Mine environment treatment method and system based on AI virtual simulation technology

Abstract

The invention relates to the technical field of mine treatment, in particular to a mine environment treatment method and system based on an AI virtual simulation technology. The method comprises the following steps: acquiring a dynamic geological parameter set of a target mine; analyzing the dynamic geological parameter set, and determining liquid injection data and soil capillary pressure detection data; determining a composite diffusion mode of the treatment agent according to the liquid injection data and the soil capillary pressure detection data; analyzing the composite diffusion mode, and determining a spatio-temporal evolution rule; according to a spatio-temporal evolution rule, constructing an AI dynamic simulation model containing a treatment agent permeation feedback mechanism; based on the AI dynamic simulation model, performing multi-node data growth simulation on the plurality of treatment schemes, and generating a treatment effect evolution graph containing stratum response time-varying characteristics; analyzing the governance effect evolution graph, and determining the matching degree of the action depth of the governance agent in each governance scheme and the vegetation planting condition; and determining an optimal treatment scheme implementation path according to the matching degree.

Description

Technical Field

[0001] The present application relates to the field of mine management technology, and in particular to a mine environment management method and system based on AI virtual simulation technology. Background Art

[0002] Mine environmental remediation, a key topic in ecological restoration, presents a core challenge, owing to the complexity of pollution diffusion mechanisms and the uncertainty of predicting remediation effectiveness. In particular, in-situ leaching, where acidic solutions are injected into the ore body through injection holes, can trigger multifaceted environmental issues.

[0003] In actual treatment, the unrecovered leachate during ore extraction will spread with surface runoff, and the residual liquid will seep into the groundwater system, causing long-term latent pollution, resulting in excessive ammonium nitrogen and sulfate in the soil, and causing changes in soil properties. Summary of the Invention

[0004] This application provides a mine environment management method and system based on AI virtual simulation technology to solve the above problems.

[0005] In a first aspect, the present application provides a mine environment management method based on AI virtual simulation technology, the method comprising:

[0006] Obtaining a dynamic geological parameter set of the target mine; analyzing the dynamic geological parameter set to determine injection data and soil capillary pressure detection data;

[0007] determining a composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data;

[0008] Analyze the composite diffusion pattern and determine the spatiotemporal evolution law; based on the spatiotemporal evolution law, construct an AI dynamic simulation model that includes the governance agent penetration feedback mechanism;

[0009] Based on the AI ​​dynamic simulation model, a multi-node data growth simulation is performed on several treatment schemes to generate a treatment effect evolution map that includes the time-varying characteristics of the formation response;

[0010] Analyze the evolution map of the treatment effect to determine the matching degree between the depth of action of the treatment agent in each treatment plan and the vegetation planting conditions; and determine the implementation path of the optimal treatment plan based on the matching degree.

[0011] This solution allows for the acquisition of a dynamic geological parameter set for the target mine, helping to eliminate biases in migration path predictions caused by single parameter sampling. Analyzing the dynamic geological parameter set to determine injection data and soil capillary pressure test data helps avoid hysteresis errors in static parameter libraries. Determining the composite diffusion pattern of the remediation agent based on injection data and soil capillary pressure test data helps eliminate misjudgments of composite migration paths by traditional linear models and avoids over-predictions of deep diffusion due to capillary action. Analyzing the composite diffusion pattern and determining its spatiotemporal evolution patterns helps eliminate biases in the prediction of agent residues caused by parameter fixation. Based on these spatiotemporal evolution patterns, an AI dynamic simulation model incorporating a remediation agent penetration feedback mechanism is constructed, providing early warning of potential risks associated with decreased vegetation survival rates. Based on this AI dynamic simulation model, multi-node data growth simulations are performed on several remediation schemes to generate a remediation effect evolution map that includes the time-varying characteristics of stratum response. This helps clearly demonstrate the time required for achieving the pollution removal rate target and assists in project progress control. Analyzing the evolution of treatment effects and determining the degree of compatibility between the depth of action of treatment agents and vegetation planting conditions in each treatment plan can help reduce resource waste and improve the compliance rate of comprehensive treatment mines. Based on the degree of compatibility, the optimal treatment plan implementation path is determined, which helps improve pollution removal rates while reducing the corresponding increase in chemical costs.

[0012] Optionally, the dynamic geological parameter set further includes the geological structure of the target mine; and determining the composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data includes:

[0013] Analyzing the injection data to determine the distribution of injection holes;

[0014] Based on the distribution of the injection holes, an image of the injection holes is acquired;

[0015] Analyzing the injection hole image to determine the characteristics of residual liquid on the surface;

[0016] determining the concentration of the residual liquid according to the characteristics of the residual liquid on the surface;

[0017] determining the migration rate of the treatment agent according to the residual liquid concentration and the soil capillary pressure detection data;

[0018] Analyze the geological structure and determine the direction of stratum fractures;

[0019] constructing a three-dimensional pollution diffusion vector field according to the migration rate and the direction of the stratum fracture;

[0020] The composite diffusion pattern of the treatment agent is determined according to the three-dimensional pollution diffusion vector field.

[0021] Optionally, the injection data includes an initial injection concentration; and determining the migration rate of the treatment agent based on the residual liquid concentration and the soil capillary pressure detection data includes:

[0022] Analyzing the soil capillary pressure detection data based on the geological structure to determine capillary pressure gradients at different levels;

[0023] Based on the residual liquid concentration measured by the initial injection concentration meter, the migration rate of the treatment agent is calculated according to Darcy's law and the capillary pressure gradients at different levels.

[0024] Optionally, constructing an AI dynamic simulation model including a governance agent penetration feedback mechanism based on the spatiotemporal evolution law includes:

[0025] Determining the spatial concentration distribution characteristics of the treatment agent according to the spatiotemporal evolution law;

[0026] Inputting the spatial concentration distribution characteristics into a preset neutralization reaction efficiency prediction model, and outputting the neutralization efficiency time series data of the treatment agent;

[0027] Dynamically generate a self-optimizing instruction set for adjusting the reagent concentration and injection hole position based on the neutralization efficiency time series data and the preset mine management standards;

[0028] By integrating the self-optimizing instruction set and the formation fracture trend, an AI dynamic simulation model including a governance agent penetration feedback mechanism is constructed.

[0029] Optionally, the construction of the preset neutralization reaction efficiency prediction model includes:

[0030] determining the chemical properties of the treatment agent based on the injection data;

[0031] determining soil buffer capacity based on the geological structure and the soil capillary pressure detection data;

[0032] A neutralization reaction efficiency prediction model is established based on the chemical properties and the soil buffer capacity.

[0033] Optionally, the dynamic geological parameter set includes soil sampling data; and establishing a neutralization reaction efficiency prediction model based on the chemical properties and the soil buffer capacity includes:

[0034] Analyzing the soil sampling data to determine the calcium carbonate content and cation exchange capacity;

[0035] Determining the relationship between the consumption of the treatment agent and the pH value according to the chemical characteristics;

[0036] A neutralization reaction efficiency prediction model is established based on the change relationship, the soil capillary pressure detection data, the calcium carbonate content, the cation exchange capacity and the soil buffer capacity.

[0037] Optionally, based on the AI ​​dynamic simulation model, a multi-node data growth simulation is performed on several treatment schemes to generate a treatment effect evolution map containing the time-varying characteristics of the formation response, including:

[0038] determining soil capillary capacity based on the soil capillary pressure detection data;

[0039] Quantifying the migration rate and the soil capillary capacity to obtain basic parameters and inputting them into the AI ​​dynamic simulation model so that the AI ​​dynamic simulation model performs multi-node data growth simulation of several governance solutions based on the basic parameters;

[0040] Obtaining simulation results of the AI ​​dynamic simulation model, analyzing the simulation results, and determining penetration data for each governance solution;

[0041] parsing the penetration data to determine a change in penetration depth and a timestamp of the change;

[0042] According to the change in penetration depth and the change timestamp, a treatment effect evolution map including the time-varying characteristics of the formation response is generated.

[0043] Optionally, analyzing the governance effect evolution map to determine the matching degree between the depth of action of the governance agent in each governance solution and the vegetation planting conditions includes:

[0044] Obtain the vegetation planting condition parameter set corresponding to each treatment plan;

[0045] Based on the governance effect evolution map, the actual action depth and corresponding soil parameters of each governance scheme at different time points are extracted;

[0046] The matching degree between the soil parameters within the actual action depth and the vegetation planting condition parameter set is calculated to determine the matching degree between the action depth of the treatment agent and the vegetation planting conditions in each treatment scheme.

[0047] Optionally, determining the optimal governance solution implementation path based on the matching degree includes:

[0048] Determine and establish a governance cost assessment model to calculate the implementation cost parameters of each governance plan;

[0049] Constructing a multi-objective optimization function, and performing weight calculation based on the matching degree and the implementation cost parameters;

[0050] Based on the calculation results, the governance plan with the highest score and lowest cost is selected as the optimal implementation path.

[0051] In a second aspect, the present application provides a mine environment management system based on AI virtual simulation technology, the system comprising:

[0052] A parameter set analysis module is used to obtain a dynamic geological parameter set of a target mine; analyze the dynamic geological parameter set to determine injection data and soil capillary pressure detection data;

[0053] a mode determination module, configured to determine a composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data;

[0054] A model building module is used to analyze the composite diffusion pattern and determine the spatiotemporal evolution law; based on the spatiotemporal evolution law, an AI dynamic simulation model including the governance agent penetration feedback mechanism is constructed;

[0055] A graph generation module is used to perform multi-node data growth simulation on several treatment schemes based on the AI ​​dynamic simulation model to generate a treatment effect evolution graph that includes the time-varying characteristics of the formation response;

[0056] The path determination module is used to analyze the evolution map of the treatment effect and determine the matching degree between the depth of action of the treatment agent in each treatment plan and the vegetation planting conditions; based on the matching degree, the optimal treatment plan implementation path is determined.

[0057] Optionally, the dynamic geological parameter set further includes the geological structure of the target mine; when the mode determination module determines the composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data, it is used to:

[0058] Analyzing the injection data to determine the distribution of injection holes;

[0059] Based on the distribution of the injection holes, an image of the injection holes is acquired;

[0060] Analyzing the injection hole image to determine the characteristics of residual liquid on the surface;

[0061] determining the concentration of the residual liquid according to the characteristics of the residual liquid on the surface;

[0062] determining the migration rate of the treatment agent according to the residual liquid concentration and the soil capillary pressure detection data;

[0063] Analyze the geological structure and determine the direction of stratum fractures;

[0064] constructing a three-dimensional pollution diffusion vector field according to the migration rate and the direction of the stratum fracture;

[0065] The composite diffusion pattern of the treatment agent is determined according to the three-dimensional pollution diffusion vector field.

[0066] Optionally, the injection data includes an initial injection concentration; when the mode determination module determines the migration rate of the treatment agent based on the residual liquid concentration and the soil capillary pressure detection data, it is used to:

[0067] Analyzing the soil capillary pressure detection data based on the geological structure to determine capillary pressure gradients at different levels;

[0068] Based on the residual liquid concentration measured by the initial injection concentration meter, the migration rate of the treatment agent is calculated according to Darcy's law and the capillary pressure gradients at different levels.

[0069] Optionally, when the model building module constructs an AI dynamic simulation model including a governance agent penetration feedback mechanism according to the spatiotemporal evolution law, it is used to:

[0070] Determining the spatial concentration distribution characteristics of the treatment agent according to the spatiotemporal evolution law;

[0071] Inputting the spatial concentration distribution characteristics into a preset neutralization reaction efficiency prediction model, and outputting the neutralization efficiency time series data of the treatment agent;

[0072] Dynamically generate a self-optimizing instruction set for adjusting the reagent concentration and injection hole position based on the neutralization efficiency time series data and the preset mine management standards;

[0073] By integrating the self-optimizing instruction set and the formation fracture trend, an AI dynamic simulation model including a governance agent penetration feedback mechanism is constructed.

[0074] Optionally, the mine environment management system based on AI virtual simulation technology further includes a prediction model establishment module for:

[0075] determining the chemical properties of the treatment agent based on the injection data;

[0076] determining soil buffer capacity based on the geological structure and the soil capillary pressure detection data;

[0077] A neutralization reaction efficiency prediction model is established based on the chemical properties and the soil buffer capacity.

[0078] Optionally, the dynamic geological parameter set includes soil sampling data; when the prediction model establishment module establishes the neutralization reaction efficiency prediction model based on the chemical properties and the soil buffer capacity, it is used to:

[0079] Analyzing the soil sampling data to determine the calcium carbonate content and cation exchange capacity;

[0080] Determining the relationship between the consumption of the treatment agent and the pH value according to the chemical characteristics;

[0081] A neutralization reaction efficiency prediction model is established based on the change relationship, the soil capillary pressure detection data, the calcium carbonate content, the cation exchange capacity and the soil buffer capacity.

[0082] Optionally, the map generation module performs multi-node data growth simulation on several treatment schemes based on the AI ​​dynamic simulation model to generate a treatment effect evolution map including the time-varying characteristics of the formation response, and is used to:

[0083] determining soil capillary capacity based on the soil capillary pressure detection data;

[0084] Quantifying the migration rate and the soil capillary capacity to obtain basic parameters and inputting them into the AI ​​dynamic simulation model so that the AI ​​dynamic simulation model performs multi-node data growth simulation of several governance solutions based on the basic parameters;

[0085] Obtaining simulation results of the AI ​​dynamic simulation model, analyzing the simulation results, and determining penetration data for each governance solution;

[0086] parsing the penetration data to determine a change in penetration depth and a timestamp of the change;

[0087] According to the change in penetration depth and the change timestamp, a treatment effect evolution map including the time-varying characteristics of the formation response is generated.

[0088] Optionally, when the path determination module analyzes the governance effect evolution map and determines the matching degree between the action depth of the governance agent and the vegetation planting conditions in each governance scheme, it is used to:

[0089] Obtain the vegetation planting condition parameter set corresponding to each treatment plan;

[0090] Based on the governance effect evolution map, the actual action depth and corresponding soil parameters of each governance scheme at different time points are extracted;

[0091] The matching degree between the soil parameters within the actual action depth and the vegetation planting condition parameter set is calculated to determine the matching degree between the action depth of the treatment agent and the vegetation planting conditions in each treatment scheme.

[0092] Optionally, when the path determination module determines the optimal governance solution implementation path based on the matching degree, it is used to:

[0093] Determine and establish a governance cost assessment model to calculate the implementation cost parameters of each governance plan;

[0094] Constructing a multi-objective optimization function, and performing weight calculation based on the matching degree and the implementation cost parameters;

[0095] Based on the calculation results, the governance plan with the highest score and lowest cost is selected as the optimal implementation path. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0097] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application;

[0098] Figure 2 A flowchart of a mine environment management method based on AI virtual simulation technology provided in one embodiment of the present application;

[0099] Figure 3 A schematic diagram of the structure of a mine environment management system based on AI virtual simulation technology is provided in one embodiment of the present application. DETAILED DESCRIPTION

[0100] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0101] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0102] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0103] In actual treatment, the unrecovered leachate during ore extraction will spread with surface runoff, and the residual liquid will seep into the groundwater system, causing long-term latent pollution, resulting in excessive ammonium nitrogen and sulfate in the soil, and causing changes in soil properties.

[0104] Based on this, the present application provides a mine environmental governance method and system based on AI virtual simulation technology, which obtains the dynamic geological parameter set of the target mine, which helps to eliminate the migration path prediction deviation caused by single parameter sampling. Analyzing the dynamic geological parameter set, determining the injection data and soil capillary pressure detection data, helps to avoid the hysteresis error of the static parameter library. Based on the injection data and soil capillary pressure detection data, the composite diffusion pattern of the governance agent is determined, which helps to eliminate the misjudgment problem of the traditional linear model on the composite migration path and avoid the over-prediction of deep diffusion by capillary action. Analyzing the composite diffusion pattern and determining the spatiotemporal evolution law helps to eliminate the prediction deviation of the agent residue caused by parameter solidification. According to the spatiotemporal evolution law, an AI dynamic simulation model including the governance agent penetration feedback mechanism is constructed, which helps to provide early warning of the potential risk of declining vegetation survival rate. Based on the AI ​​dynamic simulation model, multi-node data growth simulation is performed on several governance schemes to generate a governance effect evolution map including the time-varying characteristics of the formation response, which helps to clearly display the time for reaching the standard for the pollution removal rate and assist in project progress control. Analyzing the evolution of treatment effects and determining the degree of compatibility between the depth of action of treatment agents and vegetation planting conditions in each treatment plan can help reduce resource waste and improve the compliance rate of comprehensive treatment mines. Based on the degree of compatibility, the optimal treatment plan implementation path is determined, which helps improve pollution removal rates while reducing the corresponding increase in chemical costs.

[0105] Figure 1 This is a schematic diagram of an application scenario provided by this application. When using virtual simulation technology to manage the mine environment, the method provided by this application is applied.

[0106] Specifically, the method provided in this application is applied to any server, and the server interacts with geological monitoring equipment, which may include three-dimensional geological radar, centrifuges, and distributed fiber optic sensors. The geological monitoring equipment obtains and analyzes the dynamic geological parameter set of the target mine, determines the injection data and soil capillary pressure detection data. Based on the injection data and soil capillary pressure detection data, the composite diffusion pattern of the treatment agent is determined and analyzed, and the spatiotemporal evolution law is obtained. Based on the spatiotemporal evolution law, an AI dynamic simulation model containing the treatment agent penetration feedback mechanism is constructed. Based on the AI ​​dynamic simulation model, multi-node data growth simulation is performed on several treatment plans to generate a treatment effect evolution map containing the time-varying characteristics of the formation response, thereby determining the matching degree between the treatment agent action depth and vegetation planting conditions in each treatment plan, which helps to reduce resource waste and improve the compliance rate of comprehensive treatment mines. Based on the matching degree, the optimal treatment plan implementation path is determined, which helps to improve the pollution removal rate while reducing the corresponding increase in the cost of the agent. The specific implementation method can be referred to the following examples.

[0107] Figure 2This is a flowchart of a mine environment management method based on AI virtual simulation technology provided by an embodiment of this application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes:

[0108] S201. Obtain a dynamic geological parameter set of the target mine; analyze the dynamic geological parameter set to determine injection data and soil capillary pressure detection data;

[0109] The target mine may be a mining area that requires environmental remediation.

[0110] The dynamic geological parameter set can be a set of geological parameters with spatiotemporal evolution characteristics.

[0111] The injection data may be time series data generated during in-situ leaching operations.

[0112] The soil capillary pressure detection data may be soil capillary force parameters.

[0113] Specifically, a 3D geological radar scan was used to obtain a topological map of the fracture distribution of the target mine. Parameters such as the main fracture inclination, branch fracture density, and connectivity were extracted. A distributed fiber optic sensor array was deployed around the injection holes to collect injection pressure, flow rate, and temperature in real time. A stratified sampling method was used to obtain soil samples at different depths. The capillary pressure-saturation curve for each layer was measured using a centrifuge to extract the critical capillary pressure, porosity, and wetting angle. These data together form a dynamic geological parameter set.

[0114] Among them, injection pressure, flow rate and temperature constitute injection data; critical capillary pressure, porosity and wetting angle constitute soil capillary pressure monitoring data.

[0115] S202, determining a composite diffusion pattern of the treatment agent based on the injection data and the soil capillary pressure test data;

[0116] Remediation agents can be chemicals used to neutralize acidic pollutants.

[0117] The composite diffusion model can be a dual-channel migration model that simultaneously considers the fracture channel flow velocity and the capillary vertical seepage rate.

[0118] Specifically, the injection data was analyzed through DTS thermodynamic inversion to determine the spatial distribution of residual liquid concentration. Then, based on the modified equation of Darcy's law and the soil capillary pressure detection data, a porosity-wetting angle joint correction coefficient determined through multiple sets of soil column infiltration experiments was introduced. When the main fracture inclination angle was large, the fracture channel flow velocity determined by the simplified Navier-Stokes equation was vector-superimposed with the capillary vertical seepage rate to determine the composite diffusion pattern of the treatment agent.

[0119] S203. Analyze the composite diffusion pattern and determine the spatiotemporal evolution law; based on the spatiotemporal evolution law, construct an AI dynamic simulation model that includes the governance agent penetration feedback mechanism;

[0120] The law of spatiotemporal evolution can be the law of change of concentration distribution of the control agent in three-dimensional space and time dimensions.

[0121] The feedback mechanism of the treatment agent penetration can be a closed-loop control device that dynamically adjusts the injection parameters.

[0122] The AI ​​dynamic simulation model can be a hybrid architecture for simulating the multi-process coupling effects of agent migration-response-vegetation restoration.

[0123] Specifically, based on the composite diffusion model, the meteorological data interface is connected to obtain rainfall intensity and duration data in real time, and the dilution factor of the rainfall intensity and duration data on the shallow liquid concentration is calculated. Then, according to the soil cation exchange capacity and calcium carbonate content, the treatment agent consumption rate equation is dynamically corrected. Furthermore, at each time step, the agent concentration distribution in the infiltration vector field is updated, and the mass flux balance of the capillary zone and the fracture zone is calculated. Finally, a three-dimensional concentration field sequence containing a timestamp is output to form a spatiotemporal evolution law. Subsequently, based on the spatiotemporal evolution law, a 3D convolution layer is used to extract the spatiotemporal characteristics of the diffusion pattern. At the same time, a fully connected layer is used to process the formation response monitoring data. Combining the spatiotemporal characteristics of the diffusion pattern and the formation response monitoring data, an AI dynamic simulation model containing a treatment agent infiltration feedback mechanism is constructed.

[0124] S204. Based on the AI ​​dynamic simulation model, perform multi-node data growth simulation on several treatment schemes to generate a treatment effect evolution map including the time-varying characteristics of the formation response;

[0125] The treatment plan can be an operation combination including injection parameters, treatment agent type, and vegetation planting sequence.

[0126] The time-varying characteristics of formation response can be the dynamic change characteristics of formation parameters during the treatment process.

[0127] The governance effect evolution map can be a three-dimensional heat map generated by multi-node data growth simulation.

[0128] Specifically, according to the AI ​​dynamic simulation model, time nodes are divided according to the treatment stage, and spatial nodes are divided according to depth layers; then, during the injection period, the agent penetration depth and crack filling degree are updated; then, during the reaction period, the precipitation amount of the neutralization product is calculated, and the porosity parameters are corrected; subsequently, the root growth model is introduced during the vegetation recovery period to correlate the soil pH value with the porosity, thereby generating an evolutionary map of the treatment effect that includes the time-varying characteristics of the formation response.

[0129] S205. Analyze the evolution map of the treatment effect and determine the matching degree between the depth of action of the treatment agent and the vegetation planting conditions in each treatment plan; based on the matching degree, determine the implementation path of the optimal treatment plan.

[0130] Depth of action can be the vertical coverage of the remediation agent to effectively neutralize the pollutants.

[0131] Vegetation planting conditions can be threshold parameters for surface soil to be suitable for vegetation survival.

[0132] The matching degree can be a quantitative indicator of the adaptability of the governance plan to the mine type.

[0133] The optimal governance solution implementation path can be a dynamic execution solution selected through multi-objective optimization.

[0134] Specifically, based on the governance effect evolution map, the matching degree is determined by calculating the Pearson correlation coefficient between the action depth and vegetation planting conditions; then, Monte Carlo simulation is used to generate several geological response curves, and the success probability distribution of each governance plan is calculated; subsequently, based on the resource-stage matrix model in multi-criteria decision analysis, by integrating the cost-benefit ratio evaluation framework of classical operations research and the spatial mapping method of the risk matrix, an implementation path decision matrix is ​​constructed, in which the column dimension is the governance stage division, the row dimension is the resource input level, and the ratio of the expected effect achievement rate to the economic cost is marked in the cell; finally, by adopting the hybrid optimization framework of Pareto optimality theory and genetic algorithm, multi-objective optimization is determined, and the weight allocation rule of the non-dominated sorting mechanism and the goal programming method is combined to finally determine the optimal governance plan implementation path.

[0135] This solution allows for the acquisition of a dynamic geological parameter set for the target mine, helping to eliminate biases in migration path predictions caused by single parameter sampling. Analyzing the dynamic geological parameter set to determine injection data and soil capillary pressure test data helps avoid hysteresis errors in static parameter libraries. Determining the composite diffusion pattern of the remediation agent based on injection data and soil capillary pressure test data helps eliminate misjudgments of composite migration paths by traditional linear models and avoids over-predictions of deep diffusion due to capillary action. Analyzing the composite diffusion pattern and determining its spatiotemporal evolution patterns helps eliminate biases in the prediction of agent residues caused by parameter fixation. Based on these spatiotemporal evolution patterns, an AI dynamic simulation model incorporating a remediation agent penetration feedback mechanism is constructed, providing early warning of potential risks associated with decreased vegetation survival rates. Based on this AI dynamic simulation model, multi-node data growth simulations are performed on several remediation schemes to generate a remediation effect evolution map that includes the time-varying characteristics of stratum response. This helps clearly demonstrate the time required for achieving the pollution removal rate target and assists in project progress control. Analyzing the evolution of treatment effects and determining the degree of compatibility between the depth of action of treatment agents and vegetation planting conditions in each treatment plan can help reduce resource waste and improve the compliance rate of comprehensive treatment mines. Based on the degree of compatibility, the optimal treatment plan implementation path is determined, which helps improve pollution removal rates while reducing the corresponding increase in chemical costs.

[0136] In some embodiments, the injection data is analyzed to determine the distribution of the injection holes; based on the distribution of the injection holes, an image of the injection holes is obtained; the injection hole image is analyzed to determine the characteristics of the surface residual liquid; based on the characteristics of the surface residual liquid, the residual liquid concentration is determined; based on the residual liquid concentration and soil capillary pressure detection data, the migration rate of the treatment agent is determined; the geological structure is analyzed to determine the direction of the formation fractures; based on the migration rate and the direction of the formation fractures, a three-dimensional pollution diffusion vector field is constructed; based on the three-dimensional pollution diffusion vector field, the composite diffusion pattern of the treatment agent is determined.

[0137] The injection hole distribution status may be a three-dimensional spatial arrangement status of the injection holes in the target mine.

[0138] The injection hole image may be an optical image of the injection hole surface.

[0139] The surface residual liquid feature can be the visual attributes such as color, texture, distribution form, etc. of the residual liquid around the injection hole in the image.

[0140] The residual liquid concentration may be the mass percentage concentration of the acidic solution remaining on the surface of the injection hole and in the shallow soil.

[0141] The migration rate can be the penetration speed of the treatment agent in the vertical or horizontal direction.

[0142] The geological structure can be a physical structure composed of the stratification characteristics of the rock and soil bodies, the distribution of the fracture network and the pore connectivity in the target mine strata.

[0143] The strike of a formation fracture can be the angle between the extension direction of the main fracture in the formation and the geographic north direction.

[0144] The three-dimensional pollution diffusion vector field can be a three-dimensional spatial model constructed based on the migration rate and the direction of stratum fractures.

[0145] Specifically, the spatial coordinates of the injection holes and the injection flow parameters in the injection data are extracted, and the distribution of the injection holes is generated by the spatial interpolation algorithm. Then, based on the distribution of the injection holes, the surface images of the injection holes are collected by a drone equipped with a hyperspectral camera. Subsequently, the HSV color space segmentation algorithm is used to accurately extract the residual liquid area of ​​the acidic solution through hue separation; the area ratio of the residual liquid patch and the edge fractal dimension are calculated as the surface residual liquid characteristics. The absorption peak intensity of the residual liquid is determined by near-infrared spectroscopy analysis, and combined with the calibration curve of the ammonium sulfate standard solution, the NH4 + -N and SO4 2- The residual liquid concentration is calculated by inputting soil capillary pressure monitoring data and permeability coefficients obtained from a table lookup based on soil type. The vertical migration rate is then calculated based on the residual liquid concentration. 3D geological radar scanning data is then loaded, and planar fracture traces are detected in the 3D point cloud using the Hough transform. The spatial azimuth of the main fracture is identified through accumulator spatial peak detection. The angle between the fracture strike and the horizontal plane is then calculated, screening for effective water-conducting fractures with excessively large inclinations, i.e., the formation fracture strike. Within the finite element mesh, the mesh density is dynamically adjusted based on the permeability coefficient of the formation medium to define a 3D contamination diffusion vector field. First, the vertical velocity component dominated by capillary action is used in the shallow mesh. Then, the horizontal velocity component along the fracture strike direction is superimposed on the deeper mesh. Finally, the capillary and fracture migration mechanisms are coupled using the Darcy-Boossinesq equation to generate a 3D contamination diffusion vector field. Subsequently, the spatiotemporal distribution characteristics of the maximum diffusion direction and velocity in the 3D contamination diffusion vector field are extracted. The diffusion boundary between the capillary and fracture zones is then delineated based on a rate threshold. Finally, a composite diffusion model encompassing the range of action of both mechanisms is output.

[0146] This solution analyzes injection data, determines the distribution of injection holes, and clarifies the spatial boundaries of high-permeability risk areas, avoiding incomplete regional coverage caused by discrete sampling. Based on the distribution of injection holes, images of the injection holes are acquired, helping to eliminate subjective errors in visual inspections. Analyzing the injection hole images and determining the characteristics of the surface residual liquid helps overcome the limitations of single thickness measurements. Determining the residual liquid concentration based on the surface residual liquid characteristics helps improve detection efficiency and eliminate the risk of secondary contamination. Based on the residual liquid concentration and soil capillary pressure test data, the migration rate of the treatment agent is determined, reducing rate prediction errors in shallow capillary action zones. Analyzing the geological structure and determining the direction of stratum fractures helps eliminate the problem of two-dimensional profile analysis being unable to capture the spatial distribution of three-dimensional fractures. Constructing a three-dimensional pollution diffusion vector field based on the migration rate and the direction of stratum fractures helps improve prediction accuracy compared to traditional linear models. Based on the three-dimensional pollution diffusion vector field, the composite diffusion pattern of the treatment agent is determined, avoiding the risk of adaptation errors associated with traditional empirical judgments.

[0147] In some embodiments, based on the geological structure, the soil capillary pressure detection data is analyzed to determine the capillary pressure gradients at different levels; based on the residual liquid concentration of the initial injection concentration meter, the migration rate of the treatment agent is calculated according to Darcy's law and the capillary pressure gradients at different levels.

[0148] The capillary pressure gradient can be the rate of change of soil capillary pressure per unit depth.

[0149] The initial injection concentration meter can be the initial mass concentration of the treatment agent injected into the ore body through the injection hole.

[0150] Specifically, based on the geological structure, the capillary pressure raw data at different stratum depths were collected through a soil capillary pressure monitoring device; then, the capillary pressure raw data were spatially interpolated according to vertical stratification to generate capillary pressure gradients at different levels. Subsequently, the spectral absorption peak intensity of the residual liquid on the surface of the injection hole was obtained based on a near-infrared spectrometer; then, the NH4 + -N and SO4 2- The characteristic absorption peak intensity-concentration relationship curve is obtained; then, the residual liquid concentration is inverted according to the measured absorption peak intensity; the dynamic viscosity is measured by a rotational viscometer and the concentration inhibition coefficient is determined by a soil column experiment; then, the Darcy's law formula is constructed through the permeability coefficient, dynamic viscosity and concentration inhibition coefficient; then, according to the Darcy's law formula, the migration rates of the treatment agent in the shallow, middle and deep layers are calculated respectively according to the capillary pressure gradients at different levels.

[0151] This solution analyzes soil capillary pressure data based on geological structure and determines capillary pressure gradients at different levels, helping to eliminate the separation of shallow and deep migration mechanisms caused by the fragmented analysis of static geological parameters. Based on the residual liquid concentration from the initial injection concentration meter, Darcy's law, and capillary pressure gradients at different levels, the migration rate of the remediation agent is calculated, providing a basis for defining the penetration range of fracture extension depths in comprehensive remediation mines.

[0152] In some embodiments, the spatial concentration distribution characteristics of the treatment agent are determined according to the laws of spatiotemporal evolution; the spatial concentration distribution characteristics are input into a preset neutralization reaction efficiency prediction model, and the neutralization efficiency time series data of the treatment agent is output; based on the neutralization efficiency time series data and the preset mine treatment standards, a self-optimization instruction set for adjusting the agent dosage concentration and the injection hole position is dynamically generated; the self-optimization instruction set and the direction of the formation fracture are integrated to construct an AI dynamic simulation model including the treatment agent penetration feedback mechanism.

[0153] The spatial concentration distribution characteristics can be a quantitative representation of the concentration distribution of the treatment agent in three-dimensional space.

[0154] The preset neutralization reaction efficiency prediction model can be a preset mathematical relationship model for calculating the neutralization efficiency of the treatment agent and the pollutant, which is pre-stored in the server and called when used.

[0155] The neutralization efficiency time series data may be neutralization efficiency attenuation curve data that changes with time.

[0156] The preset mine governance standards can be quantitative governance targets set according to different mine types, which are pre-stored in the server and called when used.

[0157] The concentration of the agent injected can be the initial mass concentration of the treatment agent injected into the formation.

[0158] The injection hole position can be a spatial distribution parameter of the drilling hole used to inject the treatment agent.

[0159] The self-optimizing instruction set can be a set of dynamic control strategies generated based on neutralization efficiency time series data and mine governance standards.

[0160] Specifically, based on the laws of spatiotemporal evolution, a spatiotemporal covariance function is constructed through dynamic geological parameters. The spatiotemporal Kriging interpolation method of the three-dimensional concentration field is solved using the Kriging weight matrix through the weight relationship between crack density and migration rate and the time lag effect. Then, the spatial optimal estimation theory of the spatiotemporal Kriging interpolation method is adopted and extended to the time dimension. The migration rate is coupled with the crack direction to calculate the spatial concentration distribution characteristics of the treatment agent. Then, the spatial concentration distribution characteristics and the dynamic geological parameter set at the current moment are input, and a preset neutralization reaction efficiency prediction model is constructed based on the neutralization reaction kinetics model, combined with the linear-exponential mixed attenuation law of soil buffer capacity and residual liquid concentration, through laboratory calibration parameters. Subsequently, a nonlinear regression equation is used, and the first-order exponential model of pollutant attenuation kinetics is used to output the neutralization efficiency time series data according to the preset time step. Based on preset mine remediation standards, for comprehensive remediation mines, a penetration depth target is set using 3D geological modeling data. For simple remediation mines, a target range for surface soil pH and a target time window are set using real-time monitoring and feedback from pH sensors. If the neutralization efficiency time series data falls below the target range and the target time window, or if the penetration depth fails to meet the target, a gradient descent algorithm is used to optimize the initial injection concentration and injection hole coordinates, generating a self-optimizing instruction set for adjusting the agent concentration and injection hole position. This self-optimizing instruction set is combined with the extended Darcy formula to iteratively update the migration rate and concentration distribution. High-permeability channels are then marked in the 3D grid based on the orientation of the stratum fractures. Finally, an AI dynamic simulation model is generated that incorporates the remediation agent's penetration feedback mechanism.

[0161] Through this scheme, the spatial concentration distribution characteristics of the treatment agent are determined according to the laws of spatiotemporal evolution, which helps to eliminate the problem of insufficient adaptability of the treatment scheme and realize the quantitative expression of the nonlinear attenuation of concentration with depth. The spatial concentration distribution characteristics are input into the preset neutralization reaction efficiency prediction model, and the neutralization efficiency time series data of the treatment agent is output to quantify the impact of soil buffering capacity on neutralization efficiency, eliminating the problem of lack of dynamic feedback of the neutralization reaction. According to the neutralization efficiency time series data and the preset mine treatment standards, a self-optimization instruction set for adjusting the agent concentration and injection hole position is dynamically generated, which helps to eliminate the problem of insufficient penetration depth of the treatment agent and meet the adaptation needs of the vegetation root system. Integrating the self-optimization instruction set and the direction of stratum fractures to construct an AI dynamic simulation model that includes a treatment agent penetration feedback mechanism helps to eliminate the problem of lack of multi-objective collaborative optimization and improve the modeling robustness of heterogeneous strata.

[0162] In some embodiments, the chemical properties of the treatment agent are determined based on the injection data; the soil buffer capacity is determined based on the geological structure and soil capillary pressure detection data; and a neutralization reaction efficiency prediction model is established based on the chemical properties and soil buffer capacity.

[0163] Chemical properties can be attributes of the components of the remediation agent.

[0164] Soil buffering capacity can be described as the ability of soil to resist changes in pH through its own chemical composition.

[0165] Specifically, based on the injection data, the agent type, initial concentration, and injection pressure parameters recorded at the injection hole are extracted. Then, the molar concentration of the reaction components in the agent is determined by ion chromatography, thereby determining the chemical properties of the treatment agent. Based on the drilling exploration data, the formation fracture direction and capillary pressure detection data are extracted. Then, the capillary pressure-saturation curve of the soil at different depths is measured using a pressure membrane instrument to calculate the pore connectivity. Furthermore, the calcium carbonate content determination method is used to obtain the mass percentage of calcium carbonate. Subsequently, the soil buffering capacity per unit mass of soil is determined using a cation exchange capacity test kit. Then, under laboratory simulation conditions, the treatment agent and the target pollutant are mixed according to their chemical properties. Subsequently, the neutralization reaction endpoint is monitored using a pH meter and an ion-selective electrode, and the basic neutralization efficiency under static conditions is calculated. Finally, the soil buffering parameters are linearly combined with the basic neutralization efficiency to generate a neutralization reaction efficiency prediction model.

[0166] This approach determines the chemical properties of the remediation agent based on injection data, clarifying its effectiveness under different geological conditions. It also determines the soil buffer capacity based on geological structure and soil capillary pressure data, helping to reveal the spatial heterogeneity of buffer capacity across fracture orientation and capillary pressure data. A neutralization reaction efficiency prediction model based on chemical properties and soil buffer capacity helps to address the lack of dynamic feedback in the neutralization reaction.

[0167] In some embodiments, soil sampling data is analyzed to determine the calcium carbonate content and cation exchange capacity; based on the chemical properties, the changing relationship between the consumption of the treatment agent and the pH value is determined; and based on the changing relationship, soil capillary pressure detection data, calcium carbonate content, cation exchange capacity and soil buffering capacity, a neutralization reaction efficiency prediction model is established.

[0168] Soil sampling data can be a collection of physical and chemical properties of stratified soil samples.

[0169] The calcium carbonate content may be the mass percentage of calcium carbonate in the soil.

[0170] The cation exchange capacity can be the total amount of exchangeable cations that can be adsorbed per unit mass of soil.

[0171] The consumption can be the concentration reduction of the treatment agent due to chemical reaction, adsorption and other effects during the neutralization reaction.

[0172] The pH value can be an indicator of the acidity or alkalinity of the soil.

[0173] The changing relationship can be a dynamic correlation between the consumption of the treatment agent and the pH value.

[0174] Specifically, based on soil sampling data, layered soil samples obtained from drilling exploration are taken, and the calcium carbonate content is determined using the calcium carbonate content determination method: first, the soil sample is reacted with excess hydrochloric acid until no bubbles are generated; then, the mass percentage of calcium carbonate, i.e., the calcium carbonate content, is calculated by mass difference subtraction.

[0175] Based on soil sampling data, a cation exchange capacity test kit was used to determine the cation exchange capacity. First, the soil sample was oscillated and saturated with a barium chloride solution and then centrifuged to displace the exchangeable cations. The total amount of displaced cations was then determined by sulfuric acid titration, and the cation exchange capacity per unit mass of soil was calculated. Based on the chemical properties, the remediation agent and the target contaminated soil were mixed in the laboratory according to the molar ratio specified in the chemical properties. The pH of the mixture was then monitored in real time using a pH meter until equilibrium was reached. Finally, the relationship between the amount of remediation agent consumed and the pH value was recorded. This relationship, along with the calcium carbonate content and cation exchange capacity, was integrated, and a synergistic correction factor based on the soil buffering capacity and capillary pressure test data was introduced to generate the final neutralization reaction efficiency prediction model.

[0176] This solution analyzes soil sampling data to determine calcium carbonate content and cation exchange capacity, helping to quantify the soil's chemical buffering capacity for acidic remediation agents while avoiding redundant parameters and reflecting the soil's ability to adsorb cations from the remediation agent. Based on chemical properties, the relationship between remediation agent consumption and pH is determined, quantifying the actual dynamic process of remediation agent consumption and avoiding the drawbacks of static parameter fragmentation analysis. A neutralization reaction efficiency prediction model is developed based on this relationship, soil capillary pressure test data, calcium carbonate content, cation exchange capacity, and soil buffer capacity, helping to eliminate 3D modeling distortion caused by the interaction between capillary pressure and fracture structure.

[0177] In some embodiments, the soil capillary capacity is determined based on the soil capillary pressure detection data; the migration rate and the soil capillary capacity are parameterized to obtain basic parameters and input into the AI ​​dynamic simulation model so that the AI ​​dynamic simulation model performs multi-node data growth simulation of several treatment schemes based on the basic parameters; the simulation results of the AI ​​dynamic simulation model are obtained, the simulation results are analyzed, and the infiltration data of each treatment scheme is determined; the infiltration data is parsed to determine the change in infiltration depth and the change timestamp; based on the change in infiltration depth and the change timestamp, a treatment effect evolution map including the time-varying characteristics of the formation response is generated.

[0178] The capillary capacity of soil may be the strength of the capillary action of soil.

[0179] The basic parameters can be a parameter set generated by dimensionless processing of migration rate and soil capillary capacity.

[0180] The simulation result can be a data set output by the AI ​​dynamic simulation model.

[0181] The penetration data may be the migration characteristic data of the remediation agent extracted from the simulation results.

[0182] The change in penetration depth can be a time-varying process of the vertical penetration distance of the treatment agent.

[0183] The change timestamp may be a time node mark when the penetration depth reaches the accumulated time.

[0184] Specifically, the soil capillary capacity is calculated based on the soil capillary pressure detection data. The migration rate and soil capillary capacity are dimensionlessly processed to generate basic parameters; the basic parameters are input into the AI ​​dynamic simulation model to start the multi-node data growth simulation: first, several treatment plans are automatically generated; second, based on the difference between the initial injection concentration and the residual liquid concentration, the time-varying process of the agent migration rate is simulated; finally, the penetration depth and the capillary capacity of the surface soil are synchronously verified to predict the risk of vegetation survival rate. Then, the simulation results are extracted to establish a penetration depth-time series data set to determine the penetration data of each treatment plan; then, the maximum penetration depth of the treatment agent corresponding to each timestamp is extracted from the penetration data to generate a penetration depth change curve; then, the penetration depth is associated with the corresponding timestamp, the time node is marked, and a change timestamp is generated. Finally, the penetration depth change and the change timestamp are temporally and spatially associated to construct a treatment effect evolution map.

[0185] This solution determines soil capillary capacity based on soil capillary pressure data, eliminating modeling distortion caused by the interaction between capillary pressure and fracture structure. Migration rate and soil capillary capacity are quantified to obtain basic parameters, which are then input into an AI dynamic simulation model. This allows the model to perform multi-node data growth simulations for several remediation scenarios based on these basic parameters, eliminating model errors caused by dynamic parameter split analysis. This provides high-precision input data for the AI ​​dynamic simulation model, covering the needs of both comprehensive and simplified remediation mines, eliminating concentration distribution errors caused by the lack of spatiotemporal evolution predictions, and addressing the limitations of a multi-node data growth mechanism. Simulation results from the AI ​​dynamic simulation model are obtained and analyzed to determine infiltration data for each remediation scenario. This helps verify the coverage compliance of comprehensive remediation mines and determine whether simplified remediation mines meet the timeliness requirements of the target vegetation root adaptation range. The infiltration data is analyzed to determine changes in infiltration depth and their timestamps, providing a basis for vegetation planting timing decisions in simplified remediation mines. Based on the changes in penetration depth and the timestamps of the changes, an evolutionary map of the treatment effect is generated, which includes the time-varying characteristics of the formation response. This clarifies the dynamic evolution law of the formation response under different treatment schemes and provides a quantitative basis for multi-objective optimization.

[0186] In some embodiments, a set of vegetation planting condition parameters corresponding to each treatment scheme is obtained; based on the treatment effect evolution map, the actual action depth and corresponding soil parameters of each treatment scheme at different time nodes are extracted; the matching degree of the soil parameters within the actual action depth and the vegetation planting condition parameter set is calculated to determine the matching degree between the action depth of the treatment agent in each treatment scheme and the vegetation planting conditions.

[0187] The vegetation planting condition parameter set may be a set of quantitative parameters established according to vegetation restoration requirements.

[0188] The actual action depth can be the vertical penetration depth of the treatment agent at different time points.

[0189] Soil parameters can be the core soil properties that directly affect vegetation planting within the actual action depth range of the remediation agent.

[0190] Specifically, based on each treatment scheme, the target range of surface soil pH, the maximum depth of target vegetation root distribution, and the minimum pore connectivity required for vegetation survival are set according to the mine type, and a set of vegetation planting condition parameters is constructed. Based on the time axis of the treatment effect evolution map, the actual action depth of the treatment agent at different time nodes in each treatment scheme is extracted according to the time step; based on the three-dimensional coordinates corresponding to the actual action depth, the soil parameters are obtained. Subsequently, the difference between the actual action depth and the maximum depth of target vegetation root distribution is compared to calculate the coverage rate; then, the proportion of the actual pH value duration in the target range is calculated, and it is verified whether the porosity is continuously higher than the critical value; comprehensive weight distribution is performed to output the matching degree between the action depth of the treatment agent and the vegetation planting conditions in each treatment scheme.

[0191] Through this solution, the vegetation planting condition parameter set corresponding to each treatment solution is obtained, which helps to eliminate the problem of separation between treatment goals and vegetation conditions, and clarifies the target threshold of the depth of action of the treatment agent, avoiding the risk of reduced vegetation survival rate due to insufficient capillary capacity. Based on the treatment effect evolution map, the actual action depth and corresponding soil parameters of each treatment solution at different time nodes are extracted to achieve the spatiotemporal evolution tracking of the agent penetration process, eliminating the problem of being unable to reflect dynamic geological responses. The matching degree of the soil parameters within the actual action depth is calculated with the vegetation planting condition parameter set to determine the matching degree between the action depth of the treatment agent and the vegetation planting conditions in each treatment solution, which helps to eliminate the problem of disconnection between the penetration depth and vegetation needs, ensure the core influence of pH on vegetation survival, and ensure that the effect of the treatment agent is synchronized with the timing of vegetation planting, eliminating the problem of unintegrated time dimension.

[0192] In some embodiments, a governance cost assessment model is established to calculate the implementation cost parameters of each governance plan; a multi-objective optimization function is constructed to perform weight calculations on the comprehensive matching degree and implementation cost parameters; and based on the calculation results, the governance plan with the highest score and lowest cost is selected as the optimal implementation path.

[0193] The governance cost assessment model can be a calculation model used to quantify the economic input of mine environmental governance programs.

[0194] Implementation cost parameters can be quantifiable economic indicators generated during the implementation of the governance plan.

[0195] The multi-objective optimization function can be a mathematical decision-making tool for balancing the comprehensive matching degree of governance solutions.

[0196] The optimal implementation path can be the governance solution execution strategy with the highest score and the lowest cost.

[0197] Specifically, the agent demand per unit area is calculated based on the pollution diffusion vector field and the agent migration rate. The dynamic monitoring frequency of soil parameters is then determined based on the accuracy requirements for spatiotemporal evolution predictions. The frequency of refilling is then calculated based on the compliance rate of the vegetation planting condition parameter set, and a remediation cost assessment model is constructed. Furthermore, based on the remediation cost assessment model, the injection concentration and frequency are dynamically adjusted according to the actual depth of action extracted from the remediation effect evolution map to reduce the cost of excessive injections. A secondary remediation cost budget is then added to cross-level risk nodes to determine the implementation cost parameters for each remediation solution. Subsequently, weight coefficients are defined for the matching degree and implementation cost parameters, and the matching degree and implementation cost parameters are normalized to eliminate dimensional differences. This generates an optimized score to quantify the overall effectiveness of the remediation solution. Remediation solutions with a matching degree below the minimum or a cost exceeding the minimum are then eliminated. The matching degree-cost Pareto optimal solution set is then screened, eliminating dominated solutions. Finally, the remediation solution with the highest and lowest scores is selected as the optimal implementation path.

[0198] Through this plan, it is determined to establish a governance cost assessment model and calculate the implementation cost parameters of each governance plan, which will help eliminate the problem of excessive drug administration caused by the lack of dynamic feedback of the neutralization reaction, reduce the resource waste rate, reduce the cost of ineffective monitoring, avoid repeated monitoring redundancy caused by the gap in the multi-node data growth mechanism, and avoid cross-level correlation risks. Construct a multi-objective optimization function, and perform weight calculation based on the comprehensive matching degree and implementation cost parameters to avoid excessive drug administration caused by the interaction between capillary pressure and fracture structure, and eliminate the problem of insufficient adaptability of governance plans. Select the governance plan with the highest score and lowest cost as the optimal implementation path based on the calculation results, which will help eliminate the problem of disconnection between the governance plan and vegetation restoration goals.

[0199] Figure 3A schematic diagram of the structure of a mine environment management system based on AI virtual simulation technology is provided in one embodiment of the present application. Figure 3 As shown, the mine environment management system 300 based on AI virtual simulation technology of this embodiment includes: a parameter set analysis module 301, a pattern determination module 302, a model building module 303, a map generation module 304, and a path determination module 305.

[0200] The parameter set analysis module 301 is used to obtain the dynamic geological parameter set of the target mine; analyze the dynamic geological parameter set to determine the injection data and soil capillary pressure detection data;

[0201] A mode determination module 302 is configured to determine a composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data;

[0202] The model building module 303 is used to analyze the composite diffusion pattern and determine the spatiotemporal evolution law; based on the spatiotemporal evolution law, an AI dynamic simulation model including the governance agent penetration feedback mechanism is constructed;

[0203] A graph generation module 304 is configured to perform multi-node data growth simulation on a number of treatment schemes based on the AI ​​dynamic simulation model, and generate a treatment effect evolution graph including the time-varying characteristics of the formation response;

[0204] The path determination module 305 is used to analyze the governance effect evolution map, determine the matching degree between the depth of action of the governance agent in each governance plan and the vegetation planting conditions; and determine the optimal governance plan implementation path based on the matching degree.

[0205] Optionally, the dynamic geological parameter set further includes the geological structure of the target mine; when the mode determination module 302 determines the composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data, it is used to:

[0206] Analyzing the injection data to determine the distribution of injection holes;

[0207] Based on the distribution of the injection holes, an image of the injection holes is acquired;

[0208] Analyzing the injection hole image to determine the characteristics of residual liquid on the surface;

[0209] determining the concentration of the residual liquid according to the characteristics of the residual liquid on the surface;

[0210] determining the migration rate of the treatment agent according to the residual liquid concentration and the soil capillary pressure detection data;

[0211] Analyze the geological structure and determine the direction of stratum fractures;

[0212] constructing a three-dimensional pollution diffusion vector field according to the migration rate and the direction of the stratum fracture;

[0213] The composite diffusion pattern of the treatment agent is determined according to the three-dimensional pollution diffusion vector field.

[0214] Optionally, the injection data includes an initial injection concentration; when the mode determination module 302 determines the migration rate of the treatment agent based on the residual liquid concentration and the soil capillary pressure detection data, it is used to:

[0215] Analyzing the soil capillary pressure detection data based on the geological structure to determine capillary pressure gradients at different levels;

[0216] Based on the residual liquid concentration measured by the initial injection concentration meter, the migration rate of the treatment agent is calculated according to Darcy's law and the capillary pressure gradients at different levels.

[0217] Optionally, when the model building module 303 constructs an AI dynamic simulation model including a governance agent penetration feedback mechanism according to the spatiotemporal evolution law, it is used to:

[0218] Determining the spatial concentration distribution characteristics of the treatment agent according to the spatiotemporal evolution law;

[0219] Inputting the spatial concentration distribution characteristics into a preset neutralization reaction efficiency prediction model, and outputting the neutralization efficiency time series data of the treatment agent;

[0220] Dynamically generate a self-optimizing instruction set for adjusting the reagent concentration and injection hole position based on the neutralization efficiency time series data and the preset mine management standards;

[0221] By integrating the self-optimizing instruction set and the formation fracture trend, an AI dynamic simulation model including a governance agent penetration feedback mechanism is constructed.

[0222] Optionally, the mine environment management system based on AI virtual simulation technology further includes a prediction model establishment module 306 for:

[0223] determining the chemical properties of the treatment agent based on the injection data;

[0224] determining soil buffer capacity based on the geological structure and the soil capillary pressure detection data;

[0225] A neutralization reaction efficiency prediction model is established based on the chemical properties and the soil buffer capacity.

[0226] Optionally, the dynamic geological parameter set includes soil sampling data; when the prediction model establishment module 306 establishes the neutralization reaction efficiency prediction model based on the chemical properties and the soil buffer capacity, it is used to:

[0227] Analyzing the soil sampling data to determine the calcium carbonate content and cation exchange capacity;

[0228] Determining the relationship between the consumption of the treatment agent and the pH value according to the chemical characteristics;

[0229] A neutralization reaction efficiency prediction model is established based on the change relationship, the soil capillary pressure detection data, the calcium carbonate content, the cation exchange capacity and the soil buffer capacity.

[0230] Optionally, the map generation module 304 performs multi-node data growth simulation on several treatment schemes based on the AI ​​dynamic simulation model to generate a treatment effect evolution map including the time-varying characteristics of the formation response, and is used to:

[0231] determining soil capillary capacity based on the soil capillary pressure detection data;

[0232] Quantifying the migration rate and the soil capillary capacity to obtain basic parameters and inputting them into the AI ​​dynamic simulation model so that the AI ​​dynamic simulation model performs multi-node data growth simulation of several governance solutions based on the basic parameters;

[0233] Obtaining simulation results of the AI ​​dynamic simulation model, analyzing the simulation results, and determining penetration data for each governance solution;

[0234] parsing the penetration data to determine a change in penetration depth and a timestamp of the change;

[0235] According to the change in penetration depth and the change timestamp, a treatment effect evolution map including the time-varying characteristics of the formation response is generated.

[0236] Optionally, when the path determination module 305 analyzes the governance effect evolution map and determines the matching degree between the depth of action of the governance agent and the vegetation planting conditions in each governance scheme, it is used to:

[0237] Obtain the vegetation planting condition parameter set corresponding to each treatment plan;

[0238] Based on the governance effect evolution map, the actual action depth and corresponding soil parameters of each governance scheme at different time points are extracted;

[0239] The matching degree between the soil parameters within the actual action depth and the vegetation planting condition parameter set is calculated to determine the matching degree between the action depth of the treatment agent and the vegetation planting conditions in each treatment scheme.

[0240] Optionally, when the path determination module 305 determines the optimal governance solution implementation path based on the matching degree, it is configured to:

[0241] Determine and establish a governance cost assessment model to calculate the implementation cost parameters of each governance plan;

[0242] Constructing a multi-objective optimization function, and performing weight calculation based on the matching degree and the implementation cost parameters;

[0243] Based on the calculation results, the governance plan with the highest score and lowest cost is selected as the optimal implementation path.

[0244] The system of this embodiment can be used to execute the method of any of the above embodiments. Its implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. A mine environment management method based on AI virtual simulation technology, characterized in that: include: Obtaining a dynamic geological parameter set of the target mine; analyzing the dynamic geological parameter set to determine injection data and soil capillary pressure detection data; determining a composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data; Analyze the composite diffusion pattern and determine the spatiotemporal evolution law; based on the spatiotemporal evolution law, construct an AI dynamic simulation model that includes the governance agent penetration feedback mechanism; Based on the AI ​​dynamic simulation model, a multi-node data growth simulation is performed on several treatment schemes to generate a treatment effect evolution map that includes the time-varying characteristics of the formation response; Analyze the evolution map of the treatment effect to determine the matching degree between the depth of action of the treatment agent in each treatment plan and the vegetation planting conditions; and determine the implementation path of the optimal treatment plan based on the matching degree.

2. The method according to claim 1, characterized in that The dynamic geological parameter set also includes the geological structure of the target mine; and determining the composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data includes: Analyzing the injection data to determine the distribution of injection holes; Based on the distribution of the injection holes, an image of the injection holes is acquired; Analyzing the injection hole image to determine the characteristics of residual liquid on the surface; determining the concentration of the residual liquid according to the characteristics of the residual liquid on the surface; determining the migration rate of the treatment agent according to the residual liquid concentration and the soil capillary pressure detection data; Analyze the geological structure and determine the direction of stratum fractures; constructing a three-dimensional pollution diffusion vector field according to the migration rate and the direction of the stratum fracture; The composite diffusion pattern of the treatment agent is determined according to the three-dimensional pollution diffusion vector field.

3. The method according to claim 2, characterized in that The injection data includes an initial injection concentration; and determining the migration rate of the treatment agent based on the residual liquid concentration and the soil capillary pressure detection data includes: Analyzing the soil capillary pressure detection data based on the geological structure to determine capillary pressure gradients at different levels; Based on the residual liquid concentration measured by the initial injection concentration meter, the migration rate of the treatment agent is calculated according to Darcy's law and the capillary pressure gradients at different levels.

4. The method according to claim 2, characterized in that According to the spatiotemporal evolution law, an AI dynamic simulation model including a governance agent penetration feedback mechanism is constructed, including: Determining the spatial concentration distribution characteristics of the treatment agent according to the spatiotemporal evolution law; Inputting the spatial concentration distribution characteristics into a preset neutralization reaction efficiency prediction model, and outputting the neutralization efficiency time series data of the treatment agent; According to the neutralization efficiency time series data and the preset mine management standards, a self-optimization instruction set for adjusting the reagent concentration and the injection hole position is dynamically generated; By integrating the self-optimization instruction set and the formation fracture trend, an AI dynamic simulation model including a governance agent penetration feedback mechanism is constructed.

5. The method according to claim 4, characterized in that The construction of the preset neutralization reaction efficiency prediction model includes: determining the chemical properties of the treatment agent based on the injection data; determining soil buffer capacity based on the geological structure and the soil capillary pressure detection data; A neutralization reaction efficiency prediction model is established based on the chemical properties and the soil buffer capacity.

6. The method according to claim 5, characterized in that The dynamic geological parameter set includes soil sampling data; the neutralization reaction efficiency prediction model is established based on the chemical properties and the soil buffer capacity, including: Analyzing the soil sampling data to determine the calcium carbonate content and cation exchange capacity; Determining the relationship between the consumption of the treatment agent and the pH value according to the chemical characteristics; A neutralization reaction efficiency prediction model is established based on the change relationship, the soil capillary pressure detection data, the calcium carbonate content, the cation exchange capacity and the soil buffer capacity.

7. The method according to claim 4, characterized in that Based on the AI ​​dynamic simulation model, a multi-node data growth simulation is performed on several treatment schemes to generate a treatment effect evolution map containing the time-varying characteristics of the formation response, including: determining soil capillary capacity based on the soil capillary pressure detection data; Quantifying the migration rate and the soil capillary capacity to obtain basic parameters and inputting them into the AI ​​dynamic simulation model so that the AI ​​dynamic simulation model performs multi-node data growth simulation of several governance solutions based on the basic parameters; Obtaining simulation results of the AI ​​dynamic simulation model, analyzing the simulation results, and determining penetration data for each governance solution; parsing the penetration data to determine a change in penetration depth and a timestamp of the change; According to the change in penetration depth and the change timestamp, a treatment effect evolution map including the time-varying characteristics of the formation response is generated.

8. The method according to claim 1, characterized in that The analysis of the governance effect evolution map to determine the matching degree between the depth of action of the governance agent in each governance scheme and the vegetation planting conditions includes: Obtain the vegetation planting condition parameter set corresponding to each treatment plan; Based on the governance effect evolution map, the actual action depth and corresponding soil parameters of each governance scheme at different time points are extracted; The matching degree between the soil parameters within the actual action depth and the vegetation planting condition parameter set is calculated to determine the matching degree between the action depth of the treatment agent and the vegetation planting conditions in each treatment scheme.

9. The method according to claim 8, characterized in that Determining the optimal governance solution implementation path based on the matching degree includes: Determine and establish a governance cost assessment model to calculate the implementation cost parameters of each governance plan; Constructing a multi-objective optimization function, and performing weight calculation based on the matching degree and the implementation cost parameters; Based on the calculation results, the governance plan with the highest score and lowest cost is selected as the optimal implementation path.

10. A mine environment management system based on AI virtual simulation technology, characterized in that: The method according to any one of claims 1 to 9, characterized in that it includes: A parameter set analysis module is used to obtain a dynamic geological parameter set of a target mine; analyze the dynamic geological parameter set to determine injection data and soil capillary pressure detection data; a mode determination module, configured to determine a composite diffusion mode of the treatment agent based on the injection data and the soil capillary pressure detection data; A model building module is used to analyze the composite diffusion pattern and determine the spatiotemporal evolution law; based on the spatiotemporal evolution law, an AI dynamic simulation model including the governance agent penetration feedback mechanism is constructed; A graph generation module is used to perform multi-node data growth simulation on several treatment schemes based on the AI ​​dynamic simulation model to generate a treatment effect evolution graph that includes the time-varying characteristics of the formation response; The path determination module is used to analyze the evolution map of the treatment effect and determine the matching degree between the depth of action of the treatment agent in each treatment plan and the vegetation planting conditions; based on the matching degree, the optimal treatment plan implementation path is determined.

Images