No abstract

The success of a cement production project depends on the supply of raw materials. Long-term quarry production scheduling (LTQPS) based on resource models is essential to maintain a consistent supply to cement plants. Geological uncertainty is inherent due to sparse exploration data in resource models and significant risk factors for not achieving production targets. This research proposes a stochastic framework for LTQPS that considers the impact of geological uncertainty on raw material supply. A clustering algorithm uses multiple simulated deposit models to aggregate blocks into mining cuts. A new stochastic mixedinteger programming model is formulated with two objectives: to minimise the cost for developing the raw mix and the risk of not meeting production targets. The proposed framework is implemented successfully in a limestone deposit in Southern Vietnam, resulting in an increase of 5 million tons (Mt) and a 30% reduction in unit cost over the deterministic mixed-integer programming model.

No abstract

Blast fragmentation size distribution is one of the most critical factors in evaluating the blasting results and affecting the downstream mining and processing operations in open-pit mines. Image-based methods are widely applied to address the problem but require heavy user interaction and experience. This study deployed a deep learning model Mask R-CNN to develop an automatic measurement method of blast fragmentation. The model was trained using images captured from real blasting sites in Nui Phao open-pit mine in Vietnam. The trained model reported high average precision scores (Intersection over Union, IoU = 0.5) 92% and 83% for bounding box and segmentation masks, respectively. The results lay a solid technical basis for the automated measurement of blast fragmentation in open-pit mines.

Precise and reliable prediction of blast fragmentation is essential for the success of mining operations. Over the years, various machine learning models using artificial neural network have developed and proven to be efficient in predicting the blast fragmentation. In this research, we design multiple-output neural networks to forecast the cumulative distribution function (CDF) of blast fragmentation to improve this prediction. The model architecture contains multiple response variables in the output layer that correspond to the CDF curve’s percentiles. We apply Monte Carlo dropout procedure to estimate the uncertainty of the predictions. Data collected from a Nui Phao open-pit mine in Vietnam are used to train and validate the performance of the model. Results suggest that multiple-output neural network models provide better accuracy than single-output neural network models that predict each percentile on a CDF independently. Whereas, Monte Carlo dropout technique can give valuable and relative reliable information during decision making. Article highlights: • Precise and reliable prediction of blast fragmentation is essential for the success of mining operations. • A predictive model based on the multi-output neural network and Monte Carlo dropout technique was designed to predict the fragmentation CDF curve in the blasting operation of an open-pit mine. • The predictive model was proven reliable and provided better accuracy than models based on a single-output neural network.