THERMAL SCIENCE

International Scientific Journal

DEFORMATION PREDICTION METHOD OF SOFT ROCK IN DEEP SHAFT BY MACHINE LEARNING

ABSTRACT
Predicting the unsupported deformation behavior of a shaft is crucial for evaluating the stability of the rock mass, selecting an appropriate support scheme. Random forest, XGBoost, LightGBM, and K-nearest neighbors regression models were trained for database, and their accuracy was evaluated. It aimed to examine the effects of various parameters on shaft deformation, including the maximum tangential stress of the surrounding rock, elastic modulus, Poisson's ratio, cohesion, internal friction angle, and rock mass compressive strength. The results indicate that the coefficient of determination for random forest model is outperformed the other models. The importance of the characteristic parameters, in order, is cohesion, rock mass compressive strength, elastic modulus, rock compressive strength, internal friction angle, Poisson's ratio, and maximum tangential stress of the surrounding rock.
KEYWORDS
PAPER SUBMITTED: 2024-08-20
PAPER REVISED: 2024-11-08
PAPER ACCEPTED: 2024-11-22
PUBLISHED ONLINE: 2025-06-01
DOI REFERENCE: https://doi.org/10.2298/TSCI2502395W
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2025, VOLUME 29, ISSUE Issue 2, PAGES [1395 - 1401]
REFERENCES
  1. Sun, X., et al., Investigation of Deep Mine Shaft Stability in Alternating Hard and Soft Rock Strata Using 3-D Numerical Modelling, Processes, 7 (2018), 1, pp. 2-19
  2. Wang, D., et al., Non-Linear Large Deformation Mechanism and Stability Control of Deep Soft Rock Roadway: A Case Study in China, Sustainability, 11 (2019), 22, ID6243
  3. Han, J., et al., Deflection Mechanism and Safety Analysis of Coal Mine Shaft in Deep Soil Strata, Mathematical Problems in Engineering, 2019 (2019), 1, ID9461742
  4. Spesivtsev, P., et al., Predictive Model for Bottomhole Pressure Based on Machine Learning, Journal of Petroleum Science and Engineering, 166 (2018), pp. 825-841
  5. Wu, X., et al., Predicting Existing Tunnel Deformation from Adjacent Foundation Pit Construction Using Hybrid Machine Learning, Automation in Construction, 165 (2024), ID105516
  6. Xu, X. F., et al., Distribution Rules of Additional Force and Secondary Ground Pressure Stress of Shaft Wall in Seepage Sedimentation (in Chinese), Journal of China Coal Society, 35 (2010), 2, pp. 203-207
  7. Han, J., et al., Study on Size Design of Shaft Protection Rock/Coal Pillars in Thick Soil and Thin Rock Strata, Energies, 12 (2019), 13, ID2553
  8. Tang, Y. M., et al., Study on Coal Mine Shaft Chaos Charactristics and Deformation Prediction Model, Metal Mine, 40 (2011), 2, pp. 149-152
  9. Khan, M., et al., Evaluation of The Structural Integrity of Aging Mine Shafts, Engineering Structures, 24 (2002), 7, pp. 901-907
  10. Yuan, D., et al., Application of Gray-markov Model to Land Subsidence Monitoring of a Mining Area, Ieee Access, 9 (2021), Aug., pp. 118716-118725
  11. Bai, C., et al., Real-Time Updated Risk Assessment Model for the Large Deformation of the Soft Rock Tunnel, International Journal of Geomechanics, 21 (2021), 1, ID04020234
  12. Feng, D. L., et al., An Analytical Model to Predict the Radial Deformation of Surrounding Rock during Shaft Construction Via Shaft Boring Machine, Tunnelling and Underground Space Technology, 140 (2023), ID105321

2025 Society of Thermal Engineers of Serbia. Published by the VinĨa Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence