Mine safety monitoring method and system, electronic equipment and readable storage medium

Abstract

The invention provides a mine safety monitoring method and system, electronic equipment and a readable storage medium, and belongs to the technical field of mine monitoring, and the method comprises the steps: determining respective corresponding first spontaneous combustion probabilities based on first monitoring data corresponding to a plurality of grid regions in a mine goaf; screening out a grid region with a first spontaneous combustion probability greater than a first probability threshold value from the plurality of grid regions as a first monitoring region, and performing second spontaneous combustion probability calculation on the first monitoring region according to a first period; performing second spontaneous combustion probability calculation on the second monitoring area according to a second period to obtain a second spontaneous combustion probability corresponding to each grid area in the second monitoring area; the first period is shorter than the second period; and determining a risk area of the mine goaf based on the second spontaneous combustion probability corresponding to each grid area. According to the mine safety monitoring method and system, the electronic equipment and the readable storage medium provided by the invention, the response speed of risk monitoring can be improved.

Description

Technical Field

[0001] This application belongs to the field of mine monitoring technology, and more specifically, relates to a mine safety monitoring method and system, electronic equipment, and readable storage medium. Background Technology

[0002] During coal mining, coal left in the goaf undergoes oxidation under the influence of oxygen. If the accumulated heat cannot dissipate, it can lead to spontaneous combustion. By dynamically collecting and analyzing environmental parameters in the goaf using real-time monitoring technology, a multi-dimensional early warning system can be constructed to predict spontaneous combustion risks in advance. However, this system requires collecting a large number of environmental parameters and performing calculations based on models, which reduces the system's response speed. Summary of the Invention

[0003] The purpose of this application is to provide a mine safety monitoring method and system, electronic equipment, and readable storage medium to reduce the data computation burden and improve response speed.

[0004] A first aspect of this application provides a mine safety monitoring method, comprising: The first spontaneous combustion probability is determined based on the first monitoring data corresponding to multiple grid areas within the mine goaf; wherein, the multiple grid areas are obtained by dividing the mine goaf into grids. Grid regions with a first spontaneous combustion probability greater than a first probability threshold are selected from the plurality of grid regions and designated as the first monitoring region. A second spontaneous combustion probability calculation is performed on the first monitoring region according to a first cycle to obtain the second spontaneous combustion probability corresponding to each grid region in the first monitoring region. Similarly, a second spontaneous combustion probability calculation is performed on the second monitoring region according to a second cycle to obtain the second spontaneous combustion probability corresponding to each grid region in the second monitoring region. The second monitoring region is the grid region other than the first monitoring region among the plurality of grid regions, and the first cycle is shorter than the second cycle. The risk areas of the mine goaf are determined based on the second spontaneous combustion probability corresponding to each grid area. Specifically, for each of the monitoring areas, a second spontaneous combustion probability calculation is performed on the monitoring area, including: Based on the order of the first spontaneous combustion probability of each grid area in the monitoring area from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area; the second monitoring data contains more types of data than the first monitoring data. If the obtained second spontaneous combustion probability is less than or equal to the second probability threshold, then from the remaining grid areas of the monitoring area, in order of the first spontaneous combustion probability from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area, until all grid areas are traversed.

[0005] A second aspect of this application provides a mine safety monitoring system, comprising: The region division module is used to determine the first spontaneous combustion probability of each of the multiple grid regions within the mine goaf based on the first monitoring data; wherein, the multiple grid regions are obtained by dividing the mine goaf into grids; The region calculation module is used to select grid regions from the plurality of grid regions where the first spontaneous combustion probability is greater than a first probability threshold, as the first monitoring region; to perform a second spontaneous combustion probability calculation on the first monitoring region according to a first period, to obtain the second spontaneous combustion probability corresponding to each grid region in the first monitoring region; and to perform a second spontaneous combustion probability calculation on the second monitoring region according to a second period, to obtain the second spontaneous combustion probability corresponding to each grid region in the second monitoring region; the second monitoring region is the grid region other than the first monitoring region among the plurality of grid regions, and the first period is shorter than the second period; The result output module is used to determine the risk area of ​​the mine goaf based on the second spontaneous combustion probability corresponding to each grid area. Specifically, for each of the monitoring areas, when performing the second spontaneous combustion probability calculation for that monitoring area, the area calculation module is used for: Based on the order of the first spontaneous combustion probability of each grid area in the monitoring area from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area; the second monitoring data contains more types of data than the first monitoring data. If the obtained second spontaneous combustion probability is less than or equal to the second probability threshold, then from the remaining grid areas of the monitoring area, in order of the first spontaneous combustion probability from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area, until all grid areas are traversed.

[0006] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described mine safety monitoring method.

[0007] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described mine safety monitoring method.

[0008] The beneficial effects of the mine safety monitoring method and system, electronic device, and readable storage medium provided in this application are as follows: In this embodiment, a first spontaneous combustion probability is determined for multiple grid areas within a mine goaf based on a small amount of first monitoring data. These grid areas are then initially divided into risk areas (first monitoring areas) and safe areas (second monitoring areas) based on their respective first spontaneous combustion probabilities. For both the first and second monitoring areas, a more refined second spontaneous combustion probability calculation is performed on each monitoring area using a large amount of second monitoring data and a risk monitoring model, according to different calculation cycles. This yields the second spontaneous combustion probability for each grid area, which is then used to determine the risk areas within the mine goaf.

[0009] The calculation cycle (second cycle) of the second monitoring area is longer than that of the first monitoring area (first cycle), which can reduce the number of calculations for the safe area. This reduces the computational load of the risk monitoring model and improves the model's response speed while ensuring safety. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art 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.

[0011] Figure 1 A schematic flowchart of a mine safety monitoring method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the neighborhood grid region of the second target region provided in an embodiment of this application; Figure 3 This is a structural block diagram of a mine safety monitoring system provided in one embodiment of this application; Figure 4 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0014] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a mine safety monitoring method provided in an embodiment of this application. The method can be executed by an electronic device and may include: S101: Determine the first spontaneous combustion probability corresponding to each of the first monitoring data corresponding to multiple grid areas in the goaf of the mine; wherein, the multiple grid areas are obtained by dividing the goaf of the mine into grids.

[0015] In this embodiment, the goaf area of ​​the mine can be divided into multiple grid areas using professional software (such as GIS spatial analysis tools), and multiple sensors (such as temperature sensors, oxygen concentration sensors, etc.) can be deployed in each grid area to achieve zoned monitoring of the goaf area of ​​the mine and improve the accuracy of risk monitoring.

[0016] The first set of monitoring data can include the thickness of residual coal, oxygen concentration, and an assessment value for the spontaneous combustion tendency of residual coal. The thickness of residual coal can be obtained through actual testing, such as drilling holes in the goaf and measuring the distance from the bottom of the hole to the top of the coal seam using a measuring rope or ultrasonic probe. Oxygen concentration can be acquired in real time using an oxygen concentration sensor. The assessment value for the spontaneous combustion tendency of residual coal is mainly determined by the thickness of residual coal and the volatile matter content, and it also varies with temperature and carbon monoxide concentration. Therefore, the assessment value for the spontaneous combustion tendency of residual coal can be calculated periodically using the following formula: ; in, Indicates temperature. Reference values ​​for temperature (the critical auto-ignition temperature of residual coal can be used as a reference value for temperature, such as 70℃). Indicates carbon monoxide concentration. The reference value for carbon monoxide concentration (the safe threshold for carbon monoxide concentration can be used as a reference value for carbon monoxide concentration). Indicates the thickness of the remaining coal. The reference value for the thickness of residual coal can be obtained by statistically analyzing common values ​​for residual coal thickness and taking the average value as the reference value for residual coal thickness. This indicates the percentage of volatile matter in the remaining coal. This represents the preset scaling factor. , Represents the weighting coefficient, and , , , These are all preset constants, and those skilled in the art can set the specific values ​​of the above coefficients according to actual needs.

[0017] In the goaf of a mine, the primary monitoring data (including the thickness of residual coal, oxygen concentration, and assessment value of the spontaneous combustion tendency of residual coal) is the core factor in determining the risk of spontaneous combustion of residual coal. Among them, the thickness of residual coal is the material basis for spontaneous combustion, the oxygen concentration is a necessary condition for spontaneous combustion, and the assessment value of the spontaneous combustion tendency of residual coal is used to characterize the ease or difficulty of spontaneous combustion of coal. Therefore, the primary probability of spontaneous combustion can be quickly determined based on the primary monitoring data corresponding to each grid area.

[0018] S102: Select grid regions from multiple grid regions where the first spontaneous combustion probability is greater than the first probability threshold, and use them as the first monitoring region. Calculate the second spontaneous combustion probability of the first monitoring region according to the first cycle to obtain the second spontaneous combustion probability corresponding to each grid region in the first monitoring region. The second spontaneous combustion probability is calculated for the second monitoring area according to the second cycle, and the second spontaneous combustion probability corresponding to each grid area in the second monitoring area is obtained; the second monitoring area is the grid area other than the first monitoring area among multiple grid areas, and the first cycle is shorter than the second cycle.

[0019] Specifically, for each monitoring area, a second spontaneous combustion probability calculation is performed, including: Based on the order of the first spontaneous combustion probability of each grid area in the monitoring area from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area; the second monitoring data contains more types of data than the first monitoring data. If the obtained second spontaneous combustion probability is less than or equal to the second probability threshold, then from the remaining grid areas of the monitoring area, in order of the first spontaneous combustion probability from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area, until all grid areas are traversed.

[0020] In this embodiment, a first probability threshold can be preset. For grid areas (i.e., the first monitoring area) where the first spontaneous combustion probability is greater than the first probability threshold, they can be initially identified as risk areas. A more refined second spontaneous combustion probability calculation is then performed on the first monitoring area according to a first cycle to further determine the second spontaneous combustion probability of the first monitoring area. The first cycle is a preset constant, and those skilled in the art can set its specific value according to actual needs, for example, 1-3 days.

[0021] For grid areas (i.e., the second monitoring areas) where the first spontaneous combustion probability is less than or equal to the first probability threshold, they can be preliminarily identified as safe areas. The second spontaneous combustion probability of the second monitoring areas can be calculated more precisely according to a larger second period (e.g., 10-15 days) to further determine the second spontaneous combustion probability of the second monitoring areas.

[0022] Specifically, for each monitoring area (first monitoring area or second monitoring area), the second monitoring data corresponding to each grid area in the monitoring area can be input into the risk monitoring model to calculate the second spontaneous combustion probability of the monitoring area, thereby obtaining the second spontaneous combustion probability corresponding to each grid area in the monitoring area.

[0023] In this embodiment, the second monitoring data includes not only the first monitoring data but also data such as carbon dioxide concentration, hydrocarbon gas (C2H4 / C2H6) concentration, H2 concentration, wind speed, and air leakage intensity. The risk monitoring model can be trained using a deep learning model (e.g., convolutional neural network, Transformer model, etc.) or a machine learning model (e.g., support vector machine, random forest) based on historical data of the second monitoring data and corresponding historical data of the second spontaneous combustion probability. The historical data of the second spontaneous combustion probability can be obtained by probability labeling combined with the experience of domain experts.

[0024] In this embodiment, the calculation cycle (second cycle) of the second monitoring area is longer than the monitoring cycle (first cycle) of the first monitoring area, which can reduce the number of calculations for the safe area and thus reduce the computational load of the risk monitoring model.

[0025] S104: Determine the risk area of ​​the goaf in the mine based on the second spontaneous combustion probability corresponding to each grid area.

[0026] In this embodiment, based on the second spontaneous combustion probability corresponding to each grid area, the second spontaneous combustion probability corresponding to each grid area can be compared with a second probability threshold. If the second spontaneous combustion probability corresponding to a certain grid area is less than or equal to the second probability threshold, then the grid area is further determined to be a safe area; if the second spontaneous combustion probability corresponding to a certain grid area is greater than the second probability threshold, then the grid area is further determined to be a risk area.

[0027] As can be seen from the above, this embodiment first determines the first spontaneous combustion probability corresponding to multiple grid areas within the mine goaf based on a small amount of first monitoring data. Based on these first spontaneous combustion probabilities, the multiple grid areas are initially divided into risk areas (first monitoring areas) and safe areas (second monitoring areas). For both the first and second monitoring areas, a more refined second spontaneous combustion probability calculation is performed on each monitoring area according to different calculation cycles, based on a large amount of second monitoring data and a risk monitoring model. This yields the second spontaneous combustion probability corresponding to each grid area, and the risk areas within the mine goaf are determined based on these second spontaneous combustion probabilities.

[0028] The calculation cycle (second cycle) of the second monitoring area is longer than that of the first monitoring area (first cycle), which can reduce the number of calculations in the relatively safe area. This reduces the computational load of the risk monitoring model and improves the model's response speed while ensuring safety.

[0029] In one embodiment of this application, after obtaining the second natural probability of any first target region, if the second natural probability of the first target region is greater than the second probability threshold, then the first target region is determined as the second target region, and the target region filtering operation is performed multiple times until the stopping condition is met, thereby obtaining multiple third target regions. The methods for performing the target region filtering operation for the i-th time (i greater than or equal to 2) include: The neighborhood grid regions of the third target region obtained from the (i-1)th target region filtering operation are determined as multiple fourth target regions. According to the order of the first spontaneous combustion probability of each fourth target region from high to low, the second monitoring data corresponding to each fourth target region are sequentially input into the risk monitoring model to obtain the second spontaneous combustion probability corresponding to each fourth target region. The regions in the multiple fourth target regions whose corresponding second spontaneous combustion probability is greater than the second probability threshold are determined as the third target regions obtained from the i-th target region filtering operation. The third target regions used in the first target region filtering operation are the second target regions. The stopping condition is: the number of third target regions obtained by the i-th target region filtering operation is zero; Among them, the risk areas of the mine goaf are determined based on the second spontaneous combustion probability corresponding to each grid area, including: Risk zones in the goaf of the mine are determined based on the second target area and each third target area.

[0030] In this embodiment, after determining the first target area in descending order of the first spontaneous combustion probability, the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area. If the second natural probability of the first target area is greater than the second probability threshold, the first target area is determined to be a risk area. Considering the risk transmission effect between grid areas, the grid areas around the risk area are likely to be risk areas as well. Therefore, the first target area can be marked as the second target area, and the grid area can be gradually expanded outward from the second target area as the center. The second spontaneous combustion probability of each grid area around the second target area is calculated in turn, and the risk area, i.e. the third target area, is screened based on the calculation result of the second spontaneous combustion probability.

[0031] Specifically, the target area filtering operation can be performed multiple times to obtain multiple third target areas.

[0032] During the initial target region filtering operation, the neighboring grid regions of the second target region (e.g., the top, bottom, left, right, and diagonal 8 neighbors of the second target region, such as...) are selected. Figure 2 Regions A to H (8 regions in the model) are designated as the fourth target region. The second monitoring data corresponding to each fourth target region are sequentially input into the risk monitoring model according to the order of the first spontaneous combustion probability of each fourth target region from high to low, so as to obtain the second spontaneous combustion probability corresponding to each fourth target region. The regions in which the second spontaneous combustion probability of multiple fourth target regions is greater than the second probability threshold are determined as the third target region obtained by the second target region screening operation.

[0033] During other target area screening operations, the neighborhood grid area of ​​the third target area obtained from the previous target area screening operation (e.g., the top, bottom, left, right, and diagonal of the third target area, totaling 8 neighborhoods) is taken as the fourth target area. According to the order of the first spontaneous combustion probability of each fourth target area from high to low, the second monitoring data corresponding to each fourth target area is sequentially input into the risk monitoring model to obtain the second spontaneous combustion probability corresponding to each fourth target area. The area where the second spontaneous combustion probability of multiple fourth target areas is greater than the second probability threshold is determined as the third target area obtained in this target area screening operation.

[0034] If the target area filtering operation is executed multiple times according to the above process, and the number of third target areas obtained in a certain target area filtering operation is zero, that is, no new risk areas appear in the area expanding outward from the second target area, then the target area filtering operation is stopped.

[0035] Through the above process, multiple third target areas can be obtained. The second target area and the multiple third target areas are considered together as the risk area of ​​the mine goaf.

[0036] As can be seen from the above, this embodiment calculates the second spontaneous combustion probability of each grid area in descending order of the first spontaneous combustion probability. Grid areas with high first spontaneous combustion probability are given priority for calculating the second spontaneous combustion probability, which can quickly identify the second target area with risk. Then, the calculation is expanded to the outer grid area with the second target area as the center, and the second spontaneous combustion probability of the outer grid area of ​​the second target area is calculated first, thereby quickly locating the risk area of ​​the mine goaf.

[0037] In one embodiment of this application, after performing target area filtering operations multiple times for each monitoring area until a stopping condition is met, resulting in multiple third target areas, the method further includes: If there is a grid area in the monitoring area that has not undergone the second spontaneous combustion probability calculation, that grid area will be designated as the third monitoring area. The second spontaneous combustion probability is calculated for the third monitoring area to obtain the second spontaneous combustion probability corresponding to each grid area in the third monitoring area. Among them, the risk areas of the mine goaf are determined based on the second spontaneous combustion probability corresponding to each grid area, including: The risk areas of the mine goaf are determined based on the second spontaneous combustion probability corresponding to the second target area, each third target area, and each grid area in the third monitoring area.

[0038] In this embodiment, considering that after expanding outwards from the second target area to identify the risk areas of the mine goaf, some risk areas not connected to the second target area may be missed, this embodiment marks the grid areas where the second spontaneous combustion probability calculation has not been performed as the third monitoring area. Then, the second spontaneous combustion probability is calculated for the third monitoring area to obtain the second spontaneous combustion probability corresponding to each grid area in the third monitoring area. The process of calculating the second spontaneous combustion probability for the third monitoring area is the same as the process of calculating the second spontaneous combustion probability for the first or second monitoring area in the above embodiments.

[0039] As can be seen from the above, this embodiment performs supplementary calculations on grid areas where the second spontaneous combustion probability calculation was not performed, thus avoiding the omission of risk areas.

[0040] In one embodiment of this application, the first monitoring data includes the thickness of the residual coal, the oxygen concentration, and the assessment value of the spontaneous combustion tendency of the residual coal; For each grid area, the first spontaneous combustion probability of that grid area is determined based on the first monitoring data corresponding to that grid area within the mine goaf, including: The first assessment value corresponding to the spontaneous combustion risk of the goaf is determined based on the thickness of the residual coal in the grid area. The second assessment value corresponding to the spontaneous combustion risk of the goaf is determined based on the oxygen concentration corresponding to the grid area. Based on the assessment value of the spontaneous combustion tendency of the residual coal corresponding to the grid area, the third assessment value corresponding to the spontaneous combustion risk of the goaf is determined. The first spontaneous combustion probability of the grid area is obtained by weighted summing of the first, second, and third evaluation values.

[0041] In one embodiment of this application, a specific implementation method is provided for determining the first spontaneous combustion probability of a grid area based on the first monitoring data corresponding to each grid area in the goaf of a mine.

[0042] Specifically, the first assessment value corresponding to the spontaneous combustion risk of the goaf can be calculated using the following first formula: ; in, This indicates the first evaluation value. Indicates the thickness of the remaining coal. This indicates the minimum thickness of the remaining coal seam, typically 0.3 meters. This indicates the maximum thickness of the remaining coal, typically 3 meters.

[0043] Meanwhile, the second assessment value corresponding to the spontaneous combustion risk of the goaf can be calculated using the following second formula: ; in, This indicates the second evaluation value. Indicates oxygen concentration. This represents the lowest risk threshold for oxygen concentration, typically taken as 5%. This represents the highest risk threshold for oxygen concentration, typically taken as 15%.

[0044] Meanwhile, the third assessment value corresponding to the spontaneous combustion risk of the goaf can be calculated using the following third formula: ; in, This indicates the third assessment value. This indicates the assessment value of the spontaneous combustion tendency of leftover coal.

[0045] Based on the first, second, and third evaluation values, a weighted sum of these values ​​can be obtained to determine the first spontaneous combustion probability for each grid region. For example, the first spontaneous combustion probability can be calculated using the following formula: ; in, Indicates the probability of spontaneous combustion. , , All are weighting coefficients, and .

[0046] As can be seen from the above, this embodiment determines the first spontaneous combustion probability of each grid area based on the core factors affecting the risk of spontaneous combustion of residual coal, which is conducive to the accurate calculation of the first spontaneous combustion probability, thereby realizing the accurate division of the first monitoring area and the second monitoring area.

[0047] In one embodiment of this application, the weighted summation of the first evaluation value, the second evaluation value, and the third evaluation value includes: If the formation time of the goaf in the mine is less than or equal to the first duration, the weight corresponding to the first evaluation value is set to be less than the weight corresponding to the second evaluation value, and the weight corresponding to the first evaluation value is greater than the weight corresponding to the third evaluation value. If the formation time of the goaf in the mine is longer than the first time period, the weight corresponding to the first evaluation value is set to be greater than the weight corresponding to the third evaluation value, and the weight corresponding to the third evaluation value is greater than the weight corresponding to the second evaluation value. The first, second, and third evaluation values ​​are weighted and summed based on the weights corresponding to the first, second, and third evaluation values.

[0048] In this embodiment, when weighting and summing the first, second, and third assessment values, considering that if the goaf formation time is short (less than or equal to the first duration), the contact area between the residual coal and air, as well as the oxygen supply, are key factors for spontaneous combustion, the residual coal has not yet been fully oxidized, and the oxygen concentration directly determines the oxidation reaction rate, which is the dominant factor. Therefore, the weight of the second assessment value (corresponding to the oxygen concentration) is set to the largest, followed by the first assessment value (corresponding to the thickness of the residual coal). Since the coal quality characteristics have not yet changed significantly due to environmental changes (such as oxidation or temperature rise), the immediate impact on the current risk is weak. Therefore, the weight of the third assessment value (corresponding to the assessment value of the spontaneous combustion tendency of the residual coal) is set to the lowest.

[0049] Correspondingly, if the goaf has been formed for a long time (greater than the first time), the impact of the thickness of the residual coal on the probability of spontaneous combustion will gradually become more prominent. For example, thick residual coal areas are prone to heat accumulation during long-term oxidation. Even with moderate oxygen concentration, the temperature may rise due to continuous slow oxidation, forming a "heat storage environment." In this case, the thickness of the residual coal becomes the dominant factor in the probability of spontaneous combustion. At the same time, coal quality characteristics (spontaneous combustion tendency assessment value) will gradually emerge due to long-term oxidation. For example, residual coal with a high spontaneous combustion tendency assessment value is more likely to reach its ignition point under the same conditions, thus increasing its assessment value for the current risk. Therefore, the weight of the first assessment value (corresponding to the thickness of the residual coal) is set to the largest, followed by the third assessment value (corresponding to the spontaneous combustion tendency assessment value of the residual coal), and the weight of the second assessment value (corresponding to the oxygen concentration) is set to the smallest.

[0050] As can be seen from the above, this embodiment dynamically adjusts the weights of the first, second, and third evaluation values ​​based on the formation time of the goaf, which is more in line with the development trend of spontaneous combustion risk in the goaf, and is conducive to obtaining an accurate first spontaneous combustion probability, avoiding misjudgment and omission of spontaneous combustion risk in each grid area.

[0051] In one embodiment of this application, determining the risk area of ​​a mine goaf based on a second target area and various third target areas includes: The union of the second target area and each of the third target areas is determined as the risk area of ​​the mine goaf.

[0052] In this embodiment, the second target area and each of the third target areas are both risk areas selected with a second spontaneous combustion probability greater than a second probability threshold. By merging the second target area and each of the third target areas, the risk area of ​​the mine goaf can be obtained.

[0053] Specifically, when dividing the goaf into grids, the resulting grid areas can be numbered. Based on this, if the grid number of the second target area is 1 and the grid numbers of each third target area are [5,6,7], then the risk areas of the goaf are [1,5,6,7].

[0054] In one embodiment of this application, the mine safety monitoring method further includes: Obtain the gas concentration in the high-risk area; The risk level of a risk area is determined based on the gas concentration within that area.

[0055] In this embodiment, considering the correlation between the spontaneous combustion risk of abandoned coal and the gas risk, such as the possibility that spontaneous combustion of abandoned coal may trigger a gas explosion, combining the spontaneous combustion risk of abandoned coal with the gas risk can more comprehensively reflect the safety risks of the goaf in the mine.

[0056] Specifically, the risk level of a risk area can be further subdivided into Level I, Level II, and Level III risks based on the gas concentration. At Level I risk, spontaneous combustion of residual coal may ignite gas, posing an explosion risk, and production must be stopped immediately. At Level II risk, the gas concentration is close to the lower explosive limit, requiring enhanced monitoring and measures such as ventilation and extraction. At Level III risk, the gas concentration is low, with spontaneous combustion being the primary risk, requiring continuous monitoring and fire prevention and extinguishing measures.

[0057] As can be seen from the above, this embodiment combines the risk of spontaneous combustion of residual coal with gas concentration, which can improve the accuracy of mine safety monitoring results. Based on the mine safety monitoring results, managers can be guided to take corresponding measures to ensure mine safety.

[0058] In one embodiment of this application, the risk monitoring model may specifically employ a support vector machine, and the kernel function of the support vector machine is obtained by weighted combination of linear and nonlinear kernel functions. The mine safety monitoring method further includes: If the formation time of the goaf in the mine is less than or equal to the first duration, the weight corresponding to the linear kernel function is set to be greater than the weight corresponding to the nonlinear kernel function. If the formation time of the goaf in the mine is longer than the first time period, the weight corresponding to the linear kernel function is set to be less than the weight corresponding to the nonlinear kernel function.

[0059] In this embodiment, a support vector machine (SVM) can be used to predict the second spontaneous combustion probability. The kernel function of the support vector machine transforms low-dimensional data into a high-dimensional feature space through mapping, thereby achieving the fitting of linear or nonlinear relationships in the data.

[0060] Based on this, considering that in the goaf of a mine, there are both simple linear relationships (such as higher oxygen concentration leading to higher risk of spontaneous combustion) and complex nonlinear relationships (such as the nonlinear effect of the coupling of oxygen concentration, residual coal thickness, and time), this embodiment uses a weighted combination of linear and nonlinear kernel functions as the kernel function. This ensures that the support vector machine can capture both linear and nonlinear patterns in the data, thereby improving the prediction accuracy of the second spontaneous combustion probability.

[0061] Meanwhile, considering that when the goaf is first formed (the formation time of the goaf is less than or equal to the first duration), its internal environment (such as the distribution of residual coal, oxygen concentration, temperature field, etc.) has not yet undergone complex evolution, the distribution of key parameters such as residual coal thickness and oxygen concentration is relatively uniform, and the interaction between features is weak. At this time, the prediction results of the linear kernel function can be emphasized. Therefore, the weight corresponding to the linear kernel function is set to be greater than the weight corresponding to the nonlinear kernel function.

[0062] Correspondingly, as the formation time of the goaf increases, the internal environment gradually becomes more complex, and the coupling effect of various risk factors (such as coal spontaneous combustion tendency, geological structure, and support residue) is enhanced, forming a complex nonlinear correlation. When the formation time of the goaf in the mine is longer than the first time, it indicates that the formation time of the goaf is relatively long. At this time, the prediction results of the nonlinear kernel function can be emphasized. Therefore, the weight corresponding to the nonlinear kernel function is set to be greater than the weight corresponding to the linear kernel function.

[0063] Specifically, the kernel function of a support vector machine can be calculated using the following formula: ; in, This represents the kernel function of a support vector machine. This represents the feature vector composed of any two sets of second monitoring data. For a linear kernel function, it represents and dot product, For nonlinear kernel functions, exp() represents exponential operation with base e. express and The square of the Euclidean distance, For kernel function parameters, and All are weighting coefficients, and .

[0064] As can be seen from the above, this embodiment dynamically matches the kernel function weights according to the characteristics of different evolution stages of the goaf, making the support vector machine more in line with the actual risk model and reducing false alarms and false negatives.

[0065] Corresponding to the mine safety monitoring method in the above embodiments, Figure 3 This is a structural block diagram of a mine safety monitoring system provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 3 The mine safety monitoring system 20 includes: a region division module 21, a region calculation module 22, and a result output module 23.

[0066] Among them, the area division module 21 is used to determine the first spontaneous combustion probability of each of the multiple grid areas in the mine goaf based on the first monitoring data corresponding to each of the multiple grid areas; wherein, the multiple grid areas are obtained by dividing the mine goaf into grids; The region calculation module 22 is used to select grid regions from multiple grid regions where the first spontaneous combustion probability is greater than a first probability threshold, as the first monitoring region, and to calculate the second spontaneous combustion probability of the first monitoring region according to a first cycle, so as to obtain the second spontaneous combustion probability corresponding to each grid region in the first monitoring region; and to calculate the second spontaneous combustion probability of the second monitoring region according to a second cycle, so as to obtain the second spontaneous combustion probability corresponding to each grid region in the second monitoring region; the second monitoring region is the grid region other than the first monitoring region among the multiple grid regions, and the first cycle is shorter than the second cycle; The result output module 23 is used to determine the risk area of ​​the mine goaf based on the second spontaneous combustion probability corresponding to each grid area. Specifically, for each monitoring area, when performing the second spontaneous combustion probability calculation for that monitoring area, the area calculation module 22 is used for: Based on the order of the first spontaneous combustion probability of each grid area in the monitoring area from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area; the second monitoring data contains more types of data than the first monitoring data. If the obtained second spontaneous combustion probability is less than or equal to the second probability threshold, then from the remaining grid areas of the monitoring area, in order of the first spontaneous combustion probability from high to low, the first target area is determined, and the second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain the second natural probability of the first target area, until all grid areas are traversed.

[0067] In one embodiment of this application, the region calculation module 22 is specifically used for: After obtaining the second natural probability of any first target region, if the second natural probability of the first target region is greater than the second probability threshold, then the first target region is determined as the second target region. The target region filtering operation is performed multiple times until the stopping condition is met, and multiple third target regions are obtained. Specifically, during the i-th execution of the target region filtering operation, the region calculation module 22 is used for: The neighborhood grid regions of the third target region obtained from the (i-1)th target region filtering operation are determined as multiple fourth target regions. According to the order of the first spontaneous combustion probability of each fourth target region from high to low, the second monitoring data corresponding to each fourth target region are sequentially input into the risk monitoring model to obtain the second spontaneous combustion probability corresponding to each fourth target region. The regions in the multiple fourth target regions whose corresponding second spontaneous combustion probability is greater than the second probability threshold are determined as the third target regions obtained from the i-th target region filtering operation. The third target regions used in the first target region filtering operation are the second target regions. The stopping condition is: the number of third target regions obtained by the i-th target region filtering operation is zero; Specifically, when determining the risk area of ​​the goaf in the mine based on the second spontaneous combustion probability corresponding to each grid area, the result output module 23 is used for: Risk areas of mine goaf are determined based on the second target area and each third target area.

[0068] In one embodiment of this application, for each monitoring area, after performing target area filtering operations multiple times until a stopping condition is met to obtain multiple third target areas, the area calculation module 22 is further used for: If there is a grid area in the monitoring area that has not undergone the second spontaneous combustion probability calculation, that grid area will be designated as the third monitoring area. The second spontaneous combustion probability is calculated for the third monitoring area to obtain the second spontaneous combustion probability corresponding to each grid area in the third monitoring area. Specifically, when determining the risk area of ​​the goaf in the mine based on the second spontaneous combustion probability corresponding to each grid area, the result output module 23 is used for: The risk areas of the mine goaf are determined based on the second spontaneous combustion probability corresponding to the second target area, each third target area, and each grid area in the third monitoring area.

[0069] In one embodiment of this application, the first monitoring data includes residual coal thickness, oxygen concentration, and residual coal spontaneous combustion tendency assessment value; the area division module 21 is specifically used for: The first assessment value corresponding to the spontaneous combustion risk of the goaf is determined based on the thickness of the residual coal in the grid area. The second assessment value corresponding to the spontaneous combustion risk of the goaf is determined based on the oxygen concentration corresponding to the grid area. Based on the assessment value of the spontaneous combustion tendency of the residual coal corresponding to the grid area, the third assessment value corresponding to the spontaneous combustion risk of the goaf is determined. The first spontaneous combustion probability of the grid area is obtained by weighted summing of the first, second, and third evaluation values.

[0070] In one embodiment of this application, the region division module 21 is further used for: If the formation time of the goaf in the mine is less than or equal to the first duration, the weight corresponding to the first evaluation value is set to be less than the weight corresponding to the second evaluation value, and the weight corresponding to the first evaluation value is greater than the weight corresponding to the third evaluation value. If the formation time of the goaf in the mine is longer than the first time period, the weight corresponding to the first evaluation value is set to be greater than the weight corresponding to the third evaluation value, and the weight corresponding to the third evaluation value is greater than the weight corresponding to the second evaluation value. The first, second, and third evaluation values ​​are weighted and summed based on the weights corresponding to the first, second, and third evaluation values.

[0071] In one embodiment of this application, the region calculation module 22 is further configured to: The union of the second target area and each of the third target areas is determined as the risk area of ​​the mine goaf.

[0072] In one embodiment of this application, the result output module 23 is specifically used for: Obtain the gas concentration in the high-risk area; The risk level of a risk area is determined based on the gas concentration within that area.

[0073] See Figure 4 , Figure 4 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 4 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 3 The functions of the region division module 21, region calculation module 22, and result output module 23 are shown.

[0074] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0075] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0076] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store preset constants such as a first probability threshold and a second probability threshold.

[0077] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the mine safety monitoring method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0078] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0079] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0080] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0081] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connections shown or discussed may be indirect coupling or communication connections through some interfaces or units, or they may be electrical, mechanical, or other forms of connection.

[0083] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0084] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0085] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of mine safety monitoring, characterised by, The method comprises the following steps: determining a first spontaneous combustion probability corresponding to each grid area based on first monitoring data corresponding to the grid area, wherein the grid areas are obtained by grid division of the mine goaf; selecting a grid area with a first spontaneous combustion probability greater than a first probability threshold from the grid areas as a first monitoring area, performing second spontaneous combustion probability calculation on the first monitoring area according to a first period to obtain a second spontaneous combustion probability corresponding to each grid area in the first monitoring area, performing second spontaneous combustion probability calculation on a second monitoring area according to a second period to obtain a second spontaneous combustion probability corresponding to each grid area in the second monitoring area, wherein the second monitoring area is a grid area other than the first monitoring area in the grid areas, and the first period is less than the second period, determining a risk area of the mine goaf based on the second spontaneous combustion probability corresponding to each grid area; wherein, for each monitoring area, the second spontaneous combustion probability calculation on the monitoring area comprises: determining a first target area according to the order of the first spontaneous combustion probability of each grid area in the monitoring area from high to low, inputting second monitoring data corresponding to the first target area into a risk monitoring model to obtain a second natural probability of the first target area, wherein the second monitoring data contains more data types than the first monitoring data; if the obtained second spontaneous combustion probability is less than or equal to a second probability threshold, then a first target area is determined from the remaining grid areas in the monitoring area according to the order of the first spontaneous combustion probability from high to low, second monitoring data corresponding to the first target area is input into the risk monitoring model to obtain a second natural probability of the first target area, and the process is repeated until all grid areas are traversed.

2. The mine safety monitoring method of claim 1, wherein, After obtaining the second natural probability of any first target area, if the second natural probability of the first target area is greater than the second probability threshold, the first target area is determined as a second target area, and the target area screening operation is performed multiple times until a stop condition is met to obtain multiple third target areas; wherein, the i th target area screening operation comprises: determining a plurality of fourth target areas from the neighborhood grid areas of the third target areas obtained by the (i-1) th target area screening operation, inputting second monitoring data corresponding to each fourth target area into the risk monitoring model according to the order of the first spontaneous combustion probability of each fourth target area from high to low to obtain a second spontaneous combustion probability corresponding to each fourth target area, and determining a third target area obtained by the i th target area screening operation from the fourth target areas with a second spontaneous combustion probability greater than the second probability threshold, wherein the third target area used in the first target area screening operation is the second target area; the stop condition is that the number of third target areas obtained by the i th target area screening operation is zero; wherein, the determination of the risk area of the mine goaf based on the second spontaneous combustion probability corresponding to each grid area comprises: Determine the risk area of the mine goaf based on the second target area and each third target area.

3. The mine safety monitoring method of claim 2, wherein, After obtaining a plurality of third target areas by performing the target area screening operation multiple times until a stop condition is met for each monitoring area, the method further includes: If there is a grid area in the monitoring area that has not undergone the second spontaneous combustion probability calculation, the grid area is taken as a third monitoring area; Perform the second spontaneous combustion probability calculation on the third monitoring area to obtain a second spontaneous combustion probability corresponding to each grid area in the third monitoring area; The method further includes: Determine the risk area of the mine goaf based on the second target area, each third target area, and the second spontaneous combustion probability corresponding to each grid area in the third monitoring area.

4. The mine safety monitoring method of claim 1, wherein, The first monitoring data includes the residual coal thickness, the oxygen concentration, and the residual coal spontaneous combustion tendency evaluation value; For each grid area, determine a first spontaneous combustion probability of the grid area based on the first monitoring data corresponding to the grid area in the mine goaf, including: Determine a first evaluation value corresponding to the goaf spontaneous combustion risk based on the residual coal thickness corresponding to the grid area; Determine a second evaluation value corresponding to the goaf spontaneous combustion risk based on the oxygen concentration corresponding to the grid area; Determine a third evaluation value corresponding to the goaf spontaneous combustion risk based on the residual coal spontaneous combustion tendency evaluation value corresponding to the grid area; Weightedly sum the first evaluation value, the second evaluation value, and the third evaluation value to obtain the first spontaneous combustion probability of the grid area.

5. The mine safety monitoring method of claim 4, wherein, The weightedly summing the first evaluation value, the second evaluation value, and the third evaluation value includes: If the formation time of the mine goaf is less than or equal to a first time length, set the weight corresponding to the first evaluation value to be less than the weight corresponding to the second evaluation value, and the weight corresponding to the first evaluation value to be greater than the weight corresponding to the third evaluation value; If the formation time of the mine goaf is greater than the first time length, set the weight corresponding to the first evaluation value to be greater than the weight corresponding to the third evaluation value, and the weight corresponding to the third evaluation value to be greater than the weight corresponding to the second evaluation value; Weightedly sum the first evaluation value, the second evaluation value, and the third evaluation value based on the set weight corresponding to the first evaluation value, the weight corresponding to the second evaluation value, and the weight corresponding to the third evaluation value.

6. The mine safety monitoring method of claim 2, wherein, The method further includes: Determine the risk area of the mine goaf based on the second target area and each third target area.

7. The mine safety monitoring method of claim 1, wherein, The method further includes: Obtain the gas concentration of the risk area; Determine the risk level of the risk area based on the gas concentration of the risk area.

8. A mine safety monitoring system characterized by, The method further includes: A region division module is configured to determine a first spontaneous combustion probability corresponding to each grid area based on first monitoring data corresponding to a plurality of grid areas in a mine goaf; the plurality of grid areas are obtained by dividing the mine goaf into grid areas; The area calculation module is configured to: filter, from the plurality of grid areas, a first monitoring area in which the first spontaneous combustion probability is greater than a first probability threshold, and perform second spontaneous combustion probability calculation on the first monitoring area according to a first period to obtain a second spontaneous combustion probability corresponding to each grid area in the first monitoring area; and perform second spontaneous combustion probability calculation on a second monitoring area according to a second period to obtain a second spontaneous combustion probability corresponding to each grid area in the second monitoring area; the second monitoring area is a grid area other than the first monitoring area in the plurality of grid areas, and the first period is less than the second period. The result output module is configured to determine a risk area of the mine goaf based on the second spontaneous combustion probability corresponding to each grid area. For each monitoring area, when performing the second spontaneous combustion probability calculation on the monitoring area, the area calculation module is specifically configured to: determine a first target area in a descending order of the first spontaneous combustion probability of each grid area in the monitoring area, input second monitoring data corresponding to the first target area into a risk monitoring model, and obtain a second natural probability of the first target area; the second monitoring data contains more data types than the first monitoring data. If the obtained second spontaneous combustion probability is less than or equal to a second probability threshold, the first target area is determined from the remaining grid areas in the monitoring area in a descending order of the first spontaneous combustion probability, the second monitoring data corresponding to the first target area is input into the risk monitoring model, the second natural probability of the first target area is obtained, and the process is repeated until all grid areas are traversed.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the method according to any one of claims 1 to 7.

Images