Mining area carbon emission intelligent evaluation method and system fusing multi-source data

Abstract

The invention discloses a mining area carbon emission intelligent evaluation method and system fused with multi-source data, and particularly relates to the technical field of environment monitoring. The method comprises the following steps: acquiring historical record data of geological stress redistribution of a mining area, and extracting historical dissipation characteristic data; collecting real-time monitoring data of mining area mining activities, identifying a potential dissipation area according to historical dissipation characteristic data, and generating a distribution map; sampling the concentration of the carbon-based gas in the potential dissipation area, and predicting the dissipation flux of the carbon-based gas in the potential dissipation area in combination with the change trend of the geological stress of the mining area; analyzing the dissipation path of the carbon-based gas in the potential dissipation area according to the dissipation flux predicted value, and generating a potential dissipation path set; the overall carbon emission of the mining area is evaluated by combining the potential dissipation path set and the dissipation flux predicted value of the carbon-based gas, an evaluation result is output, hidden carbon-based gas dissipation induced by geological stress changes is effectively recognized and quantified, and the accuracy of mining area carbon emission evaluation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and more specifically, to an intelligent evaluation method and system for mine carbon emissions integrating multi-source data. Background Art

[0002] As one of the important carbon emission sources, the accurate accounting and effective control of carbon emissions in the mining industry are crucial. Traditional mine carbon emission assessment methods, especially when dealing with fugitive carbon-based gas emissions, mainly rely on direct measurement of known and centralized main gas sources or estimation based on empirical emission factors. The complex influence of the dynamic redistribution of the geological stress field caused by mining activities on the fugitive behavior of carbon-based gases in surrounding rocks and residual ore bodies is generally ignored. The existing technology lacks the ability to effectively identify, monitor, and accurately quantify the "enhanced fugitivity" indirectly induced by geological stress changes, resulting in an underestimation of the total carbon emissions in the mining area, restricting the level of carbon emission management and the effectiveness of emission reduction strategies.

[0003] To solve the above problems, a technical solution is provided now. Summary of the Invention

[0004] To overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent evaluation method and system for mine carbon emissions integrating multi-source data to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions: An intelligent evaluation method for mine carbon emissions integrating multi-source data, comprising the following steps: S1: Obtain historical record data of the redistribution of geological stress in the mining area, analyze the fugitive response characteristic parameters in the historical record data, and extract historical fugitive characteristic data; S2: Collect real-time monitoring data of mining activities in the mining area, identify potential fugitive areas induced by mining activities in the mining area according to the historical fugitive characteristic data, and generate a potential fugitive area distribution map; S3: Sample the concentration of carbon-based gases in the potential fugitive areas according to the potential fugitive area distribution map, and construct a gas concentration distribution matrix; S4: Based on the gas concentration distribution matrix, combined with the change trend of geological stress in the mining area, predict the predicted value of the fugitive flux of carbon-based gases in the potential fugitive areas; S5: Analyze the fugitive paths of carbon-based gases in the potential fugitive areas according to the predicted value of the fugitive flux, and generate a set of potential fugitive paths of carbon-based gases; S6: Combine the set of potential fugitive paths of carbon-based gases and the predicted value of the fugitive flux to evaluate the overall carbon emissions in the mining area, and output the evaluation result of mine carbon emissions.

[0006] In a preferred embodiment, S1 is specifically as follows: Calculate the difference in the surrounding rock pore structure change parameters at multiple acquisition times in the historical record data according to the time sequence to obtain the pore structure change rate; Calculate the difference in the gas permeability change parameters at multiple acquisition times in the historical record data according to the time sequence to obtain the permeability change rate; Calculate the fluctuation amplitude of the carbon-based gas desorption equilibrium change parameters across multiple acquisition times in the historical record data to obtain the desorption equilibrium change amplitude; Based on a preset threshold, screen the pore structure change rate, permeability change rate, and equilibrium change amplitude to generate historical dissipation characteristic data.

[0007] In a preferred embodiment, S2 is specifically as follows: Collect the real-time monitoring data of the mining activities in the mining area based on multiple preset monitoring points within the mining area; Synchronize and align and filter the noise of the real-time monitoring data to generate calibrated real-time monitoring data; Compare the calibrated real-time monitoring data at the same monitoring point with the historical dissipation characteristic data to determine whether the real-time monitoring data at each monitoring point exceeds the corresponding historical dissipation characteristic data; Based on the spatial coordinates of the monitoring points where the corresponding historical dissipation characteristic data is exceeded, generate a potential dissipation area distribution map.

[0008] In a preferred embodiment, S3 is specifically as follows: Divide the potential dissipation area distribution map into several sampling units according to equidistant spatial grids; Collect the carbon-based gas concentration at the center position of the sampling unit according to the preset sampling time; Generate a time series table of the carbon-based gas concentration for each sampling unit according to the sampling time, and arrange the time series table of the carbon-based gas concentration in the order of the row and column coordinates of the spatial grid; Construct a gas concentration distribution matrix according to the arranged time series table of the carbon-based gas concentration.

[0009] In a preferred embodiment, the rows of the gas concentration distribution matrix represent the row coordinates of the spatial grid, the columns of the gas concentration distribution matrix represent the column coordinates of the spatial grid, and the elements of the gas concentration distribution matrix correspond to the carbon-based gas concentration at the center position of the sampling unit.

[0010] In a preferred embodiment, S4 is specifically as follows: Pair the carbon-based gas concentration at the center position of the sampling unit in the gas concentration distribution matrix with the corresponding sampling time to obtain a carbon-based gas concentration change curve; Obtain the geological stress field change trend data covering the potential dissipation area; Based on the carbon-based gas concentration change curve and the geological stress field change trend data, construct a carbon-based gas escape flux prediction model; Predict the escape flux value of carbon-based gas in the potential escape area according to the carbon-based gas escape flux prediction model.

[0011] In a preferred embodiment, the geological stress field change trend data includes the surrounding rock stress evolution curve and the structural unit displacement data during the mining cycle.

[0012] In a preferred embodiment, S5 is specifically: Map the sampling units in the potential escape area and the adjacency relationship between sampling units into a three-dimensional node network; Assign the escape flux prediction value of the corresponding sampling unit to each node in the three-dimensional node network as the node weight; Connect the high-weight nodes to the low-weight nodes in sequence to form a set of potential escape paths of carbon-based gas.

[0013] In a preferred embodiment, S6 is specifically: Perform path traversal on each potential escape path in the set of potential escape paths of carbon-based gas, accumulate the escape flux prediction values of all sampling units, and obtain the flux accumulation value of each potential escape path; Select the potential escape path with the largest flux accumulation value as the main escape path, and extract the three-dimensional coordinates of each node in the main escape path to form a spatial trajectory data set of the main escape path; Combine the spatial trajectory data set of the main escape path with the escape flux prediction values of each sampling unit in the potential escape area to construct an overall carbon emission assessment model for the mining area; Estimate the total carbon-based gas emission amount in the potential escape area according to the overall carbon emission assessment model of the mining area, and output the carbon emission assessment result of the mining area.

[0014] On the other hand, the present invention provides an intelligent assessment system for carbon emissions in a mining area that integrates multi-source data, including: Historical analysis module: Obtain the historical record data of the geological stress redistribution in the mining area, analyze the escape response characteristic parameters in the historical record data, and extract the historical escape characteristic data; Real-time monitoring module: Collect the real-time monitoring data of the mining activities in the mining area, identify the potential escape area induced by the mining activities in the mining area according to the historical escape characteristic data, and generate a potential escape area distribution map; Concentration sampling module: Sample the carbon-based gas concentration in the potential escape area according to the potential escape area distribution map, and construct a gas concentration distribution matrix; Flux prediction module: Based on the gas concentration distribution matrix and combined with the changing trend of the geological stress in the mining area, predict the predicted value of the escape flux of carbon-based gases in the potential escape area; Path analysis module: According to the predicted value of the escape flux, analyze the escape paths of carbon-based gases in the potential escape area to generate a set of potential escape paths of carbon-based gases; Emission assessment module: Combine the set of potential escape paths of carbon-based gases and the predicted value of the escape flux to evaluate the overall carbon emissions of the mining area and output the carbon emission assessment result of the mining area.

[0015] The technical effects and advantages of an intelligent carbon emission assessment method and system for mining areas that integrates multi-source data according to the present invention: By analyzing the historical data of the redistribution of geological stress and combining the real-time monitoring data of mining activities, it is possible to identify the potential escape areas induced by mining activities in the mining area, improving the comprehensiveness of escape source identification. By sampling the concentration of carbon-based gases in the potential escape area and combining the changing trend of the geological stress in the mining area to predict the predicted value of the escape flux, the accuracy of carbon emission accounting is improved. By analyzing the set of potential escape paths and combining the predicted value of the escape flux, the overall carbon emissions of the mining area are evaluated, providing a scientific basis for formulating more targeted emission reduction measures, making the overall carbon emission assessment of the mining area more accurate, dynamic and intelligent, and effectively avoiding the underestimation of actual carbon emissions. Description of the Drawings

[0016] Figure 1 It is a schematic diagram of an intelligent carbon emission assessment method for mining areas that integrates multi-source data according to the present invention; Figure 2 It is a schematic diagram of the structure of an intelligent carbon emission assessment system for mining areas that integrates multi-source data according to the present invention. Detailed Embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1 Figure 1 An intelligent carbon emission assessment method for mining areas that integrates multi-source data according to the present invention is given, which includes the following steps: S1: Obtain the historical record data of the redistribution of geological stress in the mining area, analyze the escape response characteristic parameters in the historical record data, and extract the historical escape characteristic data; S2: Collect real-time monitoring data of mining activities in the mining area, identify potential fugitive areas induced by mining activities in the mining area according to historical fugitive characteristic data, and generate a distribution map of potential fugitive areas; S3: According to the distribution map of potential fugitive areas, sample the carbon-based gas concentration in the potential fugitive areas to construct a gas concentration distribution matrix; S4: Based on the gas concentration distribution matrix, combined with the changing trend of the geological stress in the mining area, predict the predicted value of the fugitive flux of carbon-based gas in the potential fugitive areas; S5: According to the predicted value of the fugitive flux, analyze the fugitive paths of carbon-based gas in the potential fugitive areas to generate a set of potential fugitive paths of carbon-based gas; S6: Combine the set of potential fugitive paths of carbon-based gas and the predicted value of the fugitive flux to evaluate the overall carbon emissions of the mining area and output the evaluation result of the carbon emissions of the mining area.

[0019] S1: Obtain the historical record data of the redistribution of geological stress in the mining area, analyze the fugitive response characteristic parameters in the historical record data, and extract historical fugitive characteristic data, including: Set up multiple geological monitoring devices in the geological mining area of the mining area. The layout density of the monitoring devices is determined according to the complexity of the geological structure of the mining area. For example, in areas with more complex geological structures, the number of monitoring devices is increased. The geological monitoring devices can collect in real time the stress change parameters of the geological structure in the mining area with the mining activities, such as the stress concentration degree inside the rock mass, the change characteristics of the surrounding rock stability state, the generation and expansion of internal cracks in the surrounding rock, and the change parameters of the pore structure of the surrounding rock, the change of gas permeability, and the change parameters of the desorption equilibrium of carbon-based gas, to form the historical record data of the redistribution of geological stress in the mining area.

[0020] The fugitive response characteristic parameters specifically include the change parameters of the pore structure of the surrounding rock, the change parameters of gas permeability, and the change parameters of the desorption equilibrium of carbon-based gas. Among them, the change parameters of the pore structure of the surrounding rock include the change value of the effective porosity per unit volume, the change trend of the main crack width, and the evolution record of the crack penetration rate; the change parameters of gas permeability are the change rate of the volume of fugitive gas per unit area per unit time under unit pressure difference obtained by the directional mercury intrusion penetration test or the downhole back pumping test method; the change parameters of the desorption equilibrium of carbon-based gas refer to the pressure change curve required for the gas adsorbed on the surface of the unit surrounding rock to reach desorption stability under different stress states.

[0021] Calculate the difference in the change parameters of the pore structure of the surrounding rock at multiple acquisition times in the historical record data according to the time sequence to obtain the pore structure change rate; Specifically, among the parameters of the surrounding rock pore structure change, the effective porosity data points at each historical monitoring moment are selected. According to the time sequence, the difference between the effective porosity values at two adjacent moments is calculated, and the difference is divided by the time interval between the previous moment and the next moment to obtain the porosity change rate per unit time, which is denoted as the pore structure change rate. The pore structure change rate is expressed as the volume fraction of pores increased or decreased per unit time per cubic meter of surrounding rock, with the unit of volume fraction per hour, and the spatial position of the geological unit corresponding to the pore structure change rate is recorded.

[0022] For the gas permeability change parameters at multiple acquisition moments in the historical record data, calculate the difference according to the time sequence to obtain the permeability change rate; Specifically, for the permeability change parameters, the gas escape amount measured in the unit volume of surrounding rock under the unit pressure difference in two consecutive historical monitoring time periods is extracted respectively. After taking the difference, it is divided by the time difference between the front and back time periods to obtain the permeability change rate. The permeability change rate represents the increasing or decreasing trend of the escape ability per unit time at the spatial position.

[0023] For the carbon-based gas desorption equilibrium change parameters across multiple acquisition moments in the historical record data, calculate the fluctuation amplitude to obtain the desorption equilibrium change amplitude; Specifically, the desorption equilibrium pressure values under different stress levels are extracted, and the desorption equilibrium change amplitude of the unit is represented by the difference between the maximum pressure value and the minimum pressure value of the continuous sampling points. A large desorption equilibrium change amplitude indicates more intense desorption instability and stronger gas release potential under stress disturbance.

[0024] Based on the preset threshold, screen the pore structure change rate, permeability change rate, and equilibrium change amplitude to generate historical escape characteristic data; Specifically, preset the thresholds for the surrounding rock pore structure change rate, gas permeability change rate, and carbon-based gas desorption equilibrium change amplitude respectively; the thresholds for the surrounding rock pore structure change rate, gas permeability change rate, and carbon-based gas desorption equilibrium change amplitude are determined according to the actual geological conditions of the mining area, historical statistical analysis data, and expert evaluation. Screen the surrounding rock pore structure change rate, gas permeability change rate, and carbon-based gas desorption equilibrium change amplitude respectively according to the corresponding preset thresholds, and mark the surrounding rock pore structure change rate, gas permeability change rate, and carbon-based gas desorption equilibrium change amplitude that are greater than or equal to their respective preset thresholds as historical escape characteristic data.

[0025] S2: Collect the real-time monitoring data of the mining activities in the mining area. According to the historical escape characteristic data, identify the potential escape areas induced by the mining activities in the mining area, and generate a potential escape area distribution map, including: Based on multiple preset monitoring points inside the mining area, collect the real-time monitoring data of the mining activities in the mining area; Specifically, several real-time monitoring points are established within the mining area. The locations of the real-time monitoring points are determined in accordance with the geological structure characteristics, mining layout, and historical fugitive risk distribution characteristics of the mining area. For example, more monitoring points are set in areas with concentrated geological stress in the mining area, areas where carbon-based gas fugitives frequently occurred in the past, and areas with intensive mine exploitation activities to effectively improve the spatial coverage of monitoring data. Each real-time monitoring point is equipped with the same type of real-time data monitoring device, which is used to continuously collect various real-time monitoring data closely related to the mining activities in the mining area, such as rock mass stress parameter data, gas concentration data, surrounding rock pore structure data, and gas permeability data, etc.

[0026] Synchronize and align the real-time monitoring data and perform noise filtering to generate calibrated real-time monitoring data; Specifically, the synchronization and alignment process adopts a unified timestamp marking method. For example, a high-precision clock provided by the Global Positioning System is used for data synchronization. The data collected at each real-time monitoring point is unified in time series according to the unified timestamp to ensure that the real-time monitoring data collected at each monitoring point strictly corresponds in time and eliminate the time lag problem existing between different monitoring devices. For the real-time monitoring data after synchronization processing, a noise filtering algorithm is used, such as the Kalman filtering algorithm or the wavelet filtering algorithm. By setting the filtering parameters of the filtering algorithm, the environmental noise and abnormal fluctuation data in the real-time monitoring data are removed to generate calibrated real-time monitoring data.

[0027] Compare the calibrated real-time monitoring data at the same monitoring point with the historical fugitive characteristic data to determine whether the real-time monitoring data at each monitoring point exceeds the corresponding historical fugitive characteristic data; Specifically, for each real-time monitoring point, the corresponding monitoring parameters in the calibrated real-time monitoring data are compared respectively, such as the monitored real-time change rate of the surrounding rock pore structure, the real-time change rate of gas permeability, and the real-time change amplitude of the carbon-based gas desorption equilibrium, to observe whether the above parameters exceed the historical fugitive characteristic data. During the comparison process, if the real-time monitoring parameter is greater than or equal to the corresponding historical fugitive characteristic data, mark this real-time monitoring point as a potential fugitive risk point; otherwise, it is determined as a non-potential fugitive risk point.

[0028] Generate a potential fugitive area distribution map based on the spatial coordinates of the monitoring points that exceed the corresponding historical fugitive characteristic data; Specifically, for all real-time monitoring points marked as potential fugitive risk points, based on the spatial position coordinates of the monitoring points, through a spatial data interpolation algorithm, such as the Kriging interpolation method, spatial interpolation operations are carried out based on the monitoring point coordinates to infer and mark the boundary range and distribution of the potential fugitive area. Through spatial data processing techniques, such as the spatial analysis tool of the geographic information system, the identified potential fugitive risk points are connected to form a potential fugitive area distribution map. The potential fugitive area distribution map can intuitively display the spatial positions where the mining activities in the mining area induce the fugitive of carbon-based gases.

[0029] S3: According to the potential fugitive area distribution map, sample the carbon-based gas concentration in the potential fugitive area to construct a gas concentration distribution matrix, including: Divide the potential fugitive area distribution map into several sampling units according to equidistant spatial grids; Specifically, according to the potential fugitive area distribution map, use the spatial grid division method to perform equidistant spatial grid division on the distribution map. Select an appropriate spatial grid size, and the size of the grid is determined according to the actual area of the mining area, the scope of mining activities, and the spatial characteristics of the fugitive of carbon-based gases. Usually, larger grids are used in larger areas of the mining area to ensure better spatial coverage of the sampling data; smaller grids are used in areas where the fugitive of carbon-based gases is more concentrated to improve spatial resolution and sampling accuracy. Through equidistant spatial grid division, the potential fugitive area distribution map is divided into multiple equidistant sampling units, and the carbon-based gas concentration data within a certain area is represented in each sampling unit.

[0030] Collect the carbon-based gas concentration at the center position of the sampling unit according to the preset sampling time; Specifically, within each sampling unit, select a center position to collect the carbon-based gas concentration. The sampling point is usually located at the geometric center of each sampling unit. For example, if a regular rectangular or square grid is used, the sampling point is located at the grid center position. At each predetermined sampling time, through the gas concentration monitoring device installed at the monitoring point, regularly collect the carbon-based gas concentration data at the center position of each sampling unit. The sampling time can be set according to the actual situation of the mining area, and usually, fixed-time sampling or periodic sampling methods are adopted, such as sampling the gas concentration once per hour or every half hour.

[0031] Generate a time series table of carbon-based gas concentration for each sampling unit according to the sampling time, and arrange the time series table of carbon-based gas concentration in the order of the row and column coordinates of the spatial grid; Specifically, for the carbon-based gas concentration data at the central position of each sampling unit collected, a time series list of carbon-based gas concentrations will be generated for each sampling unit at each sampling moment. The time series list of carbon-based gas concentrations lists the gas concentration data at the central position of each sampling unit at different sampling moments in chronological order, and can reflect the variation law of the carbon-based gas concentration over time. The time series lists of all sampling units will be arranged in the order of the row and column coordinates of the spatial grid. For example, after the grid is divided into several rows and columns, the time series list of each sampling unit is sorted according to the row and column coordinates of the grid.

[0032] Construct a gas concentration distribution matrix based on the arranged time series list of carbon-based gas concentrations; Specifically, the rows of the gas concentration distribution matrix represent the row coordinates of the spatial grid, the columns of the gas concentration distribution matrix represent the column coordinates of the spatial grid, and the elements of the gas concentration distribution matrix correspond to the carbon-based gas concentrations at the central positions of the sampling units. For example, if the mining area is divided into a spatial grid of 5 rows and 4 columns, the gas concentration distribution matrix will have 5 rows and 4 columns.

[0033] S4: Based on the gas concentration distribution matrix, combined with the changing trend of the geological stress in the mining area, predict the predicted value of the carbon-based gas escape flux in the potential escape area, including: Pair the carbon-based gas concentration at the central position of the sampling unit in the gas concentration distribution matrix with the corresponding sampling moment to obtain a carbon-based gas concentration change curve; Specifically, pair the carbon-based gas concentration values corresponding to the central positions of each sampling unit in the gas concentration distribution matrix with their respective corresponding sampling moments one by one to obtain a continuous data set of the carbon-based gas concentration changing with time at the central position of each sampling unit, that is, a carbon-based gas concentration change curve. The horizontal axis of the carbon-based gas concentration change curve represents continuous sampling moments, and the vertical axis represents the carbon-based gas concentration corresponding to each moment, which can completely record the trend characteristics of the gas concentration changing with the sampling moment.

[0034] Obtain the data on the changing trend of the geological stress field covering the potential escape area; Specifically, through the geological monitoring devices in the mining area, collect and obtain the data on the changing trend of the geological stress field covering the potential escape area. The data on the changing trend of the geological stress field includes: the evolution curve of the surrounding rock stress during the mining cycle and the displacement data of the structural units in the mining area. Among them, the evolution curve of the surrounding rock stress describes the changing trend of the internal stress state of the surrounding rock caused by the removal of the ore body during the mining activities in the mining area; the displacement data of the structural units specifically describes the characteristics of the spatial displacement changes of different structural units in the mining area (such as roadway support structures, goaf boundaries, rock contact interfaces, etc.) under the influence of mining activities. The above data are all obtained by high-precision geological stress sensors and displacement sensors to ensure the accuracy and reliability of the monitoring data.

[0035] Based on the carbon-based gas concentration change curve and the geological stress field change trend data, a prediction model for the carbon-based gas escape flux is constructed; Specifically, taking the carbon-based gas concentration change curve and the geological stress field change trend data as inputs, a prediction model for the carbon-based gas escape flux is established. For example, a neural network model based on time series can be selected, including a long short-term memory network model or a recurrent neural network model, and the mapping relationship between the carbon-based gas escape flux and the gas concentration change and geological stress change is learned and determined through the training of historical data. When establishing the prediction model, the historical data of the carbon-based gas concentration change curve and the geological stress field data are used as input variables at the input end of the model, and the carbon-based gas escape flux values of each sampling unit are predicted at the output end. According to the geological structure characteristics and data characteristics of different regions in the mining area, the training data of the prediction model are subjected to necessary normalization or standardization processing to improve the model training effect and prediction accuracy.

[0036] The prediction model is trained and its parameters are optimized. The training process is realized by the method of dividing the training set and the validation set. The model training method adopts a cross-validation mechanism, and the optimization is carried out by gradually adjusting the structural parameters of the model (such as the number of hidden layers, the number of nodes) and the training hyperparameters (such as the learning rate, the number of iterations) until the model prediction error meets the requirements of the mining area carbon emission prediction accuracy. The model optimization goal is usually to minimize the prediction error. For example, the mean absolute error or the mean square error is used as the objective function for model optimization, and it is optimized repeatedly through an iterative method to ensure the high precision and stability of the prediction model.

[0037] Predict the carbon-based gas escape flux prediction value in the potential escape area according to the carbon-based gas escape flux prediction model; Specifically, the optimized carbon-based gas escape flux prediction model is used to predict the potential escape area, and the carbon-based gas escape flux prediction values at the central positions of each spatial grid unit in the potential escape area are obtained. The prediction value reflects the level of carbon-based gas escape flux that may occur in different position areas during the mining process of the mining area.

[0038] S5: According to the escape flux prediction value, analyze the escape path of the carbon-based gas in the potential escape area, and generate a set of potential escape paths of the carbon-based gas, including: Map the sampling units and the adjacency relationships between sampling units in the potential escape area into a three-dimensional node network; Specifically, according to the potential fugitive area, all sampling units within the area and their spatial adjacency relationships are detailedly mapped to form a three-dimensional node network. The center position of each sampling unit after spatial grid division corresponds to a node in the three-dimensional space. The position coordinates of each node are recorded based on the actual position of the sampling unit in the mining area space. The connection relationships between the corresponding nodes are determined by the spatial geometric adjacency relationships of adjacent sampling units, that is, if there is a common contact position between the boundary or vertex of any unit in the spatial grid and the boundary or vertex of the adjacent unit, it is regarded as an adjacency relationship, thus constructing a three-dimensional node network structure representing the spatial positions and mutual relationships of sampling units in the three-dimensional space.

[0039] Assign the fugitive flux prediction value of the corresponding sampling unit to each node in the three-dimensional node network as the node weight; Specifically, based on the carbon-based gas fugitive flux prediction model, calculate and determine the carbon-based gas fugitive flux prediction value at the center position of each sampling unit during the prediction period. The fugitive flux prediction value of each node is the node weight in the node network, and the node weight represents the intensity level of possible carbon-based gas fugitive in the corresponding sampling unit. The magnitude of the node weight is expressed as the predicted value of the fugitive flux. For example, a node with a larger predicted value indicates a higher potential intensity of carbon-based gas fugitive. By assigning the node weight to the corresponding node, each node in the three-dimensional node network has the fugitive flux prediction feature.

[0040] Connect the high-weight nodes to the low-weight nodes in sequence to form a set of potential fugitive paths of carbon-based gas; Specifically, after constructing the complete node network and determining the weights of each node, according to the magnitude relationship of the fugitive flux prediction values, adopt the strategy of connecting from the high-weight nodes to the low-weight nodes in sequence to form a set of potential fugitive paths. Starting from the node with the highest fugitive flux prediction value, taking this node as the starting point, along the spatial adjacency relationships in the three-dimensional node network, connect to the node with the lowest fugitive flux prediction value step by step in sequence, and the connection process always maintains the direction from the node with a high fugitive flux prediction value to the node with a low fugitive flux prediction value.

[0041] S6: Combine the set of potential fugitive paths of carbon-based gas and the fugitive flux prediction values to evaluate the overall carbon emissions of the mining area, and output the mining area carbon emission evaluation results, including: Perform path traversal on each potential fugitive path in the set of potential fugitive paths of carbon-based gas, accumulate the fugitive flux prediction values of all sampling units, and obtain the flux accumulation value of each potential fugitive path; Specifically, according to the set of potential escape paths of carbon-based gases, each specific potential escape path in the set is traversed. The path traversal process is to successively accumulate the predicted escape fluxes of the sampling units corresponding to each node on the path according to the connection order of spatially adjacent nodes, that is, adding the predicted escape flux of the first node to the predicted escape flux of the next node, and gradually completing the summation of the predicted escape fluxes of all nodes on this path to obtain the cumulative flux value corresponding to each potential escape path. The cumulative flux value can intuitively reflect the overall carbon-based gas escape intensity on this path.

[0042] Select the potential escape path with the largest cumulative flux value as the main escape path, and extract the three-dimensional coordinates of each node in the main escape path to form the spatial trajectory dataset of the main escape path; Specifically, selecting the path with the largest cumulative flux value from the cumulative flux values of all potential escape paths as the main escape path means that this path may be the main channel with the most significant carbon-based gas escape during the mining process in the mining area and is more representative. After the main escape path is determined, extract the spatial three-dimensional coordinates of all nodes on this path to form the spatial trajectory dataset of the main escape path. The spatial trajectory dataset represents the specific position and direction of the main escape path in the mining area space and can intuitively and accurately reflect the spatial trajectory of carbon-based gas escape.

[0043] Combine the spatial trajectory dataset of the main escape path with the predicted escape fluxes of each sampling unit in the potential escape area to construct an overall carbon emission assessment model for the mining area; Specifically, based on the spatial trajectory dataset of the main escape path, combined with the predicted escape fluxes of each sampling unit in the potential escape area, an overall carbon emission assessment model for the mining area is constructed. The model construction process includes the following steps: spatially correlate the spatial trajectory coordinates of the nodes on the main escape path with the predicted escape fluxes corresponding to the nodes; also incorporate the predicted escape fluxes of other sampling units in the potential escape area outside the path into the model to form an overall carbon emission spatial database for the mining area; based on spatial interpolation methods and spatial statistical methods, such as spatial autocorrelation analysis, fuse the escape flux data of the nodes on the path and the escape flux data of the sampling units outside the path to constitute a complete assessment model that can characterize the spatial distribution of the overall carbon emissions in the mining area. The overall carbon emission assessment model for the mining area not only reflects the high escape intensity of the main escape path but also reflects the spatial distribution of the escape fluxes in the area outside the main escape path.

[0044] According to the overall carbon emission assessment model for the mining area, estimate the total carbon-based gas emissions in the potential escape area and output the mining area carbon emission assessment result; Specifically, using the overall carbon emission assessment model of the mining area, the total carbon-based gas emissions in the potential fugitive area are estimated through spatial integration and calculation. Specifically: according to the predicted fugitive flux values of each sampling unit in the model, combined with the spatial area of the sampling unit, by multiplying the predicted fugitive flux value of each sampling unit by its corresponding spatial area or volume, the total unit fugitive flux is obtained; the total unit fugitive fluxes of all sampling units are accumulated and summed to obtain an estimated value of the total carbon-based gas emissions in the entire potential fugitive area.

[0045] The estimated total carbon-based gas emissions of the entire mining area are clearly output as the mining area carbon emission assessment result. The output assessment result is represented numerically, such as the total annual carbon emissions, the total monthly carbon emissions, or the total carbon emissions during a specific mining activity period. At the same time, a map of the spatial distribution of mining area carbon emissions is also output to clearly and intuitively display the overall spatial distribution of carbon emissions within the mining area.

[0046] Example 2 The difference between Example 2 and Example 1 of the present invention is that this example introduces an intelligent assessment system for mining area carbon emissions that integrates multi-source data.

[0047] Figure 2 The structural schematic diagram of an intelligent assessment system for mining area carbon emissions that integrates multi-source data according to the present invention is given. An intelligent assessment system for mining area carbon emissions that integrates multi-source data includes: Historical analysis module: Obtain the historical record data of the redistribution of geological stress in the mining area, analyze the fugitive response characteristic parameters in the historical record data, and extract historical fugitive characteristic data; Real-time monitoring module: Collect the real-time monitoring data of the mining activities in the mining area, identify the potential fugitive areas induced by the mining activities in the mining area according to the historical fugitive characteristic data, and generate a distribution map of potential fugitive areas; Concentration sampling module: According to the distribution map of potential fugitive areas, sample the carbon-based gas concentration in the potential fugitive areas to construct a gas concentration distribution matrix; Flux prediction module: Based on the gas concentration distribution matrix, combined with the changing trend of the geological stress in the mining area, predict the predicted fugitive flux values of carbon-based gases in the potential fugitive areas; Path analysis module: According to the predicted fugitive flux values, analyze the fugitive paths of carbon-based gases in the potential fugitive areas to generate a set of potential fugitive paths of carbon-based gases; Emission assessment module: Combine the set of potential fugitive paths of carbon-based gases and the predicted fugitive flux values to evaluate the overall carbon emissions of the mining area and output the mining area carbon emission assessment result.

[0048] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulations to get a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0049] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0050] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0051] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0052] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the devices or modules can be in electrical, mechanical, or other forms.

[0053] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0054] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0055] If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0056] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0057] Finally, the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent evaluation method for mine carbon emissions integrating multi-source data, characterized in that, It includes the following steps: S1: Obtain the historical record data of the redistribution of geological stress in the mining area, analyze the dissipation response characteristic parameters in the historical record data, and extract the historical dissipation characteristic data; S2: Collect the real-time monitoring data of the mining activities in the mining area, identify the potential dissipation areas induced by the mining activities in the mining area according to the historical dissipation characteristic data, and generate a potential dissipation area distribution map; S3: According to the potential dissipation area distribution map, sample the concentration of carbon-based gases in the potential dissipation areas, and construct a gas concentration distribution matrix; S4: Based on the gas concentration distribution matrix, combined with the change trend of the geological stress in the mining area, predict the predicted value of the dissipation flux of carbon-based gases in the potential dissipation areas; S5: According to the predicted value of the dissipation flux, analyze the dissipation paths of carbon-based gases in the potential dissipation areas, and generate a set of potential dissipation paths of carbon-based gases; S6: Combine the set of potential dissipation paths of carbon-based gases and the predicted value of the dissipation flux, evaluate the overall carbon emissions of the mining area, and output the carbon emission assessment result of the mining area.

2. The intelligent evaluation method for mine area carbon emissions integrating multi-source data according to claim 1, wherein S1 specifically is: Calculate the difference in the parameters of the surrounding rock pore structure change at multiple acquisition times in the historical record data according to the time sequence to obtain the pore structure change rate; Calculate the difference in the gas permeability change parameters at multiple acquisition times in the historical record data according to the time sequence to obtain the permeability change rate; Calculate the fluctuation amplitude of the carbon-based gas desorption equilibrium change parameters across multiple acquisition times in the historical record data to obtain the desorption equilibrium change amplitude; Based on a preset threshold, screen the pore structure change rate, permeability change rate, and equilibrium change amplitude to generate historical dissipation characteristic data.

3. The intelligent evaluation method for mine carbon emissions integrating multi-source data according to claim 2, characterized in that, S2 specifically is: Based on multiple preset monitoring points inside the mining area, collect the real-time monitoring data of the mining activities in the mining area; Synchronize and align and filter the noise of the real-time monitoring data to generate calibrated real-time monitoring data; Compare the calibrated real-time monitoring data at the same monitoring point with the historical dissipation characteristic data to determine whether the real-time monitoring data at each monitoring point exceeds the corresponding historical dissipation characteristic data; Based on the spatial coordinates of the monitoring points where the corresponding historical dissipation characteristic data is exceeded, generate a potential dissipation area distribution map.

4. The intelligent evaluation method for mine carbon emissions integrating multi-source data according to claim 3, characterized in that, S3 specifically is: Divide the potential dissipation area distribution map into several sampling units according to an equidistant spatial grid; Collect the concentration of carbon-based gases at the center position of the sampling unit according to the preset sampling time; Generate a time series table of the carbon-based gas concentration for each sampling unit according to the sampling time, and arrange the time series table of the carbon-based gas concentration in the order of the row and column coordinates of the spatial grid; Construct a gas concentration distribution matrix according to the arranged time series table of the carbon-based gas concentration.

5. The intelligent evaluation method for mine area carbon emissions integrating multi-source data according to claim 4, characterized in that The rows of the gas concentration distribution matrix represent the row coordinates of the spatial grid, the columns of the gas concentration distribution matrix represent the column coordinates of the spatial grid, and the elements of the gas concentration distribution matrix correspond to the concentration of carbon-based gases at the center position of the sampling unit.

6. The intelligent evaluation method for mine carbon emissions integrating multi-source data according to claim 5, characterized in that, S4 specifically is: Pair the concentration of carbon-based gases at the center position of the sampling unit in the gas concentration distribution matrix with the corresponding sampling time to obtain a carbon-based gas concentration change curve; Obtain the change trend data of the geological stress field covering the potential dissipation area; Based on the carbon-based gas concentration change curve and the geological stress field change trend data, construct a carbon-based gas escape flux prediction model; Predict the escape flux value of carbon-based gas in the potential escape area according to the carbon-based gas escape flux prediction model.

7. The intelligent evaluation method for mine carbon emissions integrating multi-source data according to claim 6, characterized in that, The geological stress field change trend data includes the surrounding rock stress evolution curve and the structural unit displacement data during the mining cycle.

8. The intelligent evaluation method for mine carbon emissions integrating multi-source data according to claim 6, characterized in that, S5, specifically: Map the sampling units in the potential escape area and the adjacency relationship between sampling units into a three-dimensional node network; Assign the escape flux prediction value of the corresponding sampling unit to each node in the three-dimensional node network as the node weight; Connect the high-weight nodes to the low-weight nodes in sequence to form a set of potential escape paths of carbon-based gas.

9. The intelligent evaluation method for mine carbon emissions integrating multi-source data according to claim 6, characterized in that S6, specifically: Perform path traversal on each potential escape path in the set of potential escape paths of carbon-based gas, accumulate the escape flux prediction values of all sampling units, and obtain the flux accumulation value of each potential escape path; Select the potential escape path with the largest flux accumulation value as the main escape path, and extract the three-dimensional coordinates of each node in the main escape path to form the spatial trajectory data set of the main escape path; Combine the spatial trajectory data set of the main escape path with the escape flux prediction values of each sampling unit in the potential escape area to construct an overall carbon emission assessment model for the mining area; Estimate the total carbon-based gas emissions in the potential escape area according to the overall carbon emission assessment model for the mining area, and output the carbon emission assessment result of the mining area.

10. An intelligent evaluation system for mine carbon emissions integrating multi-source data, which is used to implement an intelligent evaluation method for mine carbon emissions integrating multi-source data according to any one of claims 1-9, characterized in that, Including: Historical analysis module: Obtain the historical record data of the redistribution of geological stress in the mining area, analyze the escape response characteristic parameters in the historical record data, and extract the historical escape characteristic data; Real-time monitoring module: Collect the real-time monitoring data of the mining activities in the mining area, identify the potential escape area induced by the mining activities in the mining area according to the historical escape characteristic data, and generate a potential escape area distribution map; Concentration sampling module: Sample the carbon-based gas concentration in the potential escape area according to the potential escape area distribution map, and construct a gas concentration distribution matrix; Flux prediction module: Based on the gas concentration distribution matrix, combined with the change trend of the geological stress in the mining area, predict the escape flux prediction value of carbon-based gas in the potential escape area; Path analysis module: Analyze the escape path of carbon-based gas in the potential escape area according to the escape flux prediction value, and generate a set of potential escape paths of carbon-based gas; Emission assessment module: Combine the set of potential escape paths of carbon-based gas and the escape flux prediction value to evaluate the overall carbon emissions in the mining area, and output the carbon emission assessment result of the mining area.

Images