Hyongdoo Jang

Overbreak and underbreak in underground stoping operations cause significant challenges, impacting safety and operational efficiency, leading to dilution and ore loss. This study employs machine learning methods to predict overbreak and underbreak at individual drillhole locations, enabling dynamic prediction of stope shapes before blasting in underground mining. Based on a comprehensive database collected from a longhole sublevel stoping mine in Western Australia, different machine learning-based models, including multiple linear regression, random forest regression, gradient boosting machine, and Gaussian process regression, were developed systematically. The best-performing model was the initial Gaussian process regression with the Matérn 3/2 kernel, achieving R2 value of 0.820 and a root mean squared error value of 0.452. A series of hybrid models were also developed to improve prediction accuracy by combining Gaussian process regression, gradient boosting machine[A5.1], random forest regression, and artificial neural network with linear meta-learners. The best hybrid configuration achieved with R2 value of 0.721 and RMSE value of 0.425, but further complexity led to overfitting with no gains in generalisation. SHapley Additive explanations analysis across all models highlighted the Mathews stability number, ratio of burden to spacing, and void ratio as the most influential variables, varying in impact between the random forest regression, gradient boosting machine, and Gaussian process regression models.

In recent years, mine site closure and rehabilitation have emerged as significant global challenges. The escalating number of abandoned mines, exemplified by over 60,000 in Australia in 2017, underscores the urgency. Growing public concerns and governmental focus on environmental issues are now jeopardising sustainable mining practices. This paper assesses the role of unmanned aerial vehicles (UAVs) in mine closure, exploring sensor technology, artificial intelligence (AI), and mixed reality (MR) applications. Prior research validates UAV efficacy in mining, introducing various deployable sensors. Some studies delve into AI’s use for UAV data analysis, but a comprehensive review integrating AI algorithms with MR methods for mine rehabilitation is lacking. The paper discusses data acquisition methods, repeatability, and barriers toward fully autonomous monitoring systems for mine closure projects. While UAVs prove adaptable with various sensors, constraints such as battery life and payload capacity impact effectiveness. Although UAVs hold potential for AI testing in mine closure studies, these applications have been overlooked. AI algorithms are pivotal for creating autonomous systems, reducing operator intervention. Moreover, MR’s significance in mine closure is evident, emphasising its application in the mining industry. Ultimately, a hybrid UAV–AI–MR technology is not only viable but essential for achieving successful mine closure and sustainable mining practices in the future.

This research introduces an innovative technique for estimating the particle size distribution of muckpiles, a determinant significantly affecting the efficiency of mining operations. By employing deep learning and simulation methodologies, this study enhances the precision and efficiency of these vital estimations. Utilizing photogrammetry from multi-view images, the 3D point cloud of a muckpile is meticulously reconstructed. Following this, the particle size distribution is estimated through deep learning methods. The point cloud is partitioned into various segments, and each segment’s distinguishing features are carefully extracted. A shared multilayer perceptron processes these features, outputting scores that, when consolidated, provide a comprehensive estimation of the particle size distribution. Addressing the prevalent issue of limited training data, this study utilizes simulation to generate muckpiles and consequently fabricates an expansive dataset. This dataset comprises 3D point clouds and corresponding particle size distributions. The combination of simulation and deep learning not only improves the accuracy of particle size distribution estimation but also significantly enhances the efficiency, thereby contributing substantially to mining operations.

Surface mining operations often face issues due to boulders caused by caprock layers. Caprock substantially impacts the productivity of the mine by obstructing rock fracture and posing safety hazards. This study aimed to determine an optimal bench blast design for areas where caprock is present. An initial bench blast model was designed based on the Langefors method, and the effects of caprock were simulated using AUTODYN. The Scaled Depth of Burial (SDOB) was employed to evaluate the effects of pocket charge location. The simulation revealed a 15% damage improvement with only 5% of the total explosive as a pock charge. The SDOB analysis concluded that positioning of pocket charges at the 3/5 point of the caprock thickness and making up 25% of the total explosive charge effectively crushes the caprock with minimal flyrock.

High energy consumption in size reduction operations is one of the most significant issues concerning the sustainability of raw material beneficiation. Thus, process optimization should be done to reduce energy consumption. This study aimed to investigate the applicability of artificial neural networks (ANNs) to predict the particle size distributions (PSDs) of mill products. PSD is one of the key sources of information after milling since it significantly affects the subsequent beneficiation processes. Thus, precise PSD prediction can contribute to process optimization and energy consumption reduction by avoiding over-grinding. In this study, coal particles (−2 mm) were ground with a rod mill under different conditions, and their PSDs were measured. The variables studied included volume% (vol.%) of feed (coal particle), vol.% rod load, and grinding time. Our supervised ANN models were developed to predict PSDs and trained by experimental data sets. The trained models were verified with the other experimental data sets. The results showed that the PSDs predicted by ANN fitted very well with the experimental data after the training. Root mean squared error (RMSE) was calculated for each milling condition, with results between 0.165 and 0.965. Also, the developed ANN models can predict the PSDs of ground products under different milling conditions (i.e., vol.% feed, vol.% rod load, and grinding time). The results confirmed the applicability of ANNs to predict PSD and, thus the potential contribution to reducing energy consumption by optimizing the grinding conditions.

In mining operations that employ explosives and mineral processing, one of the important factors for efficient and low-cost operation is the fragmentation size distribution of rock after it has been blasted. Automatic scaling is a critical component of fragmentation size distribution measurement as it will directly determine the accuracy of the size estimation. In this study, we propose a method to create a system for creating a scaled 3D CG model, without the use of ground truth data such as GCPs (Ground Control Points), for the purpose of improving fragmentation size distribution measurement using positional data such as GNSS (Global Navigation Satellite System)-aided photogrammetry. We confirmed the validation of the method through an experimental evaluation of actual muckpiles. The results showed evidence of improving the scaling aspect of 3D fragmentation measurement systems without using GCPs or manual scales, specifically in surface mines where GNSS data are available.

Over two decades, block caving mining has developed the application of hydraulic fracturing as a preconditioning method. This study aims to estimate hydraulic fracturing costs in block caving operations and suggests the base case of specified costs based on the U.S. Energy Information Administration (EIA) report. Furthermore, it applies cavability factors to develop the long- and short-term strategies through the fuzzy inference system. In the long-term strategy, we suggest three possible scenarios for reducing the long-term strategy’s uncertainty by considering the association for the advancement of cost engineering (AACE)’s contingency rate. Moreover, each fuzzy membership function of the three possible redeveloped scenarios was analysed through arithmetic operations over independent/dependent fuzzy numbers for comparing each scenario. The outcome of flexible cost estimation suggested deciding on the scale of infrastructure and ore production by facilitating undercut propagation and controlling block height of block caving operation including additional fragmentation processes. The result of this study also illustrated that systematic fuzzy cost engineering could help estimate the initial stage of budgeting. In addition, through solving the uncertainty of fuzzy calculation values, the project schedule identification is presented by recognising the dependence on each scenario’s common characteristic of the cavability parameter and cost contingency rate.

Numerical modelling has become an important tool in the underground rock bolt reinforcement designing process. Numerical modelling provides the advantage of easily and quickly simulating complex underground geometries and mechanisms with sensitivity analyses. However, a numerical model needs to be calibrated using mathematical solutions, lab testing or with actual in-situ observations and measurements (which is the preferred method) before its results can be quantitatively applied to reinforcement design. Instrumented rock bolts provide a useful data source for calibrating in-situ rock bolt models. In this work, procedures have been presented to identify and determine the orientation of structures in the rock mass based on the strains on the instrumented rock bolts. A method to calibrate the rock bolt model with in-situ data is also presented. The results of the presented procedures have been validated with laboratory tests and numerical modelling. The procedures have been applied to create and calibrate an in-situ rock bolt model in FLAC3D and the results are validated using in-situ data.

Fragmentation size distribution estimation is a critical process in mining operations that employ blasting. In this study, we aim to create a low-cost, efficient system for producing a scaled 3D model without the use of ground truth data, such as GCPs (Ground Control Points), for the purpose of improving fragmentation size distribution measurement using GNSS (Global Navigation Satellite System)-aided photogrammetry. However, the inherent error of GNSS data inhibits a straight-forward application in Structure-from-Motion (SfM). To overcome this, the study proposes that, by increasing the number of photos used in the SfM process, the scale error brought about by the GNSS error will proportionally decrease. Experiments indicated that constraining camera positions to locations, relative or otherwise, improved the accuracy of the generated 3D model. In further experiments, the results showed that the scale error decreased when more images from the same dataset were used. The proposed method is practical and easy to transport as it only requires a smartphone and, optionally, a separate camera. In conclusion, with some modifications to the workflow, technique, and equipment, a muckpile can be accurately recreated in scale in the digital world with the use of positional data.

The rapid industrialization in recent decades has enormously increased demands for energy and mineral resources. At the same time, economically viable resources near the surface have been nearly depleted, and the mining industry is facing new challenges of processing low-grade ore, increasing depth, climate changes, and rigorous social and environmental constraints. Furthermore, accountability for major social and sustainable development problems in the mining sector has imposed a further economic burden on mining companies. These challenges in the mining industry can be solved through technical improvements and the optimization of the entire mining value chain using advanced information and communication technologies (ICTs) and automation techniques. This paper presents future prospects of the mining industry by reviewing the sustainable development in mining, the global trend of mining innovations and initiatives of major mining companies, and some new mining technologies in Australia. Furthermore, future prospects and blueprints of the mining industry are suggested. Highlights