Mining area catastrophe early warning method, device and equipment based on rock mass multi-dimensional quantitative characterization model

Abstract

The invention provides a mining area catastrophe early warning method, device and equipment based on a rock mass multi-dimensional quantitative characterization model, and the method comprises the steps: inputting the collected multi-field data of a stress field, a rock mass damage field and a penetration field into a multi-field co-evolution model to obtain a corresponding multi-field evolution coefficient, and updating the output of a catastrophe early warning model through the evolution coefficient. A stress-rock mass damage-permeation co-evolution mechanism is constructed, the prediction precision of disasters such as rockburst and water and mud inrush is guaranteed, and advanced early warning and active control of catastrophe are achieved.

Description

Technical Field

[0001] The present application relates to the field of mining engineering technology, and in particular to a mining disaster early warning method, device and equipment based on a multi-dimensional quantitative characterization model of rock mass. Background Art

[0002] With the development of deep resources and the expansion of underground space, high-stress hard rock underground mining projects are facing a sharp increase in the risk of disasters in a coupled environment of "three highs" (high ground stress, high osmotic pressure, and high temperature). Traditional theories mostly analyze the stability of surrounding rocks based on a single physical field, ignoring the dynamic coupling of stress field, damage field, seepage field, and temperature field. For example, hard rock is prone to strain softening, crack expansion, and seepage mutation under the conditions of "three highs", but the existing constitutive model is difficult to describe the co-evolution mechanism of damage accumulation and dynamic stress concentration, resulting in insufficient prediction accuracy for disasters such as rock bursts, water and mud inrush. In addition, engineering monitoring often lacks real-time data and dynamic feedback of multi-field coupling models, making it difficult to achieve advanced warning and active control of disasters. Summary of the Invention

[0003] This application proposes a mining disaster early warning method, device and equipment based on a multi-dimensional quantitative characterization model of rock mass, which can solve one of the problems existing in the background technology.

[0004] To achieve the above objectives, this application adopts the following technical solutions:

[0005] In a first aspect, a mining disaster early warning method based on a multi-dimensional quantitative characterization model of rock mass is provided, the early warning method comprising:

[0006] Obtain the current mining area physical field data, including stress field, rock damage field and permeability field;

[0007] Inputting the current mining area physical field data into a preset multi-field co-evolution model to obtain current physical field evolution coefficients, wherein the physical field evolution coefficients include: a stress field evolution coefficient, a rock damage field evolution coefficient, and a permeability field evolution coefficient; the multi-field co-evolution model is defined by the stress field evolution coefficient, the rock damage field evolution coefficient, and the permeability field evolution coefficient; the permeability field evolution coefficient is defined by a spatiotemporal correlation weight factor, the spatiotemporal correlation weight factor is defined by a fracture network fractal dimension and a permeability tensor principal value ratio, and the spatiotemporal correlation weight factor is related to time; and

[0008] The physical field evolution coefficient is used to update the output of the disaster warning model.

[0009] Based on the above technical solution, the collected stress field, rock damage field and permeability field data are input into the multi-field co-evolution model to obtain the corresponding multi-field evolution coefficients, and the output of the disaster warning model is updated by the evolution coefficients. In this way, a stress-rock damage-permeability co-evolution mechanism is constructed, which ensures the prediction accuracy of disasters such as rock bursts, water and mud inrush, and realizes advanced warning and active control of disasters.

[0010] By dynamically adjusting the multi-field coupling intensity through the designed spatiotemporal correlation weight factor, the rockburst prediction error rate and seepage mutation prediction error can be significantly reduced.

[0011] In a possible design manner of the first aspect, the multi-field co-evolution model is:

[0012]

[0013] α(t)=D f ×exp(-K ratio ×10 -3 )

[0014] Among them, SCF is the stress field evolution coefficient; DI is the rock damage field evolution coefficient; CV is the permeability field evolution coefficient; is the effective shear stress tensor along the j direction on the surface in the i direction; is the initial stress tensor; D eff is the dynamic damage diffusion coefficient; <ε p 》is the effective plastic strain; is the porosity; is the fluid density; t is the time; K eff is the effective permeability tensor; α(t) is the time-space correlation weight factor; h is the water head height; Q is the leakage flux; D f is the fractal dimension of the fracture network; D macro is the macro damage variable; x and z are directions; β is the coupling coefficient; K ratio is the principal value ratio of the permeability tensor.

[0015] In a possible design manner of the first aspect, the physical field evolution coefficient further includes: a deformation curvature evolution coefficient, and the multi-field co-evolution model further includes:

[0016]

[0017] Among them, K is the deformation curvature evolution coefficient; a, b, and c are material coefficients.

[0018] In a possible design of the first aspect, the disaster warning model includes: a three-dimensional thermal map of rock burst hazard, an envelope surface of leakage risk warning threshold value, and a spatiotemporal evolution curve of stope stability.

[0019] In a possible design of the first aspect, the three-dimensional thermal map of rockburst hazard is generated by a rockburst risk assessment value F.

[0020]

[0021] Among them, the weight coefficient ω1+ω2+ω3=1; EPI is the energy concentration index; EPI norm 、SCF norm ,DI norm are the normalized values ​​of EPI, SCF, and DI respectively; EPI min / max 、SCF min / max ,DI min / max are the minimum and maximum values ​​of each parameter measured in engineering respectively; a, b, c are material coefficients; V is the microscopic representative volume unit.

[0022] In a possible design of the first aspect, the leakage risk equation corresponding to the leakage risk warning threshold envelope is:

[0023]

[0024] Where p is the pore water pressure; y is the direction; p crit is the critical pore water pressure, and its value is related to the burial depth and porosity; σ y is the uniaxial compressive strength of rock; is the effective normal stress in the z direction.

[0025] In a possible design of the first aspect, the equation corresponding to the stope stability spatiotemporal evolution curve is:

[0026] S(t)=ω4·η(t) γ1 +ω5·Y(t) γ2

[0027] η(t)=η0(t)·(1+a·SCF b )

[0028]

[0029] Among them, the weight coefficient ω4+ω5=1; γ1 and γ2 are constants; Y is the yield proximity; σ eq is the equivalent stress, DI crit is the critical damage threshold; η is the energy dissipation rate; η0 is the initial energy dissipation rate; a and b are material coefficients.

[0030] In a possible design of the first aspect, the macro damage variable and the micro permeability tensor have the following relationship:

[0031]

[0032] Among them, D macro is the macro damage variable; K micro is the microscopic permeability tensor; Γ is the cross-scale transfer function; K is the permeability; and f is the fracture volume fraction.

[0033] In a second aspect, a mining disaster early warning device is provided, the early warning device comprising:

[0034] The acquisition unit is used to obtain the physical field data of the current mining area, including stress field, rock damage field and permeability field;

[0035] a processing unit, configured to input the current mining area physical field data into a preset multi-field co-evolution model to obtain current physical field evolution coefficients, wherein the physical field evolution coefficients include: a stress field evolution coefficient, a rock damage field evolution coefficient, and a permeability field evolution coefficient; the multi-field co-evolution model is defined by the stress field evolution coefficient, the rock damage field evolution coefficient, and the permeability field evolution coefficient; the permeability field evolution coefficient is defined by a spatiotemporal correlation weight factor, the spatiotemporal correlation weight factor is defined by a fracture network fractal dimension and a permeability tensor principal value ratio, and the spatiotemporal correlation weight factor is time-related; and

[0036] An updating unit is used to update the output of the disaster warning model using the physical field evolution coefficient.

[0037] In a third aspect, an electronic device is provided, comprising: a processor, and a memory coupled to the processor, the memory being used to store a computer program; and the processor being used to execute the computer program stored in the memory, so that the electronic device performs the early warning method as any possible implementation method in the first aspect.

[0038] In a fourth aspect, a computer-readable storage medium is provided, comprising a computer program or instructions, which, when executed on a computer, causes the computer to execute the early warning method of any possible implementation in the first aspect.

[0039] In a fifth aspect, a computer program product is provided, comprising: a computer program or instructions, which, when the computer program or instructions are run on a computer, enables the computer to execute the early warning method of any possible implementation in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the 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.

[0041] Figure 1 This is a flow chart of a method for establishing a four-dimensional quantitative characterization model of rock mass structure-seepage-stress-deformation provided in an embodiment of the present application;

[0042] Figure 2 This is a mathematical logic architecture diagram of the stress field-damage field-seepage field coupling and spatiotemporal correlation weight factors provided in the embodiments of the present application;

[0043] Figure 3 This is a flow chart for establishing a three-dimensional thermal map of rockburst hazard provided in an embodiment of the present application;

[0044] Figure 4 This is a three-dimensional thermal map of the risk of rock burst in metal mines provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0046] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0048] The embodiment of the present application is mainly to overcome the shortcomings of the existing technology and propose a four-dimensional quantitative characterization model of rock structure-seepage-stress-deformation, such as Figure 1-2 As shown, the following steps are included:

[0049] S1. Temporally and spatially align the acquired multi-source heterogeneous data, including structure (micro-joint and fissure distribution, porosity), seepage (permeability tensor, pore water pressure), and microseismic signals, to eliminate their temporal and spatial inconsistencies and enhance physical constraints, thereby supporting cross-scale coupled modeling and numerical simulation calculations.

[0050] The spatiotemporal alignment process of multi-source heterogeneous data includes:

[0051] Based on the wavelet rigid transform, high-frequency microseismic event signals are decomposed by wavelet to extract key time features; low-frequency geological model data are reconstructed by low-frequency wavelet to retain macroscopic trends;

[0052] Based on the time registration algorithm, dynamic time warping or Kalman filtering is used to interpolate or resample the asynchronous microseismic event time series and minute-level seepage data to resolve the time scale differences between different data sources;

[0053] Based on the spatial registration algorithm, feature points are used to match the geometric transformation of fault planes and drilling trajectories, and data of different resolutions are mapped to a unified coordinate system to resolve the spatial scale differences of different data sources.

[0054] S2. Construct a spatiotemporal correlation weight factor function, introduce a time term based on the fused fracture network data and permeability tensor data to complete dynamic correction, and form a four-dimensional dynamic representation framework including the spatiotemporal correlation weight factor (α(t));

[0055] Among them, the spatiotemporal correlation weight factor α(t) is the core innovation of this invention. It dynamically adjusts the coupling strength between physical fields such as stress field, damage field, and seepage field according to the spatiotemporal position, significantly improving the prediction accuracy and engineering applicability of the model. α(t):

[0056] α(t)=D f ×exp(-K ratio ×10 -3 )(1)

[0057] Among them, D f is the fractal dimension of the fracture network, which can be calculated by the box counting method and is in the range of 1.2≤D f ≤2.5;K ratio is the principal value ratio of the permeability tensor, defined as the ratio of the maximum principal permeability K1 to the minimum principal permeability K2, K ratio ≥10.

[0058] S3. Build a cross-scale data assimilation algorithm to integrate macro- and micro-scale data and mechanism models to achieve micro-scale permeability tensor K. micro To macro damage D macr o quantitative mapping of cross-scale physical processes, providing data support for building macroscopic three-dimensional damage models;

[0059] To fuse macro- and micro-scale data, a cross-scale transfer function Γ is constructed:

[0060]

[0061] Among them, D macro is the macro damage variable, K micro is the microscopic permeability tensor;

[0062]

[0063] Where K is the permeability and f is the fracture volume fraction.

[0064] S4. Based on the multi-source heterogeneous fusion and cross-scale assimilation algorithm, the temporal and spatial differences of data are eliminated and cross-scale mapping is achieved to obtain the basic parameters required for the rock structure-seepage-stress coupling calculation model;

[0065] The basic parameters required for the rock structure-seepage-stress coupling include but are not limited to:

[0066] Basic parameters such as initial geostress data, deep rock mechanics parameters, mining disturbance increment, rock damage variable, permeability coefficient, permeability tensor, pore water pressure distribution, initial porosity, initial permeability, head height, etc. will be used in relevant formulas.

[0067] S5. Based on the spatial correlation between rock damage evolution and seepage mutation, a coupled equation is quantitatively characterized. A numerical calculation method based on the finite element method is established. The basic parameters of rock structure-seepage-stress coupling are input into the numerical simulation model to achieve a four-dimensional dynamic characterization of the rock damage evolution rate, seepage field variation coefficient, stress concentration factor, and deformation curvature change rate, achieving second-order spatiotemporal accuracy (Δx ≤ 0.1 m, Δt ≤ 1 s).

[0068] Furthermore, the stress concentration factor SCF:

[0069]

[0070] Among them, D eff is the dynamic damage diffusion coefficient, which is positively correlated with DI; <ε p > is the effective plastic strain; is the effective stress tensor; is the initial stress tensor.

[0071] Furthermore, the coefficient of variation of the seepage field CV is:

[0072]

[0073] in, is the porosity; is the fluid density; K eff is the effective permeability tensor, corrected based on Darcy's law; h is the hydraulic head height; Q is the leakage flux.

[0074] Furthermore, the rock damage evolution rate DI:

[0075]

[0076] Where β is the damage-stress coupling coefficient, 0.1≤β≤0.5.

[0077] Furthermore, the deformation curvature change rate K:

[0078]

[0079] Where a, b, and c are material constants, which are determined in the laboratory. For example, typical values ​​for granite are: a = 0.5, b = 1.2, and c = 0.3.

[0080] S6. Based on the numerical simulation results, further calculate the energy concentration index, three-dimensional envelope equation, integrated yield proximity and other parameters to generate a three-dimensional thermal map of rock burst hazard (such as Figure 3 As shown in the figure), the envelope surface of leakage risk warning threshold and the spatiotemporal evolution curve of stope stability are obtained, thus providing a basis for optimizing mining in deep mines.

[0081] Furthermore, the energy concentration index EPI:

[0082]

[0083] Where V is the microscopic representative volume unit.

[0084] Normalize EPI, SCF, and DI to eliminate dimensional differences:

[0085]

[0086] Among them, EPI min / max 、SCF min / max ,DI min / max are the minimum and maximum values ​​of each parameter measured in engineering respectively.

[0087] The normalized parameters are fused through the nonlinear weighted coupling equation:

[0088]

[0089] Among them, the weight coefficient ω1+ω2+ω3=1, which is calibrated according to engineering experience (typical values: ω1=0.5, ω2=0.3, ω3=0.2), and a, b, and c are material constants as above.

[0090] The F value ranges from 0 to 1. Based on the F value, HSV color space mapping is used to generate a three-dimensional thermal map of rock burst hazard, such as Figure 4 As shown in Figure 2, its value is positively correlated with the rockburst risk.

[0091] Based on Darcy's law, the envelope risk equation of the leakage risk warning threshold is constructed:

[0092]

[0093] Where p is the pore water pressure; p crit is the critical pore water pressure, and its value is related to the burial depth and porosity; σ y is the uniaxial compressive strength of rock, x, y, z are directions, t is time, is the effective normal stress in the z direction.

[0094] When the penetration risk equation is greater than 0, it means there is a leakage risk.

[0095] Construct the equation of the time-space evolution curve of stope stability:

[0096] S(t)=ω4·η(t) γ1 +ω5·Y(t) γ2 (12)

[0097] Among them, ω4+ω5=1, calibrated according to engineering experience (typical values: ω4=0.4, ω5=0.6), γ1=1.2, γ2=0.8.

[0098] The temporal and spatial evolution curve of stope stability, including the equation for energy dissipation rate η:

[0099] η(t)=η0(t)·(1+a·SCF b ) (13)

[0100] Where η0 is the initial energy dissipation rate, and a and b are material constants as above.

[0101] The temporal and spatial evolution curve of stope stability, including the yield proximity equation:

[0102]

[0103] Among them, σ eq is the equivalent stress, DI crit is the critical damage threshold, and its value is 0.3.

[0104] The principal component analysis (PCA) method is used to reduce the dimension and generate a three-dimensional spatial curvature cloud map and a time series trend curve.

[0105] In this way, by updating model parameters driven by real-time monitoring data, a three-dimensional visual early warning of mine rock burst hazards, permeability risk rate, and mining site stability can be achieved, supporting decision-making on optimizing the speed of mine mining.

[0106] This embodiment has the following beneficial effects:

[0107] 1. A four-dimensional quantitative characterization model of rock mass structure, seepage, stress and deformation in deep mines was constructed. The multi-field coupling intensity was dynamically adjusted by the spatiotemporal correlation weight factor (α(t)), which significantly reduced the rockburst prediction error rate and seepage mutation prediction error.

[0108] 2. The multi-field coupling calculation process is highly complex. Compared with traditional models, it breaks through the theoretical limitations of a single field and significantly improves the prediction accuracy of the coordinated evolution of multiple physical fields in deep mining engineering.

[0109] 3. By eliminating spatiotemporal delays through real-time data fusion and cross-scale data assimilation, the timeliness bottleneck of traditional methods has been broken through, providing a complete solution from theory to engineering implementation for the sustainable and safe mining of deep metal mineral projects.

[0110] The present application also provides a mining disaster early warning device, which includes:

[0111] The acquisition unit is used to obtain the physical field data of the current mining area, including stress field, rock damage field and permeability field;

[0112] a processing unit, configured to input the current mining area physical field data into a preset multi-field co-evolution model to obtain current physical field evolution coefficients, wherein the physical field evolution coefficients include: a stress field evolution coefficient, a rock damage field evolution coefficient, and a permeability field evolution coefficient; the multi-field co-evolution model is defined by the stress field evolution coefficient, the rock damage field evolution coefficient, and the permeability field evolution coefficient; the permeability field evolution coefficient is defined by a spatiotemporal correlation weight factor, the spatiotemporal correlation weight factor is defined by a fracture network fractal dimension and a permeability tensor principal value ratio, and the spatiotemporal correlation weight factor is time-related; and

[0113] An updating unit is used to update the output of the disaster warning model using the physical field evolution coefficient.

[0114] An embodiment of the present application also provides an electronic device, comprising: a processor, and a memory coupled to the processor, wherein the memory is used to store a computer program; and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method described in any one of the above embodiments.

[0115] The electronic device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The electronic device may include, but is not limited to, a processor and a memory.

[0116] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, connecting various parts of the entire device using various interfaces and lines.

[0117] The memory may be used to store the computer program, and the processor implements various functions of the electronic device by running or executing the computer program stored in the memory and calling the data stored in the memory.

[0118] The memory may primarily include a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application required for a function, and the like; and the data storage area may store data created based on the use of the mobile phone, and the like. Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0119] The embodiment of the present application also provides a storage medium, which is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0120] An embodiment of the present application further provides a computer program product, including: a computer program or instructions, which, when executed on a computer, causes the computer to execute any of the above-mentioned possible implementation methods.

[0121] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A mining disaster early warning method based on a multi-dimensional quantitative characterization model of rock mass, characterized by: The early warning method includes: obtaining physical field data of the current mining area, the physical field including stress field, rock damage field and permeability field; Inputting the current mining area physical field data into a preset multi-field co-evolution model to obtain current physical field evolution coefficients, wherein the physical field evolution coefficients include: a stress field evolution coefficient, a rock damage field evolution coefficient, and a permeability field evolution coefficient; the multi-field co-evolution model is defined by the stress field evolution coefficient, the rock damage field evolution coefficient, and the permeability field evolution coefficient; the permeability field evolution coefficient is defined by a spatiotemporal correlation weight factor, the spatiotemporal correlation weight factor is defined by a fracture network fractal dimension and a permeability tensor principal value ratio, and the spatiotemporal correlation weight factor is related to time; and The physical field evolution coefficient is used to update the output of the disaster warning model.

2. The early warning method according to claim 1, characterized in that: The multi-field co-evolution model is: α(t)=D f ×exp(-K ratio ×10 -3 ) Among them, SCF is the stress field evolution coefficient; DI is the rock damage field evolution coefficient; CV is the permeability field evolution coefficient; is the effective shear stress tensor along the j direction on the surface in the i direction; is the initial stress tensor; D eff is the dynamic damage diffusion coefficient; <ε p > is the effective plastic strain; is the porosity; is the fluid density; t is the time; K eff is the effective permeability tensor; α(t) is the time-space correlation weight factor; h is the water head height; Q is the leakage flux; D f is the fractal dimension of the fracture network; D macro is the macro damage variable; x and z are directions; β is the coupling coefficient; K ratio is the principal value ratio of the permeability tensor.

3. The early warning method according to claim 2, characterized in that: The physical field evolution coefficient also includes: deformation curvature evolution coefficient, and the multi-field co-evolution model also includes: Among them, K is the deformation curvature evolution coefficient; a, b, and c are material coefficients.

4. The early warning method according to claim 2, characterized in that: The disaster warning model includes: a three-dimensional thermal map of rock burst hazard, an envelope surface of leakage risk warning threshold value and a time-space evolution curve of stope stability.

5. The early warning method according to claim 4, characterized in that: The three-dimensional thermal map of rock burst hazard is generated by a rock burst risk evaluation value F. Among them, the weight coefficient ω1+ω2+ω3=1; EPI is the energy concentration index; EPI norm 、SCF norm ,DI norm are the normalized values ​​of EPI, SCF, and DI respectively; EPI min / max 、SCF min / max ,DI min / max are the minimum and maximum values ​​of each parameter measured in engineering respectively; a, b, c are material coefficients; V is the microscopic representative volume unit.

6. The early warning method according to claim 4, characterized in that: The leakage risk equation corresponding to the leakage risk warning threshold envelope is: Where p is the pore water pressure; y is the direction; p crit is the critical pore water pressure, and its value is related to the burial depth and porosity; σ y is the uniaxial compressive strength of rock; is the effective normal stress in the z direction.

7. The early warning method according to claim 4, characterized in that: The equation corresponding to the time-space evolution curve of the stope stability is: S(t)=ω4·η(t) γ1 +ω5·Y(t) γ2 η(t)=η0(t)·(1+a·SCF b ) Among them, the weight coefficient ω4+ω5=1; γ1 and γ2 are constants; Y is the yield proximity; σ eq is the equivalent stress, DI crit is the critical damage threshold; η is the energy dissipation rate; η0 is the initial energy dissipation rate; a and b are material coefficients.

8. The early warning method according to claim 2, characterized in that: The macroscopic damage variable and the microscopic permeability tensor have the following relationship: Among them, D macro is the macro damage variable; K micro is the microscopic permeability tensor; Γ is the cross-scale transfer function; K is the permeability; and f is the fracture volume fraction.

9. A mining disaster early warning device, characterized in that: The early warning device comprises: The acquisition unit is used to obtain the physical field data of the current mining area, including stress field, rock damage field and permeability field; a processing unit, configured to input the current mining area physical field data into a preset multi-field co-evolution model to obtain current physical field evolution coefficients, wherein the physical field evolution coefficients include: a stress field evolution coefficient, a rock damage field evolution coefficient, and a permeability field evolution coefficient; the multi-field co-evolution model is defined by the stress field evolution coefficient, the rock damage field evolution coefficient, and the permeability field evolution coefficient; the permeability field evolution coefficient is defined by a spatiotemporal correlation weight factor, the spatiotemporal correlation weight factor is defined by a fracture network fractal dimension and a permeability tensor principal value ratio, and the spatiotemporal correlation weight factor is time-related; and An updating unit is used to update the output of the disaster warning model using the physical field evolution coefficient.

10. An electronic device, characterized in that: The electronic device includes: a processor, and a memory coupled to the processor, The memory is used to store computer programs; and The processor is configured to execute the computer program stored in the memory, so that the electronic device executes the early warning method according to any one of claims 1 to 8.

Images