EUVIMEDEUVIMED entdecken
Crossref

Prediction of uniaxial compressive strength from drilling parameters using metaheuristic-optimized ensemble regression models

Cancan Liu, Haifeng Wang, Yankun Ma, Dianshang Li, Niaz Muhammad Shahani, Bo Ren, Wei Yue, Tingwei Zhang, Zike Meng

Canadian Geotechnical Journal · 01.01.2026 · 63 · 1-16

DOI: 10.1139/cgj-2025-0615 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Canadian Geotechnical Journal, erschienen am 01.01.2026. Verfasst von Cancan Liu und 8 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Open Fund of Scientific Research and Development Platform of Technology of Disaster Prevention in Deep Coal Mines, Open Fund of State Key Laboratory for Safe Mining of Deep Coal Resources and Environment Protection.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The uniaxial compressive strength (UCS) of rocks is a crucial parameter for assessing the quality of surrounding rock in mining, tunneling, and other geotechnical engineering applications. This study proposes a novel approach to predict UCS from drilling parameters using metaheuristic-optimized ensemble regression models. A comprehensive dataset of 345 rock samples with varying strengths was compiled through a literature review, incorporating penetration rate (ROP), revolutions per minute (RPM), torque, and thrust as inputs, with UCS as the output. Particle swarm optimization (PSO) was employed to optimize hyperparameters of four ensemble models: extreme gradient boosting (XGBoost), random forest (RF), backpropagation neural network (BP), and support vector regression (SVR). The dataset was split into training and testing datasets with an 80:20 ratio. Model performance was quantified by coefficient of determination ( R 2 ), root mean square error, and mean absolute error. Sensitivity analysis revealed that ROP and RPM were the most influential parameters for UCS prediction, while thrust showed the least impact. Results demonstrate that the stacking model achieved the optimal performance when PSO-BP, PSO-SVR, PSO-RF, and PSO-XGBoost were used as base models and linear regression served as the meta-model.

Förderung

  • National Natural Science Foundation of China
  • Open Fund of Scientific Research and Development Platform of Technology of Disaster Prevention in Deep Coal Mines
  • Open Fund of State Key Laboratory for Safe Mining of Deep Coal Resources and Environment Protection
  • China Postdoctoral Science Foundation

Zitieren

APA

Liu, C., Wang, H., Ma, Y., Li, D., Shahani, N. M., Ren, B., Yue, W., Zhang, T., & Meng, Z. (2026). Prediction of uniaxial compressive strength from drilling parameters using metaheuristic-optimized ensemble regression models. Canadian Geotechnical Journal, 63, 1-16. https://doi.org/10.1139/cgj-2025-0615

Vancouver

Liu C, Wang H, Ma Y, Li D, Shahani NM, Ren B, et al. Prediction of uniaxial compressive strength from drilling parameters using metaheuristic-optimized ensemble regression models. Canadian Geotechnical Journal. 2026;63:1-16. doi:10.1139/cgj-2025-0615

BibTeX
@article{Liu2026,
  author = {Liu, Cancan and Wang, Haifeng and Ma, Yankun and Li, Dianshang and Shahani, Niaz Muhammad and Ren, Bo and Yue, Wei and Zhang, Tingwei and Meng, Zike},
  title = {Prediction of uniaxial compressive strength from drilling parameters using metaheuristic-optimized ensemble regression models},
  journal = {Canadian Geotechnical Journal},
  year = {2026},
  volume = {63},
  pages = {1--16},
  doi = {10.1139/cgj-2025-0615}
}
Kostenlos starten →