Method and system for evaluating drilling gas extraction effect in real time

Abstract

The invention relates to the technical field of well drilling production processes, and discloses a real-time evaluation method and system for a drilling gas extraction effect, and the method comprises the steps: synchronously collecting the fluid flow, rock mass stress and regional geologic structure data of a target drilling hole; generating a spatial weight distribution matrix for controlling a fluid migration path based on the fault azimuth angle and the fracture density distribution diagram; constructing a permeability evolution model along the radial direction of the drilling hole in combination with rock mass stress data; fluid flow data are input into the model, and an effective extraction coefficient is output through a time-varying integral equation for calculating the effective extraction radius; and generating a real-time extraction effect grade signal according to a matching relationship between the coefficient and a preset threshold value. According to the method, coupling modeling of geologic structure heterogeneity and stress dynamic change is achieved, the problem of static evaluation lag is solved, and the extraction effect feedback efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling production technology, and in particular to a method and system for real-time evaluation of borehole gas extraction effect. Background Art

[0002] In the field of oil and gas drilling engineering, especially processes involving formation fluid extraction, accurately evaluating the dynamic extraction of fluids around the wellbore is key to optimizing production. Traditional methods rely primarily on static geological models and empirical parameters to predict fluid migration ranges. For example, fixed permeability field models are established through core permeability testing or historical data fitting. Such models fail to fully consider the real-time impact of spatial heterogeneity in geological structures (such as fault strike and fracture development) on fluid migration paths and overlook the coupling effect of dynamic changes in rock stress on permeability during drilling.

[0003] Furthermore, existing technologies typically rely on indirect methods such as periodic well testing or pressure drop tests to estimate the extraction range, resulting in significant lag in the assessment results and an inability to accurately reflect actual operating conditions. Particularly in areas with complex geological structures, such as those characterized by well-developed fault systems, static models fail to effectively quantify the correlation between structural orientation and preferred fluid migration pathways. This can easily lead to overestimation or underestimation of the effective extraction range, potentially leading to improper drilling deployment and reduced resource recovery.

[0004] Another core flaw of existing technologies lies in the indirectness and simplification of extraction efficiency assessment. Current methods often estimate extraction efficiency by monitoring wellhead flow and pressure data and combining simplified radial flow equations. However, there is a key omission: the failure to synchronously integrate key geological structural parameters (such as fault azimuth and fracture density field distribution) with real-time rock stress fluctuations into the dynamic evolution model. This omission makes it impossible for the model to dynamically reflect the spatiotemporal variation of permeability at different locations along the borehole radial, significantly restricting the calculation accuracy of the effective extraction radius. At the same time, due to the lack of real-time analysis of geological-mechanical coupling, existing evaluation systems have difficulty generating feedback signals that represent the immediate extraction effect, which seriously limits the dynamic optimization of drilling process parameters (such as adjusting the extraction negative pressure based on real-time results or optimizing the drilling density deployment). Summary of the Invention

[0005] The present invention provides a real-time evaluation method and system for borehole gas extraction effect, the main purpose of which is to solve the problems of evaluation lag caused by static models and empirical parameters and the unquantified spatial heterogeneity of geological structures and dynamic coupling of stress when evaluating the borehole gas extraction effect.

[0006] To achieve the above objectives, the present invention provides a method for real-time evaluation of borehole gas extraction effect, comprising:

[0007] S1. Simultaneously collect gas flow data, rock stress data, and geological structure data of the target borehole area;

[0008] S2. Generate a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and fracture density distribution map in the geological structure data;

[0009] S3. Constructing a radial permeability evolution model along the borehole according to the spatial weight distribution matrix and the rock stress data;

[0010] S4. Input the gas flow rate data into the permeability evolution model, and output the effective extraction coefficient of the borehole by solving the time-varying integral equation of the effective extraction radius;

[0011] S5. Generate a real-time extraction effect level signal based on the comparison relationship between the effective extraction coefficient and a preset extraction efficiency threshold.

[0012] Optionally, the synchronous acquisition of gas flow data, rock stress data, and geological structure data of the target borehole, includes:

[0013] The real-time gas flow pulse signal is obtained as the gas flow data of the target borehole through the multi-parameter sensor array in the borehole;

[0014] The stress fluctuation waveform of the surrounding rock of the borehole is measured by a stress sensor as rock mass stress data;

[0015] The fault azimuth parameters and fracture density distribution map of the area where the borehole is located are retrieved from the geological database as geological structure data.

[0016] Optionally, generating a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and the fracture density distribution map in the geological structure data includes:

[0017] Calculating a spatial angle between the fault strike and the borehole axis based on a fault azimuth parameter in the geological structure data, wherein the spatial angle is generated based on the fault azimuth and the grid point azimuth;

[0018] generating an intensity gradient field of fracture development based on a fracture density distribution map in the geological structure data;

[0019] Calculating the migration path weight value of each grid point in the radial direction of the borehole by combining the spatial angle and the intensity gradient field;

[0020] The migration path weight values are mapped into three-dimensional matrix elements to generate a spatial weight distribution matrix.

[0021] Optionally, the calculating the migration path weight value of each grid point in the borehole radial direction in combination with the spatial angle and the intensity gradient field includes:

[0022] Establishing a polar coordinate system with the fault strike as a reference axis, and projecting the intensity gradient field onto the polar coordinate system;

[0023] The azimuth alignment between the grid points and the fault is quantified by the angle cosine function, wherein the azimuth alignment is:

[0024]

[0025] in, is the azimuthal alignment, is the fault azimuth, is the grid point azimuth;

[0026] An exponential decay function is used to correlate the azimuth alignment with the fracture density to obtain a migration path weight value representing the gas preferential migration path. The calculation formula for the migration path weight value is:

[0027]

[0028] in, is the migration path weight value, is the azimuthal alignment, is the fissure development density, is the distance attenuation coefficient, is the radial distance extending outward from the center of the borehole, is the grid point azimuth.

[0029] Optionally, constructing a permeability evolution model along the radial direction of the borehole according to the spatial weight distribution matrix and the rock mass stress data includes:

[0030] Normalizing the migration path weight values in the spatial weight distribution matrix to obtain a geological structure influencing factor;

[0031] Calculating a stress sensitivity coefficient based on the rock mass stress data;

[0032] deriving a stress conversion operator between permeability and rock mass stress data based on the Coulomb failure criterion;

[0033] The geological structure influencing factor and the stress conversion operator are integrated to generate a permeability evolution model, which outputs a permeability evolution field that changes with radial distance and time.

[0034] Optionally, the permeability evolution model is:

[0035]

[0036] in, is the radial distance and time The permeability at is the baseline permeability, is the geological structure influencing factor, is the reference stress, is the radial distance extending outward from the center of the borehole, is the time variable, is the rock mass stress data, is the stress sensitivity coefficient.

[0037] Optionally, solving the time-varying integral equation of the effective extraction radius includes:

[0038] Based on Darcy's law, a radial flow integral equation is established with the permeability evolution model as a variable;

[0039] Based on the radial flow integral equation, the gas flow rate data is used as an integral constraint to solve the effective extraction radius;

[0040] The ratio of the effective extraction radius to the designed extraction radius is calculated, and the effective extraction coefficient is output.

[0041] Optionally, the radial flow integral equation is:

[0042]

[0043] in, is the gas flow data, is the coal seam height, is the pressure difference between the reservoir pressure and the borehole pressure, is the gas viscosity, is the radius of the borehole wall, is the effective extraction radius, is the radial distance of the drill hole and time The permeability at is the radial distance extending outward from the center of the borehole, is the time variable.

[0044] Optionally, generating a real-time drainage effect level signal according to a comparison relationship between the effective drainage coefficient and a preset drainage efficiency threshold includes:

[0045] Preset multi-level extraction efficiency threshold range;

[0046] The effective extraction coefficient is matched to a corresponding multi-level extraction efficiency threshold interval, and a level identifier is activated according to the matching result, wherein the level identifier is encoded as a digital signal output.

[0047] In order to solve the above problems, the present invention also provides a real-time evaluation system for borehole gas extraction effect, the system comprising:

[0048] Data acquisition module, used to synchronously collect gas flow data of the target borehole, rock stress data and geological structure data of the area where the borehole is located;

[0049] A weight distribution generation module, configured to generate a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and the fracture density distribution map in the geological structure data;

[0050] A permeability model construction module, configured to construct a permeability evolution model along the radial direction of the borehole according to the spatial weight distribution matrix and the rock mass stress data;

[0051] an effective extraction coefficient generation module, configured to input the gas flow rate data into the permeability evolution model, and output the effective extraction coefficient of the borehole by solving a time-varying integral equation of the effective extraction radius;

[0052] The extraction effect determination module is used to generate a real-time extraction effect level signal according to the comparison relationship between the effective extraction coefficient and a preset extraction efficiency threshold.

[0053] The present invention constructs a spatial weight distribution matrix based on fault azimuth and fracture density distribution maps to quantify the controlling effect of geological structures on gas migration paths. Combining a permeability evolution model derived from real-time rock stress data, the stress sensitivity coefficient is dynamically integrated with geological structure influencing factors to achieve accurate characterization of the spatiotemporal evolution of permeability. This coupled model overcomes the shortcomings of traditional static assessments that fail to consider the effects of structural orientation correlation and stress fluctuations. It enables the permeability field to respond in real time to rock stress changes (such as fracture closure caused by stress concentration) and structural guidance (such as the guidance of fault strike on the dominant gas migration path), effectively solving the problem of assessment lag. At the same time, relying on the real-time solution of time-varying integral equations and a multi-level threshold matching mechanism, dynamic feedback and graded early warning of extraction effects are achieved. By inputting gas flow data into the permeability evolution model, the radial flow integral equation constructed based on Darcy's law can dynamically solve the effective extraction radius and output a quantified effective extraction coefficient. Combined with preset multi-level extraction efficiency threshold intervals, a digital grade signal is automatically generated to directly guide engineering control. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A flow chart of a method for real-time evaluation of borehole gas extraction effect provided by one embodiment of the present invention;

[0055] Figure 2 This is a functional module diagram of a real-time evaluation system for borehole gas extraction effect provided by one embodiment of the present invention;

[0056] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0057] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] The embodiment of the present application provides a method for real-time evaluation of borehole gas extraction effects. The execution subject of the method for real-time evaluation of borehole gas extraction effects includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for real-time evaluation of borehole gas extraction effects can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms.

[0059] Reference Figure 1 FIG. 1 is a flow chart of a method for real-time evaluation of borehole gas extraction effect provided by an embodiment of the present invention. In this embodiment, the method for real-time evaluation of borehole gas extraction effect includes:

[0060] S1. Synchronously collect gas flow data, rock stress data, and geological structure data of the target borehole area.

[0061] In an embodiment of the present invention, the synchronous acquisition of gas flow data, rock stress data, and geological structure data of the target borehole area includes:

[0062] The real-time gas flow pulse signal is obtained as the gas flow data of the target borehole through the multi-parameter sensor array in the borehole;

[0063] The stress fluctuation waveform of the surrounding rock of the borehole is measured by a stress sensor as rock mass stress data;

[0064] The fault azimuth parameters and fracture density distribution map of the area where the borehole is located are retrieved from the geological database as geological structure data.

[0065] Specifically, the target borehole refers to the specific borehole where gas extraction is required and is the object of the entire assessment method.

[0066] Specifically, gas flow data refers to the real-time gas flow pulse signal obtained by the multi-parameter sensor array in the borehole, which is used to characterize the volume of gas extracted from the target borehole per unit time; rock stress data refers to the stress fluctuation waveform of the surrounding rock of the borehole measured by the stress sensor, which reflects the stress state changes of the rock mass around the borehole; geological structure data refers to the fault azimuth parameters and fracture density distribution map of the borehole area retrieved from the geological database, which is used to describe the geological structure characteristics around the borehole.

[0067] In detail, the multi-parameter sensor array refers to a sensor assembly installed in a borehole, which can synchronously collect multiple parameters and is used to obtain real-time gas flow pulse signals in this embodiment.

[0068] In detail, the stress sensor refers to a sensor device used to measure the stress fluctuation of the surrounding rock of the borehole, and generates corresponding electrical signals or waveform data by sensing the stress changes of the rock mass.

[0069] In detail, the geological database refers to a database system that stores geological exploration data of the area where the borehole is located, including geological structure information such as fault azimuth and fracture density distribution.

[0070] Furthermore, multi-parameter sensor array deployment involves implanting a multi-parameter sensor array within the target borehole. This array is typically installed at a specific depth (e.g., 10-20 meters from the borehole opening) to avoid interference from the borehole opening. The sensors are waterproof and pressure-resistant (with a pressure rating of ≥10 MPa) to ensure stable operation in the complex drilling environment.

[0071] In detail, the sensor array transmits gas flow pulse signals in real time through cables, and the sampling frequency is set to 10-100Hz (dynamically adjusted according to the gas outflow volume). For example, when the gas flow fluctuates greatly, the sampling frequency is automatically increased to 50Hz.

[0072] Furthermore, the installation and measurement of stress sensors include: placing stress sensors at different locations (such as top, bottom, and side) of the borehole surrounding rock. The sensor probes need to be in close contact with the rock mass to sense stress fluctuations through strain gauges or piezoresistive effect.

[0073] Furthermore, the stress sensor uses wireless or wired transmission to send the measured stress fluctuation waveform (such as sine wave, pulse wave) to the data processing unit in real time. The waveform sampling accuracy is 16 bits to ensure that the details of the stress change can be captured.

[0074] Furthermore, the geological database integration involves establishing a network connection to the geological database, which contains a 3D model and attribute data for regional geological exploration. Using the borehole coordinates (longitude, latitude, depth) as an index, the system retrieves the corresponding fault azimuth parameters (e.g., a fault strike is 30° north-east) and the fracture density distribution map (using a color gradient to represent the number of fractures per unit area, e.g., a red area has a fracture density of 10 fractures per square meter).

[0075] Furthermore, the gas flow pulse signal processing includes: the original pulse signal obtained by the sensor is first filtered through a hardware filter circuit (low-pass filter, cutoff frequency 10Hz) to remove high-frequency noise, and then dynamically optimized using a software Kalman filter algorithm to eliminate environmental interference (such as false signals caused by drilling rig vibration), and finally obtain smooth gas flow time series data Q(t).

[0076] Furthermore, stress fluctuation waveform analysis involves performing a fast Fourier transform (FFT) on the waveform data output by the stress sensor to extract the main frequency component and the amplitude of each harmonic, and identify characteristic parameters of the stress fluctuation (such as peak stress and fluctuation period). For example, when a small crack occurs in the rock mass, the stress waveform will have a high-frequency component, and spectral analysis can be used to identify areas of stress concentration.

[0077] Furthermore, geological data standardization involves converting fault azimuth parameters retrieved from the database into relative angles relative to the borehole axis. Fracture density distribution maps are then gridded and interpolated (e.g., using Kriging) to generate regular grid data for subsequent calculations. For example, the fault azimuth θ (absolute orientation) is compared with the borehole axis to obtain the spatial angle parameter.

[0078] Furthermore, clock synchronization technology includes: using GPS clock or Beidou clock to uniformly synchronize the time of the multi-parameter sensor array, stress sensor and database system, ensuring that the timestamp accuracy of the three types of data is ≤10ms, realizing truly synchronous collection.

[0079] Furthermore, the data synchronization trigger mechanism includes: setting data collection trigger conditions (such as a sudden change in gas flow exceeding 10% or a stress fluctuation exceeding 0.5MPa). When any of the conditions is met, the three types of sensors start collecting data at the same time to avoid data deviation caused by asynchronous collection.

[0080] In summary, this synchronized data collection method, combining hardware and algorithms, overcomes the data lag and low sampling frequency associated with traditional manual inspections, enabling real-time, high-precision acquisition of gas flow, rock stress, and geological structure data. This step provides a reliable data foundation for subsequent permeability model construction, enabling assessment results to promptly reflect the true state of drilling and drainage, improving the efficiency and accuracy of gas drainage assessments from the source.

[0081] In general, the gas flow rate data, rock stress data, and geological structure data collected in S1 serve as the input for all subsequent steps: Geological structure data (fault azimuth and fracture density) are directly used in S2 to generate a spatial weight distribution matrix to quantify the geological influence on gas migration paths; rock stress data are combined with the spatial weight matrix in S3 to construct a permeability evolution model; and gas flow rate data are used as integral constraints in S4 to solve for the effective extraction radius and extraction coefficient. The simultaneous collection of these three types of data ensures the temporal and spatial consistency of subsequent model calculations, forming a complete logical chain from data collection to effect evaluation.

[0082] S2. Based on the fault azimuth parameters and the fracture density distribution map in the geological structure data, a spatial weight distribution matrix for controlling the gas migration path is generated.

[0083] In an embodiment of the present invention, generating a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and the fracture density distribution map in the geological structure data includes:

[0084] Calculating a spatial angle between the fault strike and the borehole axis based on a fault azimuth parameter in the geological structure data, wherein the spatial angle is generated based on the fault azimuth and the grid point azimuth;

[0085] generating an intensity gradient field of fracture development based on a fracture density distribution map in the geological structure data;

[0086] Calculating the migration path weight value of each grid point in the radial direction of the borehole by combining the spatial angle and the intensity gradient field;

[0087] The migration path weight values are mapped into three-dimensional matrix elements to generate a spatial weight distribution matrix.

[0088] In detail, the calculation of the migration path weight value of each grid point in the borehole radial direction in combination with the spatial angle and the intensity gradient field includes:

[0089] Establishing a polar coordinate system with the fault strike as a reference axis, and projecting the intensity gradient field onto the polar coordinate system;

[0090] The azimuth alignment between the grid points and the fault is quantified by the angle cosine function, wherein the azimuth alignment is:

[0091]

[0092] in, is the azimuthal alignment, is the fault azimuth, is the grid point azimuth;

[0093] An exponential decay function is used to correlate the azimuth alignment with the fracture density to obtain a migration path weight value representing the gas preferential migration path. The calculation formula for the migration path weight value is:

[0094]

[0095] in, is the migration path weight value, is the azimuthal alignment, is the fissure development density, is the distance attenuation coefficient, is the radial distance extending outward from the center of the borehole, is the grid point azimuth.

[0096] In detail, the fault azimuth parameter refers to the angle between the strike of the fault in the area where the borehole is located and the north direction. It is used to characterize the extension direction of the fault in space and is one of the core parameters of geological structure data.

[0097] In detail, the fracture density distribution map refers to a visualization chart of the fracture distribution density in the area around the borehole obtained through geological exploration, which usually expresses the density of fracture development in terms of the number of fractures per unit area (fractures / m²).

[0098] Specifically, the spatial angle refers to the angle value calculated from the fault azimuth and the grid point azimuth, which is used to describe the spatial positional relationship between the fault strike and the radial grid point direction of the borehole.

[0099] In detail, the intensity gradient field of fracture development refers to the continuous field data generated based on the fracture density distribution map, which characterizes the gradient of fracture development intensity in space and reflects the dominant path direction of gas migration.

[0100] Specifically, the migration path weight value refers to a numerical value used to quantify the degree of influence of each grid point in the borehole radial direction on gas migration. A larger value indicates that the location is more likely to become a priority path for gas migration.

[0101] In detail, the three-dimensional matrix element refers to mapping the migration path weight value of each grid point in space into a numerical element in the matrix to form a three-dimensional spatial weight distribution matrix for the subsequent construction of the permeability model.

[0102] In detail, the polar coordinate system refers to a coordinate system established with the fault strike as the reference axis, which facilitates the conversion of orientation relationships in space into parameters of radial distance and angle, and simplifies the quantitative analysis of gas migration paths.

[0103] Furthermore, calculating the spatial angle between the fault strike and the borehole axis includes: extracting the fault azimuth θ (such as θ=30°, indicating that the fault strike is 30° north-east) from the geological structure data obtained in step S1, and determining the azimuth of the borehole axis (usually the absolute azimuth of the borehole extension direction, such as the borehole axis azimuth is 0°, that is, the north direction); converting the fault azimuth and the borehole axis orientation into a unified geographic coordinate system or a local borehole coordinate system, and establishing a three-dimensional spatial coordinate system with the borehole center as the origin and the axis direction as the z-axis; for each grid point in the borehole radial direction, obtaining its azimuth φ (the angle between the point and the borehole axis in the horizontal plane), and calculating the spatial angle between the fault strike and the grid point orientation by trigonometric functions, that is, using the (θ-φ) difference in the formula ζ=|cos(θ-φ)| to obtain the absolute value of the angle between the fault strike and the grid point direction. For example, when θ = 30° and φ = 45°, the spatial angle is 15°, and the absolute value of the cosine is used to characterize the azimuthal alignment.

[0104] Furthermore, generating an intensity gradient field for fracture development involves dividing the fracture density distribution map into a regular spatial grid (e.g., a 0.5m x 0.5m grid), with each grid point corresponding to a fracture density. Using kriging or inverse distance weighted interpolation, the discrete fracture density data are spatially interpolated to generate a continuous fracture density field. For example, given that the fracture densities at three points in a region are 8, 10, and 12 fractures / m², respectively, the fracture density at any point in the region can be obtained through interpolation. A gradient calculation (e.g., the finite difference method) is then performed on the interpolated fracture density field to obtain the fracture intensity gradient (including gradient magnitude and direction) at each grid point, forming an intensity gradient field. The gradient direction represents the direction of fastest fracture development, while the gradient magnitude represents the severity of fracture density changes.

[0105] Furthermore, the calculation of the migration path weight value of each radial grid point of the borehole includes: taking the fault strike as the polar axis (i.e., the 0° direction of the polar coordinate system) and the borehole center as the pole, a two-dimensional polar coordinate system is established. In this coordinate system, the position of each grid point is determined by the radial distance r and the angle φ (azimuth relative to the fault strike); projecting the three-dimensional intensity gradient field into the polar coordinate system so that the fracture development intensity gradient of each grid point corresponds to the polar coordinate parameters (r, φ), which is convenient for subsequent coupling calculation with the azimuth alignment; using the formula ζ=|cos(θ-φ)| to calculate the azimuth alignment ζ of each grid point. Among them, θ is the fault azimuth, and φ is the azimuth of the grid point in the polar coordinate system. The closer the ζ value is to 1, the higher the consistency between the grid point direction and the fault strike, and the easier it is for gas to migrate along this direction; using an exponential decay function Calculate the migration path weight value.

[0106] Specifically, ρ (unit: fractures / m²) is the density of fracture development at the grid point. The denser the fractures, the more gas migration pathways there are and the greater the weight value. is the distance attenuation term, γ is the distance attenuation coefficient (e.g. γ = 0.5m -1 ), indicating that the gas migration capacity decreases exponentially with increasing distance r. The farther from the borehole, the smaller the weight value. ζ is the azimuth alignment, reflecting the guiding effect of the fault strike on gas migration. For example, when a grid point r = 5m, ρ = 10 / m², γ = 0.5m -1 When ζ=0.966, the weight value w=10・e^(-0.5×5)・0.966≈0.792, indicating that the influence of this location on gas migration is weak.

[0107] Furthermore, the distance attenuation coefficient is currently constant, but the actual attenuation may be affected by the connectivity of the fracture network.

[0108] Furthermore, generating a spatial weight distribution matrix involves dividing the space into three-dimensional grids (e.g., radial spacing of 0.5 m, azimuth spacing of 5°, and vertical spacing of 0.5 m) based on the borehole radial range (e.g., 0 to 10 m), azimuth range (0° to 360°), and vertical height (e.g., coal seam height of 3 m), and determining the row and column dimensions of the matrix (e.g., 20 × 72 × 6). The migration path weight value w(r,φ) of each three-dimensional grid point is mapped to the element value of the corresponding position in the matrix, forming the three-dimensional spatial weight distribution matrix W. Matrix element values range from 0 to 1, with larger values indicating a stronger control effect on gas migration at that location. Matrix elements are normalized so that the sum of all elements is 1, ensuring the relativity of the weight values and the stability of the model calculation. For example, if the weight value of a grid point is 0.792, the normalized value is 0.792 / ∑w, where ∑w is the sum of the weight values of all grid points.

[0109] In summary, by quantifying the impact of fault orientation and fracture development on gas migration pathways, we address the issue of traditional assessment methods failing to account for spatial variations in geological structures. The spatial weight distribution matrix generated by this step accurately characterizes the preferential migration pathways of gas under complex geological conditions, providing a quantitative basis at the geological structural level for subsequent permeability model construction. This improves the accuracy and reliability of gas extraction effectiveness assessments and avoids biased assessments caused by neglecting geological factors.

[0110] In general, the output of step S2 (the spatial weight distribution matrix W) is one of the core inputs for constructing the permeability evolution model in step S3. Specifically, the spatial weight distribution matrix W, as a geological structural influencing factor, is combined with the rock stress data σ(t) collected in S1 to quantify the coupling effect of geological structure and stress on permeability through the permeability evolution model. The weight values in the matrix reflect the degree of gas migration dominance at different spatial locations, directly affecting the radial distribution characteristics of permeability in the borehole, and thus affecting the solution of the effective extraction radius in step S4. This step establishes a quantitative bridge between geological data and physical models, ensuring the logical coherence of the evaluation process.

[0111] S3. Constructing a permeability evolution model along the radial direction of the borehole based on the spatial weight distribution matrix and the rock mass stress data.

[0112] In an embodiment of the present invention, constructing a permeability evolution model along the radial direction of the borehole according to the spatial weight distribution matrix and the rock mass stress data includes:

[0113] Normalizing the migration path weight values in the spatial weight distribution matrix to obtain a geological structure influencing factor;

[0114] Calculating a stress sensitivity coefficient based on the rock mass stress data;

[0115] deriving a stress conversion operator between permeability and rock mass stress data based on the Coulomb failure criterion;

[0116] The geological structure influencing factor and the stress conversion operator are integrated to generate a permeability evolution model, which outputs a permeability evolution field that changes with radial distance and time.

[0117] In detail, the permeability evolution model is:

[0118]

[0119] in, is the radial distance and time The permeability at is the baseline permeability, is the geological structure influencing factor, is the reference stress, is the radial distance extending outward from the center of the borehole, is the time variable, is the rock mass stress data, is the stress sensitivity coefficient.

[0120] In detail, the spatial weight distribution matrix refers to the three-dimensional matrix generated by step S2, which is used to characterize the control effect of each position in the space around the borehole on the gas migration path. The larger the value of the matrix element, the more likely the position is to become the priority path of gas migration.

[0121] In detail, the migration path weight value refers to the element value in the spatial weight distribution matrix, which quantifies the influence of each grid point in the borehole radial direction on gas migration. The value is related to the fault orientation, fracture development density and distance from the borehole center.

[0122] In detail, the geological structure impact factor refers to the dimensionless parameter obtained after normalizing the spatial weight distribution matrix, which is used to characterize the influence of geological structure (faults, fractures) on permeability, and its value range is 0 to 1.

[0123] Specifically, the rock mass stress data refers to the stress fluctuation waveform data of the surrounding rock of the borehole collected through step S1, which reflects the change of the internal stress of the rock mass over time, and the unit is Pascal (Pa).

[0124] In detail, the stress sensitivity coefficient refers to a parameter that describes the sensitivity of permeability to changes in rock mass stress. It is obtained by experimentally fitting the permeability and stress curves of different rock masses or theoretical derivation. It is dimensionless and is used to characterize the magnitude of the influence of stress on permeability.

[0125] Specifically, the Coulomb failure criterion refers to a theoretical criterion used to describe the rupture of a rock mass under stress. It determines whether a rock mass has reached a rupture state based on the combination of normal stress and shear stress, and is the theoretical basis for deriving the relationship between permeability and stress.

[0126] In detail, the stress conversion operator refers to a mathematical expression derived based on the Coulomb failure criterion, which is used to quantify the effect of rock stress changes on permeability and establish the conversion relationship between stress and permeability.

[0127] In detail, the permeability evolution model refers to a mathematical model generated by integrating geological structure influencing factors and stress conversion operators. It is used to describe the change pattern of permeability at different radial positions of the borehole over time and output the permeability evolution field.

[0128] Furthermore, the normalization process of the spatial weight matrix includes: accumulating the weight values of all migration paths in the spatial weight distribution matrix generated by S2 to obtain the weight sum ∑w. For example, assuming that the matrix contains N grid points, the weight value of each point is ,but ; The weight value of each grid point Divide by the sum of weights , we get the normalized weight value, that is, the geological structure influencing factor, which is expressed as follows: This process limits the value range of the geological structure influence factor to between 0 and 1, facilitating coupled calculations with other parameters. The normalized weight values in three-dimensional space are statistically aggregated along the borehole radial direction (r direction) to obtain the radial distribution of the geological structure influence factor. For example, the average migration path weight values of all circumferential and vertical grid points at the same radial distance r are taken to obtain the geological structure influence factor at that radial position.

[0129] Furthermore, the calculation of stress sensitivity coefficient includes: denoising and filtering the rock stress data σ(t) collected by S1, using sliding average filtering or wavelet transform to remove high-frequency interference, extracting effective stress change characteristics (such as static load stress and dynamic disturbance stress); measuring the core permeability under different stress conditions through indoor core experiments (such as triaxial compression permeability experiments), and establishing a stress-permeability relationship curve. For example, applying gradually increasing confining pressure (1MPa to 10MPa) to coal rock samples, and synchronously measuring the permeability changes, to obtain the functional relationship between permeability and stress changes; based on experimental data, using power function fitting , where n is the stress sensitivity coefficient. The value of n is determined by the least square method to minimize the error between the fitting curve and the experimental data. For example, when the stress When the permeability increases The larger the n value is, the more sensitive the permeability is to stress changes.

[0130] Furthermore, the derivation of stress conversion operator includes: Coulomb fracture criterion expression is: , where τ is the shear stress, c is the rock mass cohesion, is the internal friction angle. This criterion is associated with the permeability-stress relationship, considering the effect of stress on the closure / opening of rock cracks. Based on the rock crack mechanics theory, when stress increases, rock cracks close and permeability decreases; conversely, when stress decreases, cracks open and permeability increases. The derivative relationship of permeability to stress is derived through differential method, and the stress conversion operator is established, namely, This operator reflects the quantitative effect of stress change on permeability.

[0131] Furthermore, the reference stress Make sure to include: Usually, the original ground stress of the rock mass or the benchmark stress value in the experiment (such as 10 MPa) is taken as the reference benchmark for stress conversion, so that the permeability calculations under different stress conditions are comparable.

[0132] Furthermore, the physical meaning of each parameter in the permeability evolution model is: is the base permeability (e.g. ), represents the initial permeability without stress and geological structure influence; Reflects the enhancement or inhibition of permeability by geological structures (faults, fractures) at the radial r; It reflects the regulatory effect of the change of real-time stress relative to the reference stress on permeability.

[0133] Furthermore, the spatiotemporal distribution calculation includes: for each radial position r (such as 0.5m to 10m) of the borehole and each time point t, the corresponding geological structure influencing factors and rock mass stress are substituted to calculate , forming a permeability evolution field that changes with radial distance and time. For example, at a certain time t1, the geological structure influence factor at the radial r=5m is 0.6, the stress is 8MPa, the reference stress is 10MPa, and the stress sensitivity coefficient is 0.8, k(5,t1)≈0.738 , which means that the penetration rate increased by 23.8% compared with the baseline value.

[0134] Furthermore, model validation and calibration include comparing the permeability results calculated by the model with the field measured permeability data (e.g., obtained through pressure drop testing), and adjusting the model parameters (e.g., n, γ) so that the error between the calculated and measured values is less than 10%, thus ensuring the accuracy and reliability of the model.

[0135] In summary, by integrating geological structural factors with stress conversion operators, we address the problem of traditional permeability models failing to account for spatial geologic heterogeneity and dynamic stress changes. The permeability evolution model constructed in this step can reflect in real time how permeability at different locations around the borehole changes with geological structure and stress. This provides a physical basis for accurately evaluating gas extraction effectiveness, avoids assessment bias caused by ignoring geological-stress coupling, and improves the model's applicability and accuracy.

[0136] In general, the output of step S3 (permeability evolution model) is the core input for solving the effective extraction coefficient in step S4: the permeability evolution model is used as a variable in the radial flow integral equation in S4, combined with the gas flow data, to calculate the dynamic effective extraction radius through Darcy's law; the geological structure influencing factors in the model are derived from the spatial weight matrix generated by S2, and the stress data are derived from the synchronous collection of S1, forming a complete data chain from geological data to physical model; the spatiotemporal distribution of the permeability evolution field directly affects the calculation results of the effective extraction radius, and then determines the extraction effect level evaluation in step S5, ensuring the logical coherence of each step and the data closed loop.

[0137] S4. Input the gas flow rate data into the permeability evolution model, and output the effective extraction coefficient of the borehole by solving the time-varying integral equation of the effective extraction radius.

[0138] In an embodiment of the present invention, solving the time-varying integral equation of the effective extraction radius includes:

[0139] Based on Darcy's law, a radial flow integral equation is established with the permeability evolution model as a variable;

[0140] Based on the radial flow integral equation, the gas flow rate data is used as an integral constraint to solve the effective extraction radius;

[0141] The ratio of the effective extraction radius to the designed extraction radius is calculated, and the effective extraction coefficient is output.

[0142] In detail, the radial flow integral equation is:

[0143]

[0144] in, is the gas flow data, is the coal seam height, is the pressure difference between the reservoir pressure and the borehole pressure, is the gas viscosity, is the radius of the borehole wall, is the effective extraction radius, is the radial distance of the drill hole and time The permeability at is the radial distance extending outward from the center of the borehole, is the time variable.

[0145] In detail, the effective extraction coefficient is:

[0146]

[0147] in, is the effective extraction radius, is the designed extraction radius (m), is the effective extraction coefficient (dimensionless).

[0148] In detail, Darcy's law refers to the basic law that describes the seepage law of fluid in porous media. It points out that the fluid flow rate is proportional to the permeability and pressure difference, and inversely proportional to the fluid viscosity and flow distance. It is the theoretical basis for establishing the radial flow integral equation.

[0149] In detail, the radial flow integral equation refers to a mathematical equation established based on Darcy's law, which is used to describe the flow pattern of gas in the radial direction of the borehole. The permeability evolution model is used as a variable and the effective extraction radius is solved in combination with the gas flow data.

[0150] In detail, the effective extraction radius refers to the maximum radial distance within which the borehole can effectively extract gas within a certain period of time, measured in meters (m), reflecting the impact range of borehole gas extraction.

[0151] In detail, the designed extraction radius refers to the radius of the extraction influence range preset during the drilling design stage, measured in meters (m). It is determined based on geological conditions and extraction technology and is used to measure the actual extraction effect.

[0152] In detail, the effective extraction coefficient refers to the ratio of the effective extraction radius to the designed extraction radius. It is dimensionless and is used to quantify the degree of match between the actual extraction effect of the borehole and the design target. It is the core indicator for evaluating extraction efficiency.

[0153] Furthermore, the radial flow derivation of Darcy's law includes: the basic expression of Darcy's law is , where Q is the flow rate, k is the permeability, A is the seepage cross-sectional area, ΔP is the pressure difference, μ is the fluid viscosity, and L is the flow distance. For the borehole radial flow scenario, the seepage cross-sectional area (r is the radial distance, h is the coal seam height), the flow distance element is dr, so the radial flow differential equation is derived: .

[0154] Furthermore, the radial flow integral equation is constructed by integrating the borehole radial direction from the wellbore radius to the effective extraction radius to obtain the radial flow integral equation:

[0155]

[0156] Where Q(t) is the gas flow data collected in real time by S1, k(r,t) is the permeability evolution model constructed by S3, h is the coal seam height (e.g., 3 m), ΔP is the pressure difference between the reservoir and the borehole (e.g., 0.5 MPa), and μ is the gas viscosity (e.g., ), is the drilling radius (such as 0.1m).

[0157] Furthermore, parameter preprocessing includes: obtaining time series data of gas flow data from S1 and performing smoothing processing (such as moving average filtering) to eliminate high-frequency noise; obtaining the numerical distribution of k(r,t) at different radial positions r and time t from S3 to form a permeability evolution field database.

[0158] Furthermore, the digitization of the integral equation includes: using a numerical integration method (such as the trapezoidal method or the Simpson method) to perform discrete calculations on the integral term of the denominator. Divide into N equally spaced subintervals (e.g. N=100), each subinterval width , calculate the midpoint of each subinterval The values are summed up to get the integral approximation: ,in is the radial distance of the midpoint of the i-th subinterval.

[0159] Furthermore, the iterative solution Includes: Settings Initial guess value (such as design extraction radius 50%); Substitute the theoretical value of Q(t) on the left side into the integral equation and compare it with the measured value; Use Newton iteration method to adjust , until the error between the theoretical Q(t) and the measured value is less than the set threshold (such as 5%). The iterative formula is: ,in, for right The derivative of is the number of iterations.

[0160] Furthermore, when Q(t) collected by S1 or k(r,t) of S3 changes, the integral equation is triggered to be re-solved to ensure Real-time reflection of the current extraction status. For example, when the rock stress σ(t) changes and causes k(r,t) to increase, Will automatically update to a larger value.

[0161] Furthermore, obtaining the designed extraction radius includes: retrieving the designed extraction radius (such as 8m) from the drilling design document. This value is pre-set based on parameters such as coal seam permeability and extraction time, and is the benchmark for evaluating the extraction effect.

[0162] Furthermore, the ratio calculation and output includes: according to the formula Calculate the effective extraction coefficient and output a dimensionless value. For example, when the effective extraction radius is 6.8m and the designed extraction radius is 8m, the effective extraction coefficient is 0.85, indicating that the current extraction range reaches 85% of the designed value.

[0163] Furthermore, accuracy calibration includes: regular verification through on-site measurements (such as drilling gas content testing) To improve the accuracy of the integral equation, adjust the integral equation solution parameters (such as numerical integration step size and iteration error threshold) to ensure that the calculation error of η(t) does not exceed 10%.

[0164] In summary, solving the effective extraction radius using the radial flow integral equation based on Darcy's law overcomes the traditional reliance on static empirical parameters to evaluate extraction effectiveness. This step enables dynamic calculation of the extraction influence range, enabling the effective extraction coefficient to reflect the extraction efficiency of the borehole in real time under different geological conditions and stress states. This provides data support for optimizing extraction processes (such as adjusting the extraction pressure and arranging more dense boreholes), and avoids waste of extraction resources due to delayed evaluation.

[0165] In general, the input and output of step S4 constitute the key data chain of the evaluation process: the input data comes from the gas flow Q(t) of S1 and the permeability evolution model k(r,t) of S3, where k(r,t) integrates the geological structure influencing factors of S2 and the rock stress data σ(t) of S1; the output effective extraction coefficient η(t) serves as the input of step S5, which is used to compare with the preset threshold to generate an extraction effect level signal; this step establishes a quantitative relationship between the physical model (permeability) and the engineering indicator (extraction radius) to ensure the logical coherence from geological data to application evaluation.

[0166] S5. Generate a real-time extraction effect level signal based on the comparison relationship between the effective extraction coefficient and a preset extraction efficiency threshold.

[0167] In an embodiment of the present invention, generating a real-time drainage effect level signal based on a comparison relationship between the effective drainage coefficient and a preset drainage efficiency threshold includes:

[0168] Preset multi-level extraction efficiency threshold range;

[0169] The effective extraction coefficient is matched to a corresponding multi-level extraction efficiency threshold interval, and a level identifier is activated according to the matching result, wherein the level identifier is encoded as a digital signal output.

[0170] In detail, matching the effective extraction coefficient to the corresponding multi-level extraction efficiency threshold range includes:

[0171] When the coefficient is lower than a first threshold, an inefficiency identifier is activated;

[0172] When the coefficient is between the first and second thresholds, a medium-effect identifier is activated;

[0173] When the coefficient is between the second and third thresholds, the high-efficiency identifier is activated;

[0174] When the coefficient exceeds a third threshold, the super-efficient identifier is activated.

[0175] In detail, the effective extraction coefficient refers to the dimensionless parameter calculated by step S4, which is the ratio of the effective extraction radius to the designed extraction radius and is used to quantify the degree of match between the actual extraction effect of the borehole and the design target.

[0176] In detail, the preset extraction efficiency threshold refers to the extraction efficiency evaluation standard value pre-set during the system initialization phase, which is used to divide the critical value of different extraction effect levels and is usually determined based on geological conditions and extraction process requirements.

[0177] In detail, the multi-level extraction efficiency threshold interval refers to several efficiency intervals divided by multiple preset thresholds, each interval corresponding to a different extraction effect level, such as low efficiency, medium efficiency, high efficiency, and super high efficiency intervals.

[0178] In detail, the level identifier refers to a symbol or code used to represent the extraction effect level, which is activated according to the effective extraction coefficient matching result, such as a text logo, icon or digital code.

[0179] In detail, digital signal refers to the conversion of level identifiers into binary or multi-binary electrical signals that can be recognized by the monitoring system, facilitating remote transmission and automated control.

[0180] In detail, the low-efficiency identifier refers to the level identifier activated when the effective extraction coefficient is lower than the first threshold, indicating that the extraction effect has not met expectations and the extraction process needs to be adjusted; the medium-efficiency identifier refers to the level identifier activated when the effective extraction coefficient is between the first and second thresholds, indicating that the extraction effect is at a medium level and the current process can be maintained; the high-efficiency identifier refers to the level identifier activated when the effective extraction coefficient is between the second and third thresholds, indicating that the extraction effect is good and meets the design requirements; the super-efficiency identifier refers to the level identifier activated when the effective extraction coefficient exceeds the third threshold, indicating that the extraction effect is better than the design expectations and resource allocation can be optimized.

[0181] Furthermore, the pre-set multi-level extraction efficiency threshold ranges are determined based on industry standards (such as the "Interim Provisions on Meeting Coal Mine Gas Extraction Standards") and field experience, combined with parameters such as coal seam permeability and extraction time. For example, for highly permeable coal seams, the first threshold could be set at 0.6, the second at 0.8, and the third at 0.95.

[0182] Furthermore, statistical analysis methods are used to cluster the effective extraction coefficients of different effect levels in historical extraction data, determine the boundary values of each interval, and ensure that the threshold division meets actual production needs.

[0183] Furthermore, the implementation of interval division includes dividing the extraction efficiency from low to high into four intervals, corresponding to four levels of effect:

[0184] Inefficient interval: η(t) < first threshold (e.g. η(t) < 0.6)

[0185] Medium efficiency interval: first threshold ≤ η(t) < second threshold (e.g. 0.6 ≤ η(t) < 0.8)

[0186] High efficiency range: second threshold ≤ η(t) < third threshold (e.g. 0.8 ≤ η(t) < 0.95)

[0187] Super high efficiency range: η(t) ≥ the third threshold (e.g. η(t) ≥ 0.95)

[0188] The threshold parameters are stored in the system configuration file, allowing users to dynamically adjust them according to actual conditions.

[0189] Furthermore, matching the effective extraction coefficient to the threshold interval includes: reading the effective extraction coefficient η(t) in real time from the output result of step S4, and the update frequency is consistent with the S4 solution frequency (such as updating once every 10 seconds) to ensure the real-time nature of the matching process; using multiple conditional branch structures (such as if-else statements) for interval matching, and using tolerance processing (such as allowing an error range of ±0.01) for precision errors that may be caused by floating-point operations to avoid level misjudgment due to calculation errors.

[0190] Furthermore, when η(t) is equal to the threshold, it is matched to a higher level interval according to the principle of "higher rather than lower" (for example, when η=0.6, it is classified into the medium efficiency interval) to ensure that the evaluation result is safety-oriented.

[0191] Furthermore, the identifier mapping rules include: establishing a mapping table between level names and identifiers

[0192] Furthermore, the hardware activation mechanism includes: outputting a level signal through the IO interface of a PLC (Programmable Logic Controller) or MCU (Micro Control Unit) to drive an indicator light or a buzzer:

[0193] Inefficiency: The red indicator light is always on and the buzzer sounds a low-frequency alarm;

[0194] Medium effect: The yellow indicator light flashes and the buzzer sounds intermittently;

[0195] High efficiency: the green indicator light is always on and there is no alarm;

[0196] Ultra-efficient: The green indicator light flashes quickly with a beep.

[0197] Furthermore, digital signal encoding and transmission includes encoding the level identifier into a binary digital signal (such as two binary digits 00-11) and transmitting it to the central monitoring system via industrial communication protocols such as RS485 and Modbus:

[0198] Furthermore, signal visualization processing includes: dynamically displaying the sampling effect level on the monitoring software interface, presenting it in a combination of color blocks and text annotations, for example:

[0199] Inefficiency: The red block shows “Inefficiency (η(t)=X.XX)”;

[0200] Super high efficiency: The green block shows “Super high efficiency (η(t)=X.XX)”.

[0201] In summary, by converting the abstract effective extraction coefficient into an intuitive grade signal, the problem of ambiguous effect judgment and inconvenient real-time control in traditional assessment methods is solved. This step enables visualization and digital expression of extraction results, enabling on-site operators to quickly understand the operating status of the extraction system and promptly implement optimization measures (such as adjusting the extraction pressure and increasing drilling depth). This avoids substandard gas extraction and resource waste caused by delayed assessments, thereby improving the automation and intelligence of gas extraction management.

[0202] In general, step S5 is the final step in the entire assessment process. Its input comes directly from the effective extraction coefficient η(t) calculated in step S4. The calculation of η(t) relies on the gas flow data from S1, the spatial weight matrix from S2, and the permeability model from S3. The specific connection is as follows: η(t) output from S4 serves as the sole input to S5, determining the logic for generating the grade signal. The generated grade signal can be fed back to the sensor acquisition frequency in S1 or the model parameter calibration in S3, forming a closed-loop control (for example, when inefficiency is detected, the sensor sampling frequency is automatically increased to obtain more accurate data). This step converts the physical model calculation results (η(t)) into engineering application signals, achieving the critical transition from data processing to production decision-making, ensuring the engineering practicality of the assessment results.

[0203] like Figure 2 , which is a functional module diagram of a real-time evaluation system for borehole gas extraction effect provided by an embodiment of the present invention.

[0204] The real-time evaluation system 100 for borehole gas drainage effectiveness described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the system 100 may include a data acquisition module 101, a weight distribution generation module 102, a permeability model construction module 103, an effective drainage coefficient generation module 104, and a drainage effectiveness determination module 105. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and is stored in the electronic device's memory.

[0205] In this embodiment, the functions of each module / unit are as follows:

[0206] The data acquisition module 101 is used to synchronously acquire gas flow data of the target borehole, rock stress data and geological structure data of the area where the borehole is located;

[0207] The weight distribution generating module 102 is used to generate a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and the fracture density distribution map in the geological structure data;

[0208] The permeability model building module 103 is used to build a permeability evolution model along the radial direction of the borehole according to the spatial weight distribution matrix and the rock mass stress data;

[0209] The effective extraction coefficient generation module 104 is configured to input the gas flow rate data into the permeability evolution model, and output the effective extraction coefficient of the borehole by solving the time-varying integral equation of the effective extraction radius;

[0210] The drainage effect determination module 105 is configured to generate a real-time drainage effect level signal based on a comparison between the effective drainage coefficient and a preset drainage efficiency threshold.

[0211] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0212] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0213] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0214] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0215] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0216] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for real-time evaluation of borehole gas extraction effect, characterized in that: The method comprises: S1. Simultaneously collect gas flow data, rock stress data, and geological structure data of the target borehole area; S2. Generate a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and fracture density distribution map in the geological structure data; S3. Constructing a radial permeability evolution model along the borehole according to the spatial weight distribution matrix and the rock stress data; S4. Input the gas flow rate data into the permeability evolution model, and output the effective extraction coefficient of the borehole by solving the time-varying integral equation of the effective extraction radius; S5. Generate a real-time extraction effect level signal based on the comparison relationship between the effective extraction coefficient and a preset extraction efficiency threshold.

2. The method for real-time evaluation of borehole gas extraction effect according to claim 1, characterized in that: The synchronous collection of target borehole gas flow data, rock mass stress data, and geological structure data of the borehole area includes: The real-time gas flow pulse signal is obtained as the gas flow data of the target borehole through the multi-parameter sensor array in the borehole; The stress fluctuation waveform of the surrounding rock of the borehole is measured by a stress sensor as rock mass stress data; The fault azimuth parameters and fracture density distribution map of the area where the borehole is located are retrieved from the geological database as geological structure data.

3. The method for real-time evaluation of borehole gas extraction effect according to claim 1, wherein: The generating of a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and the fracture density distribution map in the geological structure data includes: Calculating a spatial angle between the fault strike and the borehole axis based on a fault azimuth parameter in the geological structure data, wherein the spatial angle is generated based on the fault azimuth and the grid point azimuth; generating an intensity gradient field of fracture development based on a fracture density distribution map in the geological structure data; Calculating the migration path weight value of each grid point in the radial direction of the borehole by combining the spatial angle and the intensity gradient field; The migration path weight values are mapped into three-dimensional matrix elements to generate a spatial weight distribution matrix.

4. The method for real-time evaluation of borehole gas extraction effect according to claim 3, wherein: Calculating the migration path weight value of each grid point in the borehole radial direction by combining the spatial angle and the intensity gradient field includes: Establishing a polar coordinate system with the fault strike as a reference axis, and projecting the intensity gradient field onto the polar coordinate system; The azimuth alignment between the grid points and the fault is quantified by the angle cosine function, wherein the azimuth alignment is: ； in, is the azimuthal alignment, is the fault azimuth, is the grid point azimuth; An exponential decay function is used to correlate the azimuth alignment with the fracture density to obtain a migration path weight value representing the gas preferential migration path. The calculation formula for the migration path weight value is: ； in, is the migration path weight value, is the azimuthal alignment, is the fissure development density, is the distance attenuation coefficient, is the radial distance extending outward from the center of the borehole, is the grid point azimuth.

5. The method for real-time evaluation of borehole gas extraction effect according to claim 1, wherein: The step of constructing a radial permeability evolution model of the borehole according to the spatial weight distribution matrix and the rock mass stress data includes: Normalizing the migration path weight values in the spatial weight distribution matrix to obtain a geological structure influencing factor; Calculating a stress sensitivity coefficient based on the rock mass stress data; deriving a stress conversion operator between permeability and rock mass stress data based on the Coulomb failure criterion; The geological structure influencing factor and the stress conversion operator are integrated to generate a permeability evolution model, which outputs a permeability evolution field that changes with radial distance and time.

6. The method for real-time evaluation of borehole gas extraction effect according to claim 5, characterized in that: The permeability evolution model is: ； in, is the radial distance and time The permeability at is the baseline permeability, is the geological structure influencing factor, is the reference stress, is the radial distance extending outward from the center of the borehole, is the time variable, is the rock mass stress data, is the stress sensitivity coefficient.

7. The method for real-time evaluation of borehole gas extraction effect according to claim 1, wherein: The time-varying integral equation for solving the effective extraction radius includes: Based on Darcy's law, a radial flow integral equation is established with the permeability evolution model as a variable; Based on the radial flow integral equation, the gas flow rate data is used as an integral constraint to solve the effective extraction radius; The ratio of the effective extraction radius to the designed extraction radius is calculated, and the effective extraction coefficient is output.

8. The method for real-time evaluation of borehole gas extraction effect according to claim 7, characterized in that: The radial flow integral equation is: ； in, is the gas flow data, is the coal seam height, is the pressure difference between the reservoir pressure and the borehole pressure, is the gas viscosity, is the radius of the borehole wall, is the effective extraction radius, is the radial distance of the drill hole and time The permeability at is the radial distance extending outward from the center of the borehole, is the time variable.

9. The method for real-time evaluation of borehole gas extraction effect according to claim 1, wherein: Generating a real-time drainage effect level signal according to a comparison relationship between the effective drainage coefficient and a preset drainage efficiency threshold includes: Preset multi-level extraction efficiency threshold range; The effective extraction coefficient is matched to a corresponding multi-level extraction efficiency threshold interval, and a level identifier is activated according to the matching result, wherein the level identifier is encoded as a digital signal output.

10. A real-time evaluation system for borehole gas extraction effect, characterized in that: The system comprises: Data acquisition module, used to synchronously collect gas flow data of the target borehole, rock stress data and geological structure data of the area where the borehole is located; A weight distribution generation module, configured to generate a spatial weight distribution matrix for controlling gas migration paths based on the fault azimuth parameters and the fracture density distribution map in the geological structure data; A permeability model construction module, configured to construct a permeability evolution model along the radial direction of the borehole according to the spatial weight distribution matrix and the rock mass stress data; an effective extraction coefficient generation module, configured to input the gas flow rate data into the permeability evolution model, and output the effective extraction coefficient of the borehole by solving a time-varying integral equation of the effective extraction radius; The extraction effect determination module is used to generate a real-time extraction effect level signal according to the comparison relationship between the effective extraction coefficient and a preset extraction efficiency threshold.

Images