A gas power disaster multi-source monitoring hierarchical early warning method and system

Abstract

The application discloses a gas power disaster multi-source monitoring grading early warning method and system, relates to the coal mine gas power disaster early warning field, and comprises the following steps: acquiring gas power disaster multi-source monitoring data; performing normalization processing on the gas power disaster multi-source monitoring data to obtain normalized monitoring data, and respectively calculating the comprehensive weights of each early warning index by using a combination weighting method; calculating a total gas power disaster danger coefficient according to the normalized monitoring data and the comprehensive weights of the early warning indexes; and grading and grading early warning the gas power disaster danger according to the total gas power disaster danger coefficient. The application can improve the accuracy and reliability of gas power disaster danger prediction in the coal mining process.

Description

Technical Field

[0001] This application relates to the field of early warning of coal mine gas dynamic disasters, and in particular to a multi-source monitoring and hierarchical early warning method and system for gas dynamic disasters. Background Technology

[0002] Early warning of gas dynamic disaster hazards is a crucial link in the prevention and control of gas dynamic disasters. However, existing early warning methods mostly rely on single monitoring systems such as microseismic monitoring or stress monitoring, failing to consider the dynamic deformation patterns of the roadway roof and the pressure-bearing state of the support. These patterns, in turn, reflect the stress distribution and evolution characteristics of the coal seam, indirectly reflecting the gas migration patterns. Therefore, existing early warning methods suffer from low reliability and accuracy due to the lack of monitoring dimensions. Consequently, providing a comprehensive early warning method and system for gas dynamic disaster hazards that integrates microseismic monitoring, stress monitoring, and roof monitoring to improve the accuracy and reliability of gas dynamic disaster hazard prediction during coal mining has become a pressing technical problem in this field. Summary of the Invention

[0003] The purpose of this application is to provide a multi-source monitoring and hierarchical early warning method and system for gas dynamic disasters, which can improve the accuracy and reliability of gas dynamic disaster risk prediction during coal mining.

[0004] To achieve the above objectives, this application provides the following solution.

[0005] Firstly, this application provides a multi-source monitoring and graded early warning method for gas dynamic disasters, comprising the following steps.

[0006] Acquire multi-source monitoring data of gas dynamic disasters; the multi-source monitoring data of gas dynamic disasters includes monitoring data of multiple early warning indicators, including monitoring data of microseismic early warning indicators, stress early warning indicators and roof early warning indicators; the early warning indicators include microseismic early warning indicators, stress early warning indicators and roof early warning indicators.

[0007] The multi-source monitoring data of gas dynamic disasters were normalized to obtain normalized monitoring data, and the comprehensive weight of each early warning indicator was calculated by the combined weighting method.

[0008] The total gas dynamic disaster risk coefficient is calculated based on the normalized monitoring data and the comprehensive weight of each early warning indicator.

[0009] Based on the total gas dynamic hazard risk coefficient, the gas dynamic hazard risk is classified and graded for early warning.

[0010] Secondly, this application provides a multi-source monitoring and hierarchical early warning system for gas dynamic disasters. The multi-source monitoring and hierarchical early warning system for gas dynamic disasters is used to implement the multi-source monitoring and hierarchical early warning method for gas dynamic disasters described in the first aspect. The multi-source monitoring and hierarchical early warning system for gas dynamic disasters includes the following modules.

[0011] The data acquisition module is used to acquire multi-source monitoring data of gas dynamic disasters; the multi-source monitoring data of gas dynamic disasters includes monitoring data of multiple early warning indicators, including monitoring data of microseismic early warning indicators, stress early warning indicators, and roof early warning indicators; the early warning indicators include microseismic early warning indicators, stress early warning indicators, and roof early warning indicators.

[0012] The data processing module is used to normalize the multi-source monitoring data of gas dynamic disasters to obtain normalized monitoring data, and to calculate the comprehensive weight of each early warning indicator using a combined weighting method.

[0013] The data calculation module is used to calculate the total gas dynamic disaster risk coefficient based on the normalized monitoring data and the comprehensive weight of each early warning indicator.

[0014] The hazard level classification and early warning module is used to classify and classify the hazard of gas dynamic disasters according to the total gas dynamic disaster hazard coefficient.

[0015] According to the specific embodiments provided in this application, this application has the following technical effects.

[0016] This application provides a multi-source monitoring and hierarchical early warning method and system for gas dynamic disasters. By comprehensively conducting microseismic monitoring, stress monitoring, and roof monitoring of coal and rock strata in the intake and return airways during the mining process of a coal mine longwall face, synchronous monitoring of microseismic activity, stress, and roof conditions is achieved. The total gas dynamic disaster hazard coefficient is calculated using the collected multi-source monitoring data, solving the problems of delayed response, low reliability, and poor accuracy of early warning results from single monitoring dimensions. This enables real-time early warning of gas dynamic disasters and improves the accuracy and reliability of gas dynamic disaster hazard prediction during coal mining. By calculating the comprehensive weight of each early warning indicator and classifying and grading the early warning according to the total gas dynamic disaster hazard coefficient, the problem of unreasonable weight allocation of multi-source monitoring data is solved, achieving accurate hierarchical early warning of gas dynamic disasters. Furthermore, by calculating the comprehensive weight of each early warning indicator using a combined weighting method, the problems of difficulty in verifying and reproducing subjective weighting and poor method adaptability are solved, achieving objectivity in weight allocation and universality of the method. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the 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.

[0018] Figure 1 This is an application environment diagram of a multi-source monitoring and hierarchical early warning method for gas dynamic disasters in one embodiment of this application.

[0019] Figure 2 This is a flowchart illustrating a multi-source monitoring and graded early warning method for gas dynamic disasters, provided as an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of the planar arrangement of a microseismic sensor provided in an embodiment of this application.

[0021] Figure 4 This is a schematic diagram of the horizontal cross-sectional arrangement of a stress sensor provided in an embodiment of this application.

[0022] Figure 5 This is a schematic diagram of the arrangement of top plate delamination sensors according to an embodiment of this application.

[0023] Figure 6 for Figure 2 The flowchart below shows the detailed steps of calculating the comprehensive weight of each early warning indicator using the combined weighting method.

[0024] Figure 7 This is a schematic diagram of the process for determining the optimal value of the combination coefficients according to an embodiment of this application.

[0025] Figure 8 for Figure 2 A detailed flowchart of the steps for calculating the total gas dynamic hazard risk coefficient. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] The purpose of this invention is to provide a multi-source monitoring and hierarchical early warning method and system for gas dynamic disasters. It acquires early warning indicator data through the synergistic effect of three monitoring systems: microseismic, stress, and roof monitoring. Combined with weighted and quantitative calculations, it classifies the hazard levels of gas dynamic disasters, thereby improving the accuracy and reliability of gas dynamic disaster hazard prediction during coal mining.

[0028] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] The multi-source monitoring and hierarchical early warning method for gas dynamic disasters provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send acquired multi-source monitoring data of gas dynamic disasters to server 104. Server 104 receives the multi-source monitoring data of gas dynamic disasters, normalizes it to obtain normalized monitoring data, and calculates the comprehensive weight of each early warning indicator using a combined weighting method. Based on the normalized monitoring data and the comprehensive weight of each early warning indicator, the total gas dynamic disaster hazard coefficient is calculated. Based on the total gas dynamic disaster hazard coefficient, the gas dynamic disaster hazard is classified and graded for early warning. Server 104 can feed back the obtained results of the gas dynamic disaster hazard classification and graded early warning to terminal 102. In addition, in some embodiments, the multi-source monitoring and graded early warning method for gas dynamic disasters can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can directly classify the gas dynamic disaster hazard level and perform graded early warning processing on the acquired multi-source monitoring data of gas dynamic disasters. Alternatively, the server 104 can obtain the multi-source monitoring data of gas dynamic disasters from the data storage system and perform graded early warning processing on the acquired multi-source monitoring data of gas dynamic disasters.

[0030] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, and downhole monitoring equipment. The downhole monitoring equipment can be microseismic sensors, stress sensors, roof delamination sensors, monitoring master stations, etc. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0031] In one exemplary embodiment, such as Figure 2As shown, a multi-source monitoring and hierarchical early warning method for gas dynamic disasters is provided, including the following steps 201 to 204.

[0032] Step 201: Obtain multi-source monitoring data of gas dynamic disasters; the multi-source monitoring data of gas dynamic disasters includes monitoring data of multiple early warning indicators, including monitoring data of microseismic early warning indicators, stress early warning indicators and roof early warning indicators; the early warning indicators include microseismic early warning indicators, stress early warning indicators and roof early warning indicators.

[0033] Step 202: Normalize the multi-source monitoring data of gas dynamic disasters to obtain normalized monitoring data, and use the combined weighting method to calculate the comprehensive weight of each early warning indicator.

[0034] Step 203: Calculate the total gas dynamic disaster risk coefficient based on the normalized monitoring data and the comprehensive weight of each early warning indicator.

[0035] Step 204: Based on the total gas dynamic disaster risk coefficient, classify and classify the gas dynamic disaster risk level and issue early warnings.

[0036] In one exemplary embodiment of this application, the multi-source monitoring data of gas dynamic disasters is obtained by microseismic sensors, stress sensors, and roof delamination sensors. Figure 3 The diagram shows the planar arrangement of the microseismic sensors. Figure 4 The diagram shows a horizontal cross-sectional arrangement of the stress sensors. Figure 5 The schematic diagram of the roof delamination sensor arrangement shows the positional arrangement of the micro-vibration sensor, stress sensor, and roof sensor.

[0037] The microseismic sensors are arranged in an encircling manner, with a spacing of 100m between two adjacent microseismic sensors.

[0038] The stress sensors are arranged in a stress sensor monitoring group. Each stress sensor monitoring group includes shallow monitoring points and deep monitoring points. The shallow monitoring points have a depth of 2h, and the deep monitoring points have a depth of 4h, where h is the height of the roadway in the monitoring area. The distance between two adjacent monitoring points within the same stress sensor monitoring group is 2m along the roadway direction. Adjacent stress sensor monitoring groups (e.g., ...) Figure 4 Monitoring groups A and B are spaced 30m apart along the direction of the roadway.

[0039] The roof delamination sensor is fixed to the roof of the roadway and adopts a dual-base point monitoring method based on shallow and deep base points. The shallow base point is fixed at the end of the anchor bolt, and the deep base point is fixed at 0.5m inside the stable rock layer above the anchor bolt. The distance between two adjacent roof delamination sensors is 25m or 50m.

[0040] It should be noted that the microseismic sensors are arranged in an encircling pattern, forming a spatial monitoring network that covers the entire monitoring area, with a spacing of 100m between adjacent microseismic sensors. A communication cable connects adjacent microseismic sensors, enabling the connection between the microseismic monitoring system and the main monitoring station.

[0041] The specific spacing between two adjacent roof separation sensors is as follows: within the first 100m, the spacing between two adjacent roof separation sensors is 25m; beyond 100m, the spacing between two adjacent roof separation sensors is 50m. The data acquisition unit is connected to the sensor (i.e., the roof separation sensor) via a signal line.

[0042] The monitoring master station is connected to the monitoring system. The monitoring master station includes a microseismic monitoring master station, a stress monitoring master station, and a roof monitoring master station; the monitoring system includes a microseismic monitoring system, a stress monitoring system, and a roof monitoring system. The microseismic monitoring system consists of multiple microseismic sensors; the stress monitoring system consists of multiple stress sensors; and the roof monitoring system consists of multiple roof delamination sensors.

[0043] The monitoring master stations are all located in underground chambers with stable power supply and convenient access to the ring network, while maintaining dryness and ventilation, and avoiding contact with high-power equipment.

[0044] In one exemplary embodiment of this application, the microseismic early warning index monitoring data includes daily cumulative energy of microseismic events, daily total frequency, and density of high-energy events.

[0045] The stress early warning indicator monitoring data includes the peak stress of shallow holes, the peak stress of deep holes, and the stress increase.

[0046] The monitoring data for roof early warning indicators include roof fracture degree, roof delamination rate, and the over-limit ratio of support load. Monitoring data for each early warning indicator under the influence of mining activities are collected.

[0047] It should be noted that, in an exemplary embodiment of this application, the multi-source monitoring data of the gas dynamic disaster is normalized, and the normalization calculation formula for the normalized monitoring data is as follows.

[0048] The normalization calculation formula for multi-source monitoring data of positive gas dynamic disasters is shown below.

[0049] (1).

[0050] The normalization calculation formula for multi-source monitoring data of negative gas dynamic disasters is shown below.

[0051] (2).

[0052] in, g i For the first i Normalized data of monitoring data for each early warning indicator; x i This refers to the monitoring data for the i-th early warning indicator; x max For the first i The highest monitoring data among the early warning indicators; x min For the first i The smallest monitoring data among the early warning indicators.

[0053] In another exemplary embodiment of this application, such as Figure 6 As shown, the step 202 above, which uses the combined weighting method to calculate the comprehensive weight of each early warning indicator, can be replaced by the following steps 601 to 602.

[0054] Step 601: The coefficient of variation method and the entropy weight method are used to calculate the weight of each early warning indicator using the coefficient of variation method and the entropy weight method, respectively.

[0055] Step 602: Based on the coefficient of variation method weight and the entropy weight method weight of each early warning indicator, the comprehensive weight of each early warning indicator is calculated using a linear weighting method.

[0056] In another exemplary embodiment of this application, the formula for calculating the comprehensive weight of each early warning indicator is as follows.

[0057] (3).

[0058] in, w i For the first i The comprehensive weight of each early warning indicator; A i Weights are calculated using the coefficient of variation method. B i The weights are determined by the entropy weighting method. α These are combination coefficients, with values ​​ranging from 0 to 1. α ≤1.

[0059] In another exemplary embodiment of this application, in order to calculate the comprehensive weight of each early warning indicator, it is necessary to determine the optimal value of the combination coefficient in advance, such as... Figure 7As shown, before step 601 above, there is also a step to determine the optimal value of the combination coefficients, specifically including the following steps 701 to 703.

[0060] Step 701: Collect monitoring data of historical disaster samples from the target mine, as well as parameters of coal seam occurrence characteristics and historical disaster data volume.

[0061] Step 702: Determine the initial combination coefficients based on the coal seam occurrence characteristics and historical disaster data parameters.

[0062] Step 703: Based on the monitoring data of the historical disaster samples of the mine, calibrate the initial combination coefficients and determine the optimal value of the combination coefficients.

[0063] In another exemplary embodiment of this application, such as Figure 8 As shown, step 203 above can be replaced by steps 801 to 802.

[0064] Step 801: Calculate the gas dynamic disaster risk coefficient for each monitoring system based on the normalized monitoring data and the comprehensive weight of each early warning indicator; the monitoring system includes a microseismic monitoring system, a stress monitoring system, and a roof monitoring system.

[0065] Step 802: Calculate the total gas dynamic disaster risk coefficient based on the gas dynamic disaster risk coefficient, the normalized monitoring data, and the comprehensive weight of each early warning indicator.

[0066] In another exemplary embodiment of this application, the formula for calculating the gas dynamic disaster hazard coefficient of each monitoring system is as follows.

[0067] (4).

[0068] in, I n For the first n The gas dynamic hazard risk coefficient of each monitoring system; w i For the first i The comprehensive weight of each early warning indicator; g i For the first i Normalized data of monitoring data for each early warning indicator; h For the first n The number of early warning indicators for each monitoring system.

[0069] It should be noted that the independent alarm threshold for a single monitoring system is set as follows: when the gas dynamic disaster hazard coefficient of any monitoring system... I nWhen the value is ≥0.8, a single-system alarm of the monitoring system is triggered.

[0070] The formula for calculating the total gas dynamic hazard risk coefficient is shown below.

[0071] (5).

[0072] in, I The total gas dynamic hazard risk coefficient; m i The first among all early warning indicators i The comprehensive weight of each early warning indicator; n i The first among all early warning indicators i Normalized data of monitoring data for each early warning indicator; j This represents the total number of all early warning indicators.

[0073] In another exemplary embodiment of this application, the risk level of the gas-powered disaster includes high risk, medium risk, low risk, and no risk. Specific methods for classifying these levels include the following.

[0074] When 0.8≤ I When the value is ≤1, the gas dynamic disaster risk is classified as high risk.

[0075] When 0.5≤ I When the value is less than 0.8, the gas dynamic hazard risk is classified as medium risk.

[0076] When 0.2≤ I When the value is less than 0.5, the gas dynamic hazard risk is classified as weak risk.

[0077] When 0 < I When the value is less than 0.2, the gas dynamic hazard risk is determined to be no risk.

[0078] in, I The total gas dynamic hazard risk coefficient.

[0079] In another exemplary embodiment of this application, the risk of gas dynamic disasters is classified and warned according to the total gas dynamic disaster risk coefficient.

[0080] When the gas-powered disaster risk is determined to be high, medium, or low, the audible and visual warning system will issue an audible and visual warning; when the gas-powered disaster risk is determined to be no risk, the audible and visual warning system will not issue an audible and visual warning.

[0081] This application provides a multi-source monitoring and graded early warning method for gas dynamic disasters. The method first conducts joint monitoring of three systems—micro-seismic, stress, and roof—at the mine's longwall face to determine early warning indicators for the three systems. The monitoring data is then normalized. Subsequently, a combined weighting method, coupling the coefficient of variation method and the entropy weight method, is used to calculate the comprehensive weight of each early warning indicator. This allows for the calculation of the gas dynamic disaster hazard coefficient for each monitoring system, forming a single-system early warning model. Further, the total gas dynamic disaster hazard coefficient is calculated based on the normalized data, and the model is graded and graded for early warning. Finally, a multi-source monitoring and graded early warning method for gas dynamic disasters is established, forming a dual-response early warning model combining single and multi-system approaches, enabling accurate prediction of gas dynamic disaster hazards. This application achieves mutual verification of different early warning indicators through the coordinated monitoring of three systems. Furthermore, the combined weighting method can be adapted to different mine geological conditions, improving the accuracy and reliability of gas dynamic disaster hazard early warning.

[0082] Based on the same inventive concept, this application also provides an embodiment for implementing the aforementioned multi-source monitoring and hierarchical early warning system for gas dynamic disasters. The solution provided by this system is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the multi-source monitoring and hierarchical early warning system for gas dynamic disasters provided below can be found in the limitations of the multi-source monitoring and hierarchical early warning method for gas dynamic disasters described above, and will not be repeated here.

[0083] In one exemplary embodiment, a multi-source monitoring and hierarchical early warning system for gas dynamic disasters is provided, comprising: a data acquisition module, a data processing module, a data calculation module, and a hazard level classification and early warning module.

[0084] The data acquisition module is used to acquire multi-source monitoring data of gas dynamic disasters; the multi-source monitoring data of gas dynamic disasters includes monitoring data of multiple early warning indicators, including monitoring data of microseismic early warning indicators, stress early warning indicators, and roof early warning indicators; the early warning indicators include microseismic early warning indicators, stress early warning indicators, and roof early warning indicators.

[0085] The data processing module is used to normalize the multi-source monitoring data of gas dynamic disasters to obtain normalized monitoring data, and to calculate the comprehensive weight of each early warning indicator using a combined weighting method.

[0086] The data calculation module is used to calculate the total gas dynamic disaster risk coefficient based on the normalized monitoring data and the comprehensive weight of each early warning indicator.

[0087] The hazard level classification and early warning module is used to classify and classify the hazard of gas dynamic disasters according to the total gas dynamic disaster hazard coefficient.

[0088] This application involves conducting microseismic monitoring, stress monitoring, and roof monitoring of the coal and rock strata in the intake and return airways during the mining process in a coal mine. Multi-source monitoring data from these systems are collected under the influence of mining activities. The comprehensive weight of each early warning indicator is calculated using this multi-source monitoring data. Simultaneously, the gas dynamic hazard risk coefficient of each monitoring system is determined, forming a single-system early warning model. The overall gas dynamic hazard risk coefficient is then calculated, and a gas dynamic hazard risk level classification is established to achieve graded early warning of gas dynamic hazards.

[0089] Compared with traditional gas dynamic disaster early warning methods, this application achieves mutual verification of different early warning indicators through the coordinated monitoring of three monitoring systems, effectively avoiding misjudgments or omissions caused by interference from single system equipment or local anomalies, and significantly improving the accuracy of gas dynamic disaster early warning. This application possesses both the immediacy of single-system early warning and the precision of multi-source hierarchical early warning, forming a dual-response early warning mode of single-system and multi-system, enhancing the sensitivity and accuracy of gas dynamic disaster early warning. This application employs a combined weighting method coupling the coefficient of variation method and the entropy weight method. Both methods calculate the weights of each early warning indicator based on the variation characteristics of multi-source monitoring data (the coefficient of variation method based on data dispersion, and the entropy weight method based on data information content). Then, a linear weighting method is used to calculate the comprehensive weight of each early warning indicator, avoiding the problems of difficulty in verifying and reproducing subjective weight allocation. Simultaneously, the initial combination coefficients are calibrated using monitoring data from historical disaster samples in the mine, enhancing the adaptability of this method to different mine geological conditions, and further improving the accuracy and reliability of gas dynamic disaster hazard prediction during coal mining.

[0090] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A multi-source monitoring and hierarchical early warning method for gas dynamic disasters, characterized in that, The multi-source monitoring and graded early warning method for gas dynamic disasters includes: Acquire multi-source monitoring data of gas dynamic disasters; the multi-source monitoring data of gas dynamic disasters includes monitoring data of multiple early warning indicators, including monitoring data of microseismic early warning indicators, stress early warning indicators and roof early warning indicators; the early warning indicators include microseismic early warning indicators, stress early warning indicators and roof early warning indicators; The multi-source monitoring data of gas dynamic disasters are normalized to obtain normalized monitoring data, and the comprehensive weight of each early warning indicator is calculated by the combined weighting method. The total gas dynamic disaster risk coefficient is calculated based on the normalized monitoring data and the comprehensive weight of each early warning indicator. Based on the total gas dynamic hazard risk coefficient, the gas dynamic hazard risk is classified and graded for early warning.

2. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 1, characterized in that, The multi-source monitoring data of gas dynamic disasters was collected by microseismic sensors, stress sensors and roof delamination sensors; The microseismic sensors are arranged in an encircling manner, with a spacing of 100m between two adjacent microseismic sensors; The stress sensors are arranged in the form of stress sensor monitoring groups. The monitoring points of the same stress sensor monitoring group include shallow monitoring points and deep monitoring points. The depth of the shallow monitoring points is 2h, and the depth of the deep monitoring points is 4h, where h is the height of the roadway in the monitoring area. The distance between two adjacent monitoring points in the same stress sensor monitoring group along the roadway direction is 2m, and the distance between two adjacent stress sensor monitoring groups along the roadway direction is 30m. The roof delamination sensor is fixed to the roof of the roadway and adopts a dual-base point monitoring method based on shallow and deep base points. The shallow base point is fixed at the end of the anchor bolt, and the deep base point is fixed at 0.5m inside the stable rock layer above the anchor bolt. The distance between two adjacent roof delamination sensors is 25m or 50m.

3. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 1, characterized in that, The monitoring data for the microseismic early warning indicators include the daily cumulative energy of microseismic events, the daily total frequency, and the density of high-energy events. The stress early warning index monitoring data includes the peak stress of shallow holes, the peak stress of deep holes, and the stress increase. The monitoring data for the early warning indicators of the roof include the roof fracture degree, the roof delamination rate, and the over-limit ratio of the support load.

4. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 1, characterized in that, The method of calculating the comprehensive weight of each early warning indicator using a combined weighting approach specifically includes: The coefficient of variation method and the entropy weight method are used to calculate the weights of each early warning indicator using the coefficient of variation method and the entropy weight method, respectively. Based on the coefficient of variation weight and the entropy weight weight of each early warning indicator, a linear weighting method is used to calculate the comprehensive weight of each early warning indicator.

5. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 4, characterized in that, The formula for calculating the comprehensive weight of each early warning indicator is as follows: ； in, w i For the first i The comprehensive weight of each early warning indicator; A i Weights are calculated using the coefficient of variation method. B i The weights are determined by the entropy weighting method. α These are combination coefficients, with values ​​ranging from 0 to 1. α ≤1.

6. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 5, characterized in that, Before the step of calculating the comprehensive weight of each early warning indicator using a linear weighting method based on the coefficient of variation method weight and the entropy weight method weight of each early warning indicator, the multi-source monitoring and hierarchical early warning method for gas dynamic disasters further includes: determining the optimal value of the combination coefficient; Determining the optimal values ​​of the combination coefficients specifically includes: Collect monitoring data of historical disaster samples from the target mine, as well as parameters related to coal seam occurrence characteristics and the amount of historical disaster data; The initial combination coefficients are determined based on the coal seam occurrence characteristics and historical disaster data parameters. Based on the monitoring data of the historical disaster samples of the mine, the initial combination coefficients are calibrated to determine the optimal value of the combination coefficients.

7. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 1, characterized in that, Based on the normalized monitoring data and the comprehensive weights of each early warning indicator, the total gas dynamic hazard risk coefficient is calculated, specifically including: Based on the normalized monitoring data and the comprehensive weight of each early warning indicator, the gas dynamic disaster risk coefficient of each monitoring system is calculated; the monitoring system includes a microseismic monitoring system, a stress monitoring system, and a roof monitoring system; The total gas dynamic disaster risk coefficient is calculated based on the gas dynamic disaster risk coefficient, the normalized monitoring data, and the comprehensive weight of each early warning indicator.

8. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 7, characterized in that, The formula for calculating the gas dynamic disaster risk coefficient of each monitoring system is as follows: ； in, I n For the first n The gas dynamic hazard risk coefficient of each monitoring system; w i For the first i The comprehensive weight of each early warning indicator; g i For the first i Normalized data of monitoring data for each early warning indicator; h For the first n The number of early warning indicators for each monitoring system; The formula for calculating the total gas dynamic hazard risk coefficient is as follows: ； in, I The total gas dynamic hazard risk coefficient; m i The first among all early warning indicators i The comprehensive weight of each early warning indicator; n i The first among all early warning indicators i Normalized data of monitoring data for each early warning indicator; j This represents the total number of all early warning indicators.

9. The multi-source monitoring and hierarchical early warning method for gas dynamic disasters according to claim 1, characterized in that, The risk levels of gas-powered disasters are classified as high risk, medium risk, low risk, and no risk. When 0.8≤ I When the value is ≤1, the gas dynamic hazard risk is classified as high risk; When 0.5≤ I When the value is less than 0.8, the gas dynamic hazard risk is classified as medium risk. When 0.2≤ I When the value is less than 0.5, the gas dynamic hazard risk is classified as weak risk. When 0 < I When the value is less than 0.2, the risk of gas-related disasters is determined to be no risk. in, I The total gas dynamic hazard risk coefficient.

10. A multi-source monitoring and hierarchical early warning system for gas dynamic disasters, characterized in that, The gas dynamic disaster multi-source monitoring and hierarchical early warning system is used to implement the gas dynamic disaster multi-source monitoring and hierarchical early warning method according to any one of claims 1-9, and the gas dynamic disaster multi-source monitoring and hierarchical early warning system includes: The data acquisition module is used to acquire multi-source monitoring data of gas dynamic disasters; the multi-source monitoring data of gas dynamic disasters includes monitoring data of multiple early warning indicators, including monitoring data of microseismic early warning indicators, stress early warning indicators, and roof early warning indicators; the early warning indicators include microseismic early warning indicators, stress early warning indicators, and roof early warning indicators. The data processing module is used to normalize the multi-source monitoring data of gas dynamic disasters to obtain normalized monitoring data, and to calculate the comprehensive weight of each early warning indicator by using a combined weighting method. The data calculation module is used to calculate the total gas dynamic disaster risk coefficient based on the normalized monitoring data and the comprehensive weight of each early warning indicator; The hazard level classification and early warning module is used to classify and classify the hazard of gas dynamic disasters according to the total gas dynamic disaster hazard coefficient.

Images