Coal Fracture Research Articles

Optimization method for predicting coal reservoir fractures in the Laochang area of Eastern Yunnan using paleotectonic stress inversion

IntroductionCoal reservoir fractures serve as critical storage spaces and migration pathways for coalbed methane (CBM), significantly influencing CBM enrichment. The characteristics of coal reservoir fracture development can be obtained using traditional simulation methods, but these still have shortcomings. This work presents an optimization approach for the traditional method.MethodsThis study introduces an optimization approach for traditional methods with two novel contributions. This study integrates the simulation of tectonic stress fields with fracture prediction, using surface sandstone fractures as constraints to reconstruct the paleostress field of the coal seam, while also accounting for the influence of coal thickness on fracture development to calculate fracture density.ResultsThe predicted fracture density results were validated against measured values from the Bailongshan mine and Xiongdong coal mine with a relative error of approximately 12%, suggesting a reasonable degree of reliability.DiscussionBased on the results of the fracture simulation predictions, it is believed that the coal seam fracture density in the study area is mostly 10–20 lines/m and that the sweet spot for CBM development is located in the Yuwang block.

Coal structure evaluation and morphological properties that affect the coal usage in industries

AbstractThe contemporary research article is central to understanding coal structure evaluation and the morphological development impacting its utilization in different applications. Through Mineral Liberation Analysis (MLA) designs high content phyllosilicates minerals and swelling clay minerals were rationalized to provides a novel insight into enhanced coal beneficiation and the benefits of coal by-product re-utilization progressions that encourage safer environments and economic sustainability. This work commences with collection of five (5) different coal samples from the central district region in Botswana, sample characterization deploying Thermogravimetric coal analysis (TGA), x-ray fluorescence spectroscopy (XRF), x-ray diffraction (XRD), scanning electron microscopy (SEM) and the Hardgrove Grindability Index (HGI) test that was directed to quantification of the coal hardness and fracture toughness during milling. The cumulative objective was to understand the correlation that exists between the natural composition of the coal sample and their adaptation and application in various carbonaceous products. A solid connection was thus identified in the sulfur and phosphorus weight percentage inclusions in all the coal materials hence higher significance in sphalerite mineral phases (Zn, Fe) S critically increased the fracture toughness and hardness properties. Moreover, mineral amalgams intrinsic to the coal maceral such as aluminum oxides (Al2O3), silicate (SiO2), calcites (CaO), Iron oxide (Fe2O3), potassium feldspars (K − AlSi3O8), albite (Na − AlSi3O8), and anorthite (Ca − Al2Si2O8) compounds in alkali feldspars were detected in larger quantities. The coal industry has attracted much industrial attention to manufacturing foundations producing cement, ceramic tiles, paving bricks, and material synthesis and will continue to supply other economic sectors in the conceivable future. Graphical Abstract

The Applicability and Reflection Characteristics of Coal Failure Events for External Monitoring-While-Drilling of Underground Pressure Relief Drilling

Previous research results preliminarily indicated that the Coal Failure Events (CFEs) that occurred during the process of Underground Pressure Relief Drilling (UPRD) represented the phenomenon of coal fracture and energy release. The research results had excellent value for the monitoring and response of pressure relief drilling while drilling, but there were still some special situations that needed to be analyzed and studied in actual on-site testing. So, through on-site testing and data statistical analysis, the study investigated the applicability of the innovative external Monitoring-While-Drilling (MWD) method for UPRD with more coal failure events and made a quantitative statistic of the CFEs and their relationship with abutment pressure to reveal the applicability of the external MWD method and characteristic of CFEs. The results showed that hundreds of CFEs were produced in the UPRD process, which must be removed to ensure the accuracy of the MWD method. Although CFEs bring recognition difficulties, they also provide conditions for studying their own distribution and characteristics. Results showed that more CFEs were produced in the depth of difficult drilling, which indicated that there was a positive correlation between the degree of difficulty in drilling and the number of CFEs. In addition, spectrum analysis showed that the depths with more CFE occurrence were more likely to produce high-frequency events. When the surrounding stress of drilling rocks is high, the occurrence of small fractures with a higher main frequency may become more frequent and consistent; more fractures with similar failure forms would occur, which may have a lower fractal dimension and promote the generation of more failure. The research results were of great significance for the MWD method for UPRD, a quantitative study of CFEs and their generation characteristics during UPRD construction.

Modelling of enhanced gas extraction in low permeability coal seam by controllable shock wave fracturing

The controlled shock wave (CSW) fracturing is an effective method for enhancing permeability of coal seam to promote gas extraction. Based on Fick’s law, Darcy’s law, the ideal gas law and the Langmuir equation, a damage-seepage-deformation coupling mathematical model of CSW fracturing in coal seam combined with the maximum tensile stress and the Mohr-Coulomb criterion is established. This model is implemented into COMSOL Multiphysics to simulate the coal seam CSW fracturing and subsequent gas extraction. When the shock wave and isotropic in-situ stress are applied on the borehole wall, the coal damage zone is an annular shape, and the permeability in the damage zone increases sharply. The CSW can effectively increase the efficiency of gas extraction and reduce the gas pressure and gas content in coal seam. With the increase of CSW action times, the damage in coal mass reaches a threshold and tends to be stable after several shocks. The damage area and the gas extraction efficiency are positively correlated with the shock intensity. Under the anisotropic ground stress, the larger diversity of the stress in different directions is, the more obvious damage extension in the fractured coal along the maximum stress direction is. Ground stress can inhibit the extension of cracks in the CSW fractured coal seam. This inhibition effect becomes more obvious with the increase of in-situ stress. Parameters are substantiated of controlled shock wave impact on the coal seam, which ensures increased methane extraction from low-permeability reservoirs, are substantiated.

Study on the variability of oxygen adsorption behavior in coal gangue based on pore size structure

To investigate the adsorption and migration behavior of oxygen in coal gangue with different pore sizes, this study characterizes the multiscale morphology of coal gangue pores and fractures using SEM NMR, and low-temperature N2 (77 K) adsorption methods. As well, the study simulates the adsorption and diffusion behavior of O2 within the pore structures of coal gangue based on GCMC and MD methods. The study examines the oxygen adsorption characteristics across different pore sizes and analyzes the mass transfer mechanisms during oxygen diffusion. Results indicate that the pores in coal gangue are predominantly micropores within the 1–10 nm range. As pore size increases, the absolute adsorption amount of oxygen increases while the isosteric heat of adsorption decreases. The isosteric heat of adsorption in coal gangue models with different pore sizes is less than 42 kJ/mol, indicating the physical adsorption of oxygen within the pores. Oxygen shows adsorption layering perpendicular to the coal gangue surface, with adsorption density distribution differences decreasing and adsorption capacity weakening as pore size increases. The O2 adsorption isotherms in coal gangue follow Langmuir adsorption principles, with oxygen saturation adsorption decreasing as absolute adsorption increases. The confinement effect of coal gangue on oxygen weakens as pore size increases, and the impact of increasing pore size on oxygen diffusion is stronger than adsorption. These findings are significant for understanding the microscopic adsorption and diffusion behavior of O2 in coal gangue pores and fractures and are crucial for accurately preventing and managing spontaneous combustion in coal gangue piles.

Study on failure mechanism of cracked coal rock and law of gas migration

China possesses abundant coal resources and has extensive potential for exploitation. Nevertheless, the coal rock exhibits low strength, and the coal seam fractures due to mining activities, leading to an increased rate of gas emission from the coal seam. This poses significant obstacles to the exploration and development of the coal seam. This paper focuses on studying the failure mechanism of fractured coal rock by conducting uniaxial and triaxial compression experiments on the coal rock found at the Wangpo coal mine site. Simultaneously, in conjunction with the findings from the field experiment, a gas migration model of the mining fracture field is constructed to elucidate the pattern of coal seam gas distribution during mining-induced disturbances. The study structure reveals that coal rock exhibits three distinct failure modes: tensile failure, shear failure, and tension-shear failure. The intricate fissure in the rock layer will intensify the unpredictability of rock collapse patterns. The compressive strength of coal rock diminishes as the confining pressure drops. The coal rock in the working face area will collapse as a result of the lack of confining pressure. In the rock strata above the mining fracture zone, the gas pressure is first higher and then significantly falls with time. After 100 days of ventilation, the low gas pressure area changes little, so to ensure the safety of the project, the ventilation time of the fully mechanized mining surface is at least 100 days. The research results will help to establish the core technology system of coal seam development and improve the competitiveness of coal seam resources in China.

Experimental study on the influence of horizontal stress difference coefficient on coal rock fracture

Hydraulic fracturing is a pressure-relief and permeability-enhancing technique widely used in the mining of low-permeability coal seams. The horizontal stress difference coefficient is an important factor that affects the fracture propagation during the fracturing. To study the mechanism of the hydraulic fracturing process, in this paper, the initiation and propagation of cracks under horizontal stress difference coefficient are studied by using the developed true triaxial hydraulic fracturing system. The fracture surface morphology was obtained by 3D scanner. The experimental results are verified by the mathematical model. The results show that the fracture pressure and the peak values of AE count rate and b value increase and the cumulative AE count decreases with the increase of the horizontal stress difference coefficient. After the first pressure drop, the “pressure built-up” in the specimen increases and the peak value of AE count rate decreases with the increased horizontal stress difference coefficient. The 3D scanning results show that when the horizontal stress difference coefficient is larger, the hydraulic fracture propagation is straighter and the fracture surface area is smaller. The experimental results are in good agreement with the theoretical values. The experimental results provide a basis for engineering practice.

Research on the Recognition and Characterization of Fractures in Coal Rock Based on CT Scanning

Abstract Coal rock fractures play a vital role as key channels for gas migration and storage in the exploration and development of coalbed methane. The characteristics of these fractures, such as porosity distribution, specific surface area, and connectivity, directly impact the adsorption, diffusion, and permeability behaviors of coal reservoirs. Therefore, a detailed analysis of coal rock fracture characteristics is vital in assessing the extractability of coalbed methane and during its exploration and development process. Currently, techniques like imaging logging, seismic detection, and micro-CT are employed for characterizing and studying fractures at various scales. Among these, high-resolution non-destructive CT scanning technology, by constructing three-dimensional data models of core samples, enables a quantitative analysis of fracture distribution features and size parameters. Traditional digital image processing methods, such as threshold segmentation and binary segmentation, though advantageous in computational speed, have limitations in the accuracy of fracture identification. With the advancement of artificial intelligence technology, deep learning-based image processing techniques have increasingly become significant tools for fracture detection due to their powerful feature extraction capabilities. This study conducted micrometer-level CT scanning experiments on coal rock samples, using CT image processing technology to construct a digitalized coal rock core model. Deep learning methods were applied for precise fracture identification, establishing an appropriate deep learning architecture and optimized parameters for coal rock fracture recognition. Furthermore, this paper provides a detailed quantitative characterization of the precisely identified fractures, offering robust technical support for the exploration and development of coalbed methane. The high-resolution non-destructive CT scanning technology and three-dimensional fracture network reconstruction method used in this study have been proven to be effective tools for investigating the micro-features of rocks, enabling the three-dimensional visualization and detailed characterization of rock microstructures.

Long-time seepage evolution in coal fractures during injection of viscoelastic surfactant fracturing fluids

Long-time seepage evolution in coal fractures during injection of viscoelastic surfactant fracturing fluids

Microstructural response of coal fracture surface induced by ScCO2 injection measured with AFM

Fractures in coal serve as the principal channels for the migration of coalbed methane (CBM). The microscopic traits of coal fracture surface are of significance for evaluating reservoir permeability and directly influence the outcome of CO2 storage and displacement. To comprehend the impact of CO2 on the coal fracture surface, the alterations in the coal fracture surface before and after CO2 injection are investigated vis atomic force microscopy. As CO2 gradually transforms into a supercritical state, the fracture density and aperture on the coal fracture surface gradually escalate. The mean pore size and porosity of the coal fracture surfaces rose from 5.45 nm to 6.55 nm and from 4.66% to 6.85%, respectively. The proportion of micropores (<2 nm) gradually diminished. The proportions of mesopores (2∼50 nm) and macropores (>50 nm) proportions gradually. Swelling, extraction and mineral dissolution are the predominant reasons for the alteration in the pore structure of the coal fracture surface. CO2 injection modifies the roughness and fractal characteristics of the coal fracture surface. The mean roughness Ra dropped from 6.54 nm to 4.03 nm, and the fractal dimension Ds declined from 2.45 to 2.28. With the fixed scanning range, the injection of CO2 has been shown to reduce the roughness of coal fracture surface and lower their fractal dimension, thereby has a positive influencing permeability enhancement. Therefore, in CO2-ECBM engineering, it is essential not only to analyse the physical properties of the target reservoir, but also to conduct a comprehensive evaluation of permeability with a suitably defined area of the reservoir.

Multi-scale quantitative characterization of three-dimensional pores and fissures in deep coal and study of the evolution laws

Native pores and fissure in deep coal bodies directly influence the deformation and destruction of coal seams. The pore structure characteristics of coal tend to be complicated because of the damage caused by tectonic stress; hence, it is necessary to study the development of pore fracture in coal. In this study, two types of coal samples—primary structural coal and tectonically deformed coal—were selected from the 12403 comprehensive mining face in the Shangwan Coal Mine, part of the Shendong Coal Mine Group. The developmental characteristics, distribution patterns, and morphological and structural differences of pores and fissures in these types of structural coal were examined using X-ray diffraction, scanning electron microscopy, mercury intrusion porosimetry, and computed tomography scanning, combined with digital image processing technology. A fractal model for the evolutionary characteristics of the pore-fracture network in a coal body is proposed. The characteristics of the pore-fracture network under different measurement accuracies are also investigated. The results showed that the primary structural coal tended to develop small fissures of simple morphologies, with poor fissure connectivity and connection strength. In contrast, the morphologies of fissures in tectonically deformed coal were complex, with better fissure connectivity and connection strength, and a higher fissure rate than that of primary structural coal. A fractal model was developed to describe and characterize the geometrical features of the pore-fracture network at various measurement accuracies. The dominant pore-size segments that can be characterized are 50 nm ≤ r ≤ 10 μm and r > 10 μm, respectively. The fractal dimensions of porosity and pore-fracture network volume increase as measurement scales decrease. The accuracy and applicability of the fractal model in predicting the porosity and volume fractal dimension of the pore-fracture network across various scales were confirmed.

Nuclear Magnetic Resonance Characterization and Analytical Modeling of Compressibility of Propped Fracture in Coal: New Insights

Nuclear Magnetic Resonance Characterization and Analytical Modeling of Compressibility of Propped Fracture in Coal: New Insights

Microcracking evolution and clustering fractal characteristics in coal failure under multi step and cyclic loading

During the deep mining process, coal mass encounter intricate geo-environmental stress, such as periodic weighting loading and repeatedly excavation unloading–reloading cycles, which weakens coal’s mechanical integrity and predisposing it to severe coalburst accidents. To investigate the microcracking damage mechanisms and predictive indicators in coal failure under in-situ stress analogs, the multistage step and cyclic loading experiments are conducted on cubic coal specimens. Acoustic emission (AE) technology is employed to track the spatiotemporal-energy evolution of stress-induced damages and discern the microcracking nature through AF/RA assessments, and the power-law scaling relation of AE activity near the catastrophic failure of coal is investigated. Then the clustering fractal structures of microcracking events in the stressed coal are quantified across temporal, spatial and energetic domains, utilizing correlation integral methodologies and b-value derivations from magnitude-frequency relation. Findings indicate that irrespective of the loading mode (step or cyclic), escalating stress triggers an intensification of irreversible fatigue deformations. AE characteristic parameters manifest a gradual rise, culminating in a precipitous peak coinciding with the critical failure point. This escalation adheres to a power-law correlation between AE occurrence frequency and time to failure, observable in the immediate pre-failure seconds, reflecting a universal attribute of coal fracture. Prior to ultimate failure, a marked increase in shear microcracks is discernible, despite tensile-dominated cracks (constituting about 80 % of total microcracks) prevailing as inferred from the variation of AF/RA values, aligning with an inferred “X” conjugate wedge splitting pattern from AE event density and energy mapping. The microcracking events in the loaded coal exhibit a clustering fractal structure that spans across temporal, spatial, and energetic (or magnitude) domains. Notably, the temporal fractal dimension, spatial fractal dimension, and b-value (i.e., a parameter characterized the energetic fractal dimension) all follow a parallel decrease pattern as the loading stress escalates, with a pronounced diminution becoming especially evident as the specimen approaches its catastrophic failure threshold. This insight offers fresh perspectives for predicting rock/coal dynamic disasters, emphasizing the necessity of concurrently monitoring the shift from diffuse microcracking to localized failure across time, space and energy domains. These research findings contribute to a deeper understanding of microcracking damage evolution and failure mechanism of loaded coal, and provide a foundational basis for early warning of rock failure such as the coalburst disasters.

Energy evolution and damage deformation behavior of cemented broken coal specimen under triaxial compression condition

Coal is a major energy source, and deep coal mining often leads to fractured coal around roadways. Grouting is a common method used to reinforce fractured rock masses, where the slurry encases coal particles, forming a cemented broken coal (CBC) body. The content of coal particles (CP) significantly affects the energy characteristics of CBC specimens. To investigate this, a series of triaxial compression tests and triaxial unloading tests were conducted on CBC specimens with varying CP contents. The results indicate that as CP content increases, both peak strength and cohesion decrease, while the internal friction angle increases in both tests. In the triaxial unloading tests, specimens with higher CP content showed tensile-shear failure. Additionally, energy trends during damage were similar in both tests. In triaxial compression tests, dissipated energy increased with CP content, while in the triaxial unloading test, it initially rose and then fell. During the unloading phase of the triaxial unloading tests, the CBC specimen with 40 % CP content exhibited the most significant change in energy increment and its rate. Analysis of damage and deformation characteristics indicated that damage, deformation, and dilation were effectively restrained in CBC specimens with 40 % CP content during unloading.

Study on the Dispersion Characteristics of Coal Complex Resistivity under the Effect of Liquid Nitrogen Cyclic Freeze-Thaw and Evaluation of Permeability Enhancement.

The effect of liquid nitrogen freeze-thaw fracturing on coal seams can be potentially evaluated by the complex resistivity method. The real part (Reρ) and the imaginary part (Imρ) of the complex resistivity and permeability of coal were determined under different cycle times and in different bedding directions. The reason for permeability enhancement was discussed, and the dispersion mechanism of complex resistivity during cyclic freeze-thaw fracturing was analyzed. The results indicated that (1) the complex resistivity parameters have a good response to the cycle times; Reρ, |Imρ|, and the dispersion degree (α) are positively correlated with cycle time; the fully polarized frequency (f p) of Reρ, the characteristic frequency (f c) of Imρ, and variation are negatively correlated with cycle time. (2) The difference in complex resistivity parameters between the vertical bedding direction and the parallel bedding direction is significant, and the difference in electrical properties of the bedding structure continuously decreases with the increase in cycle time. (3) Under the effect of liquid nitrogen cyclic freeze-thaw, a complex network of fractures in coal is formed, the anisotropic characteristics of coal are weakened, and effective conductive channels are damaged. The peak frost heave force decreases exponentially with the increase in cycle time, and the difference in bedding electrical properties gradually disappears. (4) Comparing the inversion degree of measured data with three conductive models, ρ0 and τ are selected as the optimum parameters for evaluating the effect of liquid nitrogen cyclic freeze-thaw. A logarithmic permeability evaluation model is constructed based on ρ0 and τ. This work provides a new perspective based on electrical detection for evaluating the permeability enhancement of coal during liquid nitrogen cyclic freeze-thaw.

Acoustic emission spectrum characteristics of structural coal destruction in negative pressure environment

Abstract The uniaxial compression experiments under a low-pressure environment were performed by using structural coal samples. The frequency domain response characteristics of coal mass failure under loading in a low-pressure environment were acquired by FFT transformation and wavelet packet decomposition. The results show: As the loading stress of coal increases, the AE spectrum becomes more abundant, and the whole AE spectrum shows a left-shift trend. When the gas pressure increases, the acoustic emission signals change from low-frequency high-energy to high-frequency low-energy, the frequency band gradually narrates, and the spectrum changes from complex multi-peak shape to single-peak shape. As stress increases, the proportion of energy in the band 0-4.38 kHz gradually increases, while that in other bands gradually decreases. The energy response to stress changes in the two frequency bands of 2.92-4.38 kHz and 4.38-5.84 kHz is the most obvious. When the pressure changes, the energy in three frequency bands of 2.92-4.38 kHz, 4.38-5.84 kHz, and 7.3-8.76 kHz present an evident response trend with the pressure change, and the response trend (increase) of the latter two is exactly opposite (decrease) to that of the former. This phenomenon indicates that 2.92-4.38 kHz and 4.38-5.84 kHz are the characteristic frequency bands of the coal fracture process. The findings of this research offer crucial foundational data to support the monitoring and early warning of coal and gas outburst hazards.

Spatial-temporal response and precursor characteristics of tensile failure on disc coal samples of different sizes combining AE, EMR and DIC techniques

Tensile fractures in deep coal and rock mass can readily trigger dynamic calamities like rock bursts, significantly impacting the safety of coal mining. To enhance our understanding of coal’s tensile failure mechanism, Brazilian splitting failure experiments were conducted on coal samples with prefabricated cracks of different sizes. Acoustic emission (AE), electromagnetic radiation (EMR) and digital image correlation (DIC) techniques were used to analyze the instability failure process and precursor characteristics of coal samples. The results showed that, for coal samples of the same thickness, the tensile strength and peak strain gradually decreased with the increase of coal sample size, whereas the elastic modulus increased gradually, highlighting more pronounced brittleness characteristics and revealing a noticeable size effect. The time-varying evolution of AE energy, EMR energy and VE (virtual extensometer) elongation during the tensile failure process of coal samples is closely correlated to the stress evolution trend, exhibiting distinct characteristics at various loading stages. The failure modes of coal samples of varying sizes exhibited a strong correlation with the spatial distribution of AE events, as well as the strain and displacement field measured by DIC. With the coal sample’s growing size, the percentage of AE high energy events rose while the total number of AE positioning events fell, the proportion of DIC strain concentration area decreased, displacement zoning characteristics became more obvious, and the critical opening displacement of cracks increased. The variance of AE, EMR and DIC related parameters in coal samples showed significant critical slowing down characteristics. Based on their response timescales, EMR energy was identified as an “Early warning”, AE energy as a “Medium warning”, and VE elongation as a “Short-imminent warning”. A comprehensive analysis of multi-parameter monitoring information proved beneficial in accurately pinpointing precursory response points of coal mine dynamic disasters, thereby enhancing monitoring precision.

A Theoretical and Experimental Study on Asperity Damage-Driven Strain Rate Dependency of Fractured Coal

AbstractAsperities within pre-existing fractures of coals can experience local damage during the fracture closure due to external loading. Previous research postulates that this local asperity damage can lead to strain rate-dependency without causing permanent deformation to the bulk of the coal specimens. This study aims to comprehensively investigate this behavior by developing a theoretical model that characterizes the strain rate-dependency driven by fracture asperity damage in coal. To achieve this objective, an initial series of micro-scale mechanical tests are conducted on joint specimens to establish a model for effective stress acting on asperities. Building upon this model, a theoretical foundation is further developed to describe the strain rate-dependent asperity damage evolution and resulting energy dissipation. These frameworks are subsequently incorporated into elasticity and damage mechanics to capture the strain rate-dependent stress–strain relationships. To validate the proposed model across multiple scales, additional triaxial tests on core-scale specimen and micro-scale mechanical tests on joint specimens are performed. The experimentally measured strain rate-dependency aligns well with the predictions of the proposed model, indicating a successful development of a robust model. The results of the model developed in this study reveal that the strain rate-dependency in fractured coals is governed by several factors, including asperity damage, mechanical properties of the coal specimens and effective stress acting on asperities of pre-existing fractures within the bulk of coal. Moreover, it is shown that the effective stress acting on asperities is significantly affected by both applied normal stress and joint roughness coefficient (JRC). The insights derived from this study demonstrate that the strain rate-dependency induced by micro-scale asperity damage of pre-existing fractures leads to observable strain rate-dependency in bulk specimens at core-scale and the proposed model can adequately capture this behavior.

Characterization of natural fracture development in coal reservoirs using logging machine learning inversion, well test data and simulated geostress analyses

Natural fractures directly affect the permeability and mechanical strength of reservoirs, and their development degree has an important impact on the design and implementation of engineering and development projects. Although there is some correlation between logging data and fracture development, studies using algorithms to optimize logging predictions are still scarce. Meanwhile, there is a scarcity of calculations and analyses concerning the distribution of geostress at the block scale, and the pivotal role that geostress plays as a tectonic factor in the development of fractures. In this study, machine learning methods are used to predict reservoir fracture development, and regional geostress distribution patterns derived from well test data and finite element methods are combined for verification. The support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost) and back propagation neural network (BPNN) algorithms are used to predict the fracture development of No.15 coal reservoir in the block. The results showed that the accuracy of SVM is 83.3 %, RF is 91.6 %, XGBoost is 93.7 % and BPNN is 95.8 %. The BPNN can effectively predict the reservoir fracture development of the block. Combined with the regional finite element stress-strain analysis and geostress measurement, the prediction of No.15 coal geostress distribution and fracture development model is established. Under comprehensive verification, the established distribution of the degree of regional fracture development under the control of geostress is consistent with the results of the BPNN prediction of fracture development. These results show that the regional geostress calculated in association with finite element analysis (FEA) can reflect the development of fracture in coalbed methane (CBM) reservoirs, and the neural network has good performance in predicting regional fracture development. This work provides a new approach to the application of machine learning in the field of geological engineering, and the comprehensively validated model provides geologists and geological engineers with ideas in algorithmic practice.

Safety and high-recovery mechanisms and application research for initial mining of thick-coal-seam with complex structure and thick-hard roof

Thick-coal-seam with complex structures and thick-hard roof in the initial mining phase pose various challenges, including a long weighting interval, strong rock pressure, poor top coal caving performance (TCCP), and significant coal loss. These problems directly affect the safety and efficiency of the mining operations. This study employs the principles of elastic thin plates and ellipsoidal bodies to unravel the formation mechanism of strong rock pressure in thick-hard roof and the influence of parting on the TCCP. In addition, a hydraulic fracturing technique is proposed for safe-efficient recovery during the initial mining phase. The reliability of this technique is verified through numerical simulations and field experiments. The research findings reveal the following. (1) The primary causes of strong rock pressure in the mining face are attributed to a long weighting interval and wide collapse range of the main roof, and the weighting interval is primarily influenced by the thickness and tensile strength of the main roof. (2)The key factor affecting the TCCP is the cantilever beam structure formed by the fracture of the thick-hard parting, as it intersects the ellipsoidal body during coal caving. The simultaneous fracturing of both the top coal and roof can reduce the weighting interval on the working face. This process effectively decreased the strength of the thick-hard parting within the top coal, while simultaneously enhancing its load strength and eliminating the cantilever structure resulting from the parting fracture. It not only reduces the first weighting intensity but also promotes the early and proper coal release, thereby enhancing the TCCP and ensuring safe-efficient mining during the initial mining phase. (3) Aiming at the difference in the strengths of the top coal and roof, a graded hydraulic fracturing technique and system were proposed. Fracturing boreholes with a diameter of 60 mm, spacing of 10 m, and height of 20.85 m, which can economically and effectively ensure the fracturing results. Field applications have demonstrated that fractured coal and rocks in fracturing areas exhibit well-developed fractures. During the initial mining phase, the weighting interval in the working face was reduced by 20 m, resulting in a decrease in the overburden pressure and 26.9% reduction in the lumpiness of the top coal. Additionally, the recovery rate increased by 31.19%.