Coal seam gas nitrogen injection flow-increasing enhanced extraction effect evaluation method

Abstract

The invention discloses a coal seam gas nitrogen injection flow-increasing enhanced extraction effect evaluation method, which realizes accurate quantitative evaluation of a nitrogen injection displacement effect through a method of combining standard displacement efficiency experimental determination and actual displacement efficiency dynamic calculation. The problem that the nitrogen injection flow increasing effect cannot be objectively evaluated and dynamically optimized in the prior art is effectively solved; through a displacement range determination method and a multi-parameter real-time monitoring mechanism aiming at different mine geological conditions, the environmental adaptability of the evaluation system is remarkably improved; by combining a closed-loop optimization strategy constructed by a deep learning model, nitrogen injection parameters can be automatically adjusted and the extraction trend can be predicted according to real-time data, the gas extraction efficiency is improved while safe production of a mine is guaranteed, the nitrogen injection operation cost is reduced, and efficient and reliable technical support is provided for comprehensive treatment of coal mine gas.

Description

Technical Field

[0001] This application relates to the field of mining technology, and in particular to a method for evaluating the effect of nitrogen injection to enhance coal seam gas extraction. Background Technology

[0002] In the field of coal mine gas drainage, to address the problem of low gas drainage efficiency caused by the low permeability of coal seams, existing technologies employ various permeability-enhancing and flow-increasing measures, such as mining protective layers, hydraulic fracturing / fracture cutting, loosening blasting, large-diameter boreholes, and dense borehole drilling. However, these technologies have many problems, such as the difficulty in implementing mining protective layers for single coal seams; the large water consumption and water-locking effect of hydraulic permeability enhancement; the potential for secondary hazards from blasting permeability enhancement; and the high construction cost of dense boreholes. Furthermore, with increasing mining depth, the pressure on gas disaster prevention and control increases, and traditional borehole pre-drainage technologies are time-consuming and exhibit rapid gas flow decay, failing to meet the needs of mining succession and safe production.

[0003] In recent years, gas injection displacement technology has gradually attracted attention due to its high efficiency. Nitrogen (N2) has advantages such as wide availability, mature nitrogen production processes, low outburst risk, and no pollution, making it suitable for downhole gas injection displacement of coal seam gas. However, in practical applications, it still faces several problems, including:

[0004] Lack of effect evaluation: Existing technologies lack a scientific and unified evaluation standard for the effect of nitrogen injection displacement, making it impossible to quantify the actual improvement effect of gas extraction during nitrogen injection. This results in nitrogen injection parameters (such as pressure and flow rate) being set based on experience, making it difficult to achieve precise control.

[0005] Insufficient dynamic adaptability: Coal seam geological conditions (such as pore pressure and fracture distribution) and gas occurrence state have significant spatiotemporal differences. Existing methods cannot monitor the displacement effect in real time and it is difficult to optimize nitrogen injection strategies in a timely manner, resulting in a decrease in extraction efficiency as mining progresses.

[0006] Low level of intelligence: Traditional assessment methods rely on manual data collection and static analysis, which limits the accuracy of assessment and the efficiency of decision-making. Summary of the Invention

[0007] This application provides a method for evaluating the effect of nitrogen injection to enhance coal seam gas extraction, which solves the problem in the prior art that the effect of nitrogen injection displacement cannot be objectively and quantitatively evaluated.

[0008] To achieve the above objectives, the technical solution of this invention is as follows:

[0009] In a first aspect, embodiments of the present invention provide a method for evaluating the effect of nitrogen injection to enhance coal seam gas extraction, including: conducting a coal body nitrogen injection displacement experiment using coal samples from the target displacement point, simulating in-situ pressure conditions of the coal seam, adsorbing gas to equilibrium and then injecting nitrogen, and recording coal body strain and flow data during the displacement process.

[0010] The standard displacement efficiency is calculated based on the gas content of the coal body before and after displacement, displacement time, and coal sample volume.

[0011] By collecting data on gas flow rate and extraction volume in the extraction pipeline before and after nitrogen injection displacement, and combining this with the nitrogen injection displacement range, the actual displacement efficiency is calculated.

[0012] During the extraction process, extraction parameters are collected in real time and the actual displacement efficiency is calculated. The difference between the actual displacement efficiency and the standard displacement efficiency is compared to evaluate the displacement effect.

[0013] A deep learning model based on the combination of convolutional neural network (CNN) and long short-term memory network (LSTM) is constructed. The preprocessed extraction parameters and coal seam condition data are input to obtain the displacement effect evaluation value.

[0014] Based on the comparison results between the evaluation value and the preset threshold, the nitrogen injection parameters and extraction process are dynamically adjusted.

[0015] In some possible implementations, the standard displacement efficiency is calculated as follows:

[0016] ;

[0017] in, For standard displacement efficiency. To reduce the gas content of the coal seam before displacement, The gas content of the coal seam after displacement, To replace time, This represents the volume of the coal sample.

[0018] In some possible implementations, the method for determining the nitrogen injection displacement range is as follows:

[0019] Multiple monitoring boreholes are drilled at set intervals on one side of the injection borehole. By monitoring the back pressure changes of each borehole during nitrogen injection, the displacement radius is determined, and the nitrogen injection displacement range is calculated based on the displacement radius.

[0020] In some possible implementations, the nitrogen displacement range is expressed as:

[0021] ;

[0022] in, This refers to the nitrogen injection displacement range. For the displacement radius, For the length of the injection borehole, This is the length of the sealing hole. This refers to the thickness of the coal seam.

[0023] In some possible implementations, the actual displacement efficiency is calculated using the following formula:

[0024] ;

[0025] in, For actual displacement efficiency, To determine the pure gas extraction volume after displacement, The amount of gas extracted before replacement.

[0026] In some possible implementations, a convolutional neural network is used to extract spatial features of the sampling parameters, and a long short-term memory network is used to capture time-series dependencies.

[0027] The inputs to the deep learning model include, but are not limited to, gas extraction volume, pipeline flow rate, nitrogen injection pressure and flow rate, and coal seam pore pressure.

[0028] The formula for calculating the displacement effect evaluation value is as follows:

[0029] ;

[0030] in, As the evaluation value, To improve real-time displacement efficiency. For ideal gas extraction efficiency.

[0031] In some possible implementations, after obtaining the displacement effect evaluation value, the method further includes: performing closed-loop optimization control based on the evaluation value, including:

[0032] If the evaluation value is lower than the set threshold, at least one parameter among nitrogen injection pressure, flow rate, or extraction time should be adjusted, and the displacement effect should be re-monitored until the evaluation criteria are met.

[0033] Secondly, the present invention provides a coal seam gas nitrogen injection flow enhancement extraction effect evaluation system, including: a nitrogen injection displacement experiment module, used to conduct a coal body nitrogen injection displacement experiment using coal samples at the target displacement point, by simulating the in-situ pressure conditions of the coal seam, adsorbing gas to equilibrium and then injecting nitrogen, and recording the coal body strain and flow data during the displacement process.

[0034] The standard displacement efficiency calculation module is used to calculate the standard displacement efficiency based on the gas content of the coal body before and after displacement, displacement time, and coal sample volume.

[0035] The actual displacement efficiency calculation module is used to calculate the actual displacement efficiency by collecting data on the gas flow rate and extraction volume of the extraction pipeline before and after nitrogen injection displacement, combined with the nitrogen injection displacement range.

[0036] The displacement effect evaluation module is used to collect extraction parameters in real time during the extraction process and calculate the actual displacement efficiency, compare the difference between the actual displacement efficiency and the standard displacement efficiency, and evaluate the displacement effect.

[0037] The deep learning model evaluation module is used to construct a deep learning model based on the combination of convolutional neural network (CNN) and long short-term memory network (LSTM). It takes preprocessed extraction parameters and coal seam condition data as input to obtain the displacement effect evaluation value.

[0038] The data optimization module is used to dynamically adjust nitrogen injection parameters and extraction process based on the comparison results between the evaluation value and the preset threshold.

[0039] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0040] In this embodiment of the invention, a method combining standard displacement efficiency experimental measurement with actual displacement efficiency dynamic calculation is used to achieve accurate quantitative evaluation of nitrogen injection displacement effect, effectively solving the problem that existing technologies cannot objectively evaluate and dynamically optimize nitrogen injection flow enhancement effect; by using methods for determining the displacement range for different mine geological conditions and a multi-parameter real-time monitoring mechanism, the environmental adaptability of the evaluation system is significantly improved; combined with a closed-loop optimization strategy built using a deep learning model, nitrogen injection parameters can be automatically adjusted and extraction trends can be predicted based on real-time data, improving gas extraction efficiency and reducing nitrogen injection operation costs while ensuring safe mine production, providing efficient and reliable technical support for comprehensive coal mine gas management. Attached Figure Description

[0041] To more clearly illustrate the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 A schematic flowchart of an embodiment of a method for evaluating the effect of enhanced coal seam gas extraction by nitrogen injection to increase flow is provided for the implementation of this invention.

[0043] Figure 2 This is a schematic diagram of the structure of a coal seam gas nitrogen injection flow enhancement and extraction effect evaluation system according to an embodiment of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0045] In the relevant descriptions of this embodiment, the terms "including," "containing," and "possessing" are all open terms and are generally understood to include but not be limited to; the term "at least one" is generally understood to mean one or more, where "multiple" refers to two or more; the term "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items, for example, "at least one of a, b, or c", or "at least one of a, b, and c", which can all mean: a, b, c, ab (i.e., a and b), ac, bc, or abc, where a, b, and c can be single or multiple; the symbol "A / B" is used to describe the selection relationship of associated objects, generally indicating an "or" relationship.

[0046] In the following description of the embodiments, the terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms "a" and "the" as used in the embodiments of this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0047] Those skilled in the art should understand that, in the following description of the embodiments of this application, the sequence of numbers does not imply the order of execution. Some or all steps may be executed in parallel or sequentially. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0048] Those skilled in the art will understand that the numerical ranges in the embodiments of this application should be understood to specifically disclose each intermediate value between the upper and lower limits of the range. Any stated value or intermediate value within a stated range, as well as any other stated value or each smaller range between intermediate values ​​within a range, are also included within this invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0049] Unless otherwise stated, the technical / scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. While this application describes only preferred methods and materials, any methods and materials similar or equivalent to those described herein may be used in the implementation or testing of this application. All references to this specification are incorporated by way of citation to disclose and describe the methods and / or materials associated with those references. In the event of any conflict with any incorporated reference, the content of this specification shall prevail.

[0050] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0051] In the field of coal mine gas drainage, to address the problem of low gas drainage efficiency caused by the low permeability of coal seams, existing technologies employ various permeability-enhancing and flow-increasing measures, such as mining protective layers, hydraulic fracturing / fracture cutting, loosening blasting, large-diameter boreholes, and dense borehole drilling. However, these technologies have many problems, such as the difficulty in implementing mining protective layers for single coal seams; the large water consumption and water-locking effect of hydraulic permeability enhancement; the potential for secondary hazards from blasting permeability enhancement; and the high construction cost of dense boreholes. Furthermore, with increasing mining depth, the pressure on gas disaster prevention and control increases, and traditional borehole pre-drainage technologies are time-consuming and exhibit rapid gas flow decay, failing to meet the needs of mining succession and safe production.

[0052] In recent years, gas injection displacement technology has gradually attracted attention due to its high efficiency. Nitrogen (N2) has advantages such as wide availability, mature nitrogen production processes, low outburst risk, and no pollution, making it suitable for downhole gas injection displacement of coal seam gas. However, in practical applications, it still faces several problems, including:

[0053] Lack of effect evaluation: Existing technologies lack a scientific and unified evaluation standard for the effect of nitrogen injection displacement, making it impossible to quantify the actual improvement effect of gas extraction during nitrogen injection. This results in nitrogen injection parameters (such as pressure and flow rate) being set based on experience, making it difficult to achieve precise control.

[0054] Insufficient dynamic adaptability: Coal seam geological conditions (such as pore pressure and fracture distribution) and gas occurrence state have significant spatiotemporal differences. Existing methods cannot monitor the displacement effect in real time and it is difficult to optimize nitrogen injection strategies in a timely manner, resulting in a decrease in extraction efficiency as mining progresses.

[0055] Low level of intelligence: Traditional assessment methods rely on manual data collection and static analysis, which limits the accuracy of assessment and the efficiency of decision-making.

[0056] Based on this, embodiments of the present invention provide a method for evaluating the effect of nitrogen injection to enhance coal seam gas extraction, which solves the problem that the effect of nitrogen injection displacement cannot be objectively and quantitatively evaluated in the prior art.

[0057] Figure 1A schematic flowchart illustrating an embodiment of the method for evaluating the effect of enhanced coal seam gas extraction through nitrogen injection is provided for implementation of this invention. (See attached diagram.) Figure 1 As shown, the above method may include:

[0058] S101, using coal samples from the target displacement point to conduct a nitrogen injection displacement experiment on the coal body. By simulating the in-situ pressure conditions of the coal seam, nitrogen is injected after adsorbing gas to equilibrium, and the coal body strain and flow rate data are recorded during the displacement process.

[0059] Specifically, raw coal samples are collected from the target displacement point and processed into experimental coal samples according to a preset size (e.g., 50×100mm), ensuring that the coal samples are free of obvious cracks. The coal samples are then dried, and basic parameters such as initial density and porosity are recorded. Multiple sets of coal samples can be collected from different locations in the target coal seam (roof, floor, and middle) to avoid the influence of local heterogeneity on the results.

[0060] Then, the prepared coal sample is placed into the displacement reactor. The sealed coal sample is subjected to axial pressure and confining pressure step by step until the in-situ pressure of the coal seam is reached (for example, using a hydraulic servo system, the axial pressure is 10~20MPa and the confining pressure is 5~15MPa, and the specific values ​​are set according to the burial depth and geological conditions of the target coal seam). Helium (He) is introduced to the set pressure (e.g., 2MPa), and after standing for a period of time, the airtightness of the reactor is tested. The leakage rate can be monitored by a pressure gauge (for example, ≤0.1% is considered to be qualified for airtightness).

[0061] Afterwards, the coal sample is degassed using a vacuum pump for a period of time, the specific time of which can be determined based on actual needs. Referring to the coal seam gas pressure, the adsorption of methane gas is balanced according to the coal seam gas pressure. The strain gauge is turned on to collect the coal body strain during this process. When the pressure gauge reading / strain curve stabilizes simultaneously, it indicates that adsorption has reached equilibrium. The exhaust valve is opened to allow the adsorption-balanced coal sample to desorb under normal pressure. The strain gauge is turned on again to collect the coal body strain during this process. When the flow meter reading is 0, it is determined that the natural desorption of the coal body has reached equilibrium, and the displacement experiment can then be carried out. Nitrogen (N2) is injected into the reactor at a constant rate (e.g., 0.05 MPa / min), with a nitrogen injection pressure range of 0~0.5 MPa. The strain gauge and high-precision flow meter (accuracy ±0.5%FS) are simultaneously turned on to record parameters such as the axial / radial strain of the coal body, nitrogen injection pressure, and tail-end gas flow rate in real time. When the tail-end flow meter reading fluctuates less than the preset value and continues for a set time, the displacement process is determined to be stable, and the experiment is terminated. All time-series data (such as pressure, strain, and flow rate) during the experiment are summarized, and outliers caused by equipment noise or transient interference are removed to generate a complete dataset of the displacement process, which is used for subsequent standard displacement efficiency calculation and model training.

[0062] S102, the standard displacement efficiency is calculated based on the gas content of the coal body before and after displacement, displacement time and coal sample volume.

[0063] In some embodiments, the formula for calculating the standard displacement efficiency can be expressed as:

[0064] ;

[0065] in, For standard displacement efficiency. To reduce the gas content of the coal seam before displacement, The gas content of the coal seam after displacement, To replace time, This represents the volume of the coal sample.

[0066] S103, by collecting data on gas flow rate and extraction volume in the extraction pipeline before and after nitrogen injection displacement, and combining the nitrogen injection displacement range, the actual displacement efficiency is calculated.

[0067] Specifically, before starting the nitrogen injection displacement operation, high-precision turbine flow meters and gas concentration sensors can be used to simultaneously measure the gas flow rate and extraction volume (unit: m³, i.e., gas volume concentration × total extraction volume) in the extraction pipeline. Data is collected continuously for a period of time, and after eliminating abnormal fluctuations (such as equipment failure or short-term pressure fluctuations), the average value is taken as the baseline value. During nitrogen injection, real-time flow rate and volume data in the extraction pipeline can be recorded at fixed time intervals, such as once every 10 minutes, continuing until 24 hours after the nitrogen injection is completed, to ensure a stable stage of coverage and displacement effect.

[0068] Within the same coal seam plane as the nitrogen injection boreholes, a test borehole is drilled every 5 meters along the injection diffusion direction. After the borehole pressure is released, nitrogen is injected into the main borehole, and the back pressure change of each test borehole is monitored by pressure sensors. When the back pressure value of a certain test borehole exceeds a preset threshold of the initial pressure value (for example, exceeding 10%, i.e., rising from 0.1 MPa to 0.11 MPa), it is determined that the nitrogen displacement front has reached the location of that borehole; the distance between the last borehole with a back pressure change and the main borehole is the displacement radius.

[0069] In some embodiments, the nitrogen displacement range can be expressed as:

[0070] ;

[0071] in, This refers to the nitrogen injection displacement range. For the displacement radius, For the length of the injection borehole, This is the length of the sealing hole. This refers to the thickness of the coal seam.

[0072] In some embodiments, the formula for calculating the actual displacement efficiency can be expressed as:

[0073] ;

[0074] in, For actual displacement efficiency, To determine the pure gas extraction volume after displacement, The amount of gas extracted before replacement.

[0075] S104. During the extraction process, extraction parameters are collected in real time and the actual displacement efficiency is calculated. The difference between the actual displacement efficiency and the standard displacement efficiency is compared to evaluate the displacement effect.

[0076] Specifically, a series of high-precision monitoring devices and sensors can be used to continuously collect various key parameters during the extraction process. These include, but are not limited to, parameters such as the extraction volume and the flow rate in the negative pressure extraction pipeline.

[0077] Based on the collected sampling parameters, the real-time actual displacement efficiency is calculated using the aforementioned formula. This value will serve as one of the key indicators for evaluating the displacement effect, visually demonstrating the effectiveness of the actual displacement work. Comparing the real-time displacement efficiency with the standard displacement efficiency is a crucial step in assessing whether the displacement effect has met the target. The standard displacement efficiency represents the level of displacement effect that should be achieved under ideal conditions. By comparing the real-time displacement efficiency with the standard displacement efficiency, it is possible to clearly understand whether the current progress of the displacement work is better than, meets, or lags behind the expected standard.

[0078] S105, Construct a deep learning model based on the combination of convolutional neural network (CNN) and long short-term memory network (LSTM), input preprocessed extraction parameters and coal seam condition data, and obtain the displacement effect evaluation value.

[0079] Specifically, during the continuous collection of extraction parameters, in addition to the aforementioned conventional parameters, monitoring parameters are further expanded, such as adding real-time fluctuations in coal seam pore pressure, nitrogen injection flow rate and pressure, and borehole size and fracture range for hydraulic fracturing. All collected data are standardized and normalized to ensure that different parameters have the same dimensions and order of magnitude, facilitating processing by deep learning models. For example, for gas concentration, if the original range is [C... min C max If ], then normalize it to the interval [0, 1], and the same applies to other parameters.

[0080] The model is constructed using an architecture that combines convolutional neural networks (CNNs) and long short-term memory (LSTMs). The CNN part automatically extracts local features from the data, such as spatial features like gas concentration change trends and pressure fluctuation patterns; the LSTM part learns the dependencies of the data over time. The combination of the two better captures the complex spatiotemporal features of the gas extraction process.

[0081] The number of nodes in the input layer is determined based on the number of collected parameters. Multiple convolutional layers are set, such as three convolutional layers, with kernel sizes of 3x1, 5x1, and 7x1 (where 1 represents the stride in the time series direction). The number of kernels can be 16, 32, and 64, respectively. ReLU can be used as the activation function. Each convolutional layer is followed by a max pooling layer with a kernel size of 2x1 and a stride of 2x1 to reduce the data dimensionality. The feature map output from the CNN layer is flattened and connected to an LSTM layer with 128 hidden units. The output of the LSTM layer is connected to a fully connected layer with 64 nodes, and the ReLU activation function is used to further integrate the features. The output layer has one node used to predict the evaluation value of the displacement effect, and the predicted value range can be set in [0, +∞).

[0082] In some embodiments, the formula for calculating the displacement effect evaluation value is expressed as follows:

[0083] ;

[0084] in, As the evaluation value, To improve real-time displacement efficiency. For ideal gas extraction efficiency.

[0085] The preprocessed dataset is divided into training, validation, and test sets according to a certain ratio, for example, 70%:20%:10%. The Adam adaptive moment estimation algorithm is used for optimization, with an initial learning rate of 0.001. As the number of training epochs increases, the learning rate is automatically adjusted based on the validation set loss. Mini-batch gradient descent (batch size can be 32) is used for model training. After each training epoch, the loss value and evaluation metrics (such as mean absolute error, root mean square error, etc.) are calculated on the validation set. Hyperparameters (such as the number of convolutional kernels, the number of hidden units, the learning rate, etc.) are adjusted based on the validation set performance. Training is stopped early when the validation set loss no longer decreases for several consecutive epochs (e.g., 5 epochs) to prevent overfitting and ensure the model has good generalization ability.

[0086] In actual gas drainage, newly collected data, after preprocessing, is input into a trained deep learning model at fixed time steps (e.g., every 10 minutes). The model predicts the displacement effect in real time. The predicted displacement effect is compared with the ideal displacement effect. If the value is greater than or equal to a threshold, the current displacement effect is good, and the existing nitrogen injection parameters and drainage process are maintained. If the value is less than the threshold, the system automatically triggers an optimization strategy. The optimization strategy, based on the model's analysis of the importance of each parameter (by calculating the gradient or feature importance score corresponding to each parameter in the model), adjusts key parameters such as nitrogen injection pressure, flow rate, and drainage time. Then, monitoring and evaluation continue, forming a closed-loop control to continuously optimize the gas drainage effect. Simultaneously, the model can also predict the displacement effect trend over a future period based on historical and real-time data, providing a reference for adjusting the gas drainage plan in advance, further improving the efficiency and safety of gas drainage.

[0087] As gas extraction continues, coal seam conditions and gas occurrence may change. New data should be collected periodically (e.g., monthly or quarterly) and added to the training set to retrain the model, enabling it to adapt to new operating conditions and maintain predictive accuracy.

[0088] In some embodiments, a model performance monitoring system can be further established to monitor in real time the prediction error, stability, and other indicators of the model in practical applications. If a decline in model performance or abnormal prediction results are found, fault diagnosis should be performed in a timely manner to check whether the data acquisition equipment is normal, whether the model is overfitting or underfitting, and corresponding measures should be taken, such as re-acquiring data, adjusting the model structure or hyperparameters, to ensure that the model is always in good working condition and to ensure the smooth progress of gas extraction effect evaluation and optimization.

[0089] S106. Based on the comparison results between the evaluation value and the preset threshold, the nitrogen injection parameters and extraction process are dynamically adjusted.

[0090] For example, nitrogen injection parameters, nitrogen injection flow rate, and / or nitrogen injection duration can be adjusted based on comparison results.

[0091] Understandably, the nitrogen injection pressure directly affects the permeability of nitrogen in displacing methane. Appropriately increasing the pressure can enhance the displacement force and expand the methane desorption range; however, excessively high pressure may lead to the expansion of coal seam fractures or induce safety hazards. Therefore, a dynamic balance is required. The nitrogen injection flow rate must be matched with the coal seam permeability. Excessively high flow rates may cause localized nitrogen accumulation, reducing displacement efficiency; excessively low flow rates will not effectively displace methane, requiring dynamic adjustment based on real-time permeability. Furthermore, the duration of a single nitrogen injection determines the continuity of the displacement coverage area. Extending the injection time can enhance the displacement effect, but resource waste must be avoided; shortening the duration may adapt to rapidly changing coal seam conditions.

[0092] For the extraction process parameters, the extraction negative pressure, extraction interval time and / or single extraction duration can be dynamically adjusted based on the comparison results.

[0093] Understandably, the intensity of the negative pressure during gas extraction directly determines the efficiency of gas extraction. Increasing the negative pressure accelerates gas desorption, but excessively high negative pressure may lead to pipeline blockage or equipment overload; decreasing the negative pressure prolongs the extraction cycle, requiring dynamic adjustment based on the gas release rate. The extraction interval affects the continuity of the extraction operation. Shortening the interval improves extraction efficiency but increases energy consumption; extending the interval may reduce extraction effectiveness, requiring optimization based on gas concentration trends. The duration of a single extraction session must match the gas release rate. Extending the duration increases the extraction volume per session but may lead to equipment fatigue; shortening the duration requires frequent start-ups and shutdowns, necessitating a balance between efficiency and equipment lifespan.

[0094] Furthermore, by coordinating the adjustment of nitrogen injection pressure and flow rate, it is possible to ensure that nitrogen effectively displaces gas while avoiding resource waste. Dynamically limiting the upper limit of nitrogen injection pressure (e.g., 80% of the critical fracturing pressure) and the range of negative pressure during extraction prevents coal seam damage or gas outbursts. Adjusting the nitrogen injection duration and extraction interval in real time based on evaluation values ​​reduces nitrogen consumption and energy consumption while ensuring effectiveness.

[0095] In summary, by dynamically adjusting the above parameters, the system can accurately respond to changes in coal seam conditions, balance displacement efficiency, resource consumption, and safety risks, and achieve full-process optimization of nitrogen injection to enhance gas extraction.

[0096] In this invention, different mines exhibit significant differences in geological structure, coal seam characteristics, and gas occurrence. This invention, through a method for determining the displacement range specific to each mine and by comprehensively considering various practically collectable extraction parameters for calculation and evaluation, can fully adapt to the unique circumstances of each mine. For example, for mines with complex geological structures, the displacement range can be accurately determined based on the actual borehole layout and gas distribution; for coal seams with high or low gas content, by collecting and analyzing relevant parameters in real time, the evaluation strategy can be adjusted to ensure that the evaluation results accurately reflect the true effect of nitrogen injection displacement in the mine, providing strong support for developing personalized gas control solutions.

[0097] Furthermore, due to the long mining cycle of coal mines, gas conditions change continuously over time. This invention, through its ability to continuously collect extraction parameters, monitors and evaluates the nitrogen injection displacement effect uninterruptedly throughout the entire mining process. Whether it's short-term fluctuations in gas flow or long-term changes in coal seam permeability, these factors can be promptly reflected by calculating real-time displacement efficiency and comparing it with standard displacement efficiency. This not only helps to promptly identify trends in nitrogen injection displacement effects, such as taking timely reinforcement measures when the effect weakens, but also provides data for predicting future gas disaster risks, ensuring safe production in mines during long-term mining operations, while optimizing gas extraction resource allocation and avoiding unnecessary nitrogen injection operations and resource waste.

[0098] Based on the same inventive concept, this application also provides a coal seam gas nitrogen injection enhancement extraction effect evaluation system. Figure 2 This is a schematic diagram of a coal seam gas nitrogen injection enhancement and extraction effect evaluation system according to an embodiment of the present invention. See also... Figure 2 As shown, the coal seam gas nitrogen injection enhancement extraction effect evaluation system 200 may include:

[0099] Nitrogen injection displacement experiment module 201 is used to conduct a nitrogen injection displacement experiment on coal body using coal samples at the target displacement point. By simulating the in-situ pressure conditions of the coal seam, nitrogen is injected after adsorbing gas to equilibrium, and the coal body strain and flow rate data are recorded during the displacement process.

[0100] The standard displacement efficiency calculation module 202 is used to calculate the standard displacement efficiency based on the gas content of the coal body before and after displacement, displacement time, and coal sample volume.

[0101] The actual displacement efficiency calculation module 203 is used to calculate the actual displacement efficiency by collecting data on the gas flow rate and extraction volume of the extraction pipeline before and after nitrogen injection displacement, combined with the nitrogen injection displacement range.

[0102] The displacement effect evaluation module 204 is used to collect extraction parameters in real time during the extraction process and calculate the actual displacement efficiency, compare the difference between the actual displacement efficiency and the standard displacement efficiency, and evaluate the displacement effect.

[0103] The deep learning model evaluation module 205 is used to construct a deep learning model based on the combination of convolutional neural network and long short-term memory network. It takes preprocessed extraction parameters and coal seam condition data as input and obtains the displacement effect evaluation value.

[0104] The data optimization module 206 is used to dynamically adjust nitrogen injection parameters and extraction process based on the comparison results between the evaluation value and the preset threshold.

[0105] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, please refer to each other. Each embodiment focuses on describing the differences from other embodiments.

[0106] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of this application.

Claims

1. A coal seam gas nitrogen injection flow enhancement enhanced extraction effect evaluation method, characterized in that, The method comprises the following steps: A coal sample at a target displacement point is used to perform a coal body nitrogen injection displacement experiment, nitrogen is injected after gas adsorption to equilibrium under simulated in-situ pressure conditions of a coal seam, and coal body strain and flow data during displacement are recorded; A standard displacement efficiency is calculated according to gas content of the coal body before and after displacement, displacement time and volume of the coal sample; Actual displacement efficiency is calculated by collecting gas flow rate and extraction volume data of an extraction pipeline before and after nitrogen injection displacement, in combination with a nitrogen injection displacement range; During the extraction process, extraction parameters are collected in real time and the actual displacement efficiency is calculated, and differences between the actual displacement efficiency and the standard displacement efficiency are compared to evaluate displacement effect; A deep learning model based on a convolutional neural network combined with a long short-term memory network is constructed, preprocessed extraction parameters and coal seam condition data are input, and a displacement effect evaluation value is obtained; According to a comparison result of the evaluation value and a preset threshold value, nitrogen injection parameters and extraction technology are dynamically adjusted.

2. The method of claim 1, wherein, The calculation formula of the standard displacement efficiency is: ； wherein, is the standard displacement efficiency, is the coal gas content before displacement, is the coal gas content after displacement, is the displacement time, is the volume of the coal sample.

3. The method of claim 2, wherein, The determination method of the nitrogen injection displacement range is: A plurality of monitoring boreholes are arranged at intervals on one side of the injection borehole, displacement radius is determined by monitoring back pressure changes of the boreholes during nitrogen injection, and the nitrogen injection displacement range is calculated based on the displacement radius.

4. The method of claim 3, wherein, The nitrogen injection displacement range is represented as: ； wherein, is the nitrogen injection displacement range, is the displacement radius, is the injection bore length, is the seal length, is the coal seam thickness.

5. The method of claim 4, wherein, The calculation formula of the actual displacement efficiency is: ； wherein, is the actual displacement efficiency, is the post-displacement gas extraction rate, is the pre-displacement gas extraction rate.

6. The method of claim 5, wherein, The convolutional neural network is used to extract spatial features of the extraction parameters, and the long short-term memory network is used to capture time series dependency relationships; Input of the deep learning model includes but is not limited to gas extraction volume, pipeline flow rate, nitrogen injection pressure and flow rate, and coal seam pore pressure; The calculation formula of the displacement effect evaluation value is: ； wherein, is the evaluation value, is the real-time displacement efficiency, is the ideal gas extraction efficiency.

7. The method of claim 6, wherein, After the displacement effect evaluation value is obtained, the method further comprises closed-loop optimization control based on the evaluation value, including: If the evaluation value is lower than a set threshold value, at least one of nitrogen injection pressure, flow rate or extraction time is adjusted, and displacement effect is monitored again until an evaluation standard is met.

8. A coal seam gas nitrogen injection flow enhancement enhanced extraction effect evaluation system for implementing the method of any one of claims 1 to 7, characterized in that, The method comprises the following steps: A nitrogen injection displacement experiment module is used to perform a coal body nitrogen injection displacement experiment by using a coal sample at a target displacement point, nitrogen is injected after gas adsorption to equilibrium under simulated in-situ pressure conditions of a coal seam, and coal body strain and flow data during displacement are recorded; A standard displacement efficiency calculation module is used to calculate a standard displacement efficiency according to gas content of the coal body before and after displacement, displacement time and volume of the coal sample; An actual displacement efficiency calculation module is used to calculate actual displacement efficiency by collecting gas flow rate and extraction volume data of an extraction pipeline before and after nitrogen injection displacement, in combination with a nitrogen injection displacement range; A displacement effect evaluation module is used to collect extraction parameters in real time during the extraction process, calculate the actual displacement efficiency, compare differences between the actual displacement efficiency and the standard displacement efficiency, and evaluate displacement effect; A deep learning model evaluation module is used to construct a deep learning model based on a convolutional neural network combined with a long short-term memory network, input preprocessed extraction parameters and coal seam condition data, and obtain a displacement effect evaluation value; A data optimization module is used to dynamically adjust nitrogen injection parameters and extraction technology according to a comparison result of the evaluation value and a preset threshold value.

Images