Recent developments in smart mining technology have enabled the production, collection, and sharing of a large amount of data in real time. Therefore, research employing machine learning (ML) that utilizes these data is being actively conducted in the mining industry. In this study, we reviewed 109 research papers, published over the past decade, that discuss ML techniques for mineral exploration, exploitation, and mine reclamation. Research trends, ML models, and evaluation methods primarily discussed in the 109 papers were systematically analyzed. The results demonstrated that ML studies have been actively conducted in the mining industry since 2018, mostly for mineral exploration. Among the ML models, support vector machine was utilized the most, followed by deep learning models. The ML models were evaluated mostly in terms of their root mean square error and coefficient of determination.
This study proposes a method for diagnosing problems in truck ore transport operations in underground mines using four machine learning models (i.e., Gaussian naïve Bayes (GNB), k-nearest neighbor (kNN), support vector machine (SVM), and classification and regression tree (CART)) and data collected by an Internet of Things system. A limestone underground mine with an applied mine production management system (using a tablet computer and Bluetooth beacon) is selected as the research area, and log data related to the truck travel time are collected. The machine learning models are trained and verified using the collected data, and grid search through 5-fold cross-validation is performed to improve the prediction accuracy of the models. The accuracy of CART is highest when the parameters leaf and split are set to 1 and 4, respectively (94.1%). In the validation of the machine learning models performed using the validation dataset (1500), the accuracy of the CART was 94.6%, and the precision and recall were 93.5% and 95.7%, respectively. In addition, it is confirmed that the F1 score reaches values as high as 94.6%. Through field application and analysis, it is confirmed that the proposed CART model can be utilized as a tool for monitoring and diagnosing the status of truck ore transport operations.
This study stochastically predicted ore production through discrete event simulation using four different probability density functions for truck travel times. An underground limestone mine was selected as the study area. The truck travel time was measured by analyzing the big data acquired from information and communications technology (ICT) systems in October 2018, and probability density functions (uniform, triangular, normal, and observed probability distribution of real data) were determined using statistical values. A discrete event simulation model for a truck haulage system was designed, and truck travel times were randomly generated using a Monte Carlo simulation. The ore production that stochastically predicted fifty times for each probability density function was analyzed and represented as a value of lower 10% (P10), 50% (P50), and 90% (P90). Ore production was underestimated when a uniform and triangular distribution was used, as the actual ore production was similar to that of P90. Conversely, the predicted ore production of P50 was relatively consistent with the actual ore production when using the normal and observed probability distribution of real data. The root mean squared error (RMSE) for predicting ore production for ten days in October 2018 was the lowest (24.9 ton/day) when using the observed probability distribution.
In this study, we proposed a method to simulate a truck-loader haulage system in open-pit mines and visualize the results in real time using the software AnyLogic. An open-pit limestone mine in Korea was selected as the study area. The time parameters for each unit operation of the haulage system were measured via a field survey. A discrete event simulation model for the mine was then developed using AnyLogic. We intuitively confirmed the simulation results with key production indicators and visualized the truck-loader haulage operation over time. This study was thus able to overcome the limitations of previous studies, which could not measure key production indicator values and the status of haulage systems in real time during simulations.
This study proposes a novel approach for enhancing the productivity of mining haulage systems by developing a hybrid model that combines machine learning (ML) and discrete event simulation (DES) techniques to predict ore production. This study utilized time data collected from a limestone underground mine using tablet computers and Bluetooth beacons for 15 weeks. The collected data were used to train an ML model to predict truck cycle time, and the support vector regression with particle swarm optimization (PSO–SVM) model demonstrated the best performance. The PSO–SVM model accurately predicted cycle time with a mean absolute error (MAE) of 2.79 min, mean squared error (MSE) of 14.29 min2, root mean square error (RMSE) of 3.79 min, and coefficient of determination (R2) of 0.68. The output of the ML model was linked to the DES model to predict ore production for each truck, section, and time period. Verification of the DES model demonstrated its ability to accurately simulate the haulage system in the study area by comparing production logs with the simulation results. This study’s novel approach offers a new method for predicting ore production and determining the optimal equipment combination for each workplace, thus enhancing productivity in mining haulage systems.
In this study, machine learning models were developed to predict air overpressure resulting from blasting in an open-pit mine. A total of 924 blasting data were collected from an open-pit mine at the Mt. Yogmang located in Changwon-si, Gyeongsangnam-do, Korea. The blasting data consisted of hole length, burden, spacing, maximum charge per delay, powder factor, number of holes, ratio of emulsion, monitoring distance and air overpressure. Four algorithms including k-nearest neighbors (kNN), random forest (RF), extreme gradient boosting (XGBoost) and deep neural network (DNN) were used to train the machine learning models. Mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE) were analyzed to evaluate the performance of the trained models. As a result, the RF model showed superior performance with MAE, MSE and RMSE of 4.938, 42.032 and 6.483, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.