Mine disaster early warning method and system

Abstract

The present application relates to the technical field of mine exploitation, and in particular to a mine disaster early warning method and system. The method comprises: obtaining geological structure data corresponding to the mine, the geological structure data including rock layer distribution, fault occurrence and groundwater occurrence state; constructing a coupling model corresponding to the mine based on the rock layer distribution, fault occurrence and groundwater occurrence state, and determining the rock mass constitutive relation and coupling parameters in the coupling model; determining the prediction boundary conditions of the coupling model based on the rock mass constitutive relation and coupling parameters; obtaining the on-site monitoring data of the mine, and correcting the coupling model based on the on-site monitoring data and the prediction boundary conditions, to determine the potential disaster points based on the corrected coupling model, and generate the risk early warning strategy and risk recovery strategy corresponding to the potential disaster points. The embodiments of the present application construct a whole-chain prevention and control system from disaster prediction to emergency disposal, and significantly improve the safety management level and disaster prevention and control capability of mine engineering.

Description

Technical Field

[0001] This invention relates to the field of mining technology, specifically to a method and system for early warning of mine disasters. Background Technology

[0002] With the further development of science and technology, industrial production has experienced explosive growth. The consumption of large amounts of mineral resources is driving the country's rapid development and the continuous improvement of people's living standards. In the future, maintaining economic development will still require sufficient mineral resources, which has led to a year-on-year increase in the demand for mineral resources in many industries.

[0003] However, as mining activities proceed, the stability of the underground rock mass is disrupted. The original rock stress field changes with excavation, and stress is redistributed, forming a secondary stress field. If the new stress field changes only slightly compared to the original stress field, and the physical and mechanical properties of the rock mass itself can withstand this change, a new equilibrium state will emerge, and the underground rock mass will remain stable. If the rock mass itself cannot withstand the changes in the stress field, it is highly likely to become unstable, and phenomena such as surrounding rock deformation and roof movement, which manifest as ground pressure activity, will inevitably occur. If timely monitoring and prediction are not carried out, it is very likely to cause safety accidents to the normal production operations of mining enterprises, ranging from minor property damage to serious casualties. Therefore, there is an urgent need for a technical solution that can predict mine disasters in advance. Summary of the Invention

[0004] To address the aforementioned technical problems, embodiments of the present invention provide a method and system for early warning of mine disasters.

[0005] According to one aspect of the present invention, a mine disaster early warning method is provided, comprising: acquiring geological structure data corresponding to the mine, the geological structure data including rock strata distribution, fault occurrence, and groundwater occurrence; constructing a coupling model corresponding to the mine based on the rock strata distribution, fault occurrence, and groundwater occurrence, and determining the rock mass constitutive relationship and coupling parameters in the coupling model; determining the prediction boundary conditions of the coupling model based on the rock mass constitutive relationship and the coupling parameters; acquiring on-site monitoring data of the mine, and correcting the coupling model based on the on-site monitoring data and the prediction boundary conditions, so as to determine potential disaster points based on the corrected coupling model, and generating risk early warning strategies and risk recovery strategies corresponding to the potential disaster points.

[0006] According to one aspect of the present invention, determining the constitutive relationship of the rock mass and the coupling parameters in the coupled model includes: obtaining the strength parameters corresponding to the coupled model, the strength parameters including elastic modulus, Poisson's ratio, uniaxial compressive strength, triaxial compressive strength, cohesion, and internal friction angle; inverting the principal stress direction and principal stress value of the initial geostress field of the coupled model based on the hydraulic fracturing method; and determining the constitutive relationship of the rock mass and the coupling parameters in the coupled model based on the strength parameters, the principal stress direction, and the principal stress value.

[0007] According to one aspect of the present invention, the method further includes: acquiring multi-source data of the mine, and fusing the multi-source data and numerical simulation results based on a Bayesian update algorithm to obtain a fused multi-source dataset; performing sensitivity analysis on the fused multi-source dataset, and using multi-source data with sensitivity greater than a preset sensitivity threshold as target data; determining the actual boundary conditions of the mine based on the target data, and correcting the coupling model based on the actual boundary conditions and the predicted boundary conditions.

[0008] According to one aspect of the present invention, the target data includes rock mass deformation, and the step of correcting the coupled model based on the actual boundary conditions and the predicted boundary conditions includes: determining the rock mass deformation of the mine based on the field monitoring data; determining the porosity change rate of the mine based on the rock mass deformation, and determining the actual seepage field boundary conditions of the mine based on the porosity change rate; updating the predicted seepage field boundary conditions in the coupled model based on the actual seepage field boundary conditions, so as to correct the coupled model based on the updated seepage field boundary conditions.

[0009] According to one aspect of the present invention, the target data includes rock mass microseismic data, and the step of correcting the coupled model based on the actual boundary conditions and the predicted boundary conditions includes: determining the rock mass microseismic data of the mine based on the field monitoring data, wherein the microseismic data includes spatial coordinate data of microseismic events; determining the actual damage boundary conditions of the mine based on the spatial coordinate data; and updating the predicted damage boundary conditions in the coupled model based on the actual damage boundary conditions, so as to correct the coupled model based on the updated damage boundary conditions.

[0010] According to one aspect of the present invention, the target data includes support structure data, and the step of correcting the coupled model based on the actual boundary conditions and the predicted boundary conditions includes: determining support structure data corresponding to the rock mass of the mine based on the field monitoring data, wherein the support structure includes anchor stress data; determining an anchor stress threshold, and determining the actual stress boundary conditions of the mine based on the anchor stress threshold and the anchor stress data; updating the predicted stress boundary conditions in the coupled model based on the actual stress boundary conditions, so as to correct the coupled model based on the updated stress boundary conditions.

[0011] According to one aspect of the present invention, the step of determining potential disaster points based on a modified coupling model and generating risk warning strategies and risk recovery strategies corresponding to the potential disaster points includes: determining the distribution of the plastic zone, the volume of the plastic zone, and the diffusion rate of the plastic zone corresponding to the mine based on the modified coupling model; determining potential rockburst disaster points based on the distribution of the plastic zone, the volume of the plastic zone, and the diffusion rate of the plastic zone, and generating risk warning strategies and risk recovery strategies corresponding to the potential rockburst disaster points.

[0012] According to one aspect of the present invention, the step of determining potential disaster points based on a modified coupling model and generating risk warning strategies and risk recovery strategies corresponding to the potential disaster points includes: determining the displacement vector field corresponding to the mine based on the modified coupling model; determining the gradient tensor and shear displacement corresponding to the displacement vector field; determining potential disaster points based on the gradient tensor and shear displacement, and generating risk warning strategies and risk recovery strategies corresponding to the potential disaster points.

[0013] According to one aspect of the present invention, the step of determining potential disaster points based on a modified coupling model and generating risk warning strategies and risk recovery strategies corresponding to the potential disaster points includes: determining a coupled numerical model corresponding to the mine based on the modified coupling model, wherein the coupled numerical model includes a coupled model of rock mass seepage field and stress field; determining the seepage velocity field and pore water pressure distribution of the mine based on the coupled model of rock mass seepage field and stress field; determining potential water inrush disaster points and water inrush prediction time based on the seepage velocity field and pore water pressure distribution; and generating risk warning strategies and risk recovery strategies corresponding to the potential water inrush disaster points based on the water inrush prediction time.

[0014] According to one aspect of the present invention, a mine disaster early warning system is provided. The system includes an input device, a processor, an output device, and a memory, wherein the input device, the processor, the output device, and the memory are interconnected. The memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions. The system uses the aforementioned mine disaster early warning method.

[0015] In the technical solution provided in the embodiments of the present invention, a coupled model is constructed by integrating multi-source geological structural data such as rock strata distribution, fault occurrence, and groundwater occurrence. Based on the constitutive relationship of the rock mass and the coupling parameters, the predicted boundary conditions are determined, thereby achieving accurate modeling of the complex geological environment of the mine. Subsequently, the model is dynamically corrected by on-site monitoring data, which can effectively overcome the impact of geological uncertainties on prediction accuracy, enabling the model to more realistically reflect the multi-field coupling effects of rock mass stress, seepage, deformation, etc. Finally, based on the corrected model, potential disaster points are accurately identified and risk warning and recovery strategies are generated, constructing a full-chain prevention and control system from disaster prediction to emergency response. This significantly improves the safety management level and disaster prevention and control capabilities of mining engineering, providing scientific and reliable technical support for ensuring personnel safety, reducing economic losses, and predicting disasters in mining areas.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 This is a flowchart illustrating a specific method for early warning of mine disasters, as shown in an exemplary embodiment of the present invention. Figure 2 A schematic diagram of a mine disaster early warning system suitable for implementing embodiments of the present invention is shown. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0019] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0020] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0021] In this invention, "multiple" refers to two or more. "And / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0022] Throughout this specification, references to "an embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0023] First and foremost, it should be noted that mine disaster prediction is a primary measure for preventing and controlling geological disasters in mines. By predicting mine geological disasters, reasonable prevention and control measures can be formulated to reduce the impact of disasters on the mine environment and ecology, and promote the sustainable development of mines. For example, before mining activities commence, potential geological disasters that may be triggered by mining activities can be predicted based on the geological structure, hydrogeological conditions, and engineering geological conditions of the mining area, and reasonable prevention and control measures can be developed.

[0024] In one optional embodiment, please refer to Figure 1 To address the problem of predicting mine disasters, this invention proposes a mine disaster early warning method, which includes at least steps S110 to S140, detailed below: Step S110: Obtain geological structure data corresponding to the mine. The geological structure data includes rock strata distribution, fault occurrence, and groundwater occurrence status.

[0025] For example, direct and indirect information about underground rock strata and structures can be obtained through drilling and geophysical exploration (such as seismic and electromagnetic exploration); then hydrogeological surveys can be conducted to analyze groundwater parameters, and surface geological features can be extracted using remote sensing and geographic information system technology (GIS). The data can then be integrated using 3D geological modeling software to construct a visualization model of the mine, and this coupled model can be discretized into finite element meshes (such as tetrahedral and hexahedral elements). The mesh density needs to be optimized according to the requirements of computational accuracy and efficiency.

[0026] Step S120: Construct a coupled model of the mine based on the distribution of rock strata, fault occurrence, and groundwater occurrence, and determine the constitutive relationship of the rock mass and the coupling parameters in the coupled model.

[0027] For example, a three-dimensional geometric model can be generated in geological modeling software by integrating rock strata distribution data (such as borehole data and seismic exploration results), fault occurrence information (strike, dip, dip angle, and displacement), and groundwater occurrence status (permeability coefficient, pore water pressure distribution). The model is then meshed, with the mesh near faults fined to capture deformation characteristics. The constitutive model is selected based on the rock mass type; for example, a linear elastic model is typically used for intact rock masses, while a Mohr-Coulomb plastic model is used for jointed rock masses. Fault slip behavior can be simulated using contact surface elements. Subsequently, combining the seepage and stress coupling effect, the effective stress principle and Darcy's law are introduced, and boundary conditions for permeability coefficient and pore water pressure are set to simulate the influence of groundwater on the rock mass stress field. Finally, through parameter inversion and history matching methods, model parameters (such as elastic modulus, cohesion, and permeability coefficient) are adjusted to ensure consistency between numerical results and field monitoring data (displacement, stress, and pore water pressure), verifying the model's reliability.

[0028] Step S130: Determine the predicted boundary conditions of the coupled model based on the constitutive relationship of the rock mass and the coupling parameters.

[0029] For example, based on the constitutive relationship of the rock mass and coupling parameters, the predictive boundary conditions of the model can be set: in stress field analysis, mining disturbances (such as working face advancement), initial in-situ stress conditions, and fixed constraint boundaries are applied; in seepage field analysis, the head boundary of the aquifer (such as a constant head boundary or flow boundary) and the zero flow boundary of the impermeable layer are set. The spatiotemporal evolution of the seepage velocity field and stress field is solved by discretizing the coupled model using the finite element method or finite difference method, ultimately achieving the coordinated prediction of rock mass stability and groundwater dynamics during mining. Three-dimensional numerical simulation of the mine can be achieved using multiphysics coupling software, and actual monitoring data can be continuously fed back to the model to optimize parameters and boundary conditions, ensuring the reliability of the prediction results.

[0030] Step S140: Obtain on-site monitoring data of the mine, and modify the coupling model based on the on-site monitoring data and predicted boundary conditions. Based on the modified coupling model, determine potential disaster points and generate risk warning strategies and risk recovery strategies corresponding to the potential disaster points.

[0031] For example, monitoring equipment (such as displacement gauges, stress gauges, and pore water pressure gauges) is deployed in key areas of the mine (such as goaf, fault zones, and high-stress zones) to collect real-time data on rock mass displacement, stress changes, and groundwater dynamics. Subsequently, the monitoring data is compared with the results of numerical model calculations. Model input parameters (such as elastic modulus, permeability coefficient, and constitutive model parameters) are adjusted through parameter inversion or model calibration techniques (such as sensitivity analysis and genetic algorithm optimization) to ensure consistency between the model output and the measured data. Then, based on the corrected model, the rock mass response under different mining conditions is simulated to identify potential disaster points such as stress concentration, plastic zone penetration, or sudden displacement. For the identified disaster points, risk warning strategies (such as setting warning thresholds, increasing monitoring frequency, and implementing dynamic support) and risk recovery strategies (such as reserving safety coal pillars, optimizing mining sequence, and strengthening drainage measures) are developed based on engineering experience. Finally, the warning and recovery strategies are integrated into the mine safety management system to achieve dynamic control and rapid response to disaster risks. Furthermore, in practical applications, the entire process of correcting the coupled model of the mine using on-site monitoring data needs to be continuously iterated, and the model needs to be updated based on new monitoring data to ensure the effectiveness of mine disaster early warning and recovery strategies.

[0032] In some embodiments of the present invention, by comprehensively acquiring geological structure data of the mine, constructing a coupled model, and accurately defining the constitutive relationship and coupling parameters of the rock mass, a digital simulation of the complex geological environment of the mine is realized. By setting the predicted boundary conditions and dynamically correcting the data through on-site monitoring, the model accuracy can be calibrated in real time, effectively capturing dynamic changes in the geological structure, thereby accurately identifying potential disaster points and upgrading traditional static analysis to dynamic prediction. This significantly improves the timeliness and accuracy of mine disaster early warning. At the same time, through the collaborative generation of risk warning strategies and recovery plans, a full-chain technical support for disaster prevention and control is provided from early warning to disposal, ultimately enhancing the mine's safety production management capabilities and reducing economic losses and personnel risks caused by geological disasters.

[0033] Furthermore, based on the above embodiments, please refer to... Figure 2 In one exemplary embodiment provided by the present invention, the specific implementation process of step S120 may further include steps S210 to S230, which are described in detail below: Step S210: Obtain the strength parameters corresponding to the coupled model. The strength parameters include elastic modulus, Poisson's ratio, uniaxial compressive strength, triaxial compressive strength, cohesion, and internal friction angle.

[0034] For example, the coupled model can be assigned values ​​of mechanical parameters (such as elastic modulus, Poisson's ratio, uniaxial compressive strength, triaxial compressive strength, cohesion, and internal friction angle) measured in the laboratory to the corresponding rock strata in the numerical model. For instance, the constitutive relation of the rock mass can be obtained using a nonlinear model that considers damage evolution. Its parameters are determined by a combination of indoor rock mechanics tests and in-situ stress inversion. Then, the elastic modulus, Poisson's ratio, and strength parameters are obtained through uniaxial / triaxial compression tests. In the triaxial compression test, the rock mass sample is initially loaded isotropically until the principal stress equals the predetermined confining pressure. Then, the axial stress increases at a certain rate until the sample fails, and the maximum axial stress is recorded. This allows us to obtain not only the triaxial compressive strength of the rock but also the Mohr strength envelope, thereby obtaining the cohesion and internal friction angle of the rock.

[0035] Step S220: Based on the hydraulic fracturing method, the principal stress directions and principal stress values ​​of the initial geostress field are obtained from the inversion coupled model.

[0036] On the other hand, the principal stress directions and magnitudes of the initial geostress field can be inverted using measured data from the hydraulic fracturing method. Specifically, methods such as geophysical modeling, geomechanical modeling, and numerical simulation are used to process and analyze the data. Algorithms such as inverse problem solving, least squares fitting, and inversion optimization are employed to compare the observed data with the simulation results. By continuously adjusting the model parameters and fitting errors, the inversion results of the geostress field are gradually optimized to obtain the principal stress directions and magnitudes of the initial geostress field.

[0037] Optionally, the stress state at a point within a rock mass is typically described by the magnitude and direction of the principal stresses. By projecting the rock mass stress into three dimensions, and defining compressive stress as positive and tensile stress as negative, the stress is decomposed into stress components in three directions: the vertical stress component... Horizontal stress components and ,in, It is mainly generated by the gravity of the overlying strata, and its magnitude is related to the rock's burial depth, volume, and density. The calculation formula is as follows:

[0038] in, Where is the maximum burial depth, and g is the acceleration due to gravity. The density of the overlying rock strata. For depth.

[0039] Furthermore, under the influence of tectonic movements, the underground crustal movements are extremely complex, resulting in differences in horizontal geostress and a certain degree of directionality. and The magnitudes are not equal and are not equal to 0. The order of magnitude of the geostress components is as follows: > > .

[0040] Step S230: Determine the constitutive relationship of the rock mass and the coupling parameters in the coupled model based on the strength parameters, principal stress directions and principal stress values.

[0041] In some feasible embodiments, the Mohr-Coulomb elastoplastic model can be used as the constitutive relation, and its calculation formula is as follows:

[0042] in, For cohesion, It is the internal friction angle. and These represent the maximum and minimum principal stresses, respectively. The directions of the principal stresses are determined through in-situ measurements or numerical inversion, and the principal stress values ​​are used to initialize the stress field of the model. Then, the stress-strain relationship in the elastic stage can be expressed as:

[0043] in, To adapt to changing circumstances For elastic modulus, It is Poisson's ratio, and the elastic parameters can be dynamically adjusted according to the principal stress value to reflect the influence of stress state on rock mass deformation. Among these, the coupling parameters typically include the elastic modulus. Poisson's ratio Cohesion internal friction angle These parameters can be obtained through laboratory or field tests and corrected in conjunction with principal stress values. Furthermore, the elastic modulus is adjusted based on the principal stress values. Compared to Poisson Dynamic adjustments are made to reflect the influence of stress state on the deformation characteristics of rock mass.

[0044] In some embodiments of the present invention, by obtaining key strength parameters of the rock mass in the coupled model and combining them with the hydraulic fracturing method to accurately invert the principal stress directions and magnitudes of the initial geostress field, a quantitative characterization of the rock mass's mechanical properties and geostress state is achieved. This multi-parameter fusion analysis method can more realistically reflect the nonlinear deformation and failure mechanism of the rock mass under complex stress paths, thereby improving the accuracy of the coupled model in characterizing the constitutive relations of the rock mass (such as stress-strain relations) and coupling parameters (such as seepage and stress coupling coefficients).

[0045] Furthermore, based on the above embodiments, in one exemplary embodiment provided by the present invention, the specific implementation process of the above-mentioned mine disaster early warning method may further include steps S310 to S330, which are described in detail below: Step S310: Obtain multi-source data from the mine, and fuse the multi-source data and numerical simulation results based on the Bayesian update algorithm to obtain the fused multi-source dataset.

[0046] For example, in the process of multi-source data fusion in mines, firstly, heterogeneous data from multiple sources, such as geological exploration data, environmental monitoring data, and production equipment data, are acquired through sensor networks, remote sensing monitoring, and historical databases, and the data is cleaned and standardized. Then, a mine rock mechanics model or ventilation network model is constructed using numerical simulation software to generate simulation results under different working conditions. Next, based on the Bayesian update algorithm, the observed values ​​of the multi-source data are used as the likelihood function, and the prediction results of the numerical simulation are used as the prior distribution. The posterior probability distribution is updated through iterative calculation, and the model parameters are dynamically adjusted to reduce the deviation between the prediction and the measurement. Finally, the updated posterior distribution parameters are fed back into the numerical model to output a multi-source dataset that integrates spatiotemporal consistency and uncertainty, providing support for mine safety early warning and optimization decision-making.

[0047] Step S320: Based on sensitivity analysis, determine the target data in the fused multi-source dataset. The target data includes multi-source data with sensitivity greater than a preset sensitivity threshold.

[0048] Step S330: Determine the dynamic correction model parameters based on the target data, and correct the coupled model based on the dynamic correction model parameters.

[0049] For example, in mining engineering, coupled models (such as seepage, stress, and damage coupled models) are used to describe the interactions between different physical fields in a mining system. Changes in coupling parameters can significantly impact the model output. Therefore, sensitivity analysis can be used to determine the sensitivity of each data point in the fused multi-source dataset to changes in the coupling parameters of the mining coupled model, thereby providing a scientific basis for data collection priorities and mine disaster assessment.

[0050] Optionally, in some feasible embodiments, it can be assumed that the coupled model output of the mine is Y (e.g., key indicators such as displacement, stress, and seepage flow), and the coupling parameters are... , ,... The data variables in the merged multi-source dataset are , ,... Then the coupling model can be expressed as:

[0051] in, It represents the functional relationship of the coupled model.

[0052] Then, for the coupling parameters (1,2,...,m) represents the data variables. The sensitivity of (i=1,2,...,n) to changes can be measured by the first-order partial derivatives, hence the definition of the sensitivity coefficient. The calculation formula is as follows:

[0053] in, This indicates that the output Y of the coupled model is related to the coupling parameters. The first-order partial derivative reflects the rate at which the model output changes with the coupling parameters; It is a normalization factor used to eliminate the influence of dimensions and make the sensitivity coefficients of different coupling parameters comparable; Represents coupling parameters For data variables The rate of change reflects the degree of influence of the data variables on the coupling parameters. The absolute value is taken to ensure that the sensitivity coefficient is non-negative, which facilitates the comparison of the sensitivity of each data variable to different coupling parameters.

[0054] Calculate each data variable For each coupling parameter Sensitivity coefficient Then, the data variables can be sorted according to different needs. For example, for each coupling parameter, the data variables can be sorted from largest to smallest according to their sensitivity coefficients to find the data variables most sensitive to changes in that coupling parameter; alternatively, a comprehensive analysis of the sensitivity coefficients for all coupling parameters can be performed to determine the importance of the data variables in the entire coupling model.

[0055] Then, multi-source data with sensitivity coefficients greater than the preset sensitivity threshold are used as target data, and dynamic model correction parameters of the coupling model of the mine are determined based on the target data, so as to correct the coupling model according to the dynamic model correction parameters.

[0056] In some embodiments of this invention, the Bayesian update algorithm efficiently integrates multi-source mine data (such as monitoring data, geological exploration data, etc.) with numerical simulation results, effectively consolidating multi-dimensional information and reducing data uncertainty, thereby improving the completeness and reliability of the dataset. Sensitivity analysis is used to select key data that significantly impact the model as target data, focusing on core variables and avoiding redundant information interference, thus accurately determining the actual boundary conditions of the mine. The coupled model is dynamically corrected by combining the actual boundary conditions with the initial predicted boundary conditions, making the model more closely resemble the real geological and engineering environment, significantly improving the accuracy of mine disaster prediction and rock mass stability analysis, and enhancing the precision of mine disaster prediction.

[0057] Furthermore, based on the above embodiments, in one exemplary embodiment provided by the present invention, the target data includes rock mass deformation. The specific implementation process of the coupling model modified based on actual boundary conditions and predicted boundary conditions may further include steps S410 to S430, which are described in detail below: Step S410: Determine the amount of rock mass deformation in the mine based on on-site monitoring data; Step S420: Determine the porosity change rate of the mine based on the rock mass deformation, and determine the actual seepage field boundary conditions of the mine based on the porosity change rate. Step S430: Update the predicted seepage field boundary conditions in the coupled model based on the actual seepage field boundary conditions, so as to correct the coupled model based on the updated seepage field boundary conditions.

[0058] Following the examples described above, by analyzing the sensitivity of various data points from multiple sources in the mine, target data that significantly impacts the output parameters of the coupled mine model is identified. This target data includes the rock mass deformation. Specifically, real-time rock mass displacement data, including surface subsidence, tunnel convergence, and strata movement, is acquired using on-site monitoring equipment (such as displacement sensors and total stations). Based on the data acquisition time, the cumulative deformation and deformation rate of the mine's rock mass are determined. Since rock mass deformation leads to the compression or expansion of pores and fractures, it alters pore volume. Furthermore, the spatial distribution of rock mass deformation can be combined to calculate the overall porosity change rate. For example, in the numerical model, the porosity change rate of each element is calculated using nodal displacements.

[0059] Furthermore, it can be based on the permeability of the rock mass ( ) and porosity ( There is usually a positive correlation between them, which can be described by empirical formulas or theoretical models. The specific calculation formula is as follows:

[0060] in, It is the initial permeability of the rock mass in the mine. It is the initial porosity, and n is an empirical index, which is generally taken as 2 to 3.

[0061] Then, based on the full-field distribution of the porosity variation rate of the mine rock mass, the permeability field of the rock mass can be updated, and new seepage field boundary conditions can be established. For example, the head distribution can be determined by correcting the head distribution based on pore water pressure monitoring data; the flow rate boundary can be determined by adjusting the flow input or output conditions based on permeability changes; and the pore water pressure boundary can be determined by correcting the pore water pressure distribution based on the porosity variation rate. In the solid-liquid coupling model, the seepage field and stress field are typically coupled using the following calculation formula:

[0062]

[0063] Where h is the water head, For stress, For water storage rate, For rock mass density, This is the acceleration due to gravity.

[0064] Then, the rock mass deformation and porosity change rate determined based on on-site monitoring data are imported into the above calculation formula to obtain the actual seepage field boundary conditions of the mine. Subsequently, the predicted seepage field boundary conditions in the coupled model are updated based on the actual seepage field boundary conditions to update the head boundary, flow boundary, and pore water pressure boundary in the coupled model.

[0065] In some embodiments of this invention, the deformation of the mine rock mass is quantified using on-site monitoring data, thereby deriving the porosity change rate and determining the actual seepage field boundary conditions, achieving dynamic capture of the seepage-stress coupling effect in the mine. By feeding back the actual seepage field boundary conditions to the coupled model and updating the predicted values, errors caused by geological complexity or initial assumption deviations in the model can be effectively corrected. This allows the coupled model to more realistically reflect the influence mechanism of changes in rock mass pore structure on groundwater seepage. The iterative process significantly improves the prediction accuracy of the coupled model under complex hydrogeological conditions, enhances the reliability of simulating the coupling effect of seepage and stress fields in mining engineering, and provides a reliable scientific basis for mine disaster prediction.

[0066] Furthermore, based on the above embodiments, in one exemplary embodiment provided by the present invention, the target data includes rock mass microseismic data, and the specific implementation process of the coupling model based on actual boundary conditions and predicted boundary conditions may further include steps S510 to S530, which are described in detail below: Step S510: Determine the microseismic data of the mine's rock mass based on the field monitoring data. The microseismic data includes the spatial coordinate data of microseismic events. Step S520: Determine the actual damage boundary conditions of the mine based on spatial coordinate data; Step S530: Update the predicted damage boundary conditions in the coupled model based on the actual damage boundary conditions, so as to correct the coupled model based on the updated damage boundary conditions.

[0067] For example, microseismic event data within the rock mass can be collected in real time using a microseismic monitoring system at the mine site (such as seismographs, accelerometers, etc.). This microseismic data typically includes: spatial coordinates of the microseismic event representing its three-dimensional location; the time of occurrence, magnitude (energy), and waveform characteristics of the microseismic event. The spatial coordinates of the microseismic event are then projected onto a three-dimensional mine model to generate a spatial distribution map of the microseismic event. Furthermore, the magnitude of the microseismic event can be calculated from its spatial coordinates and based on waveform amplitude or energy release. Then, based on the distribution density and magnitude of the microseismic events, the boundaries of the damaged area are delineated, and the cumulative energy per unit volume of microseismic events is calculated. Finally, the initial fractures or weak surfaces of the corresponding damaged area in the mine are determined.

[0068] Furthermore, in the solid-liquid damage coupling model, the loss evolution of the mine can be represented as follows:

[0069] in, As a damage variable, For stress, In response, This refers to micro-vibration energy. Strain is a physical quantity that describes the change in the relative position of points within an object during the process of being subjected to force or deformation, and reflects the degree of deformation of the rock mass.

[0070] Furthermore, the spatial coordinates and damage levels of the actual monitored microseismic events can be imported into the coupled model. Then, based on the damage area delineated by the microseismic data, the damage field distribution of the model is initialized, thereby revealing the correction of the damage boundary conditions of the mine. Furthermore, by solving the coupled mine model, the updated stress field, seepage field, and damage field distribution can be obtained.

[0071] In some embodiments of the present invention, spatial coordinate information of microseismic events in the mine rock mass is extracted from field monitoring data to accurately locate the position of rock mass fracture and damage evolution, thereby determining the actual damage boundary conditions. By dynamically comparing and updating the actual damage boundary conditions with the predicted values ​​in the coupled model, errors caused by geological uncertainties or initial assumption deviations can be corrected in real time, making the model more realistically reflect the damage accumulation and spatial expansion process of the rock mass under mining disturbance. This dynamic feedback mechanism based on microseismic monitoring significantly improves the simulation accuracy of the coupled model for the progressive failure process of the rock mass, enhances the early warning and prevention capabilities of mine disasters, and provides reliable technical support for optimizing mining plans and ensuring operational safety.

[0072] Furthermore, based on the above embodiments, in one exemplary embodiment provided by the present invention, the target data further includes support structure data, and the specific implementation process of the coupling model modified based on actual boundary conditions and predicted boundary conditions may further include steps S610 to S630, which are described in detail below: Step S610: Determine the support structure data corresponding to the rock mass of the mine based on the on-site monitoring data. The support structure includes anchor stress data. Step S620: Determine the anchor bolt stress threshold, and determine the actual stress boundary conditions of the mine based on the anchor bolt stress threshold and anchor bolt stress data; Step S630: Update the predicted stress boundary conditions in the coupled model based on the actual stress boundary conditions, so as to correct the coupled model based on the updated stress boundary conditions.

[0073] For example, based on on-site monitoring data, the support structure data of the mine is first collected in real time using equipment such as anchor stress gauges, with a focus on obtaining anchor stress data and its spatial distribution characteristics. Then, combined with support design specifications and engineering experience, the safety threshold of anchor stress is determined, and areas in the monitoring data that exceed this threshold are identified as high-stress boundaries, thereby clarifying the actual stress boundary conditions of the mine. Finally, the actual stress boundary conditions are imported into the solid-liquid damage coupling model, updating the original predicted stress boundaries in the model (such as adjusting the support parameters or stress assignments in high-stress areas), and correcting the coupling relationship between the stress field, seepage field, and damage field by resolving the model, forming a dynamic feedback mechanism of "monitoring, identification, and correction" to ensure that the model prediction results are consistent with the actual stress state of the mine, providing a reliable basis for support structure optimization and disaster prevention.

[0074] Optionally, in the solid-liquid damage coupling model, the stress boundary conditions are described by the following expression:

[0075] in, For stress tensor, For rock mass density, This is the acceleration due to gravity.

[0076] Then, the anchor stress data can be imported into the above expression to obtain the high-stress areas of the mine (areas where the anchor stress exceeds the threshold are identified as high-stress boundaries), and to obtain the active stress boundaries where the anchor stress is actively applied to the rock mass and the passive stress boundaries where the anchor stress is passively triggered by rock mass deformation. This allows for the correction of the stress boundaries in the coupled model.

[0077] In some embodiments of the present invention, stress information of mine rock mass support structures (such as anchor bolts) is obtained through on-site monitoring data. The actual stress boundary conditions are quantified by combining the preset anchor bolt stress threshold, thereby realizing real-time perception of the stress state of the support structure and the stress distribution of the rock mass. On the other hand, by dynamically comparing and updating the actual stress boundary conditions with the predicted values ​​in the coupled model, the prediction deviation of the stress field caused by the complexity of geological conditions or construction disturbances can be effectively corrected. This makes the model more accurately reflect the synergistic mechanism between the rock mass and the support structure, significantly improving the simulation accuracy of the coupled model for rock mass stress evolution and support effectiveness. It also enhances the reliability of stress and support coupling effect assessment in mining engineering, providing a scientific basis for preventing support failure and ensuring operational safety.

[0078] Furthermore, based on the above embodiments, in one exemplary embodiment provided by the present invention, the specific implementation process of determining potential disaster points based on the modified coupling model and generating risk warning strategies and risk recovery strategies corresponding to the potential disaster points may further include steps S710 and S720, which are described in detail below: Step S710: Determine the distribution, volume, and diffusion rate of the plastic zone corresponding to the mine based on the modified coupling model; Step S720: Based on the distribution, volume and diffusion rate of the plastic zone, determine the potential rockburst hazard points, and generate the corresponding risk warning strategy and risk recovery strategy for the potential rockburst hazard points.

[0079] For example, based on the modified coupled model, the distribution of the plastic zone in the mine is first calculated through numerical simulation, that is, the area where the rock mass undergoes irreversible deformation after being subjected to stress exceeding the yield strength. Then, the volume of the plastic zone is statistically analyzed to quantify its spatial extent, and the diffusion rate of the plastic zone over time is analyzed (e.g., characterized by volume growth rate or boundary displacement rate). Further, by combining the characteristics of the plastic zone distribution (e.g., high stress concentration areas, fault intersection areas), volume size (e.g., rockburst risk increases significantly when exceeding a critical value), and diffusion rate (e.g., rapid expansion may indicate a sudden rockburst), potential rockburst hazard points are comprehensively determined. For high-risk areas, risk warning strategies are generated, including real-time monitoring of anchor bolt stress and microseismic activity, setting graded warning thresholds, and triggering risk recovery strategies, such as immediately stopping operations in high-risk areas, initiating active support (e.g., grouting reinforcement or prestressed anchor cable reinforcement), and evacuating personnel to safe areas. Simultaneously, a dynamic feedback mechanism is established to continuously optimize warning and recovery measures based on model prediction results, forming a full-chain risk prevention and control system of "monitoring, prediction, warning, and recovery" to ensure safe mine production.

[0080] In some embodiments of this invention, the distribution, volume, and diffusion rate of the plastic zone in mine rock mass are accurately quantified through a modified coupling model, enabling dynamic tracking of stress concentration and damage evolution processes in the rock mass. Identifying potential rockburst disaster points based on plastic zone parameters effectively captures precursory information of rock mass instability, overcoming the limitations of traditional single-indicator early warning systems. Furthermore, by generating targeted risk warning and recovery strategies, a full-chain prevention and control system from disaster identification to emergency response is constructed, significantly improving the accuracy and response efficiency of mine rockburst disaster prediction and providing reliable technical support for ensuring operational safety and reducing economic losses.

[0081] Furthermore, based on the above embodiments, in one exemplary embodiment provided by the present invention, the specific implementation process of determining potential disaster points based on the modified coupling model and generating risk warning strategies and risk recovery strategies corresponding to the potential disaster points may further include steps S810 to S830, which are described in detail below: Step S810: Determine the displacement vector field corresponding to the mine based on the modified coupling model; Step S820: Determine the gradient tensor and shear displacement corresponding to the displacement vector field; Step S830: Determine potential disaster points based on gradient tensor and shear displacement, and generate risk warning strategies and risk recovery strategies corresponding to the potential disaster points.

[0082] For example, the displacement vector reflects the spatial deformation characteristics of the rock mass under stress, and the displacement field of the rock mass can be solved by the modified coupled model:

[0083] in, Along respectively The displacement components in the direction are then identified. The displacement field vector can then be differentiated to obtain the displacement gradient tensor. :

[0084] The gradient tensor describes the spatial rate of change of displacement, and its eigenvalues ​​and eigenvectors can characterize the direction and magnitude of the principal strain force of the rock mass.

[0085] Shear displacement reflects the shear deformation strength of the rock mass, and the formula for calculating the shear displacement of the displacement vector field can be:

[0086] Optionally, the shear displacement amount can be set. The critical value is determined, and when the real-time shear displacement of the mine exceeds the preset critical value, it is judged as a high-risk area; on the other hand, if it is the maximum eigenvalue of the gradient tensor of the mine... A significant increase (increase efficiency greater than average efficiency) indicates that the rock mass may undergo abrupt failure. Therefore, a comprehensive assessment of potential displacement hazards can be made by combining geological structures (such as faults and joints) and mining activities. Corresponding risk warning strategies can then be generated, such as immediately halting operations in high-risk areas, evacuating personnel to safe zones, and initiating active support measures (such as grouting reinforcement and prestressed anchor cable reinforcement) to limit displacement development.

[0087] In some embodiments of this invention, the mine displacement vector field is obtained through a modified coupling model, and its gradient tensor and shear displacement are further analyzed, achieving a refined characterization of the rock mass displacement and deformation features. The gradient tensor reveals the spatial rate of change of the displacement field and local stress concentration areas, while the shear displacement reflects the shear failure trend of the rock mass. The combination of the two can accurately identify potential displacement disaster points. Based on this, the risk warning and recovery strategies form an active prevention and control mechanism, which can effectively improve the prediction accuracy and response capability of displacement disasters in mining engineering, providing scientific protection for ensuring production safety and reducing geological disaster risks.

[0088] Furthermore, based on the above embodiments, in one exemplary embodiment provided by the present invention, the specific implementation process of determining potential disaster points based on the modified coupling model and generating risk warning strategies and risk recovery strategies corresponding to the potential disaster points may further include steps S910 to S930, which are described in detail below: Step S910: Determine the corresponding coupled numerical model for the mine based on the modified coupled model. The coupled numerical model includes the coupled models of the rock mass seepage field and stress field. Step S920: Determine the seepage velocity field and pore water pressure distribution in the mine based on the coupled model of rock mass seepage field and stress field; Step S930: Based on the seepage velocity field and pore water pressure distribution, determine the potential water inrush disaster points and the water inrush prediction time, and generate risk warning strategies and risk recovery strategies corresponding to the potential water inrush disaster points based on the water inrush prediction time.

[0089] For example, based on the modified coupled numerical model, the interaction between groundwater flow and mechanical deformation in the rock mass is first characterized by the dynamic coupling equations of the seepage field and stress field, where the seepage field is described by Darcy's law:

[0090] in, For seepage velocity field, Permeability coefficient, Pore ​​water pressure, Let g be the fluid density and g be the acceleration due to gravity. Represents the coordinate components perpendicular to the main seepage direction (such as the x-axis).

[0091] As can be seen from the above embodiments, the stress field in the mine is controlled by the equilibrium equation, which can be expressed as follows: ,in, For the total stress tensor, The density of the rock mass reflects its deformation under effective stress; the coupled model can model the rock mass through the permeability coefficient. k The nonlinear relationship between stress field evolution and stress field evolution is specifically calculated using the following formula:

[0092] in, The stress sensitivity coefficient is used to achieve seepage-stress coupling through the above equation, thereby solving for the seepage velocity field in the mine. and pore water pressure distribution Based on this, by analyzing the spatial heterogeneity of the seepage velocity field (such as identifying fault zones or fracture zones where seepage velocity suddenly increases) and high-value accumulation areas of pore water pressure (such as areas close to the tensile strength of the rock mass), potential water inrush disaster points are comprehensively determined. At the same time, the water inrush time is predicted by combining the rate of change of pore water pressure over time and the critical water inrush pressure threshold. For high-risk areas, a graded risk warning strategy and risk recovery strategy are generated based on the critical water inrush pressure value and the predicted water inrush time.

[0093] In some embodiments of this invention, a modified coupled numerical model integrates the dynamic interaction between the seepage field and stress field in the rock mass, accurately simulating the seepage-stress coupling mechanism under complex hydrogeological conditions in mines. Based on quantitative analysis of the seepage velocity field and pore water pressure distribution, key triggers for water inrush disasters can be effectively identified and the timing of disasters can be predicted, overcoming the limitations of traditional single-factor early warning systems. By generating phased risk warning and risk recovery strategies, a full-process prevention and control system from disaster early warning to emergency response is constructed, significantly improving the proactive prevention and control capabilities of mine water inrush disasters and providing a scientific decision-making basis for ensuring underground operation safety and reducing economic losses from water hazards.

[0094] Please see Figure 2 , Figure 2 This is a schematic diagram illustrating the structure of a mine disaster early warning system according to an exemplary embodiment of the present invention. The system includes an input device, a processor, an output device, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to invoke the program instructions and the mine disaster early warning method used by the system.

[0095] The storage device uses a high-speed solid-state drive, which features fast read and write speeds, large capacity, and high reliability. It is mainly used to store data input from input devices and the results of data processed by the processor, and can meet the needs of storing large amounts of data.

[0096] In this embodiment, the input device includes a data interface module and a monitoring module. The data interface module is used to input geological structure data corresponding to the mine, including rock strata distribution, fault occurrence, and groundwater occurrence status. The monitoring module is used to acquire on-site monitoring data of the mine, providing data input for subsequent mine coupling model correction. The input device supports data format standardization to ensure that the collected and received data is compatible with the processor.

[0097] The processor includes a coupling module, a boundary module, and a correction module. The coupling module is used to construct a coupled model of the mine based on the rock strata distribution, fault occurrence, and groundwater occurrence status, and further determine the rock mass constitutive relationship and corresponding coupling parameters in the coupled model. The boundary module is used to determine the predicted boundary conditions corresponding to the coupled model based on the rock mass constitutive relationship and coupling parameters of the coupled model. The correction module is used to correct the coupled model of the mine based on the on-site monitoring data of the mine input by the input device and the predicted boundary conditions determined by the boundary module. Furthermore, the correction module is used to determine the potential hazard points of the mine based on the corrected coupled model and generate risk warning strategies and risk recovery strategies corresponding to the potential hazard points.

[0098] The output devices include a display terminal, a strategy generation module, and an early warning module. The display terminal is used to intuitively display the three-dimensional visualization coupled model of the mine; the strategy generation module is used to generate risk warning strategies and risk recovery strategies corresponding to potential disaster points; and the early warning module is used to provide risk warnings for potential disaster points in the mine.

[0099] In summary, this invention integrates multi-source geological data, including mine strata distribution, fault occurrence, and groundwater occurrence, to construct a coupled model. Based on the constitutive relationship of the rock mass and coupling parameters, it determines the predicted boundary conditions, achieving accurate simulation of complex geological conditions in mines. Furthermore, by dynamically correcting the model using on-site monitoring data, it effectively improves the model's prediction accuracy for multi-physics coupling processes such as rock mass stress-seepage-deformation, thereby accurately identifying potential disaster points (such as water inrush and rock bursts). Finally, by generating targeted risk warning strategies (such as graded warnings and emergency responses) and recovery strategies (such as grouting reinforcement and drainage pressure reduction), it constructs a full-chain prevention and control system from disaster prediction to emergency response, significantly enhancing the safety management capabilities and disaster prevention effectiveness of mine engineering, and providing scientific protection for ensuring personnel safety and reducing economic losses.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for early warning of mine disasters, characterized in that, The method includes: Obtain geological structure data corresponding to the mine, including rock strata distribution, fault occurrence, and groundwater occurrence status; Based on the rock strata distribution, fault occurrence, and groundwater occurrence, a coupled model corresponding to the mine is constructed, and the constitutive relationship of the rock mass and coupling parameters in the coupled model are determined, including: Obtain the strength parameters corresponding to the coupling model, including elastic modulus, Poisson's ratio, uniaxial compressive strength, triaxial compressive strength, cohesion, and internal friction angle; The principal stress directions and principal stress values ​​of the initial geostress field of the coupled model were inverted using the hydraulic fracturing method. Based on the strength parameters, the principal stress directions, and the principal stress values, the constitutive relationship of the rock mass and the coupling parameters in the coupled model are determined. The predicted boundary conditions of the coupled model are determined based on the constitutive relation of the rock mass and the coupling parameters. The on-site monitoring data of the mine is acquired, and the coupling model is modified based on the on-site monitoring data and the predicted boundary conditions. Potential disaster points are determined based on the modified coupling model, and risk warning strategies and risk recovery strategies corresponding to the potential disaster points are generated. The multi-source data of the mine is acquired, and the multi-source data and numerical simulation results are fused based on the Bayesian update algorithm to obtain the fused multi-source dataset. Sensitivity analysis is performed on the fused multi-source dataset, and multi-source data with sensitivity greater than a preset sensitivity threshold are used as target data. The actual boundary conditions of the mine are determined based on the target data, and the coupled model is corrected based on the actual boundary conditions and the predicted boundary conditions.

2. The method as described in claim 1, characterized in that, The target data includes rock mass deformation. The step of correcting the coupled model based on the actual boundary conditions and the predicted boundary conditions includes: The amount of rock mass deformation in the mine is determined based on the on-site monitoring data. The porosity variation rate of the mine is determined based on the rock mass deformation, and the actual seepage field boundary conditions of the mine are determined based on the porosity variation rate. The predicted seepage field boundary conditions in the coupled model are updated based on the actual seepage field boundary conditions, so as to correct the coupled model based on the updated seepage field boundary conditions.

3. The method as described in claim 1, characterized in that, The target data includes rock mass microseismic data, and the modification of the coupled model based on the actual boundary conditions and the predicted boundary conditions includes: Based on the on-site monitoring data, the microseismic data of the rock mass of the mine is determined, and the microseismic data includes the spatial coordinate data of the microseismic events; The actual damage boundary conditions of the mine are determined based on the spatial coordinate data. The predicted damage boundary conditions in the coupled model are updated based on the actual damage boundary conditions, so as to correct the coupled model based on the updated damage boundary conditions.

4. The method as described in claim 1, characterized in that, The target data includes support structure data, and the step of correcting the coupling model based on the actual boundary conditions and the predicted boundary conditions includes: Based on the on-site monitoring data, the support structure data corresponding to the rock mass of the mine is determined, and the support structure includes anchor stress data; Determine the anchor bolt stress threshold, and determine the actual stress boundary conditions of the mine based on the anchor bolt stress threshold and the anchor bolt stress data; The predicted stress boundary conditions in the coupled model are updated based on the actual stress boundary conditions, so as to correct the coupled model based on the updated stress boundary conditions.

5. The method as described in claim 1, characterized in that, The process of determining potential disaster points based on the modified coupling model and generating corresponding risk warning and risk recovery strategies for these potential disaster points includes: Based on the modified coupling model, the distribution, volume, and diffusion rate of the plastic zone corresponding to the mine are determined. Based on the distribution of the plastic zone, the volume of the plastic zone, and the diffusion rate of the plastic zone, potential rockburst hazard points are determined, and risk warning strategies and risk recovery strategies corresponding to the potential rockburst hazard points are generated.

6. The method as described in claim 1, characterized in that, The process of determining potential disaster points based on the modified coupling model and generating corresponding risk warning and risk recovery strategies for these potential disaster points includes: The displacement vector field corresponding to the mine is determined based on the modified coupling model. Determine the gradient tensor and shear displacement corresponding to the displacement vector field; Based on the gradient tensor and the shear displacement, potential disaster points are determined, and risk warning strategies and risk recovery strategies corresponding to the potential disaster points are generated.

7. The method as described in claim 1, characterized in that, The process of determining potential disaster points based on the modified coupling model and generating corresponding risk warning and risk recovery strategies for these potential disaster points includes: The corresponding coupled numerical model for the mine is determined based on the modified coupled model, which includes a coupled model of the rock mass seepage field and the stress field. The seepage velocity field and pore water pressure distribution of the mine are determined based on the coupled model of the seepage field and stress field of the rock mass. Based on the seepage velocity field and the pore water pressure distribution, potential water inrush disaster points and water inrush prediction times are determined, and risk warning strategies and risk recovery strategies corresponding to the potential water inrush disaster points are generated based on the water inrush prediction times.

8. A mine disaster early warning system, characterized in that, The system uses the mine disaster early warning method according to any one of claims 1 to 7. The system includes an input device, a processor, an output device, and a memory. The input device, the processor, the output device, and the memory are interconnected. The memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions.

Images