Rock Mechanics
Festus Kunkyin-Saadaari; Jude Baah Offei; Sadique Ibn Sadique; Victor Kwaku Agadzie; Ishamel Abeiku Forson
Abstract
The underground mining operations at the Obuasi Gold Mine rely heavily on the stability of hard rock pillars for safety and productivity. The traditional empirical and numerical methods for predicting pillar stability have limitations, prompting the exploration of advanced machine learning techniques. ...
Read More
The underground mining operations at the Obuasi Gold Mine rely heavily on the stability of hard rock pillars for safety and productivity. The traditional empirical and numerical methods for predicting pillar stability have limitations, prompting the exploration of advanced machine learning techniques. Hence, this work investigates the applicability of stacked generalisation techniques for predicting the stability status of hard rock pillars in underground mines. Four stacked models were developed, using Gradient Boosting Decision Trees (GBDTs), Random Forest (RF), Extra Trees (ET), and Light Gradient Boosting Machines (LightGBMs), with each model taking turns as the meta-learner, while the remaining three models acted as the base learners in each case. The models were trained and tested on a dataset of 201 pillar cases from the AngloGold Ashanti Obuasi Mine in Ghana. Model performance was evaluated using classification metrics, including accuracy, precision, recall, F1-score and Matthews Correlation Coefficient (MCC). The RF-stacked model demonstrated the best overall performance, achieving an accuracy of 93.44%, precision of 94.27%, recall of 93.44%, F1-score of 93.59%, and MCC of 88.90%. Feature importance analysis revealed pillar depth and pillar stress as the most influential factors affecting pillar stability prediction. The results indicate that stacked generalisation techniques, particularly the RF-stacked model, offer promising capabilities for predicting hard rock pillar stability in underground mining operations.
Rock Mechanics
Sajjad Khalili; Masoud Monjezi; Hasel Amini Khoshalan; Amir Saghat foroush
Abstract
Determining the appropriate blasting pattern is important to prevent any damage to the tunnel perimeter in conventional tunneling by blasting operation in hard rocks. In this research work, the LS-DYNA software and numerical finite element method (FEM) are used for simulation of the blasting process ...
Read More
Determining the appropriate blasting pattern is important to prevent any damage to the tunnel perimeter in conventional tunneling by blasting operation in hard rocks. In this research work, the LS-DYNA software and numerical finite element method (FEM) are used for simulation of the blasting process in the Miyaneh-Ardabil railway tunnel. For this aim, the strong explosive model and nonlinear kinematic plastic material model are considered. Furthermore, the parameters required for the Johnson-Holmquist behavioral model are based on the Johnson-Holmquist-Ceramic material model relationships and are determined for the andesitic rock mass around studied tunnel. The model geometry is designed using AUTOCAD software and Hyper-mesh software is applied for meshing simulation. After introducing elements properties and material behavioral models and applying control and output parameters in LS-PrePost software, the modeling process is performed by LS-DYNA software. Different patterns of blastholes including 66, 23, and 19 holes, with diameters of 40 and 51 mm, and depths of 3 to 3.8 m are investigated by three-dimensional FEM. The borehole pressure caused by the ammonium nitrate-fuel oil (ANFO) detonation is considered based on the Jones-Wilkins-Lee (JWL) equation of state in the LS-DYNA software. The outer boundaries of the model are considered non-reflective to prevent the wave’s return. The results showed that LS-DYNA software can efficiently simulate the blasting process. Moreover, the post-failure rate of the blasting is reduced by more than 30% using the main charge with less explosive power and reducing the distance and diameter of contour holes.
