Search Results (395)

In industrial applications such as in situ leaching and uranium mining, permanent magnet synchronous motors (PMSMs) for submersible pumps are frequently connected to frequency converters via long cables. During this long-distance transmission, traveling wave reflections induced by high-frequency pulse width modulation (PWM) generate severe transient overvoltages that threaten motor insulation. Because installation space at deep-well motor terminals is severely restricted, overvoltage suppression must be implemented at the inverter output. Here, the parameter design and optimization of a passive LC filter specifically developed for 250 Hz high-frequency PMSMs are presented. The optimal inductance and capacitance parameters were determined by balancing multiple operational constraints, including fundamental voltage drop, high-frequency harmonic attenuation, and the avoidance of low-order harmonic resonance. Furthermore, the anti-saturation performance of the magnetic core material, evaluated thermal characteristics through electromagnetic-thermal co-simulation, and analyzed the risk of self-excited oscillation between the filter capacitors and the motor was analyzed. Finally, hardware experiments conducted on a 20 m cable test bench validate that the designed LC filter effectively mitigates terminal overvoltage. The peak terminal voltage was reduced from 900 V to 505 V, and total harmonic distortion (THD) was limited to below 5%. This design provides a highly reliable, space-efficient solution for overvoltage suppression in high-speed, long-cable motor drive systems. Full article

The greater cane rat algorithm (GCRA) represents an emerging swarm intelligence paradigm derived from the instinctual survival patterns exhibited by greater cane rats (GCRs), which simulates the typical male-dominated survival patterns of the GCR species, including rainy-season mating and reproduction behaviors, dry-season behavioral differentiation of solitary males and clustered females, and their nonlinear adaptive foraging characteristics. Nevertheless, the original GCRA suffers from inherent defects in complex and high-dimensional optimization scenarios, encompassing premature convergence phenomena, inadequate local exploitation proficiency, constrained convergence precision, and a proneness to stagnation at local optima, which severely restrict its practical engineering application. To address the aforementioned limitations, this work introduces an enhanced hybrid variant of the greater cane rat algorithm, amalgamated with Teaching-and-Learning-Based Optimization (TLBO) and designated as the TLGCRA, incorporating three pivotal targeted innovations. Specifically, the TLGCRA innovatively introduces the two-stage teacher–student interactive learning mechanism of TLBO on the basis of retaining the core evolutionary and behavioral characteristics of the original GCRA, which effectively compensates for the insufficient local disturbance capability of the original algorithm and enriches population diversity to avoid local optimum stagnation. Furthermore, an adaptive parameter tuning strategy is innovatively designed and embedded in the iterative optimization process, which dynamically balances the global exploration and local exploitation capabilities of the algorithm, fundamentally improving the low learning efficiency and weak mining performance of the GCRA. A suite of computational simulations is conducted across 23 canonical benchmark functions and six representative constrained engineering design optimization scenarios. The introduced TLGCRA is benchmarked against the canonical GCRA, LPSO, and ten cutting-edge metaheuristic approaches. Empirical outcomes substantiate that the TLGCRA attains marked performance advantages in terms of convergence velocity, solution precision, and algorithmic resilience. In particular, the optimized design effectively improves the optimal solution precision of the algorithm in complex multimodal function optimization, and the standard deviation of multiple independent runs in six engineering application cases is close to zero, verifying its excellent stability. Statistical verification employing the Friedman test and Wilcoxon signed-rank test additionally corroborates that the TLGCRA exhibits statistically robust and dependable optimization efficacy. In summary, the proposed innovative fusion strategies endow the TLGCRA with stronger environmental adaptability and comprehensive optimization performance, enabling it to realize faster convergence speed and higher computational accuracy, as well as outstanding stability and robustness, thus furnishing a viable resolution framework for intricate constrained engineering optimization challenges. Full article

Pebbles are competent ore fragments that are difficult to further reduce in size in conventional comminution circuits, and their efficient treatment is essential for improving circuit stability and lowering downstream grinding energy consumption. In this study, pebbles from the Julong Copper Mine were used to optimize the key operating parameters for high-pressure grinding roll (HPGR)-based pebble treatment. A uniaxial piston compression device was employed to simulate the confined particle-bed breakage process in HPGR, and the effects of feed volume, moisture content, applied pressure, loading speed, and roll surface profile on pebble compression performance were systematically investigated. The compressed products were characterized by particle size distribution, fine fraction yields, and grinding energy indices. The results indicated that the optimal compression conditions were a feed volume of 240 cm³, a moisture content of 6%, a loading speed of 0.2 mm/s, and an applied pressure of 1000 kN. Under these conditions, the products exhibited higher fine fraction yields and lower grinding energy indices, indicating improved subsequent grindability. Moreover, among the tested roll surface profiles, the cylindrical studded platen with 60% coverage produced the best compression performance. The findings provide a useful basis for optimizing HPGR operating parameters for copper ore pebble treatment. Full article

As a core crushing equipment in mining, building materials, and related industries, the cone crusher relies heavily on the optimal design and health state prediction of its mantle liner to enhance equipment reliability and reduce maintenance costs. This paper proposes a comprehensive approach integrating dynamic modeling, intelligent optimization, and health prognosis. First, a virtual prototype model is established based on laminated crushing theory and multibody dynamics simulation to analyze the motion and force characteristics of the mantle liner. Second, for the two key parameters—counterweight mass and motor speed—an improved butterfly optimization algorithm (IBOA) incorporating Cauchy mutation and an adaptive weight is proposed to achieve efficient global optimization. Furthermore, vibration signal features are extracted at different wear stages; a comprehensive health indicator curve is constructed by combining PCA dimensionality reduction with adaptive feature fusion (ASFF), and the Weibull degradation model is employed for life extrapolation prediction. Finally, fuzzy C-means (FCM) clustering is applied to autonomously partition the health states. Parameter optimization reduces the standard deviation of the force acting on the mantle liner by approximately 15.4%, markedly improving system operational stability. Health prognosis reveals that the liner enters a faulty state after 785 h, and the health condition is effectively classified into four stages: healthy, good, degraded, and faulty. The results demonstrate that the proposed optimization and health prognosis methods can effectively improve the operational efficiency and reliability of cone crushers, exhibit favorable engineering applicability, and provide a quantitative basis for condition monitoring and maintenance decision-making. Full article

Due to their unique topography, deep open-pit coal mines are prone to temperature inversions, which, in turn, exacerbate dust pollution. To characterize this phenomenon, we combined field measurements with FLUENT-based numerical simulations to analyze how inversion layer properties and dust transport patterns respond to varying conditions. The results show that the temperature contrast between the pit walls is positively correlated with the inversion layer’s temperature difference, thickness, and strength. In contrast, ambient wind speed is negatively correlated with the layer’s temperature difference and strength, yet positively correlated with its thickness. Surface temperature has no significant effect on the inversion layer’s temperature difference or thickness and exhibits only a weak correlation with its strength. Furthermore, higher wall temperature contrasts lead to increased dust concentration, whereas stronger winds promote dispersion and lower concentrations. These findings confirm that temperature inversion intensifies pollution, with stronger inversions causing more severe contamination. Therefore, mitigating the formation of inversion layers is crucial for effective dust control in deep pits. Unlike previous phenomenological observations, this study provides novel quantitative data on the thermal-aerodynamic coupling within deep open pits. Specifically, it establishes exact mathematical correlations between discrete rock wall temperature differentials and inversion layer thickness, providing critical thresholds for predicting severe dust retention. Full article

Near-bit multi-parameter MWD (measurement while drilling) is a key technology for achieving precise and efficient directional drilling in underground and tunnel engineering. The near-bit multi-parameter MWD method was studied, and a “center + side wall” distributed measurement scheme was proposed, based on an analysis of special application scenarios in underground and tunnel engineering. The transmission characteristics of Bluetooth wireless signals in water were investigated. An analysis of the underwater Bluetooth signal link was conducted. When the transmission distance is 100 mm, the received signal strength is −17.5 dBm, and the link margin is 69.5 dB. Wireless Bluetooth was used to transmit the near-bit data. A Bluetooth wireless communication simulation model was established using ANSYS software, and the influence of transmission power, transmission medium, and transmission distance on the Bluetooth signal strength was analyzed. The results indicate that: (1) the received signal strength increases with transmission power, and appropriately increasing the transmission power can improve the effect of Bluetooth wireless communication and extend the communication distance. (2) When the transmission medium is water, the received signal is unstable, and the echo loss curve shows a high and low oscillation form, presenting a frequency shift feature; when the transmission medium is air, the received signal is relatively stable, and the echo loss curve shows a parabolic form. The echo loss of Bluetooth wireless signal in water transmission is significantly higher than that in air transmission, indicating that the Bluetooth signal attenuates more rapidly when transmitted in water. (3) When the transmission distance increases near the optimal transmission frequency of 2.4 GHz, the echo loss increases accordingly, and the received signal strength of the wireless receiving module gradually decreases. The theoretical analysis, simulation, and indoor test results are in good agreement. The reasonable Bluetooth transmission power is 1 mW, and the transmission distance is 100 mm. After completing the overall scheme design and simulation analysis optimization, the structure, circuit, and program development were carried out, and the near-bit multi-parameter MWD device was developed. A laboratory water supply test was conducted, and the power supply, collection, and wireless transmission were all normal. A drilling test was carried out at an underground engineering of a coal mine in Wuhai City, achieving a drilling depth of 2328 m. A continuous and stable collection of various parameters such as WOB (weight on bit), torque, rotation speed, vibration, and gamma was carried out. A wireless transmission channel for near-bit data was established across the screw drilling tool. It can provide key technical support for the research and development of near-bit MWD in underground and tunnel engineering. Full article

Object detection in underground coal mines is plagued by critical challenges, including low illumination, high dust-induced noise, extensive target scale variation, frequent occlusion, and fragmented target feature representation, which commonly result in severe missed detections and insufficient detection confidence. To tackle these bottlenecks, this study proposes DLR-YOLO, a high-performance lightweight object detector built upon the YOLOv11n baseline, with three core optimized modules. Specifically, a dynamic multi-scale global perception enhancement module (DMGPEM) is embedded in the backbone to realize adaptive multi-scale feature extraction under low-light conditions; a lightweight cross-attention (LCA) module is integrated into the neck to achieve efficient fusion of shallow detail features and deep semantic features while suppressing dust-related noise; and a Reparameterized stem (RepStem) module is developed for initial feature extraction to minimize critical information loss during downsampling. Experimental results on our self-collected and annotated in-house underground coal mine dataset demonstrate that DLR-YOLO achieves 94.4% mAP@50 and 66.7% mAP@50–95, corresponding to 3.5 and 5.7 percentage point improvements over the YOLOv11n baseline, respectively. Ablation studies further validate the independent effectiveness of each proposed module. Meanwhile, the detector maintains a lightweight architecture with only 2.7M parameters and 6.6 GFLOPs, and reaches an inference speed of 157.1 FPS, outperforming several state-of-the-art real-time detectors, including YOLOv12, YOLOv13, and RT-DETR, on the same dataset. These findings confirm that DLR-YOLO provides a robust, high-performance technical foundation for real-time safety monitoring systems in complex underground coal mine environments. Full article

The asbestos mine “Stragari” (Kragujevac municipality, central Serbia) operated for approximately four decades, exploiting chrysotile asbestos and generating several million tons of tailings composed primarily of finely crushed serpentinite rock. These tailings are rich in magnesium (≈25 wt.%); yet, efficient magnesium recovery is hindered by the high acid consumption associated with serpentinite mineral dissolution. The objective of this study was to optimize the extraction of magnesium as magnesium chloride hexahydrate (MgCl₂×6H₂O) from asbestos mine tailings using hydrochloric acid as the leaching agent. The effects of key process parameters (including thermal activation—roasting, hydrochloric acid concentration, leaching temperature, and leaching duration) were systematically investigated. Experiments in this study were conducted using concentrations of HCl 0.5, 1, 1.5 and 2 M, temperatures of 60, 70 and 80 °C and durations of 60 and 180 min, with constant stirring speed (350 rpm) and 20% initial pulp density. The resulting pregnant leach solution was purified by controlled neutralization with Mg(OH)₂ followed by evaporation to obtain MgCl₂×6H₂O. A preliminary techno-economic assessment indicates that the proposed process is economically feasible and provides a foundation for future scale-up studies. The results demonstrate that balancing acid consumption with magnesium recovery, rather than pursuing maximum extraction efficiency, can enable profitable industrial-scale production of a value-added magnesium compound while contributing to asbestos tailings remediation. Full article

With mining operations worldwide comprehensively advancing the development of intelligent mines, mine digitalization has become an inevitable trend in the evolution of the mining industry. In this context, efficient and high-precision fracture identification has emerged as a critical prerequisite technology for achieving digital transformation in intelligent mining systems. However, severe environmental noise in deep mines and the limitations of standard pixel-wise loss functions, which ignore the geomechanical continuity of fractures, often lead to fragmented segmentation results. To address this, we introduce the existing SCSegamba architecture as an efficient feature extraction backbone and propose a novel Fracture Orientation Consistency Loss (FOCL) as our core optimization objective. By penalizing directional discrepancies between predicted and actual fracture networks, FOCL explicitly enforces geometric and topological continuity. We evaluated our framework on a custom dataset of 600 high-resolution images from deep underground roadways. The results demonstrate that the SCSegamba-FOCL framework effectively bridges discontinuous fine cracks in low-contrast zones. It achieves a superior Mean Intersection over Union (mIoU) of 85.67% and an F1-Score of 0.869, while maintaining a real-time inference speed of 38 frames per second (FPS) on edge hardware. Full article

Deciphering the dynamic fracture evolution of rock masses, particularly the interaction between dynamic stress waves and localised weak interlayers, is essential for optimising dynamic rock excavation in mining engineering. To systematically explore how these structural planes halt propagating cracks and generate a dynamic shielding effect, this study integrated Split Hopkinson Pressure Bar experiments, Digital Image Correlation techniques, and computational modeling. The findings demonstrate that altering the geometric orientation of the soft layer dictates the ultimate failure pattern. While an orthogonal interface (i.e., an interface with 0° inclination perpendicular to the loading direction) allows a tension-driven crack to cleave directly through the entire composite specimen, introducing an inclined obliquity of 15° forces the advancing fracture to deviate and permanently halt inside the soft stratum. Macroscopically, this barrier capability is validated by a rapid decrease in fracture speed, which drops abruptly by 75.5% upon encountering the inclined zone. Microscopic numerical evaluations confirm that this fracture arrest originates from wave mode conversion at the misaligned boundary. The angled interface forces incoming compressional pulses to transform into intense shear stresses, promoting extensive fracture. Substantial energy dissipation within the interlayer fully deprives the primary crack of the tensile stress required for propagation, effectively confining the stress-propagated hard rock within an energy shadow zone and suppressing further fragmentation. Full article

Gas concentration series in coal mining faces are jointly affected by multiple coupled factors, including geological conditions, mining disturbances, ventilation organization, and gas drainage intensity, and therefore exhibit pronounced nonstationarity, strong fluctuations, spatiotemporal correlations across multiple monitoring points, and occasional abrupt spikes. To address these challenges, this study proposes a gas concentration prediction and early-warning method that integrates CEEMDAN–SST with GraphPINN-TimesFM (Graph Physics-Informed Neural Network–Time Series Foundation Model). First, based on multi-source monitoring data such as wind speed, gas concentrations at multiple monitoring points, and equipment operating status, anomaly removal, operating-condition segmentation, and change-point detection are performed to construct stable operating-state labels. Feature selection is then conducted by combining optimal time-lag correlation, Shapley value contribution, and dynamic time warping. Second, WGAN-GP is employed to augment samples from minority operating conditions, while CEEMDAN–SST is used to decompose and reconstruct the target series so as to reduce the interference of nonstationary noise and enhance sequence predictability. On this basis, TimesFM is adopted as the backbone for long-sequence forecasting to capture long-term dependency features in gas concentration evolution. Furthermore, GraphPINN is introduced to embed the topological associations among monitoring points, airflow transmission delays, and convection–diffusion mechanisms into the training process, thereby enabling collaborative modeling that integrates data-driven learning with physical constraints. Finally, the predictive performance, early-warning capability, and interpretability of the proposed model are systematically evaluated through regression forecasting, warning discrimination, and Shapley-based interpretability analysis. The results demonstrate that the proposed method can effectively improve the accuracy, robustness, and physical consistency of gas concentration prediction under complex operating conditions, thereby providing a new technical pathway for gas over-limit early warning and safety regulation in coal mining faces. Full article

To address the critical challenges of lithology acquisition and low blasting refinement under extreme low temperatures and varying thermal conditions in high-altitude environments, this study develops a real-time dynamic identification method for rock-like interfaces using Measurement While Drilling (MWD) technology. The scope of this research involves the use of a self-developed indoor digital drilling experimental platform to simulate both ambient and freezing (−20 °C) conditions. Procedures included conducting comprehensive comparative drilling experiments on various rock-like materials with distinct strength levels to evaluate their mechanical responses during penetration. The major findings reveal a significant influence of low-temperature hardening effects on MWD parameters; specifically, the frozen state notably increases drilling torque and feed pressure while simultaneously decreasing the stable rotational speed of the drill bit. To resolve the feature parameter drift induced by temperature variations, a novel interface recognition algorithm is proposed that integrates Z-score normalization, change-point detection, and multi-dimensional spatial clustering. Through a dual-detection mechanism involving both single-point and cumulative features, the algorithm effectively captures precise mutation information during rock layer transitions. It further incorporates multi-dimensional indicators, such as consistency, change intensity, and point density, to perform comprehensive weighted scoring. Experimental results demonstrate that the proposed algorithm effectively eliminates the systematic offset of parameters caused by temperature fluctuations. The prediction error at both “strong-weak” and “weak-strong” transition interfaces is maintained within 1.5 mm, which significantly improves the accuracy and robustness of interface recognition under complex and varying working conditions. These key conclusions provide essential technical support for the implementation of differentiated charging and green refined mining operations, ensuring greater energy efficiency and environmental protection in cold-region engineering. Full article

Real-time coal–rock identification is essential for intelligent mining, enabling hazard prevention and geological modeling. However, existing methods often suffer from unclear bit–rock interaction mechanisms, signal distortion, sensor remoteness, or delayed data acquisition, limiting their effectiveness in continuous operations. This study proposes a novel approach for real-time coal–rock identification based on multi-source near-bit drilling data. A near-bit data acquisition system was developed and positioned directly behind the drill bit, integrating sensors to capture high-fidelity parameters—including weight on bit (WOB), torque, rotational speed, rate of penetration (ROP), natural gamma ray, and borehole trajectory—thereby eliminating frictional interference from the drill string. A data-driven theoretical model was established to derive a near-bit drillability index (NDI) for rock strength and to correlate gamma ray responses with lithology. Field trials were conducted in a coal mine in northern Shaanxi, involving over 30 boreholes and systematic core validation. The results demonstrate that the method enables continuous, high-resolution identification of coal–rock interfaces and strength variations along the borehole trajectory, with interpreted results aligning well with core logs and achieving approximately 85% accuracy in strength estimation. By ensuring compatibility with conventional drilling rigs and supporting real-time data transmission and 3D geological updating, this study offers a practical and robust technical pathway for achieving geological transparency and real-time steering in underground coal mining. Full article

Currently, deep mining has become the development trend of underground mines, and the harsh working environment underground seriously affects the efficiency of personnel and equipment operations. The operational efficiency of the human–machine system composed of personnel and equipment is not only affected by the status of personnel and equipment, but also closely related to the interaction between human–machine–environment. How to ensure the efficient operation of human–machine systems has become the key to improving the quality and efficiency of mines. Therefore, in order to analyze the interaction relationship between human–machine–environment in the process of human–machine system operation and explore the variation law of human–machine system efficiency. This paper constructs a deep mining human–machine system efficiency system dynamics model under the multi-factor coupling effect of deep well mining, guided by system dynamics theory, and obtains the variation laws of system efficiency under single-factor changes and multi-factor coupling effects. The research results solve the problem of difficulty in quantitatively describing the logical and quantitative relationships between various elements in the study of human–machine system efficiency, providing new ideas for the study of underground work efficiency. Through mathematical modeling, the temperature threshold for the efficient operation of the human–machine system is determined, and the quantitative relationships among temperature, humidity, and wind speed are elaborated, providing a reference for ensuring the efficient operation of the human–machine system in deep mining. Full article

Against the global carbon neutrality target, predictive maintenance (PdM) of automotive engines represents a core technical strategy to advance the sustainable development of the automotive industry. Conventional single-modal diagnostic approaches for engine abnormal sound defects suffer from low accuracy and weak anti-interference capability. Existing multi-modal fusion methods fail to deeply mine the physical coupling between cross-modal features and often entail excessive model complexity, hindering deployment on resource-constrained on-board edge devices. To resolve these limitations, this study proposes a Physical Prior-Embedded Cross-Modal Attention (PPE-CMA) mechanism for lightweight multi-modal fusion diagnosis of engine abnormal sound defects. First, wavelet packet decomposition (WPD) and mel-frequency cepstral coefficients (MFCC) are integrated to extract time-frequency features from engine audio signals, while a channel-pruned ResNet18 is employed to extract spatial features from engine thermal imaging and vibration visualization images. Second, the PPE-CMA module is designed to adaptively assign attention weights to audio and image features by exploiting the physical coupling between engine fault acoustic and visual characteristics, enabling efficient cross-modal feature fusion with redundant information suppression. A rigorous theoretical derivation is provided to link cosine similarity with the physical correlation of engine fault acoustic-visual features, justifying the attention weight constraint (β = 1 − α) from the perspective of fault feature physical coupling. Third, an improved lightweight XGBoost classifier is constructed for fault classification, and a hybrid data augmentation strategy customized for engine multi-modal data is proposed to address the small-sample challenge in industrial applications. Ablation experiments on ResNet18 pruning ratios verify the optimal trade-off between diagnostic performance and computational efficiency, while feature distribution analysis validates the authenticity and effectiveness of the hybrid augmentation strategy. Experimental results on a self-constructed multi-modal dataset show that the proposed method achieves 98.7% diagnostic accuracy and a 98.2% F1-score, retaining 96.5% accuracy under 90 dB high-level environmental noise, with an end-to-end inference speed of 0.8 ms per sample (including preprocessing, feature extraction, and classification). Cross-engine and cross-domain validation on a 2.0T diesel engine small-sample dataset and the open-source SEMFault-2024 dataset yield average accuracies of 94.8% and 95.2%, respectively, demonstrating strong generalization. This method effectively enhances the accuracy and robustness of engine abnormal sound defect diagnosis, offering a lightweight technical solution for on-board real-time fault diagnosis and in-plant online quality inspection. By reducing engine fault-induced energy loss and spare parts waste, it further promotes energy conservation and emission reduction in the automotive industry. Quantified experimental data on fuel efficiency improvement and carbon emission reduction are provided to substantiate the ecological benefits of the proposed framework. Full article