A coal mine suspended roof goaf danger assessment method and device

Abstract

This application discloses a method and apparatus for assessing the hazard of overhanging goaf areas in coal mines, relating to the field of disaster prevention and control technology. The method includes: acquiring data on stability influencing factors of the overhanging goaf area, covering the mining depth-to-thickness ratio, area extraction rate, key roof strata conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor, thereby determining the collapse probability level; acquiring data on collapse hazard influencing factors, covering surface buildings and structures and their protection levels, impact on the mine production system and underground personnel, collapse seismic intensity, and the degree of threat posed by the collapse to the surrounding area, thereby determining the collapse hazard level; and combining the two levels to determine the final hazard level according to preset judgment rules. This application enables a systematic, hierarchical, and accurate assessment of the hazards of overhanging goaf areas, providing a reliable assessment basis for differentiated prevention and control of goaf disasters.

Description

Technical Field

[0001] This application relates to the field of disaster prevention and control technology, and in particular to a method and apparatus for assessing the risk of coal mine goaf areas. Background Technology

[0002] Due to limitations in mining technology and equipment, early coal mines developed numerous room-and-pillar goaf areas. Once these goaf areas become unstable during long-term operation, they can easily trigger large-scale roof collapses, mine tremors, and rapid surface subsidence, seriously threatening underground safety and the safety of personnel and buildings on the surface. Therefore, scientific hazard assessment methods are urgently needed to support disaster prevention and control.

[0003] Existing assessments of goaf areas mostly involve a single analysis of coal pillar stability, failing to systematically integrate multi-dimensional stability influencing factors such as mining depth-to-thickness ratio, area extraction rate, key roof conditions, coal pillar width-to-height ratio, and coal pillar safety factor. Furthermore, they do not incorporate factors such as the protection level of surface structures, the impact of underground production and personnel, the magnitude of collapse tremors, and the degree of threat from surrounding areas into a unified assessment system. The lack of clear standards for collapse probability and hazard classification, as well as comprehensive risk assessment rules, makes it difficult to accurately match the needs of graded prevention and control, and thus cannot provide a reliable basis for differentiated disaster prevention and control in goaf areas. Summary of the Invention

[0004] This application provides a method and apparatus for assessing the hazard of coal mine roof goaf areas. It can solve the problem in related technologies where assessment results are difficult to match the needs of graded prevention and control due to the single assessment dimension and lack of a unified grading system.

[0005] According to a first aspect of this application, a method for assessing the hazard of coal mine goaf areas is provided, comprising: Data on stability influencing factors of the suspended goaf area were obtained. These factors include the mining depth-to-thickness ratio, area extraction rate, key roof strata conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor. Based on the data on factors affecting stability, the collapse probability level of the suspended goaf area is determined; Data on the factors influencing the risk of collapse in the suspended goaf area were obtained. These factors include surface buildings and structures and their protection levels, the impact on the mine production system and underground personnel, the magnitude of the mine earthquake that may be caused by the collapse, and the degree of threat posed by the collapse to the surrounding area of ​​the mine. Based on the data on factors influencing the risk of collapse, the collapse hazard level of the suspended goaf area is determined; Based on the collapse probability level and collapse hazard level, the hazard level of the suspended goaf is determined according to the preset hazard assessment rules.

[0006] According to a second aspect of this application, a device for assessing the hazard of coal mine goaf areas is provided, comprising: The first acquisition module is configured to acquire data on stability influencing factors of the suspended goaf area. These stability influencing factors include the mining depth-to-thickness ratio, area extraction rate, key roof layer conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor. The first determination module is configured to determine the collapse probability level of the suspended goaf area based on stability influencing factor data; The second acquisition module is configured to acquire data on the impact factors of collapse hazards in the suspended goaf area. The impact factors of collapse hazards include surface buildings and structures and their protection levels, the impact on the mine production system and underground personnel, the level of mine tremors that may be formed by the collapse, and the degree of threat of the collapse to the surrounding area of ​​the mine. The second determination module is configured to determine the collapse hazard level of the suspended goaf area based on the collapse hazard influencing factor data; The third determination module is configured to determine the hazard level of the suspended goaf area based on the collapse probability level and collapse hazard level, according to preset hazard judgment rules.

[0007] According to a third aspect of this application, an electronic device is provided, comprising: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the coal mine goaf risk assessment method described in the first aspect above.

[0008] According to a fourth aspect of this application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the coal mine roof goaf hazard assessment method of the first aspect described above.

[0009] According to a fifth aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the coal mine goaf risk assessment method as described in the first aspect above.

[0010] This application integrates multiple stability-influencing factors such as mining depth-to-thickness ratio and area extraction rate with multiple collapse-hazard-influencing factors such as the protection level of ground structures and the collapse tremor level. It constructs a progressive judgment rule from collapse probability level to collapse hazard level to comprehensive risk level. Therefore, it can solve the problem in related technologies where the assessment results are difficult to match the needs of graded prevention and control due to the single assessment dimension and lack of a unified graded judgment system. It achieves the technical effect of realizing the systematic and graded accurate judgment of the risk of overhanging goaf areas, and providing a reliable assessment basis for the differentiated prevention and control of goaf disasters.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating a method for assessing the risk of coal mine goaf areas provided in this application embodiment; Figure 2 A schematic diagram of the structure of a coal mine goaf risk assessment device provided in an embodiment of this application; Figure 3 A schematic block diagram of an example electronic device provided in the embodiments of this application; Figure 4 A schematic diagram of the hazard assessment hierarchy analysis structure model provided in the embodiments of this application; Figure 5 This is a schematic diagram of the optimal classification surface for two types of linear classification provided in the embodiments of this application. Detailed Implementation

[0014] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0015] The following describes, with reference to the accompanying drawings, a method and apparatus for assessing the risk of coal mine goaf areas under suspended roofs, according to embodiments of this application.

[0016] Figure 1 This is a flowchart illustrating a method for assessing the risk of coal mine goaf areas provided in an embodiment of this application.

[0017] like Figure 1 As shown, the method includes the following steps: Step 101: Obtain data on the stability influencing factors of the suspended goaf area. The stability influencing factors include the mining depth-to-thickness ratio, area extraction rate, key roof layer conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor.

[0018] In some embodiments, when conducting a hazard assessment of a coal mine's overhanging goaf, it is first necessary to collect data on factors affecting the stability of the overhanging goaf. This data can be obtained through mine geological exploration reports, mining designs and historical data, on-site underground measurements, roof strata detection, and calculation of coal pillar mechanical parameters. The data should cover five core indicators: mining depth to thickness ratio, area recovery rate, key roof strata conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor.

[0019] The mining depth-to-thickness ratio refers to the ratio of the coal seam burial depth to the coal seam mining thickness within the assessment area. It is a fundamental parameter reflecting the mining stress environment and the overall bearing capacity of the roof. The area extraction rate refers to the proportion of the coal seam mining area to the total area within the assessment area, directly reflecting the spatial development degree of the goaf and the overall bearing capacity of the remaining coal pillar. The key roof strata condition refers to the location, thickness, and continuity of the distribution of hard, key strata in the coal seam roof. It is a core geological element determining the overall stability of the roof after exposure. The coal pillar width-to-height ratio refers to the ratio of the width to the height of the remaining coal pillar, a key parameter characterizing the geometric bearing capacity of the coal pillar itself. The coal pillar stability safety factor is a quantitative safety index calculated by combining the coal pillar's own strength and actual bearing stress, used to directly reflect the bearing capacity safety reserve level of the coal pillar.

[0020] This step comprehensively covers the stability control elements of the overhanging goaf from multiple dimensions such as geological occurrence conditions, mining space parameters, and coal pillar bearing characteristics, providing complete and reliable data support for subsequent collapse probability level determination and ensuring the comprehensiveness and objectivity of the assessment results.

[0021] Step 102: Determine the collapse probability level of the suspended goaf area based on the stability influencing factor data.

[0022] In some embodiments, after obtaining data on various stability influencing factors, the determination of the collapse probability level of the overhanging goaf can be carried out. The determination process first classifies the stability level of each individual factor, and then combines the determination results of multiple factors to comprehensively determine the final collapse probability level.

[0023] For each stability influencing factor, a corresponding grading threshold is preset. By comparing the actual collected data with the threshold, three stability levels (high, medium, and low) can be obtained for each factor. A mining depth-to-thickness ratio greater than 60 corresponds to high stability, between 30 and 60 to medium stability, and less than 30 to low stability. An area recovery rate less than 40% corresponds to high stability, between 40% and 60% to medium stability, and greater than 60% to low stability. For the key roof strata, the presence of a continuous, thick, hard rock layer with a thickness of not less than 15m corresponds to high stability; the presence of a continuous, hard rock layer with a thickness of 5m to 15m corresponds to medium stability; and the absence of a hard rock layer or the presence of thin, alternating layers of soft and hard rock corresponds to low stability. A coal pillar width-to-height ratio greater than 3.5 corresponds to high stability, between 2 and 3.5 to medium stability, and less than 2 to low stability. A coal pillar stability safety factor greater than 2 corresponds to high stability, between 1.2 and 2 corresponds to medium stability, and less than 1.2 corresponds to low stability.

[0024] After determining the stability level of each individual factor, the overall collapse probability level of the goaf can be determined by referring to the preset stability grading mapping table and combining the level results of the five factors. This level is also divided into three levels: high, medium, and low, which correspond to different probability levels of goaf collapse.

[0025] This step classifies various influencing factors through clear quantitative thresholds, and then comprehensively determines the possibility of collapse through unified mapping rules. The judgment criteria are clear and practical, and can objectively and accurately reflect the stability state and collapse risk probability of the overhanging goaf area itself, providing a reliable judgment basis for subsequent collapse hazard assessment and comprehensive risk classification.

[0026] Step 103: Obtain data on the factors influencing the collapse hazards of the suspended goaf area. These factors include surface buildings and structures and their protection levels, the impact on the mine production system and underground personnel, the magnitude of the mine earthquake that may be caused by the collapse, and the degree of threat posed by the collapse to the surrounding area of ​​the mine.

[0027] In some embodiments, after collecting data on factors affecting the stability of the goaf, it is necessary to further obtain data on factors affecting the hazards of collapse, in order to characterize the degree of disaster loss that may be caused by a collapse of the goaf. Relevant data can be obtained through on-site surveys of surface buildings and structures, analysis of the mine production system, theoretical calculations of roof collapse energy, and surveys of the surrounding environment of the mine. Specifically, this data covers four core indicators: the impact of surface buildings and structures and their protection levels, the impact on the mine production system and underground personnel, the magnitude of the potential mine tremor caused by the collapse, and the degree of threat posed by the collapse to the surrounding area of ​​the mine.

[0028] The protection levels of ground buildings and structures correspond to the importance classification of various ground buildings and structures within the impact area of ​​the overhanging mining subsidence zone. Buildings include historical buildings, industrial plants, office buildings, residences, and public service buildings, while structures include bridges, highways, power transmission towers, oil and gas pipelines, and water conservancy dams. The protection levels are classified according to the functional attributes, importance, and social and economic impact of the facilities after damage, reflecting the sensitivity of the ground objects subject to disaster.

[0029] The impact on the mine production system and underground personnel refers to the degree of disruption to underground mining, ventilation, transportation and other production systems after the collapse of the goaf, as well as the degree of safety threat to underground workers. It is the core parameter for assessing underground disaster losses.

[0030] The potential seismic magnitude of a collapse refers to the seismic magnitude corresponding to the energy released by the overall collapse of the roof of a goaf area, used to characterize the energy intensity and impact range of a collapse event.

[0031] The degree of threat posed by a collapse to the surrounding area of ​​a mine refers to the level of threat posed by the surface subsidence and vibration propagation effects caused by the collapse of the goaf to ground facilities, personnel, and the environment outside the mine boundary. It is used to assess the disaster impact outside the mine area.

[0032] This step collects hazard data from four dimensions: the surface disaster-bearing body, underground production and personnel safety, collapse energy intensity, and surrounding environmental impact. It comprehensively covers various disaster loss scenarios after the collapse of the overhanging goaf area, providing complete data support for the subsequent collapse hazard level determination, and ensuring that the assessment results can take into account the comprehensive disaster impact both above and below ground, inside and outside the mine.

[0033] Step 104: Determine the collapse hazard level of the suspended goaf area based on the data on factors affecting collapse hazards.

[0034] In some embodiments, after obtaining data on various factors influencing the risk of collapse, the determination of the collapse hazard level of the overhanging goaf can be carried out. The determination process first classifies the four influencing factors into levels one by one, and then combines the determination results of each factor to comprehensively determine the overall collapse hazard level of the goaf, which is divided into three levels: small, medium, and large.

[0035] For ground buildings and structures and their protection levels, the protection levels of buildings and structures within the assessment scope must first be classified according to the functional attributes, importance, and impact range after damage. Building protection levels are divided into four grades from highest to lowest: Special Grade, Grade I, Grade II, Grade III, and Grade IV, covering different types such as historical buildings, industrial plants, office and residential buildings, and village houses. Structure protection levels are also divided into four grades: Special Grade, Grade I, Grade II, Grade III, and Grade IV, covering types such as bridges, highways, power transmission and transformation facilities, and pipeline dams. When only Grade III or IV structures exist on the ground, the corresponding collapse hazard is low; when Grade IV buildings or Grade II structures exist, the corresponding collapse hazard is moderate; when Special Grade, Grade I, Grade II, and Grade III buildings, or Special Grade and Grade I structures exist, the corresponding collapse hazard is high.

[0036] The impact on the mine production system and underground personnel is classified according to the degree of production disruption and personnel safety risk after the collapse. If the collapse of the goaf will not affect the mine production system or underground personnel, the collapse hazard is low; if the collapse has a minor impact on the production system and can be quickly restored with simple adjustments without causing casualties, the collapse hazard is moderate; if the collapse has a significant impact on the production system and production cannot be restored in the short term, or may cause casualties, the collapse hazard is high.

[0037] The severity of potential mine-related seismic events caused by collapses is classified according to the magnitude of the energy released during the collapse. A magnitude less than 2 indicates a low risk of collapse; a magnitude between 2 and 3 indicates a moderate risk; and a magnitude greater than 3 indicates a high risk. Regarding the threat posed by a collapse to the surrounding area, the severity is classified according to the extent of impact and damage beyond the mine boundary. A collapse with no impact on the surrounding area indicates a low risk; a collapse with minimal impact on surrounding surface facilities and no casualties indicates a moderate risk; and a collapse with significant impact on surrounding surface facilities or casualties indicates a high risk.

[0038] After determining the level of each of the four influencing factors individually, the overall collapse hazard level of the suspended goaf can be determined by referring to the preset hazard classification mapping table and combining the level results of each factor.

[0039] This step establishes a multi-dimensional classification standard covering the surface disaster-bearing body, underground production safety, collapse energy intensity, and surrounding environmental impact. The judgment rules are clear and explicit, and can objectively and comprehensively reflect the degree of disaster loss after the collapse of the goaf, providing a reliable hazard assessment basis for subsequent comprehensive risk level determination.

[0040] Step 105: Based on the collapse probability level and collapse hazard level, determine the hazard level of the suspended goaf according to the preset hazard assessment rules.

[0041] In some embodiments, after obtaining the collapse probability level and collapse hazard level of the suspended goaf, any one of the three preset classification methods can be selected to comprehensively determine the final hazard level of the suspended goaf. The level is divided into three levels: low, medium, and high, which are used to intuitively characterize the comprehensive risk level of the goaf collapse disaster.

[0042] Method 1 uses the Analytic Hierarchy Process (AHP) to evaluate the path. A three-level hierarchical evaluation model is constructed. The hazard of the overhanging goaf is set as the target layer; the stability and collapse hazard of the overhanging goaf are set as the criteria layer; and nine indicators, including five stability influencing factors (mining depth to thickness ratio, area extraction rate, etc.) and four collapse hazard influencing factors (protection level of ground structures, seismic intensity, etc.), are set as the scheme layer. The 1-9 scaling method is used to compare the relative importance of each factor in each layer pairwise, constructing a positive-negative judgment matrix. The eigenvector corresponding to the largest eigenvalue of the matrix is ​​calculated, and a hierarchical single ranking is completed, followed by a consistency check. The matrix is ​​considered consistent when the consistency ratio (CR) is less than 0.1. After calculating the total ranking weight of each factor in the scheme layer relative to the target layer layer, the quantitative values ​​of each factor are normalized. The normalized values ​​are then weighted and summed with their corresponding weights to obtain the hazard index (RI). The risk index (RI) is statistically analyzed and a cumulative RI histogram is generated. The inflection point of the histogram is identified as the critical value of the partition interval, thereby determining the three risk assessment level intervals of high, medium and low.

[0043] Method two employs the entropy-weighted fuzzy comprehensive evaluation approach. First, a sample database of overhanging goaf areas with known hazard levels is established, summarizing sample data for nine key influencing factors. Based on the statistical characteristics of the sample data, a normal distribution membership function is constructed for each indicator corresponding to different hazard levels. The values ​​of each indicator in the goaf area to be evaluated are substituted into the membership function to obtain a single-factor evaluation matrix, which is then normalized. The information entropy and information utility value of each indicator are calculated using the entropy method, and the weight of each influencing factor is determined by the proportion of information utility value. Fuzzy operations are performed on the weight set and the single-factor evaluation matrix to obtain the fuzzy comprehensive evaluation result of the object to be evaluated. Finally, its hazard level is determined based on the principle of maximum membership degree.

[0044] Method three employs a support vector machine (SVM) classification assessment approach. A database of samples from overhanging goaf areas, labeled with hazard levels, is established. All samples undergo uniform normalization for nine influencing factors. Using the normalized multi-dimensional index data as input features and the hazard level of each sample as the classification label, a radial basis function (RBF) kernel is used to map the low-dimensional data to a high-dimensional feature space. This allows for the training of an SVM classification model that maximizes the classification margin between samples of different hazard levels. The influencing factor data for the goaf area to be assessed are then normalized in the same way and input into the trained model. The model directly outputs the hazard level corresponding to the goaf area.

[0045] It offers three risk classification methods adaptable to different application scenarios. When there are few cases to be assessed, the analytic hierarchy process can be used to achieve quantitative assessment. As case data accumulates, it can be switched to the entropy weight fuzzy comprehensive evaluation method or the support vector machine method to further improve the objectivity and intelligence of the assessment. The method selection is flexible and highly adaptable, and can provide a reliable decision-making basis for the prevention and control of goaf disasters with different data foundations.

[0046] Compared with related technologies, this embodiment obtains stability influencing factor data for the suspended goaf, including mining depth-to-thickness ratio, area extraction rate, key roof strata conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor. Based on the stability influencing factor data, the collapse probability level of the suspended goaf is determined. It also obtains collapse hazard influencing factor data for the suspended goaf, including surface buildings and structures and their protection levels, impact on the mine production system and underground personnel, the magnitude of the potential mine tremor caused by the collapse, and the degree of threat posed by the collapse to the surrounding mine. Based on the collapse hazard influencing factor data, the collapse hazard level of the suspended goaf is determined. Finally, based on the collapse probability level and collapse hazard level, and according to preset hazard judgment rules, the hazard level of the suspended goaf is determined. This addresses the problem in related technologies where the assessment results are difficult to match the needs of graded prevention and control due to a single assessment dimension and a lack of a unified grading and judgment system. It achieves the technical effect of systematically and accurately determining the hazard of suspended goafs, providing a reliable assessment basis for differentiated prevention and control of goaf disasters.

[0047] As a specific implementation of this application, based on the basic scheme, it further specifies that the collapse probability level of the suspended goaf area is determined according to stability influencing factor data, including: The mining depth-to-thickness ratio, area extraction rate, key roof layer conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor are compared with the preset classification thresholds for each factor to determine the stability level corresponding to each factor. Based on the stability levels of each factor and referring to the preset stability grading mapping table, the collapse probability level of the suspended goaf area is determined.

[0048] Specifically, Table 1 is a classification and quantification table of the main controlling factors affecting the stability of the column-type cantilever goaf. As shown in Table 1, when determining the collapse probability level of the cantilever goaf based on the stability influencing factor data, a combination of single-factor classification and comprehensive mapping is adopted. The specific process is as follows.

[0049] First, a single-factor stability level determination was conducted. Five indicators—mining depth to thickness ratio, area extraction rate, key roof conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor—were compared with preset grading thresholds for each factor to determine the stability level corresponding to each factor. The levels were uniformly divided into three levels: high, medium, and low.

[0050] After completing the stability level determination of all single factors, the level results of the five factors are comprehensively matched with reference to the preset stability grading mapping table to finally determine the overall collapse probability level of the overhanging goaf area. This level is also divided into three levels: high, medium and low. It can be directly used for subsequent comprehensive risk determination, or it can be normalized and assigned to participate in quantitative calculation.

[0051]

[0052] Furthermore, the stability level classification criteria for each stability influencing factor are as follows: A mining depth-to-thickness ratio greater than 60 corresponds to high stability, between 30 and 60 corresponds to medium stability, and less than 30 corresponds to low stability. Area recovery rate of less than 40% corresponds to high stability, between 40% and 60% corresponds to medium stability, and greater than 60% corresponds to low stability. The key conditions for the top plate are: high stability when there is a continuous distribution of thick, hard rock layers with a thickness of not less than 15m; medium stability when there is a continuous distribution of hard rock layers with a thickness of 5m to 15m; and low stability when there are no hard rock layers or thin layers of alternating soft and hard rocks. A coal pillar width-to-height ratio greater than 3.5 corresponds to high stability, a ratio between 2 and 3.5 corresponds to medium stability, and a ratio less than 2 corresponds to low stability. A coal pillar stability safety factor greater than 2 corresponds to high stability, between 1.2 and 2 corresponds to medium stability, and less than 1.2 corresponds to low stability.

[0053] This implementation method standardizes the process of determining the probability of collapse by using clear quantitative grading thresholds and unified mapping rules. The determination logic is clear and reproducible, which can effectively reduce the subjective bias of manual assessment and improve the accuracy and consistency of assessment results.

[0054] As a specific implementation of this application, based on the basic scheme, it further specifies that the collapse hazard level of the suspended goaf area is determined according to the data on factors affecting collapse hazards, including: The protection level of surface buildings and structures, the degree of impact on the mine production system and underground personnel, the magnitude of the potential mine earthquake caused by the collapse, and the degree of threat posed by the collapse to the surrounding area of ​​the mine are obtained respectively. Based on the above levels and referring to the preset hazard classification mapping table, the collapse hazard level of the suspended goaf area is determined.

[0055] Specifically, when determining the hazard level of a goaf under a suspended roof based on data on factors influencing the hazard of a collapse, a combination of single-factor level determination and comprehensive mapping is used, and the specific process is as follows.

[0056] First, a single-factor hazard level assessment was conducted. The assessment was based on four indicators: the level of protection of surface buildings, the impact on the mine production system and underground personnel, the intensity of the potential mine tremor caused by the collapse, and the threat level of the collapse to the surrounding area of ​​the mine. This yielded the hazard level corresponding to each factor, and each factor's level corresponded and was consistent with the overall hazard classification system.

[0057] Table 2 can be used as a reference for classifying the protection level of buildings in mining areas, and Table 3 can be used as a reference for classifying the protection level of structures in mining areas.

[0058]

[0059]

[0060] Regarding the impact on the mine production system and underground personnel, this study characterizes the degree of disruption caused by the collapse of the overhanging goaf to underground mining, ventilation, and transportation systems, as well as the degree of safety threat to underground workers. If the collapse does not affect the mine production system or underground personnel, the corresponding hazard is low; if the impact on the production system is minor, and production can be restored immediately with simple adjustments without causing casualties, the corresponding hazard is moderate; if the collapse has a significant impact on the production system, and production cannot be restored in the short term, or if it causes casualties, the corresponding hazard is high.

[0061] The seismic intensity level is used to characterize the energy released by the collapse of the roof in a goaf. The lower the seismic intensity level, the lower the corresponding hazard. Specifically, a seismic intensity level less than 2 indicates low hazard, a seismic intensity level between 2 and 3 indicates moderate hazard, and a seismic intensity level greater than 3 indicates high hazard.

[0062] The threat level of a collapse to the surrounding area is characterized by the degree of threat posed by the collapse of the goaf to surface subsidence and vibration propagation outside the mine boundary, affecting surface facilities and personnel. If the collapse has no impact on the surrounding area, the corresponding hazard is low; if it has a minor impact on surface facilities and does not cause casualties to surface personnel, the corresponding hazard is moderate; if it has a significant impact on surface facilities or causes casualties to surface personnel, the corresponding hazard is high.

[0063] After completing the hazard level determination for all single factors, the results of the four factors are comprehensively matched with the preset hazard classification mapping table (see Table 4, Classification Table of Collapse Hazards in Overhanging Goaf) to finally determine the overall collapse hazard level of the overhanging goaf. This level is uniformly divided into three levels, which can be directly used for subsequent comprehensive hazard determination, or they can be normalized and assigned values ​​to participate in quantitative assessment calculations.

[0064]

[0065] This implementation method incorporates four dimensions—surface disaster-bearing body, underground production safety, collapse energy intensity, and surrounding environmental impact—into a unified hierarchical mapping system. The judgment process is standardized and reproducible, and it can comprehensively cover various disaster impact scenarios of goaf collapse, effectively improving the systematicness and objectivity of hazard assessment and providing a reliable judgment basis for subsequent comprehensive risk classification.

[0066] As a specific implementation of this application, based on the basic scheme, the risk level of the suspended goaf is further determined according to the collapse probability level and collapse hazard level, and in accordance with the preset risk assessment rules, including: The hazard level can be determined using any one of the following three classification methods: Method 1: Determine the weights of each stability influencing factor and each collapse hazard influencing factor using the analytic hierarchy process (AHP). Calculate the hazard index based on the normalized quantified value of each factor and its corresponding weight. Determine the hazard level based on the hazard index. Method 2: Determine the weights of each stability influencing factor and each collapse hazard influencing factor using the entropy method, perform fuzzy comprehensive evaluation based on the membership function of each factor, and determine the hazard level based on the principle of maximum membership degree; Method 3: Establish a sample database of overhanging goaf areas with known hazard levels. Use the data of each stability influencing factor and each collapse hazard influencing factor as input to train a support vector machine classification model. Input the data to be evaluated into the trained support vector machine classification model and output the hazard level.

[0067] Specifically, in this embodiment, when determining the risk level of the suspended goaf based on the collapse probability level and the collapse hazard level, three classification assessment methods are preset and can be selected as needed. Any one of them can be selected and executed based on the engineering data foundation, the scale of historical case accumulation, and the assessment accuracy requirements, as detailed below.

[0068] Method 1 employs the Analytic Hierarchy Process (AHP) for quantitative assessment. A three-level hierarchical evaluation model is constructed, with the hazard of the overhanging goaf set as the target layer, the stability and collapse hazard of the overhanging goaf set as the criteria layer, and all stability-influencing factors and collapse-influencing factors set as the alternative layer. A judgment matrix is ​​constructed by comparing the relative importance of each factor to the upper-level target in pairs. After consistency verification, the weights of each influencing factor are calculated. The hazard index is obtained by weighted summing the normalized quantitative values ​​of each factor. Finally, the hazard level of the goaf is determined based on the preset grading threshold of the hazard index.

[0069] Method 2 employs entropy-weighted fuzzy comprehensive evaluation to achieve semi-quantitative assessment. Based on existing sample data of overhanging goaf projects, the information entropy and information utility value of each influencing factor are calculated using the entropy method to determine the objective weight of each factor. Simultaneously, membership functions corresponding to different risk levels for each factor are constructed, generating a single-factor evaluation matrix. Fuzzy comprehensive calculations are performed on the weights and evaluation matrix, and the risk level of the goaf to be evaluated is determined based on the principle of maximum membership.

[0070] Method 3 employs Support Vector Machines (SVMs) for intelligent classification and assessment. A sample database of overhanging goaf areas labeled with known hazard levels is established. After uniformly normalizing the data of various influencing factors in the samples, the normalized data is used as input features, and the hazard level as the classification label to train an SVM classification model. An optimal classification boundary is constructed in a high-dimensional feature space through nonlinear mapping. The corresponding data of the goaf area to be assessed is then subjected to the same normalization process and input into the trained model to output the hazard level of the goaf area.

[0071] This implementation provides three differentiated hazard classification paths to adapt to different engineering application scenarios. The Analytic Hierarchy Process (AHP) is suitable for stages with few assessment cases and primarily based on engineering experience, transforming complex qualitative problems into quantitative results. The Entropy Weight Fuzzy Comprehensive Evaluation Method and Support Vector Machine (SVM) are suitable for scenarios with sufficient sample data, reducing the interference of subjective judgment and improving the objectivity of the assessment results. These three methods can be flexibly selected, taking into account the assessment needs under different data foundations and ensuring the scientific rigor and applicability of the hazard classification results.

[0072] As a specific implementation of this application, based on the basic solution, method one is further defined as follows: A hierarchical model was constructed, with the danger of the suspended goaf area set as the target layer, the stability and collapse hazards of the suspended goaf area set as the criteria layer, and the stability influencing factors and collapse hazard influencing factors set as the scheme layer. Construct the judgment matrix for each layer of factors; Calculate the eigenvector corresponding to the largest eigenvalue of the judgment matrix, and perform hierarchical single sorting and consistency testing on each factor; Calculate the total hierarchical ranking weight of each factor in the scheme layer to the target layer; The risk index is calculated based on the normalized quantitative value of each factor and the corresponding hierarchical total ranking weight. The risk level of the suspended goaf area is determined based on the risk index.

[0073] Specifically, Figure 4 This is a schematic diagram of the hierarchical analysis structure model for hazard assessment, such as... Figure 4 As shown, after analyzing the main controlling factors affecting the hazard of suspended goaf areas, the target problem is divided into three levels. The hazard assessment of pillar-type suspended goaf areas is the ultimate problem to be solved, and constitutes the target level (Level A) of the hierarchical model. The stability and collapse hazards of pillar-type suspended goaf areas determine the hazard level of disasters caused by them, but their influencing mechanisms need to be reflected through specific related factors. This is the intermediate link in solving the problem of assessing the hazard of suspended goaf areas, serving as the criterion level (Level B). The various specific controlling factor indicators constitute the scheme level (Level C) of the hierarchical model. Through decision-making at this level, the target problem can ultimately be solved.

[0074] The judgment matrix is ​​constructed as follows: Assume that 9 factors need to be compared. To determine the magnitude of the impact of the column-type cantilever goaf hazard Z, a comparison matrix was established by comparing each factor pairwise, with two factors selected each time. and ,by express and The ratio of the magnitudes of the effects on Z, and all comparison results. Represented by matrices (Table 5), matrix A is the judgment matrix between Z and X.

[0075] like and The ratio of the influence on Z is ,but and The ratio of the influence on Z is its reciprocal, that is If the matrix conform to >0 and ( The condition (=1,2,…,9) is called a positive reciprocal matrix.

[0076]

[0077] The relationships in Table 5 can be represented using a judgment matrix as follows:

[0078] Determined using the numbers 1 through 9 and their reciprocals as a scale. The values ​​of 1 to 9 are as follows: 1 indicates that the two factors are equally important; 3 indicates that the former is slightly more important than the latter; 5 indicates that the former is significantly more important than the latter; 7 indicates that the former is strongly more important than the latter; 9 indicates that the former is extremely more important than the latter; 2, 4, 6, and 8 represent the intermediate values ​​of the above adjacent judgments.

[0079] The reciprocal indicates if factors With factors The ratio of importance is Then the ratio of the importance of factor j to factor i is .

[0080] Based on the analysis of the main controlling factors of the collapse risk of pillar-type cantilever goaf, scores are assigned according to the 1-9 scale method established by TLSAATY. The relative importance of each factor is ranked according to the magnitude of its influence on the collapse risk of the cantilever goaf, and a quantitative score is given for each factor. Based on the final cumulative scores, the total scores of each factor are compared to form an expert evaluation set for each influencing factor. Thus, the AHP evaluation judgment matrix of the pillar-type cantilever goaf risk of a certain mine is constructed.

[0081] The eigenvector W of the largest eigenvalue λmax in the judgment matrix A, after normalization, can be used to obtain the relative weight of the corresponding factor at the same level to a certain factor at the previous level. This process is called hierarchical single sorting.

[0082] The steps for the consistency check of the judgment matrix are as follows: (1) Calculation of the Consistency Index (CI)

[0083] (2) Finding the average random consistency index R. For n=1, 2, ..., 9, the R values ​​are shown in Table 6.

[0084]

[0085] Several sample matrices are selected using a random method, and numbers are randomly drawn from 1 to 9 and their reciprocals to construct positive and negative reciprocal matrices. The average value of the largest eigenvalue is then calculated. That is, to obtain the value of R, i.e. .

[0086] (3) The formula for calculating the consistency ratio (CR) is: .

[0087] When CR < 0.1, the consistency of the judgment matrix meets the requirements; otherwise, the judgment matrix needs to be appropriately modified.

[0088] Hierarchical overall ranking refers to calculating the ranking weights of all factors at the same level relative to the highest level. It is performed layer by layer from the highest level to the lowest level.

[0089] Let level A include m factors (A1, A2, ..., Am), with total ranking weights a1, a2, ..., am. Now assume level B includes n factors (B1, B2, ..., Bn), with ranking weights b1j, b2j, ..., bnj for each factor in level B with respect to Aj. The goal is to calculate the weights of each factor in level B with respect to the objective. The calculations are performed as shown in Table 7. (i=1,2,…,n).

[0090]

[0091] If the consistency index of certain factors at level B for a single ranking of Aj is CIj, and the corresponding average random consistency index is Rj, then the random consistency ratio of the overall ranking at level B is: .

[0092] When CR < 0.10, the overall hierarchical ranking results are considered to have satisfactory consistency and the analysis results are accepted.

[0093] The weight of each indicator Ci relative to the overall goal is the result of the weight of each indicator Ci in the indicator layer through the Bi layer to the target layer A. The symbol A / Ci represents the weight of each indicator Ci relative to the overall goal A, and WA / Ci is the weight of each indicator Ci relative to the overall goal A.

[0094] The overall random consistency ratio of the C-level can be calculated as follows:

[0095] With satisfactory consistency, WA / Ci can be used as the final decision-making basis, thereby determining the weight values ​​of the nine main control factors affecting the collapse risk of the column-type cantilever goaf.

[0096] There are two methods for quantifying single-factor values: one is the direct assignment method based on the specific conditions of the mine and work experience, as shown in Tables 1 and 4. The other is the assignment method based on GIS-based visualization vector maps. Specifically, a thematic zoning of a single controlling factor refers to an electronic map with attribute data reflecting the distribution of a certain factor within the column-type overhanging goaf area. The steps for creating the thematic zoning map are: first, to organize the basic data of the mine's overhanging goaf area, such as mining depth and thickness, roof characteristics, coal pillar dimensions, mining area, mechanical parameters, and building attributes, and compile them into a database; second, to perform preliminary interpolation processing on the organized data, at which point the resulting interpolation map does not contain attribute data; and third, to use the GIS graphic vectorization function to assign corresponding attribute values ​​to the surface files, process and analyze the data, and finally display the results and output the single-factor influence thematic map.

[0097] After the thematic maps of each controlling factor are assigned attribute data, problems arise such as inconsistent dimensions, lack of comparability, and statistical significance. Therefore, it is necessary to normalize the quantitative values ​​of each factor to unify the standards and ensure comparability of their impact on the collapse risk of the overhanging goaf. The normalization formula is: ; Where Ni represents the normalized data. These are the quantified values ​​of each factor before normalization; , It refers to the minimum and maximum values ​​of the quantized value.

[0098] Because the nine main control factors selected in this study have varying effects on the collapse of the overhanging goaf area—some promoting and some preventing it—meaning that each factor has a positive or negative correlation with the assessment of collapse risk, the normalization methods also differ. For factors with a negative correlation to collapse risk, the final normalized data is obtained by subtracting the result calculated using the formula from 1, thus standardizing the criteria for factors with different correlations.

[0099] The "Collapse Risk Index of Suspended Goaf Areas" evaluates the collapse risk of suspended goaf areas under the influence of multiple factors, introducing the Risk Index (RI). The Risk Index refers to the sum of the influences of various factors on a specific block within the study area. The formula for the RI index model is: ; Where: RI is the risk index of the goaf in a column-type cantilevered goaf; Weights of influencing factors; This is a single-factor influence value function; x and y are geographical coordinates; n is the total number of influencing factors, which is taken as 9 here.

[0100] Statistical analysis of the hazard index RI was performed to generate a cumulative RI histogram. The inflection points r1 and r2 of the histogram were identified as the critical values ​​for the zoning intervals, thereby determining the three hazard assessment levels: high, medium, and low. When RI∈[0, r1), the hazard level of the pillar-type cantilever goaf was determined to be low; when RI∈[r1, r2), the hazard level was determined to be medium; and when RI∈[r2, 1], the hazard level was determined to be high.

[0101] As a specific implementation of this application, method two is further defined based on the basic solution, including: Obtain the normalized quantitative values ​​of each stability influencing factor and each collapse hazard influencing factor; The information entropy and information utility value of each influencing factor are determined using the entropy method, and the weight of each factor is determined based on the information utility value. Determine the single-factor evaluation matrix based on the membership functions of each factor; Based on the single-factor evaluation matrix and the weights of each factor, a fuzzy comprehensive evaluation matrix is ​​obtained. The hazard level of the suspended goaf is determined based on the principle of maximum membership.

[0102] Specifically, as the number of cases assessing the hazard of goaf areas increases, a corresponding data model is constructed based on these cases as the foundation database and the hazard assessment factors for goaf areas as parameters. The models to be assessed are then categorized.

[0103] Based on data on the hazard levels and production practices of overhanging goaf areas in my country, this study statistically analyzes nine indicators: the probability of collapse (mining depth to thickness ratio, area extraction rate, coal pillar width to height ratio, coal pillar stability safety factor, roof hardness), the presence or absence of surface buildings and their protection level, the impact on underground production systems and personnel, the magnitude of potential mine tremors caused by collapse, and the degree of threat posed by collapse to the mine and surrounding areas. These indicators are combined with the probability and hazard indicators of overhanging goaf areas and the disaster risk indexes of overhanging goaf areas at three levels: high, medium, and low.

[0104] Analysis of the evaluation index values ​​in the constructed database shows that the index values ​​exhibit a normal distribution centered on the average value across different risk levels. Therefore, the membership function is constructed based on this normal distribution, and its expression is: ; in, The single-factor index value of the object to be evaluated. This represents the sample average value of this indicator under this risk level. This represents the standard deviation of the index under this hazard level. By calculating the mean and variance of the sample data for each evaluation index belonging to different hazard index levels of overhanging goaf areas, the membership function of each evaluation index belonging to different hazard index levels of overhanging goaf areas can be obtained.

[0105] By substituting the index values ​​of each hazard index level for different overhanging goaf areas into the corresponding membership functions, a single-factor evaluation matrix can be obtained. Then, the membership degrees are normalized according to the normalization formula to obtain the membership degree normalization matrix.

[0106] Based on the principle of entropy weight determination, the information entropy, information utility value, and weight values ​​of each indicator of the collapse probability and hazard index of the suspended goaf are calculated.

[0107] The entropy-weighted fuzzy comprehensive evaluation model is a quantitative method that uses the entropy value method to determine the weight of evaluation factors, combines single-factor and multi-factor comprehensive evaluation methods, determines the degree of membership of the suspended goaf area to be evaluated to the target evaluation set, and finally determines the risk of the suspended goaf area.

[0108] In the quantitative assessment of the hazard of overhanging goaf areas, stability indicators and hazard discrimination indicators of overhanging goaf areas are used as a factor set. ,in, Single-factor indicators for judging the stability and hazard of overhanging goaf areas; the target overhanging goaf area hazard assessment object is used as the evaluation set. ,in, This involves assessing the hazard of a specific overhanging goaf. Based on the factor set and evaluation set, the degree of membership of the hazard of the overhanging goaf to the individual factors of the stability and hazard discrimination indicators is determined, forming a single-factor evaluation matrix. The single-factor evaluation matrix, in turn, constitutes the multi-factor evaluation matrix for assessing the risk of the suspended goaf area. .Right now:

[0109] Meanwhile, the entropy method determines the weights of the stability and hazard discrimination indicators for each suspended goaf area. In fuzzy comprehensive discrimination, information entropy is used to evaluate the degree of orderliness and utility value of information; the higher the information entropy, the lower the utility value of the information, and vice versa. Given nine stability and hazard discrimination indicators for suspended goaf areas with m samples, the following can be obtained: Information entropy value of the indicator : ; Where k is the adjustment coefficient. m is the total number of known historical cases (samples); i is the sample number index, representing the i-th known sample in the database; Let be the normalized feature value of the j-th indicator in the i-th sample.

[0110] The information utility value of the stability and hazard discrimination index for overhanging goaf areas depends on the information entropy of the index. The difference from 1 : ; The weights of the stability and hazard discrimination indicators for overhanging goafs in the evaluation results are represented by the information utility value coefficients of these indicators. The higher the value coefficient of a certain overhanging goaf stability and hazard discrimination indicator, the greater its role in identifying the stability of the target overhanging goaf. Therefore, the weight of the j-th indicator is: ; Weighting factors for each indicator Once determined, a weight set W is formed. This is the single-factor evaluation matrix for the stability and hazard assessment indicators of the suspended goaf area. When the weight matrix W of each indicator is known, the fuzzy comprehensive evaluation matrix for determining the stability of the unsupported goaf area is obtained through fuzzy multiplication. ,Right now:

[0111] Determine the evaluation criteria Then, based on the principle of maximum membership, This is the final judgment result.

[0112] After determining the weights and membership functions of the collapse probability and hazard indicators for the suspended goaf, a comprehensive judgment is made on the suspended goaf to be assessed based on the collapse probability and hazard indicator values. Finally, the hazard level of the evaluation unit or sample is determined according to the principle of maximum membership.

[0113] This implementation method calculates objective weights using the entropy method, avoiding biases caused by subjective weighting. It also combines fuzzy membership functions to handle uncertainties and ambiguities in goaf hazard classification, resulting in assessment results that are more in line with actual working conditions. It can stably output objective and accurate hazard classification results in scenarios with a certain amount of sample data accumulation.

[0114] As a specific implementation of this application, based on the basic scheme, method three is further defined to include: Establish a sample database of overhanging goaf areas with known hazard levels, and normalize the data of stability influencing factors and collapse hazard influencing factors for each sample. Using normalized data as input and known risk levels as output, a support vector machine classification model is trained. Input the stability influencing factors and collapse hazard influencing factors of the suspended goaf to be evaluated into the trained support vector machine classification model, and output the hazard level of the suspended goaf.

[0115] Specifically, the first step is to establish a sample database of overhanging goaf areas with known hazard levels and complete data normalization. Multiple engineering cases of room-and-pillar overhanging goaf areas with completed hazard assessments and clearly defined hazard levels are collected and organized to construct a sample database. Each sample contains complete measured or calculated data on all stability influencing factors and collapse hazard influencing factors, and is labeled with the corresponding hazard level as a classification label. A unified normalization process is performed on the data of all influencing factors in all samples to eliminate differences in dimensions, numerical ranges, and positive / negative correlations between different indicators, ensuring that all input features are within a unified numerical range and guaranteeing data consistency for model training.

[0116] Support Vector Machine (SVM) was first proposed by Vapnik. The main idea of ​​SVM is to non-linearly map the input vector to a classification hyperplane, maximizing the classification margin, as shown in Figure 5. Figure 5 As can be seen, the rhombus and the circle represent two classes of samples, H is the dividing line, and H1 and H2 are the lines connecting the samples in each group that are closest to the dividing line and are parallel to the dividing line. The distance between the two groups of samples is called the classification margin. The purpose of SVM is to ensure that the classification margin between the two groups of samples is maximized.

[0117] For a linearly separable problem, given the training sample set: ,in , Given i = 1, 2, ..., m, find the optimal hyperplane (ω·x) + b = 0, ensuring that both sets of data satisfy this condition. Where i = 1, 2, ..., m. Simultaneously satisfying the condition of maximizing the classification margin, that is, obtaining... Maximum, equivalent to Minimum. That is, solve. Its constraints are: . Using the Lagrangian function, the linearly separable optimization problem is transformed into a dual objective function: ; Its constraints are: .

[0118] The optimal solution is obtained by solving the quadratic function under the inequality constraints. And only a portion ≠0. The optimal classification function obtained after solving the above problem is: .

[0119] When the training set is linearly inseparable, a nonlinear mapping function is used to transform the training set samples in the input space. Mapping to a high-dimensional feature space G, and constructing an optimal hyperplane in G. The training algorithm uses the inner product of the feature vectors. When introducing a kernel function that satisfies the Mercer condition, ensure the existence of the kernel function. To achieve linear classification of nonlinear changes, a radial basis function kernel is used, and the dual problem then becomes: ; Its constraints are: .

[0120] Find the optimal solution to this problem. , and then calculate The classification decision function is .

[0121] A support vector machine model is trained using a database of risks assessments for overhanging goaf areas. The trained overhanging goaf risk assessment model is then used in conjunction with case studies of overhanging goaf risks to be assessed to evaluate the risk of overhanging goaf hazards in pillar-type goaf areas.

[0122] This implementation method utilizes support vector machines to uncover the nonlinear relationships between multi-dimensional influencing factors and risk levels. It eliminates the need for manually setting indicator weights and classification thresholds, effectively reducing the interference of subjective experience in the assessment results. In scenarios with sufficient sample data, the assessment accuracy and execution efficiency are higher, supporting rapid classification of batches of goaf areas and adapting to the engineering needs of risk assessment in large-scale mining areas and old goaf areas.

[0123] As a specific implementation of this application, after further defining and determining the hazard level of the suspended goaf area based on the basic scheme, it also includes: When the risk level is high, disaster prevention and control shall be carried out by means of "partial or comprehensive treatment, isolation of goaf areas and monitoring and early warning". When the risk level is low or medium, disaster prevention is carried out by means of "partial treatment or temporary non-treatment, isolation of goaf areas and monitoring and early warning".

[0124] Specifically, after determining the hazard level of the overhanging goaf, differentiated disaster prevention and control strategies are matched with the grading results, and graded measures are implemented according to the risk level to ensure the pertinence and economy of goaf disaster prevention and control.

[0125] When the risk level of the suspended goaf is high, disaster prevention and control are carried out by combining "local or comprehensive treatment, goaf isolation, and monitoring and early warning". For the disaster risks such as coal pillar instability and large-scale roof collapse in high-risk goaf areas, local key section treatment or systematic treatment of the entire area can be selected according to the actual geological and mining conditions to eliminate or weaken the potential for collapse. At the same time, goaf isolation measures are used to block the transmission path of disaster energy and impact, reducing the scope of the disaster. A supporting monitoring and early warning system is deployed to monitor the movement of roof strata, the stress and deformation of coal pillars in real time, and to issue timely warnings for abnormal changes, ensuring the safety of personnel and facilities both above and below ground.

[0126] When the risk level of the suspended goaf is low or moderate, disaster prevention is carried out using the approach of "partial treatment or temporary non-treatment, goaf isolation and monitoring and early warning". For goafs where the overall risk is controllable, targeted treatment is implemented only as needed for sections with weak local stability, and large-scale treatment projects can be temporarily suspended for overall stable areas; goaf isolation and protection and routine monitoring and early warning are implemented simultaneously, and the dynamic changes in the stability of the goaf are continuously tracked. While preventing potential risks, disaster prevention and control investment is reasonably controlled.

[0127] Based on the risk classification results, corresponding prevention and control plans are matched. High-risk areas are mainly managed by proactive governance to strengthen risk control, while medium- and low-risk areas are mainly managed by monitoring and prevention while taking into account cost-effectiveness. This achieves graded and precise management of goaf disasters, which can effectively prevent and control the risk of major collapse disasters, and avoid the waste of resources caused by over-management, thus improving the scientific and economic nature of goaf disaster prevention and control.

[0128] Figure 2 This is a structural schematic diagram of a coal mine goaf hazard assessment device provided in an embodiment of this application, as shown below. Figure 2 As shown, it includes: The first acquisition module 201 is configured to acquire stability influencing factors data of the suspended goaf area. The stability influencing factors include mining depth to thickness ratio, area extraction rate, key roof layer conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor. The first determining module 202 is configured to determine the collapse probability level of the suspended goaf area based on stability influencing factor data; The second acquisition module 203 is configured to acquire data on the impact factors of collapse hazards in the suspended goaf area. The impact factors of collapse hazards include surface buildings and their protection levels, the impact on the mine production system and underground personnel, the level of mine tremors that may be formed by the collapse, and the degree of threat of the collapse to the surrounding area of ​​the mine. The second determining module 204 is configured to determine the collapse hazard level of the suspended goaf area based on the collapse hazard influencing factor data; The third determination module 205 is configured to determine the hazard level of the suspended goaf area according to the collapse probability level and collapse hazard level, and in accordance with the preset hazard judgment rules.

[0129] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0130] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0131] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0132] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 302 or a computer program loaded from storage unit 308 into RAM (Random Access Memory) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O (Input / Output) interface 305 is also connected to the bus 304.

[0133] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0134] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the method for assessing the risk of coal mine goaf. For example, in some embodiments, the method for assessing the risk of coal mine goaf can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by computing unit 301, one or more steps of the method described above can be performed. Alternatively, in other embodiments, computing unit 301 can be configured to perform the aforementioned coal mine goaf hazard assessment method by any other suitable means (e.g., by means of firmware).

[0135] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0137] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0139] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0140] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0141] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0142] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0143] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0144] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0145] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for assessing the hazard of coal mine goaf areas with suspended roofs, characterized in that, include: Data on stability influencing factors of the suspended goaf area are obtained. These stability influencing factors include mining depth to thickness ratio, area extraction rate, key roof layer conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor. Based on the stability influencing factors data, the collapse probability level of the overhanging goaf area is determined; Data on the factors influencing the risk of collapse in the suspended goaf area are obtained. These factors include surface buildings and structures and their protection levels, the impact on the mine production system and underground personnel, the magnitude of the mine earthquake that may be caused by the collapse, and the degree of threat posed by the collapse to the surrounding area of ​​the mine. Based on the data on factors influencing the collapse hazards, the collapse hazard level of the overhanging goaf is determined; Based on the collapse probability level and the collapse hazard level, the hazard level of the suspended goaf is determined according to the preset hazard determination rules.

2. The method for assessing the risk of coal mine goaf areas according to claim 1, characterized in that, The determination of the collapse probability level of the suspended goaf area based on the stability influencing factor data includes: The mining depth-to-thickness ratio, area extraction rate, key roof layer conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor are compared with preset grading thresholds for each factor to determine the stability level corresponding to each factor. Based on the stability levels of each factor and referring to a preset stability grading mapping table, the collapse probability level of the suspended goaf area is determined.

3. The method for assessing the risk of coal mine goaf areas according to claim 2, characterized in that, The stability level classification criteria for each of the aforementioned stability influencing factors are as follows: A mining depth-to-thickness ratio greater than 60 corresponds to high stability, a ratio between 30 and 60 corresponds to medium stability, and a ratio less than 30 corresponds to low stability. The area recovery rate is less than 40% and corresponds to high stability, between 40% and 60% and corresponds to medium stability, and greater than 60% and corresponds to low stability. The key conditions for the top plate are: high stability when there are continuous thick layers of hard rock with a thickness of not less than 15m; medium stability when there are continuous hard rock layers with a thickness of 5m to 15m; and low stability when there are no hard rock layers or when there are thin layers of alternating soft and hard rocks. A coal pillar width-to-height ratio greater than 3.5 corresponds to high stability, a ratio between 2 and 3.5 corresponds to medium stability, and a ratio less than 2 corresponds to low stability. A coal pillar stability safety factor greater than 2 corresponds to high stability, between 1.2 and 2 corresponds to medium stability, and less than 1.2 corresponds to low stability.

4. The method for assessing the risk of coal mine goaf areas according to claim 1, characterized in that, The determination of the collapse hazard level of the suspended goaf area based on the collapse hazard influencing factor data includes: The protection level of the ground buildings and structures, the impact level on the mine production system and underground personnel, the mine earthquake level that the collapse may cause, and the threat level of the collapse to the surrounding area of ​​the mine are obtained respectively. Based on the above levels and referring to the preset hazard classification mapping table, the collapse hazard level of the suspended goaf area is determined.

5. The method for assessing the risk of coal mine goaf areas according to claim 1, characterized in that, The step of determining the hazard level of the suspended goaf area according to the collapse probability level and the collapse hazard level, and in accordance with preset hazard assessment rules, includes: The hazard level is determined using any one of the following three classification methods: Method 1: Determine the weights of each stability influencing factor and each collapse hazard influencing factor using the analytic hierarchy process (AHP). Calculate the hazard index based on the normalized quantified value of each factor and its corresponding weight. Determine the hazard level based on the hazard index. Method 2: Determine the weights of each stability influencing factor and each collapse hazard influencing factor using the entropy method, perform fuzzy comprehensive evaluation based on the membership function of each factor, and determine the hazard level based on the principle of maximum membership degree; Method 3: Establish a sample database of overhanging goaf areas with known hazard levels. Use the data of each stability influencing factor and each collapse hazard influencing factor as input to train a support vector machine classification model. Input the data to be evaluated into the trained support vector machine classification model and output the hazard level.

6. The method for assessing the risk of coal mine goaf areas according to claim 5, characterized in that, The first method includes: A hierarchical model is constructed, with the danger of the suspended goaf area set as the target layer, the stability and collapse hazards of the suspended goaf area set as the criteria layer, and the stability influencing factors and collapse hazard influencing factors set as the scheme layer. Construct the judgment matrix for each layer of factors; Calculate the eigenvector corresponding to the largest eigenvalue of the judgment matrix, and perform hierarchical single sorting and consistency check on each factor; Calculate the total hierarchical ranking weight of each factor in the scheme layer to the target layer; The risk index is calculated based on the normalized quantitative value of each factor and the corresponding hierarchical total ranking weight. The hazard level of the suspended goaf area is determined based on the aforementioned hazard index.

7. The method for assessing the risk of coal mine goaf areas according to claim 5, characterized in that, The second method includes: Obtain the normalized quantitative values ​​of each of the stability influencing factors and each of the collapse hazard influencing factors; The information entropy and information utility value of each influencing factor are determined using the entropy method, and the weight of each factor is determined based on the information utility value. Determine the single-factor evaluation matrix based on the membership functions of each factor; Based on the single-factor evaluation matrix and the weights of each factor, a fuzzy comprehensive evaluation matrix is ​​obtained. The hazard level of the suspended goaf is determined based on the principle of maximum membership.

8. The method for assessing the risk of coal mine goaf areas according to claim 5, characterized in that, The third method specifically includes: Establish a sample database of overhanging goaf areas with known hazard levels, and normalize the data of stability influencing factors and collapse hazard influencing factors for each sample. Using normalized data as input and known risk levels as output, a support vector machine classification model is trained. Input the stability influencing factors and collapse hazard influencing factors data of the suspended goaf to be evaluated into the trained support vector machine classification model, and output the hazard level of the suspended goaf.

9. The method for assessing the risk of coal mine goaf areas according to claim 1, characterized in that, After determining the hazard level of the suspended goaf area, the following is also included: When the risk level is high, disaster prevention and control shall be carried out by means of "partial or comprehensive treatment, goaf isolation and monitoring and early warning". When the risk level is low or medium, disaster prevention is carried out by means of "partial treatment or temporary non-treatment, isolation of goaf areas and monitoring and early warning".

10. A device for assessing the risk of coal mine goaf areas with suspended roofs, characterized in that, include: The first acquisition module is configured to acquire stability influencing factors data of the suspended goaf area, including the mining depth-to-thickness ratio, area extraction rate, key roof layer conditions, coal pillar width-to-height ratio, and coal pillar stability safety factor. The first determining module is configured to determine the collapse probability level of the suspended goaf area based on the stability influencing factor data. The second acquisition module is configured to acquire data on the impact factors of collapse hazards in the suspended goaf area. The impact factors of collapse hazards include ground buildings and structures and their protection levels, the impact on the mine production system and underground personnel, the level of mine tremors that may be formed by the collapse, and the degree of threat of the collapse to the surrounding area of ​​the mine. The second determining module is configured to determine the collapse hazard level of the suspended goaf area based on the collapse hazard influencing factor data; The third determining module is configured to determine the hazard level of the suspended goaf area according to the collapse probability level and the collapse hazard level, and in accordance with preset hazard judgment rules.

Images