A coal mine pressure monitoring system and method based on deep learning

Abstract

The present application belongs to the technical field of coal mine pressure monitoring, and discloses a coal mine pressure monitoring system and method based on deep learning. The method establishes a coal mining geological model, a model of the upper three zones of a typical goaf, response calculation, characteristic analysis of the coal mine pressure characteristic curve influenced by the coal mine fracturing fluid resistivity and the mining hole size in the profile of the upper three zones of the goaf, and characteristic analysis of the coal mine pressure characteristic curve influenced by the deformation and surrounding rock in the profile of the upper three zones of the goaf. The present application monitors the coal mine pressure in the deformation process of the upper three zones (curved subsidence zone, fracture zone and caving zone) of the goaf, utilizes the time-space complementarity and process synergy of multiple means, realizes the deformation dynamic monitoring under the mining hole of the coal goaf, has high monitoring precision, and provides technical support for further coal mining.

Description

Technical Field

[0001] This invention belongs to the field of coal mine pressure monitoring technology, and particularly relates to a coal mine pressure monitoring system and method based on deep learning. Background Technology

[0002] In the process of coal mining, safe production in coal mines is of paramount importance. Among these, mine pressure monitoring technology plays a vital role in timely and effective monitoring of mine pressure, accurately grasping the manifestation pattern of mine pressure in the mining area, improving the mine pressure value of roadway support, and ensuring safe production in coal mines.

[0003] In existing coal mining processes, mine pressure monitoring devices are required to monitor the interior of the mine tunnels in real time. Conventional monitoring methods use image cameras and pressure monitors to monitor the interior of the mine tunnels in real time, thereby ensuring the safety of the mine tunnels during use. However, image cameras and pressure monitors are easily affected by falling objects inside the mine tunnels. Large falling objects can easily damage image cameras and pressure monitors, thus requiring regular maintenance and replacement of image cameras and pressure monitors, reducing the value of the coal mine pressure monitoring device.

[0004] To address this issue, a coal mine pressure monitoring device and method (publication number CN115575012A, publication date 2023.01.06) is disclosed, comprising mounting columns and a frame. Mounting rods are distributed in a ring around the top of the frame, and protective components are provided on the outer sides of multiple mounting rods. The protective components include two protective nets, an inner ring frame, and an outer ring frame. By providing these protective components, the image capture device and pressure monitor are protected by a double-layered protective net during use. When a small object falls through the two layers of nets, its impact is weakened. Once it reaches above the image capture device and pressure monitor, its downward impact cannot cause any damage. When a large object falls onto the upper protective net, the net is compressed and dented. The spring rod below the pressure-bearing rod is passively compressed, and the elastic potential energy of the spring rod's return causes the upper protective net to bounce off the large object, preventing it from accumulating on the net and causing damage.

[0005] The technical flaw of this invention is that it does not utilize advanced deep learning technology to predict coal mine pressure data in advance, thus failing to eliminate potential hazards at the outset.

[0006] Currently, safety in production has become a focal point and a major challenge in coal mine production. Accidents caused by mine pressure mainly manifest in aspects such as roadway wall stability, roof support stress range, and hydraulic support stability. The primary reason for these accidents is the failure to collect, process, and provide early warnings in a timely and accurate manner for parameters such as internal mine pressure, roadway wall pressure, and periodic pressure.

[0007] Currently, the main method for preventing roof falls in coal mines is mine pressure monitoring. Mine pressure monitoring methods include installing pressure sensors on the hydraulic supports of the longwall mining face below the mining hole, installing roof layer sensors on the roadway roof, installing bearing stress sensors in the coal and rock mass, and installing anchor bolt stress sensors on the roadway surrounding rock support anchor bolts. These monitoring methods are all independently deployed or manually read, resulting in low automation, inconvenient data acquisition, cumbersome processing, susceptibility to errors, and long information feedback cycles, failing to fundamentally meet the requirement of timely production guidance. To overcome these shortcomings, another type of mine pressure monitoring system exists. This system primarily collects and displays mine pressure data, but it lacks a comprehensive database, cannot perform various statistical analyses and early warnings, and cannot review historical data to recreate historical conditions.

[0008] To address this issue, a utility model patent for a coal mine pressure analysis system (publication number CN205297648U, publication date 2016.06.08) discloses a data processing subsystem above the mining hole that receives raw data collected by the data acquisition subsystem below the mining hole via a communication module. The data is then parsed by the data processing subsystem above the mining hole and transmitted to the mine pressure management subsystem above the mining hole via the communication module. The coal mine pressure analysis system provided by this utility model can collect more comprehensive monitoring data for mine pressure analysis through the data acquisition subsystem below the mining hole. Furthermore, the data processing subsystem and the mine pressure management subsystem above the mining hole adopt a client / server (C / S) architecture, enabling real-time information monitoring, searching, and early warning of the fully mechanized mining face, as well as information storage and historical retrieval. It also allows for the analysis and review of historical data.

[0009] However, the technical flaw of this patent is that the analysis of coal mine pressure data is based on the currently used data processing methods, and there is still room for improvement in the accuracy of judging the data evolution information of the three zones (bending subsidence zone, fracture zone and caving zone) deformation process in complex geology and goaf areas. Summary of the Invention

[0010] To overcome the problems existing in related technologies, the present invention discloses a coal mine pressure monitoring system and method based on deep learning.

[0011] The technical solution is as follows: A coal mine pressure monitoring method based on deep learning, comprising the following steps:

[0012] S1. Establish a geological model for coal mining. Based on the multi-source parameter coupling method for coal mine pressure, complete the decomposition of the magnetic field of the lidar for coal mine pressure, the progression of the lidar wave field, the solution of the lidar magneton vector, the calculation of the conductivity of the geological layer for coal mining, and the synthesis of the characteristic curve of coal mine pressure.

[0013] S2, Model establishment and response calculation of geological strata in the upper three zones of typical goaf, for homogeneous strata, strata with mining holes, strata without deformation, and strata with deformation, the original coal mine pressure characteristic curve of the upper three zones of the goaf is analyzed to provide the original coal mine pressure characteristic curve for synthetic processing.

[0014] S3, in the upper three-zone profile of the goaf, analyzes the characteristics of coal mine pressure characteristic curves affected by the resistivity of coal mine fracturing fluid and the size of the mining hole; analyzes different strata thicknesses and different coal mine fracturing fluid resistivities, evaluates the coal mine pressure characteristic curve values ​​of shallow and deep exploration coal mines, and provides coal mine pressure characteristic curves for strata evaluation work.

[0015] S4, Characteristic analysis of coal mine pressure curves influenced by deformation and surrounding rock in the upper three zones of the goaf profile; Characteristic analysis of coal mine pressure curves influenced by surrounding rock in the upper three zones of the goaf in the mining geological model for coal mines with mining holes and no deformation, and selection of synthetic coal mine pressure characteristic curves to provide a basis for coal and shale identification.

[0016] In step S1, based on the multi-source parameter coupling method for coal mine pressure, the following steps are completed: decomposition of the magnetic field of the lidar for coal mine pressure, lidar wave field progression, lidar magneton vector solution, calculation of the conductivity of the geological layer in coal mining, and synthesis of the characteristic curve of coal mine pressure.

[0017] A geological model for coal mining with M horizontal interfaces is established. Each layer is radially non-uniform and consists of a mining hole, a bending subsidence zone, a fracture zone, a caving zone, a deformation zone, and undisturbed strata. (f, χ, h) are cylindrical coordinates, where f is the layer thickness, χ is the angular frequency, and h is the diameter of the mining hole axis.

[0018] The lidar emission line structure is located on the ground plane h s Above, using a point (r, h) on the meridian plane s ) represents, r is the radius, h s The distance from the ground plane; the lidar emitting line structure generates an axisymmetric coal mine pressure lidar magnetic field; the lidar emitting line structure carries an alternating current A T =A0d iat A0 is the initial value of the alternating current, d iat Given that the magnetic field of the coal mine pressure lidar contains a time factor, based on the classical differential equations, we obtain:

[0019]

[0020] d 2 =a 2 β(η-iγ / a)

[0021] In the formula, Let F be the differential deviation, Q be the lidar magnetic field power, a be the lidar emission conduction coefficient, β be the lidar emission conduction permeability, i be time (in seconds), d be the time factor, η be the dielectric constant, γ be the conductivity, and F be the differential deviation. T The emission current density;

[0022] Due to axisymmetry, Q is independent of χ. For the passive region, Q in the m-th layer... χ =Q m Q χ Q is the magnetic field power of the lidar at the angular frequency. m Let the magnetic field power of the m-th layer lidar be , then we have:

[0023]

[0024] In the formula, a m Let be the transmission coefficient of the lidar at layer m;

[0025] The wave number is:

[0026]

[0027] In the formula, β m (f) is the magnetic permeability of the m-th layer, η m (f) is the dielectric constant of the m-th layer, γ m (f) represents the electrical conductivity of the m-th coal mining geological layer;

[0028] Solving using the method of separation of variables, we obtain:

[0029]

[0030] In the formula, e m (f) represents the electrical conductivity of the geological strata separated during coal mining at the m-th layer. γ is the separation distance between the upper and lower layers of the m-th layer below the diameter of the mining borehole shaft. m It is an N-order diagonal matrix;

[0031] After establishing the boundary conditions that the basis functions should satisfy, the above formula is transposed, e m (f) Only numerical solutions are available. Solve for the generalized complex eigenvalues ​​and calculate the electrical conductivity of the geological strata in coal mining.

[0032] The resistivity of a uniform infinite coal mine geological model was set to vary from 0.01 Ω·m to 200 Ω·m. The characteristics of the original coal mine pressure characteristic curves obtained from different sub-mine pressure sets were observed, and the applicable conditions of the lidar analysis equipment for the three zones of the goaf under pressure induction were obtained.

[0033] In step S2, the characteristic curves of the original coal mine pressure in the three zones above the goaf under mine pressure induction are analyzed, including:

[0034] (1) Establish an infinite-thickness coal mining geological model considering the extraction holes, and compare the original response signals of multiple sub-mining pressure sets at different frequencies under different coal mine fracturing fluid conditions;

[0035] (2) Establish a multi-layer coal mining geological model considering the extraction holes and surrounding rocks, and compare the original response signals of multiple sub-mining pressure sets at different frequencies under different layer thickness and surrounding rock conditions;

[0036] (3) Establish a multi-layer coal mining geological model considering the extraction holes, surrounding rocks, and deformation, and compare the original response signals of multiple sub-mining pressure sets at different frequencies at different radial deformation depths under high-pressure conditions;

[0037] (4) Establish a multi-layer coal mining geological model considering the extraction holes, surrounding rocks, and deformation, and compare the original response signals of multiple sub-mining pressure sets at different frequencies at different radial deformation depths under low-pressure conditions.

[0038] In steps (1) - (4), the coal mining geological model is used to handle the problem of immiscible multi-zones. When simulating and calculating the two-zone problem, the free surface position of the deformation zone under mining pressure and the volume of the deformation zone under mining pressure are represented by processing the deformation volume fraction equation under mining pressure;

[0039] If the deformation volume fraction of a certain zone under mining pressure in each control volume is A, then A = 0 indicates that the control volume does not contain this zone, A = 1 indicates that the control volume only contains this zone, and 0 < A < 1 indicates that there is an interface of two-zone deformations in the control volume;

[0040] The coal mining geological model is used to handle transient problems, and the expression of its deformation volume fraction equation under mining pressure is as follows:

[0041]

[0042] In the formula, c q is the density of the q-th zone, is the deformation volume fraction of the q-th zone under mining pressure, l q is the deformation frequency of the q-th zone, is the momentum source term, is the mining pressure value transferred from the p-th zone to the q-th zone, is the mining pressure value transferred from the q-th zone to the p-th zone, t is the time, is the differential deviation.

[0043] Furthermore, the deformation volume fraction equation under mining pressure is:

[0044]

[0045] The momentum equation of the coal mining geological model:

[0046]

[0047] In the formula, c is the density, v is the deformation angle, and w is the phase frequency deformation coefficient. The differential difference of the phase frequency, for The transpose of the matrix, l is the phase frequency, Δp is the pressure difference, g is the gravitational acceleration frequency, l T Let W be the phase frequency transpose matrix, and W be the volume force.

[0048] The energy equation for the geological model of coal mining is:

[0049]

[0050] In the formula, D is energy, p is pressure, ΔT is temperature, k is conductivity coefficient, and Γ is... h This is an energy source term.

[0051] Furthermore, in the geological model of coal mining, the surface repulsion model is a continuous surface force model. When the surface repulsion is activated, the momentum equation adds a source term. When the surface repulsion is constant and only the interface normal force is considered, the expression for the pressure difference across the surface is:

[0052]

[0053] In the formula, p2-p1 is the pressure difference between the two sides of the surface, ζ is the surface repulsion coefficient, and E1 and E2 are the radii of curvature of the interface.

[0054] Furthermore, in the geological model of coal mining, the deformation angle model between the zone surface and the deformation zone under mining pressure is combined with the surface repulsion model. The deformation angle formed by the deformation zone under mining pressure and the zone surface is used to adjust the normal of the zone interface near the zone surface, which leads to a change in the curvature of the zone interface near the zone surface.

[0055] Define v w Let be the deformation angle formed by the deformation zone phase and the zone surface under ore pressure. The expression for the normal of the unit zone interface between adjacent zones is:

[0056] X = X w cosv w +t w sinv w

[0057] In the formula, X is the normal angle of the unit interface between adjacent zones, and v w X is the deformation angle formed by the deformation zone phase and the zone surface under ore compression. w Let t be the unit vector normal to the surface. w It is a unit vector tangential to the surface.

[0058] In step S3, analysis is performed on different formation thicknesses and different coal mine fracturing fluid resistivities to evaluate the coal mine pressure characteristic curves at both shallow and deep depths, providing coal mine pressure characteristic curves for formation evaluation work, including:

[0059] (1) Establish a multi-layer coal mine geological model, set the radius of the mining hole, change the type of coal mine fracturing fluid from salt water coal mine fracturing fluid to clear water coal mine fracturing fluid, change the formation thickness from thin to thick, and determine the characteristics of the coal mine pressure characteristic curve of the coal mine pressure induction synthesis by the influence of the coal mine fracturing fluid in the mining hole.

[0060] (2) Establish a uniform infinite-large coal mine mining geological model and determine the coal mine pressure characteristic curves of different detection depths with the same resolution when the mining hole changes under different coal mine fracturing fluid conditions.

[0061] In step S4, the synthetic coal mine pressure characteristic curves that provide a basis for coal and shale identification are selected, including:

[0062] (1) Under the condition of salt and cement slurry, the radius of the mining hole is set, and in the geological model of three-layer coal mine mining considering deformation under high pressure surrounding rock, the influence of coal mine fracturing fluid in the mining hole on the characteristic curve of coal mine pressure induction is determined.

[0063] (2) Under the condition of fresh slurry, the radius of the mining hole is set, and in the geological model of three-layer coal mine mining considering deformation under low-pressure surrounding rock conditions, the influence of coal mine fracturing fluid in the mining hole on the characteristic curve of coal mine pressure induction is determined.

[0064] Another objective of this invention is to provide a deep learning-based coal mine pressure monitoring system, which implements the deep learning-based coal mine pressure monitoring method. The system includes:

[0065] A coal mine geological model module is established to create a coal mine geological model. Based on the coal mine pressure multi-source parameter coupling method, it completes the decomposition of the coal mine pressure lidar magnetic field, lidar wave field progression, lidar magneton vector solution, calculation of the conductivity of the coal mine geological layer, and synthesis of coal mine pressure characteristic curves.

[0066] The module for model establishment and response calculation of the three geological strata above a typical goaf is used for model establishment and response calculation of the three geological strata above a typical goaf. It performs characteristic analysis of the original coal mine pressure characteristic curves of the three geological strata above a typical goaf for homogeneous strata, strata with mining holes, strata without deformation, and strata with deformation, and provides the original coal mine pressure characteristic curves for synthetic processing.

[0067] The curve feature analysis module is used to analyze the coal mine pressure characteristic curves affected by the resistivity of fracturing fluid and the size of the mining hole in the three-zone profile of the goaf; it analyzes different formation thicknesses and different coal mine fracturing fluid resistivities, evaluates the coal mine pressure characteristic curve values ​​of shallow and deep exploration coal mines, and provides coal mine pressure characteristic curves for formation evaluation work.

[0068] The module for obtaining characteristic curves of coal mine pressure in synthetic coal mines is used for the characteristic analysis of coal mine pressure curves affected by deformation and surrounding rock in the upper three zones of the goaf. For coal mines with mining holes and no deformation, the module analyzes the characteristic curves of coal mine pressure in the upper three zones of the goaf affected by the surrounding rock in the mining geological model, and selects the characteristic curves of synthetic coal mine pressure to provide a basis for coal and shale identification.

[0069] Combining all the above technical solutions, the beneficial effects of this invention are as follows: The coal mine pressure monitoring system and method based on deep learning provided by the embodiments of this invention have carried out coal mine pressure monitoring in the coordinated dynamic coupling monitoring of the deformation process of the three zones (bending subsidence zone, fracture zone and caving zone) in the goaf. It utilizes the spatiotemporal complementarity and process synergy of multiple means to realize dynamic monitoring of deformation under the mining hole in the coal mine goaf. The monitoring accuracy is high, providing technical support for further coal mining. Attached Figure Description

[0070] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure;

[0071] Figure 1 This is a flowchart of a coal mine pressure monitoring method based on deep learning provided in an embodiment of the present invention;

[0072] Figure 2 This is a characteristic effect diagram of the influence of the mining hole on different detection depth curves provided in the embodiment of the present invention;

[0073] Figure 3 This is a schematic diagram of a coal mine pressure monitoring system based on deep learning provided in an embodiment of the present invention;

[0074] The diagram shows: 1. Module for establishing a geological model of coal mining; 2. Module for establishing a model and calculating the response of the three geological strata in a typical goaf; 3. Module for curve feature analysis; 4. Module for obtaining characteristic curves of coal mine pressure. Detailed Implementation

[0075] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0076] Example 1, as Figure 1 As shown in the embodiments of the present invention, the coal mine pressure monitoring method based on deep learning includes:

[0077] S1. Establish a geological model for coal mining. Based on the multi-source parameter coupling method for coal mine pressure, complete the decomposition of the magnetic field of the lidar for coal mine pressure, the progression of the lidar wave field, the solution of the lidar magneton vector, the calculation of the conductivity of the geological layer for coal mining, and the synthesis of the characteristic curve of coal mine pressure.

[0078] S2, Model establishment and response calculation of geological strata in the upper three zones of typical goaf, for homogeneous strata, strata with mining holes, strata without deformation, and strata with deformation, the original coal mine pressure characteristic curve of the upper three zones of the goaf is analyzed to provide the original coal mine pressure characteristic curve for synthetic processing.

[0079] S3, in the upper three-zone profile of the goaf, analyzes the characteristics of coal mine pressure characteristic curves affected by the resistivity of coal mine fracturing fluid and the size of the mining hole; analyzes different strata thicknesses and different coal mine fracturing fluid resistivities, evaluates the coal mine pressure characteristic curve values ​​of shallow and deep exploration coal mines, and provides coal mine pressure characteristic curves for strata evaluation work.

[0080] S4, Characteristic analysis of coal mine pressure curves influenced by deformation and surrounding rock in the upper three zones of the goaf profile; Characteristic analysis of coal mine pressure curves influenced by surrounding rock in the upper three zones of the goaf in the mining geological model for coal mines with mining holes and no deformation, and selection of synthetic coal mine pressure characteristic curves to provide a basis for coal and shale identification.

[0081] For example, in step S1, a geological model of coal mining is established. Based on the multi-source parameter coupling method of coal mine pressure, the following steps are performed: decomposition of the magnetic field of the lidar for coal mine pressure, lidar wave field progression, lidar magneton vector solution, calculation of the conductivity of the geological layer of coal mining, and synthesis of the characteristic curve of coal mine pressure. The applicable scope of the lidar analysis equipment includes:

[0082] A geological model for coal mining with M horizontal interfaces is established. Each layer is radially non-uniform and consists of a mining hole, a bending subsidence zone, a fracture zone, a caving zone, a deformation zone, and undisturbed strata. (f, χ, h) are cylindrical coordinates, where f is the layer thickness, χ is the angular frequency, and h is the diameter of the mining hole axis.

[0083] The lidar emission line structure is located on the ground plane h s Above, using a point (r, h) on the meridian plane s ) represents, r is the radius, h s The distance from the ground plane; the lidar emitting line structure generates an axisymmetric coal mine pressure lidar magnetic field; the lidar emitting line structure carries an alternating current A T =A0d iat A0 is the initial value of the alternating current, d iat Given that the magnetic field of the coal mine pressure lidar contains a time factor, based on the classical differential equations, we obtain:

[0084]

[0085] d 2 =a 2 β(η-iγ / a)

[0086] In the formula, Let F be the differential deviation, Q be the lidar magnetic field power, a be the lidar emission conduction coefficient, β be the lidar emission conduction permeability, i be time (in seconds), d be the time factor, η be the dielectric constant, γ be the conductivity, and F be the differential deviation. T The emission current density;

[0087] Due to axisymmetry, Q is independent of χ. For the passive region, Q in the m-th layer... χ =Q m Q χ Q is the magnetic field power of the lidar at the angular frequency. m Let the magnetic field power of the m-th layer lidar be , then we have:

[0088]

[0089] In the formula, a m Let be the transmission coefficient of the lidar at layer m;

[0090] The wave number is:

[0091]

[0092] In the formula, β m (f) is the magnetic permeability of the m-th layer, η m (f) is the dielectric constant of the m-th layer, γ m (f) represents the electrical conductivity of the m-th coal mining geological layer;

[0093] Solving using the method of separation of variables, we obtain:

[0094]

[0095] Where, e m (f) is the conductivity of the separated coal mining geological layer of the m-th layer, is the separation distance between the upper and lower layers of the m-th layer under the diameter of the mining hole axis, γ m is an N-order diagonal matrix;

[0096] After establishing the boundary conditions that the basis function should satisfy, perform transpose transformation on the above formula, e m (f) has only numerical solutions, solve the generalized complex eigenvalue, and calculate the conductivity of the coal mining geological layer;

[0097] Set the resistivity of the homogeneous infinite coal mining geological model to vary from 0.01 Ω·m to 200 Ω·m, observe the characteristics of the original coal mine pressure characteristic curve obtained from different subsets of mine pressure, and obtain the applicable conditions of the lidar analysis equipment for the three zones above the goaf with mine pressure induction.

[0098] In step S2, perform an analysis on the characteristics of the original coal mine pressure characteristic curve of the three zones above the goaf with mine pressure induction, including:

[0099] (1) Establish an infinitely thick coal mining geological model considering the mining hole, and compare the original response signals of multiple subsets of mine pressure at different frequencies under different coal mine fracturing fluid conditions;

[0100] (2) Establish a multi-layer coal mining geological model considering the mining hole and surrounding rock, and compare the original response signals of multiple subsets of mine pressure at different frequencies under different layer thickness and surrounding rock conditions;

[0101] (3) Establish a multi-layer coal mining geological model considering the mining hole, surrounding rock, and deformation, and compare the original response signals of multiple subsets of mine pressure at different frequencies at different radial deformation depths under high pressure conditions;

[0102] (4) Establish a multi-layer coal mining geological model considering the mining hole, surrounding rock, and deformation, and compare the original response signals of multiple subsets of mine pressure at different frequencies at different radial deformation depths under low pressure conditions.

[0103] Exemplarily, the coal mining geological model is used to handle the problem of immiscible multi-zones. When simulating and calculating the two-zone problem, the free surface position of the deformation zone under mine pressure and the volume of the deformation zone under mine pressure are represented by processing the deformation volume fraction equation under mine pressure. The basic idea is that if the deformation volume fraction of a certain zone under mine pressure in each control volume is A, then A = 0 means that the control volume does not contain this zone, A = 1 means that the control volume only contains this zone, and 0 < A < 1 means that there is an interface of two-zone deformation in the control volume;

[0104] The coal mining geological model has the advantages of less memory occupation, less calculation amount, and high efficiency. The coal mining geological model is used to handle transient problems, and the expression of its deformation volume fraction equation under mine pressure is as follows:

[0105]

[0106] In the formula, c q For the density of the qth band, Let l be the volume integral of the deformation under pressure in the q-th zone of the ore. q The deformation frequency of the qth band. For momentum source term, Let be the mining pressure value transmitted from zone p to zone q. Let t be the value of the mine pressure transmitted from zone q to zone p, and t be the time. This is the differential deviation.

[0107] The integral equation for deformation volume under ore pressure is:

[0108]

[0109] Momentum equation for geological model of coal mining:

[0110]

[0111] In the formula, c is the density, v is the deformation angle, and w is the phase frequency deformation coefficient. The differential difference of the phase frequency, for The transpose of the matrix, l is the phase frequency, Δp is the pressure difference, g is the gravitational acceleration frequency, l T Let W be the phase frequency transpose matrix, and W be the volume force.

[0112] The energy equation for the geological model of coal mining is:

[0113]

[0114] In the formula, D is energy, p is pressure, ΔT is temperature, k is conductivity coefficient, and Γ is... h This is an energy source term.

[0115] For example, to accurately represent the two driving states, the geological model for coal mining considers both the surface repulsion effect between the two zones and the deformation angle effect between the zone surface and the deformation zone under mining pressure. The surface repulsion can be specified as a constant. The governing equations include shear stress terms added due to the variation of the surface repulsion coefficient, and solving them yields interaction terms. Under high or low mining pressure conditions, the surface repulsion effect usually has a significant impact on the two driving states.

[0116] In coal mine geological models, the surface repulsion model is a continuous surface force model. When the surface repulsion is activated, a source term needs to be added to the momentum equation. When the surface repulsion is constant and only the interface normal force is considered, the expression for the pressure difference across the surface is as follows:

[0117]

[0118] In the formula, p2-p1 is the pressure difference between the two sides of the surface, ξ is the surface repulsion coefficient, and E1 and E2 are the radii of curvature of the interface.

[0119] Deformation angle model between the zone surface and the deformation zone under ore pressure.

[0120] In the geological model of coal mining, the deformation angle model between the zone surface and the deformation zone under mining pressure is used in conjunction with the surface repulsion model. The deformation angle formed by the deformation zone under mining pressure and the zone surface is used to adjust the normal of the zone interface near the zone surface, which leads to a certain change in the curvature of the zone interface near the zone surface.

[0121] Define v w Let be the deformation angle formed by the deformation zone phase and the zone surface under ore pressure. The expression for the normal of the unit zone interface between adjacent zones is:

[0122] X = X w cosv w +t w sinv w

[0123] In the formula, X is the normal angle of the unit interface between adjacent zones, and v w X is the deformation angle formed by the deformation zone phase and the zone surface under ore compression. w Let t be the unit vector normal to the surface. w The unit vector tangential to the surface

[0124] For example, in step S3, analysis is performed on different formation thicknesses and different coal mine fracturing fluid resistivities to evaluate the coal mine pressure characteristic curve values ​​at both shallow and deep exploration depths, providing coal mine pressure characteristic curves for formation evaluation work, including:

[0125] (1) Establish a multi-layer coal mine geological model, set the radius of the mining hole, change the type of coal mine fracturing fluid from salt water coal mine fracturing fluid to clear water coal mine fracturing fluid, change the formation thickness from thin to thick, and determine the characteristics of the coal mine pressure characteristic curve of the coal mine pressure induction synthesis by the influence of the coal mine fracturing fluid in the mining hole.

[0126] (2) Establish a uniform infinite-large coal mine mining geological model and determine the coal mine pressure characteristic curves of different detection depths with the same resolution when the mining hole changes under different coal mine fracturing fluid conditions.

[0127] For example, in step S4, the synthetic coal mine pressure characteristic curves that provide a basis for coal and shale identification are selected, including:

[0128] (1) Under the condition of salt and cement slurry, the radius of the mining hole is set, and in the geological model of three-layer coal mine mining considering deformation under high pressure surrounding rock, the influence of coal mine fracturing fluid in the mining hole on the characteristic curve of coal mine pressure induction is determined.

[0129] (2) Under the condition of fresh slurry, the radius of the mining hole is set, and in the geological model of three-layer coal mine mining considering deformation under low-pressure surrounding rock conditions, the influence of coal mine fracturing fluid in the mining hole on the characteristic curve of coal mine pressure induction is determined.

[0130] This invention adopts the multi-source parameter coupling method of coal mine pressure to establish a two-dimensional coal mine geological model, and performs coal mine pressure lidar magnetic field decomposition, lidar wave field progression, lidar magneton vector solution and coal mine geological layer conductivity calculation. The following environmental factors affecting the response of the three zones in the goaf under pressure induction are systematically analyzed: (1) formation resistivity; (2) coal mine fracturing fluid resistivity; (3) coal mine fracturing fluid deformation; (4) mining hole size; (5) formation thickness.

[0131] A uniform, infinitely large coal mine geological model was established. The response characteristics of the three zones in the goaf under mine pressure in strata with different electrical conductivity were analyzed to determine the stratigraphic conditions affected by trend effects and to standardize the instrument's applicable range. A geological model of an infinitely thick coal mine with a borehole was established to obtain the variation characteristics of the coal mine pressure characteristic curves influenced by the borehole and the resistivity of the fracturing fluid. Simultaneously, the original signals at multiple transmission frequencies of the instrument were compared to analyze the variation characteristics of the coal mine pressure characteristic curves affected by trend effects, and to determine the type of original coal mine pressure characteristic curve with the best pressure value. A coal mine geological model was established where the deformation radius of the fracturing fluid varies from shallow to deep. The deformation relationship of the fracturing fluid can be divided into two states: high pressure and low pressure. The variation characteristics of the synthetic coal mine pressure characteristic curves were analyzed, and synthetic coal mine pressure characteristic curves with the best pressure value were identified, laying the foundation for deformation zone inversion. Establish geological models for coal mining with different layer thicknesses, considering two cases of coal mine fracturing fluid deformation: high pressure and low pressure. Analyze the original coal mine pressure characteristic curves of each sub-mine pressure set to avoid the phenomenon of coal mine pressure characteristic curves crossing at different source distances.

[0132] This invention utilizes a multi-source parameter coupling method for coal mine pressure to systematically analyze the main environmental factors influencing the characteristic curves of coal mine pressure in the upper three zones of a pressure-inducing goaf. Different coal mine geological models are designed and simulated for complex strata and well conditions. From coal mine pressure lidar magnetic field decomposition, lidar wavefield progression, lidar magneton vector solving, to calculation of the conductivity of the coal mine geological layer and resolution matching, the characteristic curves of coal mine pressure in the upper three zones of a pressure-inducing goaf under different coal mine geological models are obtained. Furthermore, the invention analyzes and summarizes the characteristic patterns of coal mine pressure curves under the individual influence of one of the following factors: coal mine fracturing fluid resistivity, coal mine fracturing fluid deformation, well size, formation thickness, and formation resistivity. This invention can improve the accuracy of the interpretation results of the characteristic curves of coal mine pressure in the upper three zones of a pressure-inducing goaf, providing a theoretical basis for strata evaluation and coal seam identification.

[0133] Borehole size is also an important factor affecting curve quality. The following presents the formation model and its composite processing results when the borehole size changes. Figure 2 The influence characteristics of a 12-inch borehole on the 120-inch probe depth curve (M1RX) and the 10-inch probe depth curve (M1R1) are presented. The horizontal axis represents the true resistivity of the formation, Rt, and the vertical axis represents the ratio of the synthesized apparent resistivity to the true resistivity, Ra / Rt.

[0134] The following conclusions can be drawn:

[0135] (1) The larger the production hole, the more unfavorable it is to the measurement results, especially for large production holes under brine fracturing fluid conditions, which is extremely unfavorable to HDIL measurement and makes the application range of HDIL instruments significantly smaller.

[0136] (2) The magnitude of Rt / Rm (i.e., the contrast between the resistivity of the formation and the fracturing fluid) has a great influence on the measurement results. If the drilling hole is enlarged, the influence will be more obvious.

[0137] (3) Deep detection curves have a wider range of applications.

[0138] Example 2, as Figure 3 As shown, the deep learning-based coal mine pressure monitoring system provided in this embodiment of the invention includes:

[0139] Module 1 for establishing a geological model of coal mining is used to establish a geological model of coal mining. Based on the multi-source parameter coupling method of coal mine pressure, it completes the decomposition of the magnetic field of the lidar of coal mine pressure, the progression of the lidar wave field, the solution of the lidar magneton vector, the calculation of the conductivity of the geological layer of coal mining, and the synthesis of the characteristic curve of coal mine pressure.

[0140] Module 2, Model Establishment and Response Calculation of Geological Layers in Three Zones of Typical Goaf, is used for model establishment and response calculation of geological layers in three zones of typical goaf. It analyzes the original coal mine pressure characteristic curves of the three zones of goaf under mine pressure induction for homogeneous strata, strata with mining holes, strata without deformation, and strata with deformation, and provides the original coal mine pressure characteristic curves for synthetic processing.

[0141] The curve feature analysis module 3 is used to analyze the coal mine pressure characteristic curves affected by the resistivity of coal mine fracturing fluid and the size of the mining hole in the three-zone profile of the goaf; it performs analysis on different formation thicknesses and different coal mine fracturing fluid resistivities, evaluates the coal mine pressure characteristic curve values ​​of shallow and deep exploration coal mines, and provides coal mine pressure characteristic curves for formation evaluation work.

[0142] Module 4, which obtains the characteristic curves of coal mine pressure in the upper three zones of the goaf, is used for the characteristic analysis of coal mine pressure curves affected by deformation and surrounding rock in the profile. For coal mines with mining holes and no deformation, the characteristic analysis of coal mine pressure curves affected by surrounding rock in the mining geological model is used to select the characteristic curves of coal mine pressure in the upper three zones of the goaf to provide a basis for coal and shale identification.

[0143] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0144] The deep learning-based coal mine pressure monitoring system and method provided in this invention were applied to the goaf area of ​​the 5-20303 working face in a coal mine, covering a width of 350m and a length of 1000m. Coal mine pressure monitoring was conducted through the coordinated dynamic coupling monitoring of the deformation process of the three zones (bending and subsidence zone, fracture zone, and caving zone) in the goaf area. Utilizing the spatiotemporal complementarity and process synergy of multiple methods, dynamic monitoring of deformation under the mining hole in the coal mine goaf was achieved with high accuracy, providing technical support for further coal mining.

[0145] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention and within the spirit and principles of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A deep learning-based coal mine pressure monitoring method, characterized in that, The method comprises the following steps: S1, a coal mining geological model is established, based on a coal mine pressure multi-source parameter coupling method, laser radar magnetic field decomposition, laser radar wave field progression, laser radar magnetic sub-vector solution, and coal mining geological layer conductivity calculation, and coal mine pressure characteristic curve synthesis are completed; S2, model establishment and response calculation of the upper three zones of the typical goaf, for uniform strata, strata with mining holes, non-deformation strata, and deformation strata, the original coal mine pressure characteristic curve features of the mining-induced goaf upper three zones are analyzed, and the original coal mine pressure characteristic curve is provided for synthesis processing; S3, in the goaf upper three zone profile, the coal mine pressure characteristic curve features affected by the coal mine pressure fracturing fluid resistivity and the mining hole size are analyzed; different strata thicknesses and different coal mine pressure fracturing fluid resistivities are analyzed, and the deep and shallow detection coal mine pressure characteristic curve pressure values are evaluated, thereby providing the coal mine pressure characteristic curve for strata evaluation work; S4, in the goaf upper three zone profile, the coal mine pressure characteristic curve features affected by deformation and surrounding rock are analyzed; for the strata with mining holes and non-deformation coal mines, the surrounding rock influence of the mining-induced goaf upper three zones of the mining geological model is analyzed, and the synthesized coal mine pressure characteristic curve is selected as the basis for coal and shale identification work.

2. The coal mine pressure monitoring method based on deep learning according to claim 1, characterized in that, In step S1, based on the coal mine pressure multi-source parameter coupling method, the coal mine pressure laser radar magnetic field decomposition, laser radar wave field progression, laser radar magnetic sub-vector solution, and coal mining geological layer conductivity calculation, and coal mine pressure characteristic curve synthesis are completed, including: A coal mining geological model with M horizontal interfaces is established, each layer is radially non-uniform, and is composed of mining holes, curved subsidence zones, fracture zones, caving zones, deformation zones, and undisturbed strata; (f, χ, h) is the cylindrical coordinate, f is the layer thickness, χ is the angular frequency, and h is the mining hole shaft diameter; Laser radar emission line structure is located in the stratum plane h s Above, with a point (r, h s ) on the meridian plane, r is the radius, h s Is the distance from the stratum plane; Laser radar emission line structure produces an axisymmetric coal mine pressure laser radar magnetic field; Laser radar emission line structure through the alternating current A T =A0d iat , A0 is the initial value of alternating current, d iat For coal mine pressure laser radar magnetic field contains time factor, based on the classical differential form of equations, get: d 2 = a 2 β(η - iγ / a) wherein is the differential bias, Q is the laser radar magnetic field power, a is the laser radar launch transmission coefficient, β is the laser radar launch permeability, i is the time in seconds, d is the time factor, η is the dielectric constant, γ is the conductivity, F T is the launch current density; According to the axial symmetry, Q is independent of x, for the passive region, in the mth layer Q χ = Q m , Q χ is the laser radar magnetic field power at the angular frequency, Q m is the mth layer laser radar magnetic field power, then: In the formula, a m is the coefficient in the mth layer laser radar transmission conduction The wave number is: wherein β m (f) is the magnetic permeability of the mth layer, η m (f) is the dielectric constant of the mth layer, γ m (f) is the electrical conductivity of the mth layer of the coal mining geological layer; The separation of variables method is used to obtain: In the formula, e m (f) the electrical conductivity of the coal mining geological layer separation of the mth layer, is the upper and lower layer separation distance of the mth layer under the mining hole shaft diameter, γ m is the N-order diagonal matrix; After the boundary conditions that the base functions should satisfy are established, the above formula is transposed, e m (f) Only numerical solution, solving generalized complex eigenvalues, calculating the conductivity of coal mining geological layers; The resistivity of the uniform infinite coal mining geological model is set to vary from 0.01 Ω.m to 200 Ω.m, the original coal mine pressure characteristic curve features obtained by different sub-pressure sets are observed, and the application conditions of the laser radar analysis equipment for the mining-induced goaf upper three zones are obtained.

3. The coal mine pressure monitoring method based on deep learning according to claim 1, characterized in that, In step S2, the original coal mine pressure characteristic curve features of the mining-induced goaf upper three zones are analyzed, including: (1) an infinite thick coal mining geological model considering the mining holes is established, and the original response signals of multiple sub-pressure sets of different frequencies are compared under different coal mine pressure fracturing fluid conditions; (2) a multi-layer coal mining geological model considering the mining holes and surrounding rock is established, and the original response signals of multiple sub-pressure sets of different frequencies are compared under different layer thickness surrounding rock conditions; (3) a multi-layer coal mining geological model considering the mining holes, surrounding rock, and deformation is established, and the original response signals of multiple sub-pressure sets of different frequencies are compared under high pressure conditions when the radial deformation depth is different; (4) a multi-layer coal mining geological model considering the mining holes, surrounding rock, and deformation is established, and the original response signals of multiple sub-pressure sets of different frequencies are compared under low pressure conditions when the radial deformation depth is different.

4. The coal mine pressure monitoring method based on deep learning according to claim 3, characterized in that, In steps (1)-(4), the coal mining geological model is used to process the immiscible multi-zone problem, and in the simulation of the two-zone problem, the free surface position of the deformation zone under the mine pressure and the volume integral equation of the deformation zone under the mine pressure are used to express the deformation zone under the mine pressure; If the volume integral equation of the deformation zone under the mine pressure in each control volume is A, A=0 indicates that the control volume does not contain the zone, A=1 indicates that the control volume only contains the zone, and 0 The coal mining geological model is used to process the transient problem, and the volume integral equation of the deformation zone under the mine pressure is expressed as follows: where c q is the qth zone density, is the qth zone deformed volume integral fraction, l q is the qth zone deformation frequency, is the momentum source term, is the pth zone to qth zone transmitted pressure value, is the qth zone to pth zone transmitted pressure value, t is time, is the differential bias.

5. The coal mine pressure monitoring method based on deep learning according to claim 4, characterized in that, The volume integral equation of the deformation zone under the mine pressure is: The momentum equation of the coal mining geological model is: where c is the density, v is the deformation angle, w is the phase frequency deformation coefficient, is the phase frequency differential, is the transpose matrix, l is the phase frequency, Δp is the pressure difference, g is the gravitational acceleration frequency, l T is the phase frequency transpose matrix, W is the volume force; The energy equation of the coal mining geological model is: where D is energy, p is pressure, ΔΤ is temperature, k is the conduction coefficient, Γ h is the energy source term.

6. The coal mine pressure monitoring method based on deep learning according to claim 5, characterized in that, In the coal mining geological model, the surface repulsive force model is a continuous surface force model. When the surface repulsive force is activated, the momentum equation increases the source term. When the surface repulsive force is constant and only the interface normal force is considered, the pressure difference on both sides of the surface is expressed as: In the formula, p2-p1 is the pressure difference on both sides of the surface, ξ is the surface repulsive force coefficient, and E1 and E2 are the curvature radii of the zone interface.

7. The coal mine pressure monitoring method based on deep learning according to claim 5, characterized in that, In the coal mining geological model, the deformation angle model between the zone surface and the deformation zone under the mine pressure is used in combination with the surface repulsive force model. The deformation angle formed by the deformation zone under the mine pressure and the zone surface is used to adjust the normal of the zone interface near the zone surface, which causes the change of the curvature of the zone interface near the zone surface; Definition v w is the deformation angle formed by the deformation zone phase and the deformation zone plane, and the unit zone interface normal expression of the adjacent zone plane is X = X w cosv w +t w sinv w where X is the normal angle of the unit band interface between adjacent band surfaces, v w is the deformation angle of the deformation band and the band surface, X w is the normal unit vector of the band surface, t w is the tangent unit vector of the band surface.

8. The coal mine pressure monitoring method based on deep learning according to claim 1, characterized in that, In step S3, different stratum thicknesses and different coal mine fracturing fluid resistivities are analyzed, and the deep and shallow exploration coal mine pressure characteristic curve pressure values are evaluated to provide the coal mine pressure characteristic curve for stratum evaluation work, including: (1) Establishing a multi-layer coal mining geological model, setting the mining hole radius, and changing the coal mine fracturing fluid type from salt water coal mine fracturing fluid to fresh water coal mine fracturing fluid, and changing the stratum thickness from thin to thick, to determine the influence of the mining hole coal mine fracturing fluid on the mine pressure induction synthesis coal mine pressure characteristic curve characteristics; (2) Establishing a uniform infinite coal mining geological model, and determining the characteristics of the coal mine pressure characteristic curve of the same resolution at different exploration depths under different coal mine fracturing fluid conditions when the mining hole changes.

9. The coal mine pressure monitoring method based on deep learning according to claim 1, characterized in that, In step S4, the synthesized coal mine pressure characteristic curve is selected to provide a basis for coal and shale identification work, including: (1) Under the condition of salt water slurry, setting the mining hole radius, and determining the influence of the mining hole coal mine fracturing fluid on the mine pressure induction synthesis coal mine pressure characteristic curve characteristics in the three-layer coal mining geological model considering deformation under high pressure surrounding rock conditions; (2) Under the condition of fresh water slurry, setting the mining hole radius, and determining the influence of the mining hole coal mine fracturing fluid on the mine pressure induction synthesis coal mine pressure characteristic curve characteristics in the three-layer coal mining geological model considering deformation under low pressure surrounding rock conditions.

10. A deep learning-based coal mine pressure monitoring system, characterized in that, The system implements the coal mine pressure monitoring method based on deep learning according to any one of claims 1-9, and the system comprises: A coal mining geological model establishing module (1) is used to establish a coal mining geological model, and based on the coal mine pressure multi-source parameter coupling method, the coal mine pressure laser radar magnetic field decomposition, laser radar wave field progression, laser radar magnetic sub-vector solution, and coal mining geological layer conductivity calculation are completed, and the coal mine pressure characteristic curve synthesis is completed. The model establishment and response calculation module (2) for the geological layers in the upper three zones of a typical goaf is used for model establishment and response calculation of the geological layers in the upper three zones of a typical goaf, and analyzes the original coal mine pressure characteristic curves for uniform strata, strata with mining holes, non-deformation strata, and deformation strata, to provide the original coal mine pressure characteristic curves for the synthesis processing; The curve characteristic analysis module (3) is used for analyzing the coal mine pressure characteristic curves influenced by the coal mine fracturing fluid resistivity and the size of the mining holes in the profile of the upper three zones of a goaf; analyzes different strata thicknesses and different coal mine fracturing fluid resistivities, evaluates the pressure values of the deep and shallow detection coal mine pressure characteristic curves, and provides the coal mine pressure characteristic curves for the strata evaluation work; The synthesized coal mine pressure characteristic curve obtaining module (4) is used for analyzing the coal mine pressure characteristic curves influenced by the deformation and the surrounding rock in the profile of the upper three zones of a goaf; analyzes the coal mine pressure characteristic curves of the mining geological model influenced by the surrounding rock in the upper three zones of a goaf pressure-induced goaf for the coal mines with mining holes and without deformation, to select the synthesized coal mine pressure characteristic curves providing the basis for the coal and shale identification work.

Images