Exploitation
Tapan Dey; Gopinath Samanta
Abstract
Accurate grade prediction is an important step in the mining planning process. Various methods, namely the Inverse Distance Method and Kriging, are widely used. The application of machine learning is a new development in the grade estimation technique. The present study focused on the application of ...
Read More
Accurate grade prediction is an important step in the mining planning process. Various methods, namely the Inverse Distance Method and Kriging, are widely used. The application of machine learning is a new development in the grade estimation technique. The present study focused on the application of XGBoost, Random Forests (RFs), Multi Layer Perceptron (MLP), and Gradient Boosting Regression (GBR) models to predict iron ore grades in an Indian mine. An ensemble model was also applied to obtain a more stable grade prediction in the deposit. Models were trained using 4,112 sample data, which have spatial coordinates (east, north, and altitude) and iron grades. The dataset was divided into two parts: 80% (3,289 samples) of the data was used for model training, and 20% (823 samples) was used for model testing. The performance of the models was assessed through the coefficient of determination (R²), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE). The results show that the XGBoost model performs better in the estimation process when compared with other methods, such as RFs, GBR, and MLP. The XGBoost model produced R² of 0.77, MSE of 2.87, and MAPE of 1.8%. The findings indicate that the XGBoost model is effective for predicting iron ore grades in this type of deposit. However, considering geological uncertainty, the application of an ensemble model may be beneficial for grade prediction in an iron deposit.
Exploitation
Gopinath Samanta; Tapan Dey; Suranjan Sinha
Abstract
The optimal layout of the stope (stope boundary) in an underground metal mine maximizes the profit of a deposit, subject to the geotechnical and operational mining constraints such as stope length, stope width, stope height. Various approaches have been introduced to address the stope boundary optimization ...
Read More
The optimal layout of the stope (stope boundary) in an underground metal mine maximizes the profit of a deposit, subject to the geotechnical and operational mining constraints such as stope length, stope width, stope height. Various approaches have been introduced to address the stope boundary optimization problem, but due to the computational complexity and numerous practical constraints, the existing models offer partial solutions to the problem. In the present work, a mixed integer programming model has been developed by incorporating mining constraints in a three-dimensional framework. This model is developed based on profit maximization. The sensitivity analysis applied in a case study mine indicates that the model is efficient in assessing the upside potential and downside risk of profit under fluctuating metal prices and mining costs. Additionally, it can be applied at different stages of mine design to facilitate resource appraisal, selection of stoping methods, and comprehensive mine planning. In a practical application on a real orebody, it shows that the proposed model can generate upto 37.32% more profit compared to current stope design practice in the mines.
