Coal Seam Roof Research Articles

Study on Instability Characteristics of the Directional Borehole on the Coal-Seam Roof: A Case Study of the Tingnan Coal Mine

Directional long drilling on the roof is an effective gas control measure in the goaf, but there is little research on the stability of the surrounding rock. In this study, the geological conditions of the #4 coal seam in the Tingnan Coal Mine, Shaanxi Province, China taken as the application background, and the deformation characteristics of boreholes under four typical coal and rock conditions were first analyzed based on the Universal Distinct Element Code (UDEC) numerical simulation. Secondly, the stress, strain, and plastic deformation of the rock surrounding the borehole with different diameters were carried out using the Fast Lagrangian Analysis of Continua 3D (FLAC 3D). The effect of the casing on the stability of the borehole was also simulated. The results showed that the borehole stability of coal and mudstone was lower than that of fine-grained sandstone and coarse-grained sandstone. The larger the borehole diameter, the lower the stability. The borehole tended to be unstable, especially when the diameter was 160 mm and 200 mm. Traditional pipes can provide some protection, but for large boreholes, the protection is poor. Based on the above research, uniaxial compression tests were carried out on various internal support tubes, such as ‘line-shaped’, ‘Y-shaped’, and ‘cross-shaped’. The results showed that the cross-shaped pipe had the highest compressive strength, which was 4–5 times that of the other types of protective pipe and had a good protective effect. The research results can provide reliable technical support for the protection of directional boreholes on roofs through strata and have important implications for the popularization and application of the directional long borehole technique.

Biogas production characteristics of lignite and related metabolic functions with indigenous microbes from different coal seams

To investigate the effects of different exogenous microorganisms on coal biomethanation and its related microbial metabolic functions. Bacterial sources were obtained from the mine water of the Xinsheng, Qinan, Fangzhuang, and Tianyuan coal mines, and lignite was utilized for conducting experiments to produce biomethane. The biomethane yield and statistical analysis based on KEGG metabolic pathways were used to assess the biomethane production potential and the difference of metabolic functions during anaerobic fermentation. The results showed that the accumulative production of biomethane in the anaerobic fermentation system with microorganisms from Qinan mine was 1.80 times, 1.18 times and 1.13 times that of the fermentation systems with other microbes from the Xinsheng, Fangzhuang and Tianyuan mine, respectively. Based on the geological environment of groundwater, it was observed that the moderate water-rich fractures in the coal seam fractures of Qinan Mine are relatively developed, which facilitates the transport of organic matter during microbial metabolism. On the other hand, the Fangzhuang and Tianyuan coal mines are situated in the groundwater runoff zone, their fracture development characteristics are comparatively lower than those of the Qinan mine. In contrast, the coal seam roof and floor of Xinsheng mine are characterized by a stable aquifer comprising thick mudstone and claystone, which presents difficulties for hydrogen-producing bacteria and methanogenic bacteria in obtaining liquid nutrients. This leads to a lower potential for methane production in the Xinsheng mine as compared to the other coal mines. The prediction based on 16S rRNA gene function showed that the microorganisms in Qinan mine had the largest abundance of annotated homologous genes involved in glycolysis, fatty acid synthesis, and methane metabolism, which had a significant positive correlation with methane production. An important observation was the absence of acetate-CoA ligase in the glycolytic pathway, which rules out the acetate-trophic pathway as a significant contributor to coal biodegradation and methanogenesis. Moreover, the abundance of genes related to the hydrogenotrophic methanogenesis pathway was found to be the highest during methane metabolism, indicating that the CO2 reduction pathway plays a significant role during the anaerobic fermentation of coal to produce biomethane.

The Retention and Control Technology for Rock Beams in the Roof of the Roadway: A Case Study

Background: Coal mining requires safe and effective roadway support to ensure production and worker safety. Anchor support is a common method used for controlling the roof of coal seams. This study aims to analyze the effectiveness of different anchor support schemes and provide a theoretical basis for designing safe and effective roadway support. Methods: The authors used a computer simulation tool called FLAC3D to simulate and analyze the spacing between anchor bolts, anchor bolt length, anchor cable length, and effective roadway roof control, and support the schemes at the western wing roadway in the no. 15 coal seam of no. 1 mine of Ping’an Coal Mine. Results: The study found that using different combinations of anchor bolts and cables with varying lengths could effectively control the deformation of the roadway surrounding rock, depending on the spacing between layers of the coal seam. The most effective support schemes were recommended depending on the specific conditions. Conclusion: The study provides a theoretical basis for the design of anchor support in coal mines, which can ensure the safety of production and improve roadway stability. The results could be useful for other mining operations facing similar challenges in roadway support and stability.

Experimental investigation on effect of loading rate on fracture behavior of coal-seam roof rock

The fracture behavior of coal-seam roof rock in coal mining is a key and controlling factor for the mode optimization of the artificial roof caving. However, the fracture mechanism of roof rock under loading is not clear. In the work, the split Hopkinson pressure bar (SHPB) experiment was carried out using semicircular bending samples from the sandstone of coal-seam roof rock in the Junger mining area of Inner Mongolia at the loading rate of 0.35–3.78 GPa·m0.5·s−1, and the dynamic fracture behavior and energy dissipation mechanism of samples under different loading rates were investigated. The result shows that the dynamic stress–strain process of the hard roof rock includes four stages: linear instantaneous compaction, linear elastic compression, failure, and fracture extension, in which the failure forms changes from brittle fracture to ductile fracture with the increase of loading rate. The mode I fracture toughness increases linearly under confining pressure. In addition, the propagation orientation of induced fractures is parallel to the loading direction, and the gravel in the samples can inhibit fracture extension, resulting in changing the fracture extension path. Further, the energy absorption efficiency of the samples during the fracture process decreases with the increase in the loading rate.

Application research of autoregressive and moving average power spectrum in mine ground‐penetrating radar structure detection data analysis

AbstractThe mine roadway built in the same thick rock stratum will not change the lithologic medium in front of the roadway under the influence of the small structure of the mine, which makes the mine radar face many difficulties in structural interpretation. In the coal measure strata in southwest China, the coal seam roof is the weak aquifer of the Kayitou (T1k) group. The mine structure is the excellent drainage boundary of an aquifer, resulting in the water content of the structural belt being different from that of the surrounding rock. This paper proposes a method to identify hidden structures in mine roadways using the autoregressive and moving average power spectrum energy enveloping medium water content inversion technique. Based on the actual water content of strata in the study area, 48 roadway models are constructed. The finite‐difference time‐domain algorithm was used to obtain the forward data and calculate the volumetric water content of the model. The structure of the roadway model is accurately identified by the water content difference. In the numerical simulation study, the segmentation frequency of high‐frequency and low‐frequency envelope of the autoregressive and moving average spectrum of 100‐MHz radar antenna is determined to be 155 MHz, and the value range of water content calculation regulation parameter k is determined. The high‐ and low‐frequency envelope inversion characteristics of the autoregressive and moving average spectrum of different tunnel media models are summarized and analysed. To solve the calculation problem of energy envelope selection of autoregressive and moving average power spectrum of engineering data, the k‐nearest neighbour machine learning algorithm was used to learn and classify the power spectrum features of different tunnel models. The detection application is analysed through the whole‐rock medium and coal and rock medium roadway in the study area. The results show that the method can effectively identify the location and strike characteristics of the hidden structures in front of the roadway.

Prediction of the stability of gob‐side entry formation by roof cutting by machine learning‐based models

AbstractGob‐side entry formation by roof cutting is a new technology for no pillar coal mining, which can maximize coal resources and reduce roadway drivage ratio. However, the mechanical behavior of the formed entry is complex while it is crucial to ensure the stability of the entry for mining safety. This paper proposed a machine learning‐based method for predicting the stability of the formed entry, which combined artificial neural network (ANN) with particle swarm optimization (PSO) algorithm or genetic optimization (GO) algorithm. The data set from 75 coal mining faces from 2009 to 2022 was employed to train and test the models. A descriptive variable of dynamic unstable distance was introduced to evaluate the stability state of the formed entry and six other parameters were chosen as influence parameters. The two intelligent models were compared with each other to have a comprehensive assessment. Model assessment indices such as R2, mean absolute error, mean absolute percentage error, and root mean square error were used to evaluate the accuracy of the models. The results of both developed models are promising, and the predictive accuracy of the PSO‐ANN model is higher than that of the GO‐ANN model. Through sensitivity analyses, it has been found that the coal seam thickness and roof rock hardness are the most important parameters for influencing entry stability. The developed method provides a practical tool for the prediction of entry stability and the optimization of entry design.

An FDM-Based Dynamic Zoning Method for Disturbed Rock Masses above a Longwall Mining Panel

Underground longwall mining can seriously disturb the surrounding rock masses above the panel. A surface cracking zone, continuous deformation zone, fractured zone, and caved zone can be formed in the overlying strata (termed the “four zones”), which may further result in the spontaneous combustion of coal seams and water inrush. It is essential to study and predict the development characteristics of the four zones induced by longwall mining to guarantee mining safety. These four zones are developed during the mining process, and the mechanical properties in different regions correspondingly differ. Thus, the dynamic zoning characteristics of the disturbed rock masses should be considered in any simulations. In this paper, an FDM-based dynamic zoning method for disturbed rock masses above a longwall mining panel is proposed. This method is mainly composed of four stages: (1) establishing a simplified complete stress-strain curve; (2) determining the zoning criteria; (3) adaptively adjusting the mechanical parameters of the disturbed rock mass; and (4) numerically modeling the longwall mining based on the FDM. The proposed method was applied to a study site in the Taixi coal mine. The dynamic development process of the four zones induced by longwall mining was clearly observed in the modeling procedure. The numerical modeling results achieved in this work, including the periodical coal-seam roof caving and the dynamic development characteristics of the four zones, are consistent with the observed distribution and other studies. The heights of the caved and fractured zones are basically consistent with the empirical formula. Thus, the dynamic zoning method can analyze and predict the dynamic development characteristics of four regions.

Anomalous concentrations of rare earth elements in acid mine drainage and implications for rare earth resources from late Permian coal seams in northern Guizhou

Rare earth elements (REEs) have attracted much attention in recent decades due to their growing applications in high-tech industries. Coal and acid mine drainage (AMD) are considered promising alternative sources due to their high concentrations of REEs. Here, AMD with anomalous REEs concentrations was reported in a coal-mine area in northern Guizhou, China. The AMD had a total concentration as high as 22.3 mg/l, suggesting that regional coal seams may be enriched with REEs. Five segments from borehole samples, which contained coal, rocks from the roof and floor of the coal seam were collected from the coal mine site to investigate the abundance, enrichment, and occurrence of REE-bearing minerals. Elemental analysis showed that the REE contents in the coal, mudstone and limestone from the coal seam roof, and claystone from the floor (all dating to the late Permian) varied greatly, with averages of 388, 549, 60.1 mg/kg and 2030 mg/kg, respectively. Encouragingly, the REEs content in the claystone is over an order of magnitude higher than the average content reported in most other coal-based materials. The enrichment of REEs resources in regional coal seams is particularly associated with the contribution of REEs in the claystone that comprises the coal seam floor, rather than just the coal, as considered in previous studies. The minerals in these claystone samples were dominated by kaolinite, pyrite, quartz and anatase. Two types of REE-bearing minerals, bastnaesite and monazite, were detected in the claystone samples by SEM–EDS analysis, and they were found to be adsorbed by a large amount of clay minerals, mainly kaolinite. Additionally, the results of chemical sequential extraction also confirmed that the majority of the REEs in the claystone samples are mainly in their ion-exchangeable, metal oxide and acid-soluble forms, which are viable prospects for REE extraction. Therefore, the anomalous concentrations of REEs and most of them are in extractable phases, which demonstrates that the claystone from the floor of the late Permian coal seam should be a potential secondary source of REEs. Future studies will further consider the extraction model and the economic benefits of REEs from the floor claystone samples.

A Toxicological Study of the Respirable Coal Mine Dust: Assessment of Different Dust Sources within the Same Mine

Respirable coal mine dust (RCMD) exposure is one of the utmost health hazards to the mining community causing various health issues, including coal worker pneumoconiosis (CWP). Considering multiple potential sources of RCMD having different physicochemical properties within the same mine suggests a wide range of health impacts that have not yet been studied extensively. In this work, we investigate the toxicity of lab-created RCMD based on different sources: coal seam, rock dust, host floor, and host roof collected from the same mine. Comparative samples obtained from several mines situated in various geographic locations were also assessed. This work quantifies metal leaching in simulated lung fluids and correlates dissolution with in vitro immune responses. Here, dissolution experiments were conducted using two simulated lung fluids; Gamble solution (GS) and artificial lysosomal fluid (ALF). In vitro studies were performed using a lung epithelial cell line (A549) to investigate their immune responses and cell viability. Si and Al are the most dissolved metals, among several other trace metals, such as Fe, Sr, Ba, Pb, etc. RCMD from the coal seam and the rock dust showed the least metal leaching, while the floor and roof samples dissolved the most. Results from in vitro studies showed a prominent effect on cell viability for floor and roof dust samples suggesting high toxicity.

Damage evolution of rock containing prefabricated cracks based on infrared radiation and energy dissipation

This study aims to study the damage evolution characteristics of rock mass containing prefabricated cracks with different angles. First, similar material proportioning tests were carried out referring to the composition and mechanical properties of coal seam roof in Xin-ji No. 1 Coal Mine based on the analog simulation theory. Afterwards, macroscopic cracks with different angles were prefabricated on the specimens. During the uniaxial loading experiments, the infrared radiation information of the specimen surface was obtained using an infrared monitoring system. Moreover, the damage variables were defined based on the accumulated infrared radiation temperature and the proportion of dissipative strain energy in the energy evolution. The results show that with the increase in prefabricated crack’s dip angle, the brittleness of the rock mass diminishes; the closing strain of the prefabricated crack decreases; the stress concentration location of the crack tip starts to spread outward from the center of the specimen; and the failure changes from a tensile-shear composite mode to a tensile splitting mode. The infrared radiation temperature on the specimen surface fluctuates; specifically, it falls first and then rises. The abrupt change of the maximum infrared radiation temperature near the peak stress is significant, and this change reaches the maximum when the dip angle of the prefabricated crack is 45°. In addition, the damage evolution process of the rock mass can be roughly divided into three phases: initial damage, stable damage and accelerated damage. The stresses calculated from the defined damage variables have the same trend with the measured stresses, with a correlation of over 0.9, so it can well characterize the progressive evolution process from the crack emergence, expansion to failure. The research presented in this paper can provide a theoretical support for the early warning of coal-rock dynamic disaster.

Enrichment of lithium in the claystone coal gangue from the Malan mine, Xishan Coalfield, Shanxi Province, Northern China

In China, the lack of Li resources is in stark contrast to a large amount of coal gangue produced by coal mining. To determine the distribution patterns and existing status of lithium (Li) elements in the coal gangue, the mineralogical and geochemical analysis were formed on samples of the roof, floor, and parting of No. 02, 2, 8, and 9 coal seams, being mined in Malan mine, Xishan coalfield, Shanxi Province. The results show that the lithium content in this study area is relatively enriched, the highest content is 499 μg/g in sample 02-G, and the average content is 109.8 μg/g, which is two times that of the world average value of claystone (45 μg/g). XRD analysis shows that the mineral composition of parting samples is mainly clay mineral kaolinite, while the coal seam roof and floor samples also include quartz and some iron-bearing minerals, such as pyrite and siderite. Likewise, possible lithium-rich mineral phases and possible lithium-rich factors were investigated in this paper. A comprehensive clay separation experiment and correlation analysis between lithium and major elements indicate that lithium is likely to exist in the clay mineral kaolinite in the study area. It is also found that the content of Li adsorbed by cryptocrystalline kaolinite is generally higher than that of crystalline kaolinite. According to the mechanism of Li+ adsorption in clay minerals, the higher lithium content of cryptocrystalline kaolinite is due to its larger specific surface area, which can adsorb more lithium on the surface.

Development Characteristics of Roof Separation of Coal Seam Based on UDEC

The formation, development and fracture of the separation space of the coal seam roof are accompanied by the formation of water hazard of the separation layer of the working face. Using UDEC numerical simulation method, taking a certain working face of a mine as the research object, the dynamic development process of the separation space of overburden of the coal seam roof during the mining process of the working face is analyzed, and the separation development position and three-zone height are determined, which provides theoretical basis for the formation mechanism of water hazard of the separation layer of the mine.

A novel method to retain a waterproof coal pillar near water-conducting fault

AbstractReducing the width of safe coal pillar near geological structures, such as a water-conducting fault, to improve the extraction ratio of coal seam is a major concern that needs to be addressed urgently for mining shallow coal resources in China. To tackle the contradiction between improving the extraction ratio of resources and the disaster caused by reducing the width of the waterproof coal pillar, this study focuses on retaining the coal (rock) pillar near the water-conducting fault and proposes a novel method for calculating the waterproofing of the coal pillar precisely. We consider the different location relationships between the water-conducting fault, confined aquifer and coal seam, and suggest the principle of retaining the waterproofing of the coal pillar. First, we develop a mechanical model describing a waterproof coal pillar near the water-conducting fault by using elastic–plastic mechanics theory and subsequently calculate the length of plastic zone of the coal pillar under water pressure of the fault by using the limit equilibrium method. Furthermore, we use FLAC3D software to simulate the stress distribution of the coal seam roof and floor under fault water pressure. Subsequently, based on the Mohr–Coulomb strength criterion, we propose a method to calculate the width of waterproof coal pillars by combining the plastic zone with the maximum principal stress propagation line. Ultimately, we assess and discuss the accuracy and simplicity of this method by combining it with engineering methods.

Mechanical and Microcrack Evolution Characteristics of Roof Rock of Coal Seam with Different Angle of Defects Based on Particle Flow Code

The creation of the natural ceiling rock of the coal seam is rife with fractures, holes, and other flaws. The angle of the defects has a significant influence on the mechanical characteristics and crack evolution of coal seam roof rock. Multi-scale numerical simulation software PFC2D gets adapted to realize the crack propagation and coalescence process in the roof rock of a coal seam with different angles of defects under uniaxial compression. The effect of flaw angles on the micro and macro mechanical characteristics of rock is also discovered. The results show that: (1) the defect angle has influence on the stress-strain, elastic modulus, peak strength, peak strain, acoustic emission (AE) and strain energy of roof rock of coal seam. When the defect angles are different, the starting position of the roof rock in a coal seam fracture is different. The quantity of microcracks firstly reduces with an increase in defect angles before gradually increasing. At the same fault angle, the cracks are mostly tensile ones and only a few shear ones. (2) When the defect angle is less than 90°, tensile and shear fractures are mostly localized at the defect's two tips and propagate along the loading direction. When the defect angle is 90°, the tensile and shear cracks are not concentrated at the tip of the defect. (3) As the defect angles increase, the elastic strain energy rises initially and then falls, and the dissipated energy and total input energy both increase continuously. The elastic strain energy is greatest at the highest strength. The study provides a certain reference for the use of various analysis methods in practical engineering to evaluate the safety and stability of rock samples with pre-existing defects.

Understanding the Distribution Laws of In Situ Stress in Mines Based on Global Positioning System Data and Numerical Simulation Analysis

To ensure safe exploitation of the Muduchaideng Mine, we use a numerical simulation to invert the in situ stress field based on observation data from GPS stations, investigate differences in movement velocities at different locations, and analyze the lefthanded movement in the area around the wellfield. The relationship between the difference in motion velocity and the in situ stress field was explained through theoretical analysis. The law of in situ stress distribution was studied using data collected from the surrounding mines, and a regression equation as well as the relationship between the magnitudes of the three-way stresses was obtained. The inversion results were consistent with the measured data, indicating that inversion of the in situ stress field was accurate under the conditions found in the intact Ordos block. Additionally, the influence of tectonic stress on the key layer was larger than that on the bedrock of the coal seam roof, and the energy accumulated in the key layer was higher. The stress concentration coefficient of the key layer was similar to the variation law of the coal seam thickness. Therefore, the southwest area of the wellfield with a thicker coal seam is the key area for impact ground pressure prevention and control.

Research on the Distribution Characteristics of the Bulking Coefficient in the Strike Direction of the Longwall Goaf Filled with Slurry

Coal gangue slurry filling is an important technical means for harmless and large-scale disposal of gangue under low-interference conditions, and is one of the most important ways to achieve green mining, which is in line with the national concept of green development. This paper systematically expounds the technical background and scientific connotations of the birth of slurry filling, clarifies the key technology and process principles of slurry filling, and constructs the lag distance and optimization method of slurry filling based on the bulking coefficient. In order to explore the distribution law of the bulking coefficient of the overburden broken zone in the mining process, UDEC numerical simulation and similar simulations were used to analyze the movement law of a coal seam roof and the distribution characteristics of the bulking coefficient. The results show that with the evolution of the spatial structure of the overlying strata of the goaf, the subsidence of the coal seam roof decreases from the bottom to the top, and finally becomes stable. In the advancing direction of the working face, the bulking coefficient decreases continuously, and shows certain zoning characteristics. With the mining, it moves forward periodically with dynamic changes. In the strike direction, it can be divided into three areas: the natural accumulation area, the load-affected area and the gradual compaction area. Finally, the lag distance of slurry filling is determined to be 60 m, and the effect of adjacent grouting filling is good in the field test.

Study on stability of underlying room and pillar old goaf in close coal seam and mining of the upper coal seam

Possible issues during mining of the upper coal seam in old goaf of nearby coal seams, including step subsidence, gas overflow in goaf, and roadway around rock fragmentation. Using the Hanjiawa Coal Mine’s upper coal seam mining, which takes place 28 m above the working face of the lower coal seam, as the research’s focal point. The paper focuses on the self-stability of the coal pillar in the old goaf, the failure form of the upper coal seam mining floor, the roof caving rule of the old goaf in the lower coal seam mining of the upper coal seam, and the bearing capacity of the interlayer rock strata using the pillar goaf stability evaluation system, field geological borehole electrical logging and borehole peeping, finite element difference numerical calculation, and other methods. The conclusion that the old goaf’s coal pillar can be completely stable and that the interlayer rock strata can bear the stress of upper coal seam mining is reached. The results show that the failure depth of the coal pillar in the lower coal seam old goaf is 1–3 m, the maximum failure depth accounting for 15% of the width of the coal pillar, and the failure depth of the roof in the old goaf is 0–3 m; After the mining of the upper coal seam, the floor above the coal pillar of the lower coal seam is plastic failure, and the failure depth is 1–10 m, and the failure depth of the roof of the old goaf of the lower coal seam is 3–15 m, which is 4 times greater than that before the mining. The maximum failure depth of the interlayer rock strata is 22 m, accounting for 78.6% of the rock strata spacing. The interlayer rock strata can bear the mining disturbance of the upper coal seam. The plastic zone of the floor of the upper coal seam is not connected with the plastic zone of the roof of the lower coal seam.

The influence of roof lithology on the fracture propagation of horizontal well multistage fracturing in the roof of broken soft coal seams

Horizontal well multistage fracturing in the roof of broken soft coal seams has been demonstrated to be an effective technique to extract coalbed methane (CBM). However, fracture propagation behaviours under this technology vary significantly with different roof lithologies. Therefore, the influence of roof lithology on fracture propagation was investigated in this study. Based on the No. 5 and No. 11 coal seams in the Hancheng block of the Ordos Basin in China, field tests of horizontal well multistage fracturing in the sandstone and mudstone roof of crushed soft coal seams were performed and fractures were detected by microseismic monitoring. Corresponding hydraulic fracturing physical simulation experiments were conducted. The results show that the effectively propped fractures in the roof can provide flow channels for CBM. The better microseismic monitoring fractures and higher CBM production than direct fracturing in coal seams demonstrated the desirable feasibility of this technology. For the sandstone roof, the morphologies of hydraulic fractures were regular and one main fracture was formed by each perforation cluster. For the mudstone roof, the shapes of fractures were irregular and complicated fracture networks were formed. The findings can improve the design of horizontal well multistage fracturing in the roof of broken soft coal seams.

ПРИМЕНЕНИЕ МЕТОДА КОНЕЧНЫХ ЭЛЕМЕНТОВ ДЛЯ ОБОСНОВАНИЯ НАПРАВЛЕННОГО ГИДРОРАЗРЫВА ПРИ ОТРАБОТКЕ СБЛИЖЕННЫХ ПЛАСТОВ

The problem of determining the stress-strain state of two closely spaced sloping coal seams was solved numerically by the finite element method. The influence of the upper coal seam being mined on the strength state of the pillar, which is formed during the preparation of the lower coal seam for excavation, was studied. It has been established that the use of directed hydraulic fracturing of the roof of the upper coal seam allows unloading the pillar on the lower coal seam by 25 % and maintaining its strength state.

Evaluation of Water Inrush Hazard in Coal Seam Roof Based on the AHP-CRITIC Composite Weighted Method

The more complex the hydrogeological conditions of a mine, the more likely the coal seam is to experience water inrush during the mining process, and the greater the degree of the water inrush hazard. The scientific and reasonable prediction of water inrush in mines with complex hydrogeological conditions is of great significance to the safe and efficient operation of coal mines. Taking the roof water inrush problem of the No. 3 lower coal seam in the Jisan Coal Mine as the research object, the factors affecting the roof water inrush of the coal seam were comprehensively considered from three aspects: the aquifer property, the mining fracture development and the geological structure. The evaluation index system was constructed by selecting 10 factors, including the aquifer depth and thickness, core recovery rate, brittle–plastic rock thickness ratio, number of water-resisting layers, development height of the water-conducting fracture zone, fault density, frequency density, scale index and variation coefficient of the coal seam floor dip angle. At the same time, based on the dual influence of subjective and objective weighting, the scientific and reasonable weight of each factor was ensured. The AHP-CRITIC composite weighting method was used to calculate the comprehensive weight of each factor. Finally, the roof water inrush risk prediction model was constructed. According to the prediction results, the study area was divided into a low-risk area, medium-risk area and high-risk area. Compared with the actual situation, the prediction results were basically consistent with the actual situation, and the prediction results can provide the basis for the prevention and control of water in a coal mine.