A machine learning method for the support design in underground mine haul roads

Date

2023-7-18

Author

Kutlubay, Gökhan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

443
views

185
downloads

Cite This

Permanent openings in underground mines require extensive geomechanical and geological investigation to determine the excavation dimensions and the support configuration assuring the long-term stability.Empirical systems have been adopted in underground excavation design due to their advantages in terms of matching the rock mass quality with the potential support configuration.Geomechanical classification system and Q-tunneling index are the most commonly accepted techniques for the preliminary support analysis. However, they cover only the significant conditions and they require to specify the intermediate conditions by field observations or numerical analyses. Computational geomechanics makes use of computational power to simulate the various excavation and support designs well-before the implementation. This research carries out a parametric study to examine the support requirements for underground mine haul roads excavated in various geomechanical conditions at different depths and field loadings. Performance of the empirically recommended support systems were checked with the finite element models relying on stress and deformation analyses. Finally, an artificial neural network model was trained using the numerical simulation outputs. Predictions of the model approve a good correlation computational outputs, which implies the proposed method can be considered for certain conditions.

Subject Keywords

Underground Mining, Main Haul Roads, Support Design, Numerical Analysis, Machine Learning

URI

https://hdl.handle.net/11511/104804

Collections

Graduate School of Natural and Applied Sciences, Thesis