Methods and devices for monitoring gas in mine goaf areas, electronic equipment, and storage media

Abstract

This application provides a method, device, electronic equipment, and storage medium for monitoring gas in mine goaf areas, belonging to the field of mine monitoring technology. The method includes: acquiring gas data collected by sensors installed in different areas of the goaf; generating a gas concentration matrix with temporal and spatial correlation based on the gas data; establishing a gas diffusion model based on the geological structure data and ventilation parameters of the goaf; inputting the gas data into the gas diffusion model to calculate a gas concentration prediction matrix for the goaf; determining a target monitoring strategy based on the deviation coefficient matrix between the gas concentration matrix and the gas concentration prediction matrix; and monitoring the goaf based on the target monitoring strategy. The method, device, electronic equipment, and storage medium provided in this application improve the accuracy of gas monitoring in mine goaf areas.

Description

Technical Field

[0001] This application belongs to the field of mine monitoring technology, and more specifically, relates to a method and device, electronic equipment and storage medium for monitoring gas in mine goaf areas. Background Technology

[0002] During mining operations, the gas conditions in the goaf directly affect mine safety. As mining activities progress, various harmful gases such as methane and carbon monoxide accumulate in the goaf. If these gases are not effectively monitored and controlled, they can easily lead to serious safety accidents such as explosions, poisoning, and asphyxiation.

[0003] Currently, most gas monitoring methods in mine goaf areas rely on single-point sensors for decentralized monitoring, which fails to comprehensively reflect the overall gas concentration distribution and dynamic changes in the goaf area, resulting in monitoring blind spots and time lags. Furthermore, existing monitoring methods cannot adjust the focus of monitoring according to actual needs, leading to inefficient allocation of monitoring resources and an inability to meet the increasingly complex demands of mine safety production.

[0004] Therefore, there is an urgent need for an accurate method for monitoring gas in mine goaf areas. Summary of the Invention

[0005] The purpose of this application is to provide a method and device for monitoring gas in mine goaf areas, electronic equipment, and storage medium to improve the accuracy of gas monitoring in mine goaf areas.

[0006] A first aspect of this application provides a method for monitoring gas in a mine goaf, comprising:

[0007] Acquire gas data collected by sensors set up in different areas of the goaf, and generate a gas concentration matrix with temporal and spatial correlation based on the gas data;

[0008] A gas diffusion model is established based on the geological structure data and ventilation parameters of the goaf. The gas data is input into the gas diffusion model to calculate the gas concentration prediction matrix of the goaf.

[0009] The target monitoring strategy is determined based on the deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix.

[0010] Monitoring of goaf areas is based on target monitoring strategies.

[0011] A second aspect of this application provides a gas monitoring device for goaf areas in mines, comprising:

[0012] The matrix generation module is used to acquire gas data collected by sensors set in different areas of the goaf, and generate a gas concentration matrix with temporal and spatial correlation based on the gas data;

[0013] The prediction matrix module is used to establish a gas diffusion model based on the geological structure data and ventilation parameters of the goaf. The gas data is input into the gas diffusion model to calculate the gas concentration prediction matrix of the goaf.

[0014] The strategy determination module is used to determine the target monitoring strategy based on the deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix;

[0015] The gas monitoring module is used to monitor the goaf based on the target monitoring strategy.

[0016] 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 method for monitoring gas in goaf areas of a mine.

[0017] 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 method for monitoring gas in goaf areas of a mine.

[0018] The beneficial effects of the gas monitoring method, device, electronic equipment, and storage medium for goaf areas provided in this application are as follows: This application collects gas data by installing sensors in different areas of the goaf and generates a gas concentration matrix with temporal and spatial correlation, which can accurately capture the dynamic changes in gas concentration at different time points in each area and avoid monitoring blind spots. This application establishes a gas diffusion model based on geological structure data and ventilation parameters, uses this model to simulate gas diffusion laws, and combines actual collected data to predict gas concentration, making the prediction results more consistent with the actual situation. This application also determines the monitoring strategy based on the deviation coefficient matrix between the gas concentration matrix and the prediction matrix, which can adjust the monitoring focus in a timely manner to compensate for the prediction error. At the same time, it determines the target monitoring indicators based on mining information and gas hazard levels, focusing on key gas parameters and reducing unnecessary interference factors. By combining the target monitoring strategy with the indicators, the accuracy of monitoring is improved, providing accurate data support for mine safety management and effectively reducing the risk of safety accidents caused by gas problems. Attached Figure Description

[0019] 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.

[0020] Figure 1A schematic flowchart of a method for monitoring gas in a mine goaf provided in an embodiment of this application;

[0021] Figure 2 A structural block diagram of a gas monitoring device for goaf areas provided in an embodiment of this application;

[0022] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] 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.

[0024] 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.

[0025] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a method for monitoring gas in a mine goaf according to an embodiment of this application. The method includes:

[0026] S101: Acquire gas data collected by sensors set in different areas of the goaf, and generate a gas concentration matrix with temporal and spatial correlation based on the gas data.

[0027] In this embodiment, various types of sensors, including but not limited to carbon monoxide sensors, methane sensors, oxygen sensors, and hydrogen sulfide sensors, are deployed in different areas of the goaf (such as air inlets, air outlets, near the roof, near the roadway walls, and deep within the goaf) to collect gas data at a set sampling frequency (e.g., once per minute). Based on the collected gas data, the sensor's geographical location information, and the collection time information, this embodiment constructs a gas concentration matrix with temporal and spatial correlations. The gas concentration matrix uses time series data as rows and the spatial locations of different sensors as columns, displaying the gas concentration data of different areas of the goaf at different times.

[0028] In this embodiment, before deploying the sensors, a 3D model of the goaf is created using a Geographic Information System (GIS). Combined with historical mining data of the goaf, the distribution patterns of previously anomaly gas areas are analyzed. Special geological structures such as roof collapse zones and fracture development zones within the goaf are also considered to determine the sensor deployment locations. Furthermore, temperature sensors are added to areas within the goaf that pose a high-temperature ignition risk to prevent fires. The density of sensors is increased at the junctions between the goaf and adjacent mining areas or roadways to prevent gas from flowing to other areas.

[0029] In this embodiment, the raw gas data collected by the sensor is first validated to remove invalid data caused by sensor failure, communication anomalies, etc.; then, a moving average filtering algorithm is used to smooth the data and remove random noise; finally, for missing data, linear interpolation or a machine learning-based prediction model is used to fill in the missing data based on data from previous and subsequent time points and data from adjacent sensors to ensure the integrity and continuity of the data.

[0030] In constructing the gas concentration matrix, this embodiment can also correlate gas data with mine production activity data (such as coal mining operation periods, blasting times, etc.) and meteorological condition data (such as atmospheric pressure, ambient temperature, etc.). For example, during coal mining operations, the changes in gas concentration in various areas during that period are recorded, and the impact of production activities on gas concentration is analyzed. At the same time, the influence of changes in atmospheric pressure and ambient temperature on gas diffusion is considered, and these factors are incorporated as additional dimensions into the gas concentration matrix to form a more comprehensive and accurate multidimensional data matrix that reflects the gas change patterns in the goaf.

[0031] S102: Based on the geological structure data and ventilation parameters of the goaf, a gas diffusion model is established, and the gas data is input into the gas diffusion model to calculate the gas concentration prediction matrix of the goaf.

[0032] In this embodiment, the collected geological structure data of the goaf includes: the shape, size, rock strata distribution, and fracture development of the goaf. Simultaneously, ventilation parameters of the goaf are acquired, such as ventilation volume, ventilation method (exhaust, forced, or mixed), and airflow direction. Based on the above geological structure data and ventilation parameters, a gas diffusion model is established using computational fluid dynamics principles or other suitable mathematical modeling methods. The gas diffusion model constructed in this embodiment can simulate the diffusion, migration, and mixing processes of gas in the complex environment of the goaf. This embodiment uses the collected gas data as input to the model and solves the gas diffusion model through numerical calculations, thereby calculating a gas concentration prediction matrix for the goaf over a future period (e.g., 1 hour, 2 hours, etc.). This matrix also contains temporal and spatial dimension information, predicting the changing trends of gas concentration in each area.

[0033] S103: Determine the target monitoring strategy based on the deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix.

[0034] In this embodiment, the deviation coefficient matrix between the gas concentration matrix and the gas concentration prediction matrix is ​​calculated. By comparing the elements at corresponding positions of the two matrices, appropriate error calculation methods such as mean square error and absolute error are used to quantify the difference between the actual gas concentration and the predicted gas concentration.

[0035] In this embodiment, the characteristics of gas concentration variation and abnormal situations are analyzed based on the deviation coefficient matrix. If the deviation coefficient of a certain area is large, it indicates that the actual value of gas concentration in that area differs significantly from the predicted value, and there may be potential dangers such as abnormal ventilation and gas leakage.

[0036] In this embodiment, the target monitoring strategy is determined based on the analysis results, specifically including: for areas with large deviation coefficients, increasing the deployment density of sensors or increasing the sampling frequency of sensors to obtain gas data for the area more accurately and timely; for areas with unstable gas concentration trends or potential hazards, arranging manual inspections or using equipment such as drones for key inspections; adjusting ventilation system parameters to optimize ventilation effects and reduce the risk of hazardous gas accumulation.

[0037] S104: Monitor the goaf area based on the target monitoring strategy.

[0038] In this embodiment, the goaf area is monitored according to the determined target monitoring strategy, gas data is acquired and updated in real time, the gas concentration matrix and gas concentration prediction matrix are continuously analyzed and compared, and the monitoring strategy is dynamically adjusted to ensure that gas safety hazards in the goaf area can be detected and dealt with in a timely manner, thereby ensuring the safe production of the mine.

[0039] For example, suppose that three sensors (referred to as sensor A, sensor B and sensor C) are set up in the goaf area, and carbon monoxide (CO) gas concentration data (unit: ppm) are collected at four different times (referred to as time 1, time 2, time 3 and time 4).

[0040] Based on the actual collected data, the gas concentration matrix is ​​constructed as follows:

[0041]

[0042] In this matrix, the rows represent different times (from top to bottom: time 1, time 2, time 3, time 4), and the columns represent different sensors (from left to right: sensor A, sensor B, sensor C).

[0043] Based on a gas diffusion model, the carbon monoxide gas concentration at three locations and four future time points is predicted. The resulting gas concentration prediction matrix is ​​as follows:

[0044]

[0045] The meanings of the rows and columns in the gas concentration prediction matrix are consistent with those in the gas concentration matrix. By comparing these two matrices, the deviation coefficient matrix can be further calculated to analyze the difference between the actual situation and the prediction, so as to determine the monitoring strategy.

[0046] As can be seen from the above, this application collects gas data by installing sensors in different areas of the goaf and generates a gas concentration matrix with temporal and spatial correlations. This enables precise capture of dynamic changes in gas concentration at different points in time in each area, avoiding monitoring blind spots. A gas diffusion model is established based on geological structure data and ventilation parameters. This model simulates gas diffusion patterns, and combined with actual collected data, gas concentrations are predicted, resulting in predictions that more closely match reality. A monitoring strategy is determined based on the deviation coefficient matrix between the gas concentration matrix and the prediction matrix, allowing for timely adjustments to monitoring priorities to compensate for prediction errors. Simultaneously, target monitoring indicators are determined based on mining information and gas hazard levels, focusing on key gas parameters and reducing unnecessary interference factors. By combining the target monitoring strategy with indicators, the accuracy of monitoring is improved, providing precise data support for mine safety management and effectively reducing the risk of safety accidents caused by gas-related issues.

[0047] In one embodiment of this application, gas data collected by sensors located in different areas of the goaf are acquired, and a gas concentration matrix with temporal and spatial correlation is generated based on the gas data, including:

[0048] The gas data is segmented according to the first time window to generate a time series matrix;

[0049] Construct an adjacency matrix based on the spatial topological relationships between the deployment locations of all sensors;

[0050] The gas concentration matrix is ​​obtained by fusing the time series matrix and the adjacency matrix through a spatiotemporal graph convolutional network.

[0051] In this embodiment, the length of the first time window needs to be determined based on the characteristics of gas changes in the goaf and the actual monitoring requirements. The changes in gas concentration in the goaf are affected by various factors, such as the operating cycle of the ventilation system and the frequency of coal mining operations. If the ventilation system adjusts its airflow every hour, the first time window can be set to one hour, allowing the segmented data to capture the pattern of gas concentration changes with ventilation.

[0052] This embodiment segments the continuous gas data collected by the sensors using a first time window as the interval. For example, assuming the sensors continuously collect gas data for 24 hours, and the first time window is 1 hour, then the 24 hours of gas data will be divided into 24 time periods. For the gas data within each time period, the data collected by different sensors are arranged into a vector according to the sensor numbers. For example, if 5 sensors are set up in the goaf area, and the gas concentrations collected by the sensors in a certain 1-hour time period are c1, c2, c3, c4, c5, then a vector [c1, c2, c3, c4, c5] can be formed. The vectors corresponding to each time period are arranged in chronological order to obtain a time series matrix. Assuming there are M time periods and N sensors, the dimension of the time series matrix is ​​M×N.

[0053] This embodiment determines the spatial topology relationships between sensors based on their deployment locations within the goaf. For example, two sensors are more closely spaced and located on the same ventilation path, indicating a stronger correlation. Conversely, two sensors separated by obstacles or located in different ventilation zones have a weaker correlation. This embodiment constructs an N×N adjacency matrix based on the spatial topology relationships, where N is the number of sensors. For each element Aij in the matrix, if sensor i and sensor j are spatially correlated, Aij is assigned a value of 1; otherwise, it is assigned a value of 0. Alternatively, the matrix elements can be normalized using the reciprocal of the physical distance between the sensors.

[0054] This embodiment employs a spatiotemporal graph convolutional network to process the time-series features of gas data, extracting the temporal features of the gas data. Simultaneously, it extracts the spatial features between sensors from the adjacency matrix. The temporal and spatial features are then fused through a fusion layer in the spatiotemporal graph convolutional network to generate a gas concentration matrix. This gas concentration matrix includes the gas concentration values ​​of each sensor at different time points, containing spatial relationship information between sensors, and can more comprehensively and accurately describe the distribution and changes in gas concentration within the goaf.

[0055] In one embodiment of this application, gas data is segmented according to a first time window to generate a time series matrix, including:

[0056] The initial time window length is calculated based on the operating parameters of the ventilation fans installed in the goaf. The operating parameters include the ventilation fan start-stop cycle, the average wind speed in the goaf, and the gas diffusion time constant.

[0057] The periodic characteristics of gas concentration fluctuations in historical gas data are extracted, and the period corresponding to the dominant frequency in the periodic characteristics is identified by the Fourier transform algorithm as the window adjustment factor.

[0058] The first time window is obtained by weighting the initial time window length and the window adjustment factor.

[0059] The gas data is segmented according to the first time window to generate a time series matrix.

[0060] In this embodiment, the start and stop of the ventilation fan directly affects the airflow state within the goaf, thereby altering the diffusion and distribution patterns of the gas. Historical start and stop records of the ventilation fan are obtained, and its start-stop cycle is analyzed. For example, if the ventilation fan starts every 6 hours and runs continuously for 2 hours, this 6-hour cycle interval is the start-stop cycle. This embodiment obtains the average wind speed within the goaf by weighted averaging of wind speed data from multiple locations over a period of time (e.g., the past 24 hours). For example, the wind speeds near the air inlet, air outlet, and the middle of the roadway are calculated according to their weighted impact on gas diffusion to obtain a comprehensive average wind speed. The gas diffusion time constant in this embodiment describes the diffusion characteristics of gas in the goaf medium. The gas diffusion time constant is related to the geological structure of the goaf (e.g., rock porosity, degree of fracture development) and the intrinsic properties of the gas (e.g., molecular diffusion coefficient).

[0061] This embodiment calculates the initial time window length based on the fan start-stop cycle T, the average wind speed V in the goaf, the gas diffusion time constant τ, and the first formula. The first formula is:

[0062]

[0063] in, α is the initial time window length, L is the ventilation path length of the goaf, and α, β, and γ are weighting coefficients adjusted according to the actual situation.

[0064] In this embodiment, firstly, the historical gas data undergoes preprocessing operations such as denoising and missing value imputation. Median filtering is used to remove random noise from the data, and missing data is imputed using linear interpolation or machine learning-based methods based on data from adjacent time points and adjacent sensors. Secondly, the preprocessed historical gas concentration data is used as a time-domain signal and transformed to the frequency domain using a Fourier transform algorithm. In the frequency domain, each frequency corresponds to a specific period; the higher the frequency, the shorter the corresponding period. By analyzing the spectrum of the frequency domain signal, the frequency component with the largest energy proportion is identified; this frequency is the dominant frequency, and the period corresponding to the dominant frequency is used as a window adjustment factor. For example, if the dominant frequency is f=0.1Hz, the corresponding period indicates that the gas concentration exhibits a significant periodic fluctuation every 10 hours.

[0065] In one embodiment of this application,

[0066] A gas diffusion model based on geological structure data and ventilation parameters of the goaf includes:

[0067] The geological structure data of the goaf area is discretized into a three-dimensional grid, and the geological attribute parameters of each grid cell are extracted, including permeability tensor and porosity.

[0068] Based on ventilation parameters and geological property parameters, the Darcy equation is solved to obtain the first result. The ventilation parameters include gas pressure.

[0069] A gas diffusion model is established based on the first result and the diffusion effect.

[0070] In this embodiment, geological structure data of the goaf is acquired using technologies such as Geographic Information System (GIS) and 3D laser scanning, including the spatial morphology, rock strata distribution, and fracture development of the goaf. A 3D geological model is then constructed based on this data. For example, the goaf is scanned using 3D laser scanning technology to obtain point cloud data, which is then converted into a 3D solid model using specialized software.

[0071] This embodiment employs the finite element method or finite volume method to discretize the three-dimensional geological model into a mesh, dividing the goaf into numerous small three-dimensional mesh units. The mesh size and density are adjusted according to the complexity of the geological structure of the goaf and the required computational accuracy. In areas with complex geological structures and well-developed fractures, the mesh is densified to improve computational accuracy; in areas with relatively simple geological structures, the mesh size is appropriately increased to reduce computational load. For each mesh unit, its geological property parameters—permeability tensor and porosity—are extracted.

[0072] This embodiment establishes a Darcy equation model suitable for gas flow in goaf areas based on ventilation parameters (such as gas pressure, which can be obtained in real time by pressure sensors at different locations in the goaf area) and extracted geological attribute parameters (permeability tensor and porosity).

[0073]

[0074] in, Here, k is the Darcy velocity, i.e., the gas seepage velocity; μ is the permeability tensor; and μ is the gas dynamic viscosity. This represents the pressure gradient.

[0075] In this embodiment, numerical calculation methods (such as the finite element method and the finite difference method) are used to solve the Darcy equation. The boundary conditions of the goaf (such as the gas pressure and flow rate at the air inlet and the pressure at the air outlet) and the initial conditions (such as the gas pressure and concentration of each grid cell at the initial moment) are substituted into the equation. Through iterative calculation, the gas seepage velocity of each grid cell at different times is solved, which is the first result.

[0076]

[0077] in, Where is porosity, t is time, c is gas concentration, D is effective diffusion coefficient tensor (including molecular diffusion and mechanical dispersion), and S is source term (such as gas emission). The gas concentration c is due to the velocity field. If the net outflow is positive, the gas in that region diffuses outward; if it is negative, the gas accumulates there.

[0078] In one embodiment of this application,

[0079] The target monitoring strategy is determined based on the deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix, including:

[0080] The gas concentration matrix includes concentration data for various gases, the gas concentration prediction matrix includes concentration prediction data for various gases, and the deviation coefficient matrix includes multiple deviation coefficients, each of which is the difference between the gas concentration data and the corresponding gas concentration prediction data.

[0081] For each gas:

[0082] In response to the fact that the deviation coefficient between the gas concentration data and the corresponding gas concentration prediction data is less than or equal to a first threshold, a target monitoring strategy is determined from multiple standard monitoring strategies.

[0083] In response to the deviation coefficient between the gas concentration data and the corresponding gas concentration prediction data being greater than a first threshold and less than or equal to a second threshold, a first monitoring strategy is determined from multiple standard monitoring strategies, and the monitoring frequency of the sensor in the first monitoring strategy is adjusted based on a preset first value to obtain the target monitoring strategy.

[0084] If the deviation coefficient between the gas concentration data and the corresponding gas concentration prediction data is greater than the second threshold, an emergency monitoring strategy is selected, and the emergency monitoring strategy is used as the target monitoring strategy.

[0085] The second threshold is greater than the first threshold.

[0086] In this embodiment, the gas concentration matrix covers the actual concentration data of various gases (such as carbon monoxide, methane, oxygen, etc.) at different times and spatial locations; the gas concentration prediction matrix is ​​the predicted concentration data of these gases at the same time and spatial location calculated by the gas diffusion model; the deviation coefficient matrix consists of multiple deviation coefficients, each of which is the difference between the actual concentration data of a certain gas and the corresponding predicted concentration data.

[0087] In this embodiment, when the deviation coefficient between the concentration data of a certain gas and the corresponding predicted concentration data is less than or equal to a first threshold, it indicates that the actual gas concentration is close to the predicted concentration, and the gas concentration change is within a predictable and normal range. At this time, a suitable strategy is selected as the target monitoring strategy from a set of pre-defined standard monitoring strategies. Standard monitoring strategies are typically formulated based on the routine monitoring needs of the goaf area, such as collecting data from all sensors at fixed time intervals (e.g., once per hour) and conducting regular manual inspections. The first threshold is a value pre-set based on the accuracy requirements of gas monitoring and the actual conditions of the goaf area.

[0088] In this embodiment, when the deviation coefficient is between the first threshold and the second threshold, it indicates that the gas concentration has undergone a certain degree of abnormal change, but is still within a controllable range. At this time, a relatively strict first monitoring strategy is selected from multiple standard monitoring strategies. The monitoring frequency of the sensor in the first monitoring strategy is adjusted based on a preset first value. Assuming the first value is 2, if the sensor's monitoring frequency in the first monitoring strategy is once every half hour, then the adjusted sensor's monitoring frequency becomes once every 15 minutes, thus obtaining the target monitoring strategy to more promptly capture changes in gas concentration. The second threshold is greater than the first threshold.

[0089] In this embodiment, when the deviation coefficient exceeds the second threshold, it indicates a significant deviation between the actual and predicted gas concentration, suggesting potential hazards such as abnormal ventilation or gas leaks, requiring immediate emergency measures. In this case, a pre-defined emergency monitoring strategy is selected as the target monitoring strategy. Emergency monitoring strategies typically include significantly increasing the sensor monitoring frequency (e.g., collecting data once per minute), increasing the frequency and scope of manual inspections, and activating alarm systems to notify relevant personnel, ensuring a rapid response and handling of potential hazards.

[0090] This embodiment uses a hierarchical decision-making mechanism based on the deviation coefficient matrix to adjust the monitoring strategy according to changes in gas concentration, thereby improving the effectiveness and safety of gas monitoring in goaf areas.

[0091] In one embodiment of this application, monitoring of the goaf based on a target monitoring strategy includes:

[0092] Target monitoring indicators are determined from multiple standard monitoring indicators based on mining information and gas hazard levels in the goaf area.

[0093] Monitoring of goaf areas is conducted based on target monitoring indicators.

[0094] In this embodiment, the current mining progress of the goaf is obtained, identifying the areas currently being mined, the areas that have been mined out, and the areas to be mined. For example, through the mine mining plan and real-time mining records, it is determined that at a certain moment, area A in the goaf is undergoing mining operations, area B has been mined out and is in a closed state, and area C is the target area for the next stage of mining. The gas generation and distribution characteristics differ in different mining stages and areas. Areas currently being mined will release more methane and other gases due to rock fracturing and mechanical disturbance; while closed areas will experience gas accumulation.

[0095] In this embodiment, the hazard level of each gas is assessed based on the gas concentration matrix and deviation coefficient matrix, combined with the hazard characteristics of different gases (such as the flammability and explosiveness of methane, the toxicity of carbon monoxide, etc.); the overall gas hazard level of the goaf is determined by combining the hazard levels of each gas.

[0096] This embodiment utilizes a gas diffusion model and actual monitoring data to determine the diffusion range and speed of hazardous gases. If a hazardous gas rapidly diffuses to a large area within a short period, it indicates a high level of hazard. For example, when methane rapidly diffuses into multiple roadways under poor ventilation conditions, more stringent monitoring measures are required.

[0097] In this embodiment, the standard monitoring index library is a pre-established index library containing a variety of standard monitoring indicators, sensor numbers, gas concentration ranges, etc.; these standard monitoring indicators are formulated according to different goaf conditions and safety requirements.

[0098] In one embodiment of this application, the standard monitoring indicator includes: a standard monitoring device number and a standard data range; the target monitoring indicator includes: a target monitoring device number and a target data range.

[0099] Target monitoring indicators were determined from multiple standard monitoring indicators based on mining information and gas hazard levels in the goaf, including:

[0100] The target monitoring device number is determined from multiple standard monitoring devices based on mining information from the goaf area;

[0101] The target data interval is determined from multiple standard data intervals based on mining information and gas hazard levels in the goaf area;

[0102] The target monitoring equipment number and the target data range are used as target monitoring indicators.

[0103] In this embodiment, based on the goaf mining design drawings and real-time mining progress, the goaf is divided into different functional areas, such as the mining operation area, the preparatory area to be mined, and the closed goaf. For example, according to the mining plan, the current operation area is located in the eastern part of the goaf, where the rock strata are fractured due to continuous mining activities, resulting in a high risk of gas release; while the western closed area will have the problem of gas accumulation.

[0104] Analyze the characteristics of mining activities in each area, including mining technology (such as fully mechanized mining and conventional mining), equipment operation (start-up and shutdown times and workload of equipment such as coal mining machines and conveyors), and personnel distribution. For example, in fully mechanized mining areas, the frequent operation of large machinery can cause significant disturbance to the surrounding gas flow, and the friction between the equipment can generate heat, increasing the risk of flammable gases.

[0105] In this embodiment, based on the established correspondence between standard monitoring equipment numbers and goaf areas, each standard monitoring equipment number is selected to correspond to a specific monitoring location and function. For example, the equipment numbered S-001 is a gas concentration sensor, deployed near the air intake to monitor the gas content in the fresh air; the equipment numbered S-010 is a carbon monoxide sensor, located in the return airway of the working face, mainly monitoring the carbon monoxide concentration generated during operations. This example can select suitable equipment from the standard monitoring equipment based on the characteristics and risk level of the mining area. For high-risk mining areas, high-precision, fast-response equipment, such as gas sensors with real-time continuous monitoring capabilities, is prioritized, and the number of such devices is increased; while in closed goaf areas, the number of devices is reduced, retaining monitoring equipment for key gases (such as oxygen and carbon dioxide) to ensure timely detection of abnormal gas accumulation. The determined equipment number is the target monitoring equipment number.

[0106] In this embodiment, the trends of gas generation and diffusion are assessed by combining information such as the intensity and progress of mining activities and ventilation conditions. For example, when the mining speed increases, the amount of gas such as methane will increase significantly; if the ventilation system malfunctions or is not adjusted, gas accumulation will occur, thereby increasing the hazard level.

[0107] In this embodiment, gas hazard levels are classified according to the characteristics and hazard thresholds of different gases. Taking methane as an example, its hazard levels are divided into three levels: low (concentration < 0.5%), medium (0.5% ≤ concentration < 1%), and high (concentration ≥ 1%). Carbon monoxide is divided into safe (concentration < 24 ppm), warning (24 ppm ≤ concentration < 50 ppm), and dangerous (concentration ≥ 50 ppm).

[0108] In this embodiment, the standard data range is a pre-set normal data range and alarm threshold range for different monitoring devices and gas types. This embodiment also dynamically adjusts the standard data range based on mining information and gas hazard levels. In high-risk areas, the data range is narrowed to lower warning and alarm thresholds, enabling more timely detection of gas anomalies; while in low-risk areas, the data range is widened to reduce false alarms. The adjusted data range is the target data range.

[0109] Corresponding to the mine goaf gas monitoring method in the above embodiment, Figure 2 This is a structural block diagram of a gas monitoring device for goaf areas in a mine, provided as an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The gas monitoring device 20 for the goaf area of ​​the mine includes: a matrix generation module 21, a prediction matrix module 22, a strategy determination module 23, and a gas monitoring module 24.

[0110] Among them, the matrix generation module 21 is used to acquire gas data collected by sensors set in different areas of the goaf, and generate a gas concentration matrix with temporal and spatial correlation based on the gas data;

[0111] Prediction matrix module 22 is used to establish a gas diffusion model based on the geological structure data and ventilation parameters of the goaf. The gas data is input into the gas diffusion model to calculate the gas concentration prediction matrix of the goaf.

[0112] Strategy determination module 23 is used to determine the target monitoring strategy based on the deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix;

[0113] Gas monitoring module 24 is used to monitor the goaf based on the target monitoring strategy.

[0114] In one embodiment of this application, the matrix generation module 21 is specifically used for:

[0115] The gas data is segmented according to the first time window to generate a time series matrix;

[0116] Construct an adjacency matrix based on the spatial topological relationships between the deployment locations of all sensors;

[0117] The gas concentration matrix is ​​obtained by fusing the time series matrix and the adjacency matrix through a spatiotemporal graph convolutional network.

[0118] In one embodiment of this application, the matrix generation module 21 is specifically used for:

[0119] The initial time window length is calculated based on the operating parameters of the ventilation fans installed in the goaf. The operating parameters include the ventilation fan start-stop cycle, the average wind speed in the goaf, and the gas diffusion time constant.

[0120] The periodic characteristics of gas concentration fluctuations in historical gas data are extracted, and the period corresponding to the dominant frequency in the periodic characteristics is identified by the Fourier transform algorithm as the window adjustment factor.

[0121] The first time window is obtained by weighting the initial time window length and the window adjustment factor.

[0122] The gas data is segmented according to the first time window to generate a time series matrix.

[0123] In one embodiment of this application, the prediction matrix module 22 is specifically used for:

[0124] The geological structure data of the goaf area is discretized into a three-dimensional grid, and the geological attribute parameters of each grid cell are extracted, including permeability tensor and porosity.

[0125] Based on ventilation parameters and geological property parameters, the Darcy equation is solved to obtain the first result. The ventilation parameters include gas pressure.

[0126] A gas diffusion model was established based on the first result and the diffusion effect.

[0127] In one embodiment of this application, the strategy determination module 23 is specifically used for:

[0128] The gas concentration matrix includes concentration data for various gases, the gas concentration prediction matrix includes concentration prediction data for various gases, and the deviation coefficient matrix includes multiple deviation coefficients, each of which is the difference between the gas concentration data and the corresponding gas concentration prediction data.

[0129] For each gas:

[0130] In response to the fact that the deviation coefficient between the gas concentration data and the corresponding gas concentration prediction data is less than or equal to a first threshold, a target monitoring strategy is determined from multiple standard monitoring strategies.

[0131] In response to the deviation coefficient between the gas concentration data and the corresponding gas concentration prediction data being greater than a first threshold and less than or equal to a second threshold, a first monitoring strategy is determined from multiple standard monitoring strategies, and the monitoring frequency of the sensor in the first monitoring strategy is adjusted based on a preset first value to obtain the target monitoring strategy.

[0132] If the deviation coefficient between the gas concentration data and the corresponding gas concentration prediction data is greater than the second threshold, an emergency monitoring strategy is selected, and the emergency monitoring strategy is used as the target monitoring strategy.

[0133] The second threshold is greater than the first threshold.

[0134] In one embodiment of this application, the gas monitoring module 24 is specifically used for:

[0135] Target monitoring indicators are determined from multiple standard monitoring indicators based on mining information and gas hazard levels in the goaf area.

[0136] Monitoring of goaf areas is conducted based on target monitoring indicators.

[0137] In one embodiment of this application, the gas monitoring module 24 is specifically used for:

[0138] Standard monitoring indicators include: standard monitoring equipment number and standard data range; target monitoring indicators include: target monitoring equipment number and target data range.

[0139] Target monitoring indicators were determined from multiple standard monitoring indicators based on mining information and gas hazard levels in the goaf, including:

[0140] The target monitoring device number is determined from multiple standard monitoring devices based on mining information from the goaf area;

[0141] The target data interval is determined from multiple standard data intervals based on mining information and gas hazard levels in the goaf area;

[0142] The target monitoring equipment number and the target data range are used as target monitoring indicators.

[0143] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 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 the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the matrix generation module 21, prediction matrix module 22, strategy determination module 23, and gas monitoring module 24 are shown.

[0144] 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.

[0145] 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.

[0146] 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 device type information.

[0147] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation methods described in the first and second embodiments of the mine goaf gas monitoring method provided in the embodiments of this application, or they can execute the implementation methods of the electronic devices described in the embodiments of this application, which will not be repeated here.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0153] 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.

[0154] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0155] 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 monitoring a mine goaf for gas, characterised by, The method comprises: acquiring gas data collected by sensors arranged in different areas of the goaf, and generating a gas concentration matrix with time and space correlation based on the gas data; wherein the length of an initial time window is calculated according to operating parameters of a ventilator arranged in the goaf, the operating parameters including a ventilator start-stop cycle, an average wind speed in the goaf, and a gas diffusion time constant; extracting periodic characteristics of gas concentration fluctuations in historical gas data, and taking a period corresponding to a dominant frequency in the periodic characteristics identified by a Fourier transform algorithm as a window adjustment factor; performing weighted calculation on the initial time window length and the window adjustment factor to obtain a first time window; segmenting the gas data according to the first time window to generate a time series matrix; constructing an adjacency matrix according to the spatial topological relationship between the deployment positions of all sensors; fusing the time series matrix and the adjacency matrix through a spatio-temporal graph convolution network to obtain a gas concentration matrix; establishing a gas diffusion model based on geological structure data and ventilation parameters of the goaf, including: performing three-dimensional grid discretization processing on the geological structure data of the goaf, and extracting geological attribute parameters of each grid unit, including permeability tensor and porosity; solving the Darcy equation according to the ventilation parameters and the geological attribute parameters to obtain a first result, the ventilation parameters including gas pressure; establishing a gas diffusion model according to the first result and diffusion effect; inputting the gas data into the gas diffusion model to calculate a gas concentration prediction matrix of the goaf; determining a target monitoring strategy based on a deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix, the deviation coefficient matrix including a plurality of deviation coefficients, each deviation coefficient being a difference between the concentration data of a gas and the concentration prediction data of the corresponding gas; monitoring the goaf based on the target monitoring strategy.

2. The method of monitoring a mine gob for a gas as set forth in claim 1, wherein, The method of determining a target monitoring strategy based on a deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix comprises: the gas concentration matrix includes concentration data of a plurality of different gases, and the gas concentration prediction matrix includes concentration prediction data of a plurality of different gases, for each gas: in response to the deviation coefficient of the concentration data of a gas and the concentration prediction data of the corresponding gas being less than or equal to a first threshold value, determining a target monitoring strategy from a plurality of standard monitoring strategies; in response to the deviation coefficient of the concentration data of a gas and the concentration prediction data of the corresponding gas being greater than the first threshold value and less than or equal to a second threshold value, determining a first monitoring strategy from the plurality of standard monitoring strategies, adjusting the monitoring frequency of the sensors in the first monitoring strategy based on a preset first value to obtain a target monitoring strategy; in response to the deviation coefficient of the concentration data of a gas and the concentration prediction data of the corresponding gas being greater than the second threshold value, selecting an emergency monitoring strategy as the target monitoring strategy; the second threshold value is greater than the first threshold value.

3. The method of monitoring a mine gob for a gas as set forth in claim 1, wherein, The method of monitoring the goaf based on the target monitoring strategy comprises: determining a target monitoring indicator from a plurality of standard monitoring indicators based on mining information and gas risk levels of the goaf; Monitoring the goaf based on the target monitoring index.

4. The method of monitoring a mine void for a gas as claimed in claim 3, wherein, The standard monitoring index includes a standard monitoring device number and a standard data range, and the target monitoring index includes a target monitoring device number and a target data range. The target monitoring index is determined from the multiple standard monitoring indexes based on the goaf mining information and the gas danger level, including: The target monitoring device number is determined from the multiple standard monitoring devices based on the goaf mining information; The target data range is determined from the multiple standard data ranges based on the goaf mining information and the gas danger level; The target monitoring device number and the target data range are used as the target monitoring index.

5. A mine goaf gas monitoring device, characterized by, It includes: The matrix generation module is configured to obtain gas data collected by sensors arranged in different areas of the goaf, and generate a gas concentration matrix with time and space correlation based on the gas data; The matrix generation module is specifically configured to calculate an initial time window length according to operating parameters of a ventilator arranged in the goaf, wherein the operating parameters include a ventilator start-stop cycle, an average wind speed in the goaf, and a gas diffusion time constant; The periodic characteristics of the gas concentration fluctuation in the historical gas data are extracted, and a period corresponding to a dominant frequency identified by a Fourier transform algorithm in the periodic characteristics is taken as a window adjustment factor; The initial time window length and the window adjustment factor are weighted to obtain a first time window; The gas data are segmented according to the first time window to generate a time series matrix; An adjacency matrix is constructed according to the spatial topological relationship between the deployment positions of all sensors; The time series matrix and the adjacency matrix are fused by a spatio-temporal graph convolution network to obtain a gas concentration matrix; The prediction matrix module is configured to establish a gas diffusion model based on geological structure data and ventilation parameters of the goaf, The prediction matrix module is specifically configured to: perform three-dimensional grid discretization processing on the geological structure data of the goaf, and extract geological attribute parameters of each grid unit, including permeability tensor and porosity; solving the Darcy equation according to the ventilation parameters and the geological attribute parameters to obtain a first result, wherein the ventilation parameters include gas pressure; establishing a gas diffusion model according to the first result and diffusion effect; inputting the gas data into the gas diffusion model to obtain a gas concentration prediction matrix of the goaf; The strategy determination module is configured to determine a target monitoring strategy based on a deviation coefficient matrix of the gas concentration matrix and the gas concentration prediction matrix, wherein the deviation coefficient matrix includes multiple deviation coefficients, and each deviation coefficient is a difference between concentration data of a gas and corresponding concentration prediction data of the gas; The gas monitoring module is configured to monitor the goaf based on the target monitoring strategy.

6. 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 realize the steps of the method of any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 6. The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 4.

Images