Mining

Mining operations conducted beneath water-bearing strata pose significant risks associated with the development of water-conducting fracture zones in the overburden. The height criterion for this parameter is critical to ensuring the stability of underground mine workings and preventing the risk of water inrush incidents. The research is based on physical and numerical simulations and aims to forecast the development of the water-conducting fracture zone. The methodology is based on in situ hydrogeology data, geotechnical boreholes, physical 2D modeling of rock strata, discrete element modeling using UDEC, and finite–discrete element modeling using Prorock software. A physical model of layered rock mass is constructed to simulate unfilled excavation areas induced deformation under real polymetallic ore field conditions. Based on the results, relationships between vertical subsidence, layer curvature, inclination, and the height of the water-conducting fracture zone were obtained. Particular attention is given to the effects of tectonic discontinuities, chamber geometry, and backfilling on fracture development. A stepwise excavation sequence is simulated to reproduce field conditions and assess the evolution of stress and deformation fields in the overburden. The study reveals that the propagation of the fracture zone around a mine excavation adheres to a polynomial law, characterized by an increase in height concurrent with the expansion of the excavation. This approach enables the design of safe extraction strategies beneath aquifers or surface water bodies. The proposed framework is expected to enhance prediction accuracy and reduce uncertainties. Full article

The effects of key variables on weak-acid-dissociable (WAD) and free cyanide oxidation by ozone injection in gold mine pulp were studied at laboratory scale to find an alternative cyanide treatment. A fractional factorial analysis of five process variables (O₃/O₂ flow, reaction time, NH₄HSO₃ concentration, temperature, and pH) informed a 60-run experimental matrix, in a 1 L cylindrical reactor, with the process variables controlled during the ozone injection. The findings may inform future strategies for safer cyanide management in gold mining processes. Free cyanide is the most toxic form of cyanide. Its oxidation increases with higher O₃/O₂ concentrations, longer exposure time, and higher pH. Maintaining a pH above 7 is crucial. Lower pH values favor the dissociation of cyanide into its toxic, free form. WAD cyanide oxidation depends mainly on the O₃/O₂ concentration, exposure time, and NH₄HSO₃ concentration. Increasing O₃/O₂ and time enhanced both WAD and free cyanide oxidation, while NH₄HSO₃ concentration affected oxidation rates differently. The results show that free cyanide was significantly more oxidized (84.1413%) than WAD cyanide (67.2423%). Controlling the WAD cyanide process yields excellent free cyanide oxidation. This represents ongoing improvement at an industrial scale. This approach quantifies the extent to which process variables affect the WAD and free cyanide oxidation under controlled conditions, thereby greatly reducing environmental impact. Full article

Mining conveyor belts are critical components in bulk material transportation, but their operational safety is frequently threatened by diverse damages such as blocks, cracks, foreign objects, and holes. Existing detection methods, including traditional computer vision and conventional neural networks, struggle to balance accuracy and efficiency in harsh mining environments—marked by high levels of dust, uneven lighting, and extreme scale variability (5–300 pixels). Our study proposes WTConv-YOLO, an improved model based on YOLOv11, integrating two core modules: (1) wavelet transform convolution (WTConv), which achieves a logarithmically expanding receptive field with linearly growing parameters, allowing for the concurrent capture of high-frequency local details and low-frequency global context; (2) Scale-based Dynamic Loss (SD Loss), which dynamically adjusts bounding box similarity and localization loss weights according to target scale, mitigating IoU fluctuation interference and enhancing small-target detection stability. Experiments on the Mining Industrial Conveyor Belt Dataset show that WTConv-YOLOv11 achieves a mean Average Precision (mAP@0.5) of 73.8%—a 3.5% improvement over the baseline YOLOv11. A Python-based software system is developed for end-to-end detection. This work provides a practical solution for reliable conveyor belt damage detection in mining scenarios. Full article

In the mining industry, where equipment breakdowns cause expensive unplanned downtime, operational continuity is paramount. Internet of Things (IoT) technologies have the potential to make predictions; however, most solutions lack a holistic view and mapping of complex system interdependencies. This study presents a comprehensive predictive maintenance (PdM) framework specifically designed for continuous-operation mining environments, with a primary focus on Semi-Autogenous Grinding (SAG) mills. By combining exploratory data analysis, advanced feature engineering, classical machine learning (Gradient Boosting Classifier), and deep learning (LSTM with multiple time-window configurations), the system achieves real-time anomaly detection, root-cause explanation, and failure forecasting up to 48 h in advance (average lead time: 17 h). A four-layer digital twin architecture integrated with Streamlit enables actionable alerts classified as emergency, planned, or preventive interventions. Applied to a one-year dataset comprising 99,854 hourly records from an industrial SAG mill, the hybrid model prevented an estimated 219.5 h of unplanned downtime, yielding substantial economic benefits. The proposed solution is deliberately designed for high adaptability across multiple equipment types and industrial sectors beyond mining. Full article

Water wastage management (WWM) in deep-level mines remains a critical challenge, as wastage increases operational costs and threatens sustainability. This study presents a systematic state-of-the-art review of WWM in deep-level mines. Relevant literature was critically assessed to establish current practices, identify limitations, and explore emerging solutions. Five principal approaches were identified: leak detection and repair, pressure control with fixed schedules, network optimisation, accountability measures, and smart management. While each provides benefits, significant challenges persist. Particularly, current pressure control techniques, essential for limiting leakage, rely on static demand profiles that cannot accommodate the stochastic nature of service water demand, often resulting in over- or under-supply. Smart management systems, which have proven effective for managing stochastic utilities in other industries, present a promising alternative. Enabling technologies such as sensors, automated valves, and tracking systems are already widely deployed in mining, underscoring the technical feasibility of such systems. However, no studies have yet examined their development for WWM in deep-level mines. This study recommends a framework for smart water management tailored to mining conditions and highlights three opportunities: developing real-time demand approximation methods, leveraging occupancy data for demand estimation, and integrating these models with mine water supply control infrastructure for implementation and evaluation. Full article

To address the severe geological hazards (e.g., high ground stress and rock burst) that threaten safety and efficiency in ultra-deep mining, this study develops a comprehensive microseismic monitoring system tailored for the Sishanling Iron Mine—a typical ultra-large-scale, ultra-deep mine with an extraction depth exceeding 1500 m. The system integrates high-sensitivity sensors, real-time data transmission, and intelligent processing algorithms. A scientifically designed sensor deployment plan achieves full-coverage of key mining areas, while a multi-level data processing framework encompassing signal acquisition, event detection, location inversion, and magnitude calculation enhances result accuracy. Applied in actual operations, the system effectively captures microseismic events with magnitudes from −2.14 to −1.96, achieving optimal planar and spatial positioning errors of 6.75 m and 9.66 m, respectively. It provides real-time early warning for hazards like rock burst, thereby mitigating risks and ensuring operational continuity. This work offers a practical reference for constructing microseismic systems in similar “double super” mines and enriches the theoretical and technical framework for safety monitoring in deep mining. Full article

Assessing the stress–strain state around interacting mining excavations using the finite element method (FEM) is computationally expensive for parametric studies. This study evaluates tabular machine-learning surrogate models for the rapid prediction of full stress–strain fields in fractured rock masses treated as an equivalent continuum. A dataset of 1000 parametric FEM simulations using the elastoplastic generalized Hoek–Brown constitutive model was generated to train Random Forest, LightGBM, CatBoost, and Multilayer Perceptron (MLP) models based on geometric features. The results show that the best models achieve R² scores of 0.96–0.97 for stress components and 0.99 for total displacements. LightGBM and CatBoost provide the optimal balance between accuracy and computational cost, offering speed-ups of 15 to 70 times compared to FEM. While Random Forest yields slightly higher accuracy, it is resource-intensive. Conversely, MLP is the fastest but less accurate. These findings demonstrate that data-driven surrogates can effectively replace repeated FEM simulations, enabling efficient parametric analysis and intelligent design optimization for mine workings. Full article

While multi-view visualization systems are widely used for mining vehicle teleoperation, they often impose high cognitive load and restrict operator attention. To explore a more efficient alternative, this study evaluated a merged-view interface that integrates multiple camera perspectives into a single coherent display. In a controlled experiment, 35 participants navigated a teleoperated robot along a 50 m lab-scale path representative of an underground mine under both multi-view and merged-view conditions. Task performance and eye-tracking data—including completion time, path adherence, and speed-limit violations—were collected for comparison. The merged-view system enabled 6% faster completion times, 21% higher path adherence, and 28% fewer speed-limit violations. Eye-tracking metrics indicated more efficient and distributed attention: blink rate decreased by 29%, fixation duration shortened by 18%, saccade amplitude increased by 11%, and normalized gaze-transition entropy rose by 14%, reflecting broader and more adaptive scanning. NASA-TLX scores further showed a 27% reduction in perceived workload. Regression-based sensitivity analysis revealed that gaze entropy was the strongest predictor of efficiency in the multi-view condition, while fixation duration dominated under merged-view visualization. For path adherence, blink rate was most influential in the multi-view setup, whereas fixation duration became key in merged-view operation. Overall, the results indicated that merged-view visualization improved visual attention distribution and reduced cognitive tunneling indicators in a controlled laboratory teleoperation task, offering early-stage, interface-level insights motivated by mining-relevant teleoperation challenges. Full article

Optimizing the blast energy distribution is crucial for enhancing rock fragmentation, minimizing overexcavation, and boosting profitability in mining operations. This study introduces a theoretical model to predict the blasting Energy Factor ${(\mathrm{F}}_{\mathrm{e}})$ in mining tunnels, based on the Cracking Energy ${(\mathrm{E}}_{\mathrm{g}})$ of the rock mass, derived from the deformation energy of brittle materials (Young’s modulus) and adjusted by the Rock Mass Rating (RMR). The model was validated using 42 blasting datasets from horizontal galleries at El Teniente mine, Chile. Data included geometric parameters (tunnel sections, drilling length, diameter, number of holes, meters drilled), explosive type and consumption, and geomechanical properties, particularly the RMR. Results show that as rock mass quality improves (higher RMR), both ${\mathrm{F}}_{\mathrm{e}}$ and $\%{\mathrm{E}}_{\mathrm{g}}$ increase, more competent rock masses require higher input energy to initiate and propagate cracks, and a greater portion of that energy is effectively utilized for crack formation. For instance, rock masses with an RMR of 66 exhibited an average ${\mathrm{F}}_{\mathrm{e}}$ of 7.62 MJ/m³ and $\%{\mathrm{E}}_{\mathrm{g}}$ of 4.8%, while those with an RMR of 75 showed higher values (${\mathrm{F}}_{\mathrm{e}}$ = 8.47 MJ/m³, $\%{\mathrm{E}}_{\mathrm{g}}$ = 6.4%). This confirms that less fractured rock masses require higher ${\mathrm{F}}_{\mathrm{e}}$ and $\%{\mathrm{E}}_{\mathrm{g}}$ for effective fragmentation. Lithology also plays a significant role in energy consumption. Diorite displayed the highest ${\mathrm{F}}_{\mathrm{e}}$ (8.34 MJ/m³) and higher efficiency ($\%{\mathrm{E}}_{\mathrm{g}}$ = 7.0%), whereas andesite showed lower ${\mathrm{F}}_{\mathrm{e}}$ (7.61 MJ/m³) and lower crack propagation efficiency ($\%{\mathrm{E}}_{\mathrm{g}}$ = 3.7%). Unlike traditional ${\mathrm{F}}_{\mathrm{e}}$ prediction methods, which rely solely on explosive data and excavation volume, this model integrates RMR, enabling more precise energy allocation and fostering sustainable mining practices. This approach enhances decision-making in blast design, offering a more robust framework for optimizing energy use in mining operations. Full article

The classification of mineral resources and reserves provides a structured framework for evaluating the geological, technical, and economic aspects of mineral deposits. To reduce subjectivity and enhance reliability, international reporting standards established the principles of transparency, materiality, and competence. Many operating mines are seeking alignment with these frameworks to strengthen governance and access global capital. Within this context, the Mineral Resources and Reserves Readiness Index (MR³ Index) is introduced as a tool to assess the degree of alignment of mining operations with international reporting requirements. For operating mines, a key variable in the MR³ Index is the demonstrated ability to consistently convert Inferred Mineral Resources into mine production, even without prior reclassification into Indicated or Measured categories. When supported by geological homogeneity and well-defined controls, this track record serves as a strong proxy for geological confidence and operational maturity. The methodology was applied to an underground lithium mine in Brazil, which achieved a readiness level of 95.5%. A sensitivity analysis demonstrated the robustness of the MR³ Index and showed that the final score is considerably more sensitive to the class scores than to the selection of class weights, reinforcing the importance of documentation quality and technical consistency in public reporting. Full article

Reclamation of tailings facilities at oil sands mines in northern Alberta presents a significant challenge for industry, regulators, and researchers. Atterberg limits are an established method for quantifying clay behaviour in geotechnical engineering, which has been adopted for oil sands tailings due to their high clay mineral content. Correlations between remoulded undrained shear strength and liquidity index, originally developed for natural clays, have also been applied to oil sands tailings. This paper proposes a new material-specific correlation between remoulded undrained shear strength and liquidity index based on laboratory testing of oil sands tailings. Additionally, the results of Atterberg limits tests on oil sands tailings suggests that the inherent variability of the test itself has a greater effect on the measured value than the preparation method and test procedure. The results of this study support the idea that index properties such as Atterberg limits can provide a cost-effective method for field monitoring and early-stage reclamation design. Full article

This article delineates the outcomes of a comprehensive analysis of occupational conditions in coal mining, focusing on dust exposure. A multifaceted model is proposed for the holistic evaluation of occupational environments, integrating risk assessment methodologies and decision-making frameworks within a risk-based paradigm. Risk assessment involved pairwise comparison, T. Saaty’s Analytic Hierarchy Process, a pessimistic decision-making approach, and fuzzy set membership functions. Correlations were established between respiratory disease risk among open pit coal mine workers and dust generation sources at the project design phase. The risk values were then validated using source attributes and particle physicochemical parameter analysis, including disperse composition and morphology. The risk assessment identified haul roads as a predominant factor in occupational disease pathogenesis, demonstrating a calculated risk level of R = 0.512. The dispersed analysis indicated the prevalence of PM1.0 and submicron particles (≤1 µm) with about 77% of the particle count, the mass distribution showed the respirable fraction (1–5 µm) comprising up to 50% of the total dust mass. Considering in situ monitoring data and particulate morphology analysis haul roads (R = 0.281) and the overburden face (R = 0.213) were delineated as primary targets for the implementation of enhanced health and safety interventions. While most critical at the design stage amidst data scarcity and exposure uncertainty, the approach permits subsequent refinement of occupational risks during operations through the incorporation of empirical monitoring data. Full article

This paper presents a real-time quarry truck monitoring system that combines deep learning and license plate recognition (LPR) for operational monitoring and weighbridge reconciliation. Rather than estimating load volumes directly from imagery, the system ensures auditable matching between detected trucks and official weight records. Deployed at quarry checkpoints, fixed cameras stream to an edge stack that performs truck detection, line-crossing counts, and per-frame plate Optical Character Recognition (OCR); a temporal voting and format-constrained post-processing step consolidates plate strings for registry matching. The system exposes a dashboard with auditable session bundles (model/version hashes, Region of Interest (ROI)/line geometry, thresholds, logs) to ensure replay and traceability between offline evaluation and live operations. We evaluate detection (precision, recall, mAP@0.5, and mAP@0.5:0.95), tracking (ID metrics), and (LPR) usability, and we quantify operational validity by reconciling estimated shift-level tonnage T against weighbridge tonnage T* using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), R², and Bland–Altman analysis. Results show stable convergence of the detection models, reliable plate usability under varied optics (day, dusk, night, and dust), low-latency processing suitable for commodity hardware, and close agreement with weighbridge references at the shift level. The study demonstrates that vision-based counting coupled with plate linkage can provide regulator-ready KPIs and auditable evidence for production control in quarry operations. Full article

Suspended conveyor belts are widely used in mining, including in systems with non-contact support such as magnetically suspended conveyors, where the maximum admissible linear mass of the loaded belt determines the required supporting forces. This paper presents a method for estimating the upper limit of the linear mass of a suspended belt for a given belt width and bulk material. Several cross-sectional configurations are analysed, and analytical expressions for the bulk cross-sectional area under limiting fill are derived. A numerical search over the troughing radius is then performed to find the radius that maximises the cross-sectional area and to select the configuration that provides the largest area. For this configuration, the extremum condition leads to a transcendental equation; so, symbolic regression with the PySR package is used to obtain an explicit approximation for the radius that maximises the area as a function of belt width and angle of repose. Substituting this expression into the standard formula for linear mass yields a closed-form estimate of the maximum admissible linear mass. Numerical examples show good agreement with the optimisation results and indicate that the formula is suitable for preliminary design of suspended and magnetically suspended belt conveyors. Full article

The mining industry places high priority on occupational safety, process quality and operational efficiency. Roadheaders are widely deployed in coal mines to support fully automated excavation, reducing workers’ physical strain and improving overall safety. This article examines an automatic control system for a roadheader cutting head designed to increase mining efficiency, reduce energy consumption and maintain stable performance under varying coal and rock conditions. The system integrates advanced control algorithms with geological strength index (GSI) analysis and asynchronous motor control strategies. GSI-based adaptive speed control conserves energy and increases cutting efficiency compared to manual control. By reducing dynamic load fluctuations, transitions between different cutting zones become smoother, which decreases equipment wear. The proposed control system incorporates speed feedback loops that use a proportional–integral (PI) controller with field-oriented control (FOC), as well as super-twisted sliding mode control (STSMC) with FOC. FOC with STSMC improves roadheader productivity by applying advanced control strategies, adaptive speed regulation and precise geological strength analysis. It is also better able to handle disturbances and sudden loads thanks to STSMC’s nonlinear control robustness. The result is safer, more efficient, and more cost-effective mining that can be implemented across a wide range of underground mining scenarios. Full article

This article describes the current status and future development trends of mine hoist control systems. The growing market demand for hoists and the need for stable, uninterrupted operation ensure the practical application of this article. A permanent magnet synchronous motor (PMSM) is used as the primary power source for the mine hoist. A MATLAB model is developed, using PID controllers to control the PMSM’Scheme 10. tons of CO₂ from electricity consumption, this equates to a reduction of 300 to 800 tons per year. Full article

Despite technological advancements in mining, Chile lacks comprehensive risk management models for tailings storage facilities (TSFs), which hinders the prevention and mitigation of structural and environmental risks. This study aims to develop an integrated risk management model for TSFs in Chile, combining geological and mining engineering with an updated regulatory framework to enhance safety and reduce environmental impacts. The research adopts a mixed-methods approach. Qualitatively, it draws on 10 semi-structured interviews with engineers, geologists, academics, and professionals from the Chilean mining industry, selected through purposive sampling, to explore how and why the current risk management model should be improved. Quantitatively, it analyzes data from 303 surveys assessing the existing regulatory framework, a proposed new regulatory decree for Chile, and key variables to be considered in TSF risk management. The results present a new model that integrates geochemical and geotechnical characterization, process variables, in situ sensors, remote sensing, and artificial intelligence to generate dynamic risk indicators and early warning systems throughout the life cycle of the facility, including closure and liability valuation. Its multiscale design, adaptable to seismic and hydrogeological conditions and suitable for small- and medium-scale mining, overcomes existing static and fragmented approaches, enabling more effective decision-making with a focus on environmental and community safety. The study concludes that the model provides a robust and coherent tool for TSF risk management by integrating technical expertise, the current regulatory framework, and the management of key variables that enhance the ability to anticipate and mitigate structural and environmental risks. Full article

Reliable detection of defects in steel wire ropes is pivotal to ensuring safety and maintaining operational reliability of hoisting and lifting systems in mining and other industries. This study proposes an automated monitoring method based on analyzing the cross-sectional size profile extracted from high-quality visual images. Each image undergoes preprocessing—adaptive binarization, noise suppression, and edge extraction—followed by formation of a one-dimensional thickness profile along the rope’s longitudinal axis. Aggregate statistical descriptors (mean, standard deviation, extrema, and shape descriptors) computed from this profile are supplied to a CatBoost gradient boosting classifier. The model achieves an F1-score exceeding 0.93 across diagnostic categories (intact, bend, kink, break), with particularly high accuracy for critical damage such as wire breaks. Compared with conventional image CNN classifiers, the proposed approach offers higher interpretability, lower computational complexity, and robustness to noise and visual artifacts. The results substantiate the method’s efficacy for real-time automated condition monitoring of mining equipment and its suitability for integration into industrial machine-vision systems. The results substantiate the method’s efficacy for real-time automated condition monitoring of mining equipment and its suitability for integration into industrial machine-vision systems. Full article