4795. doi:10.3390/app16104795

BibTeX
@article{Li2026,
  author = {Li, Sheng and Wang, Yiteng and Li, Baijun and Xu, Rui and Sun, Fengyi and Ma, Xiaolong},
  title = {Study on While-Drilling Prediction of Rock Mechanical Parameters Based on the CNN-LSTM-MoE Hybrid Deep Learning Model},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {4795},
  doi = {10.3390/app16104795}
}
Kostenlos starten →