Method for evaluating full-life-cycle efficiency of high-negative-pressure gas extraction drill hole

Abstract

The invention provides a high-negative-pressure gas extraction drill hole full-life-cycle efficiency evaluation method, and belongs to the technical field of mineral exploitation. A ground stress distribution model is established through microseism monitoring to determine drill hole arrangement parameters; a distributed optical fiber sensing system and a multi-parameter gas flow meter are used for monitoring the stress change around a drill hole and gas extraction data in real time, the coal fracture development degree is obtained in combination with sound wave testing, and all the data are input into a physical numerical value coupling model to calculate a permeability dynamic evolution curve. Establishing a permeability influence coefficient matrix and determining a key parameter weight, constructing an evaluation index system including the extraction amount, the permeability change rate, the drilling life and the coverage range, and performing multi-objective optimization configuration by applying a Pareto optimal solution theory. The technical problem that full-life-cycle dynamic monitoring and comprehensive efficiency evaluation of the high-negative-pressure gas extraction drill hole are lacked at present is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of mineral mining, and specifically relates to a method for evaluating the full life cycle efficiency of a high-negative-pressure gas extraction drilling hole. Background Art

[0002] Coal mine gas hazards are a major safety hazard in coal mining. High-vacuum gas extraction technology is a key measure for preventing and controlling gas hazards. Traditional gas extraction techniques rely primarily on empirically determined drilling parameters and evaluate extraction effectiveness using fixed extraction systems and simple monitoring devices. These techniques typically use single-point measurements to obtain gas flow and concentration data, lacking the ability to continuously monitor changes in coal permeability around the borehole.

[0003] However, traditional gas extraction technology has many shortcomings in practical applications. For example, the drilling arrangement lacks a scientific basis and is difficult to adapt to complex geological conditions; the extraction parameter setting lacks a dynamic adjustment mechanism, resulting in low extraction efficiency; the monitoring method is single and has limited accuracy, which cannot reflect the dynamic changes in the permeability of the coal body around the borehole in real time; the evaluation index system is imperfect, making it difficult to accurately evaluate the performance of the borehole throughout its life cycle.

[0004] Especially under conditions of high geostress and low-permeability coal seams, the permeability of the coal mass surrounding the borehole can vary significantly with the mining stress field. Traditional technologies lack the ability to accurately describe and predict these dynamic changes, making it impossible to evaluate and optimize the performance of borehole extraction throughout its lifecycle. This ultimately leads to low gas extraction efficiency, increased safety risks, and increased energy consumption. In other words, existing technologies lack the technical capability to dynamically monitor and comprehensively evaluate the performance of high-negative-pressure gas extraction boreholes throughout their lifecycle. Summary of the Invention

[0005] In view of this, the present invention provides a method for evaluating the full life cycle performance of high-vacuum gas extraction drilling holes, which can solve the technical problem in the existing technology of lack of dynamic monitoring and comprehensive performance evaluation of the full life cycle of high-vacuum gas extraction drilling holes.

[0006] The present invention is implemented as follows: The present invention provides a method for evaluating the full life cycle efficiency of high-negative pressure gas extraction drilling, including: conducting geological structure and stress field analysis to determine drilling parameters; installing a distributed fiber optic sensing system on the inner wall of the borehole to collect stress change data and gas pressure data; using a multi-parameter gas flowmeter to collect gas flow data to establish a dynamic extraction efficiency database; obtaining coal body fracture development degree data through an acoustic wave tester to form a fracture density distribution map; inputting the collected data into a physical numerical coupling model to calculate the dynamic evolution curve of permeability; establishing a permeability influence coefficient matrix to determine the weight values of key influencing parameters; constructing a drilling efficiency evaluation index system to form a comprehensive scoring model; applying the Pareto optimal solution theory to optimize the configuration of the borehole; and triggering an alarm when the extraction efficiency drops by more than a preset threshold of 25%.

[0007] Among them, the step of conducting geological structure and stress field analysis to determine drilling parameters is specifically to conduct geological structure and stress field analysis before arranging coal seam drilling, use microseismic monitoring instruments to establish a three-dimensional ground stress distribution model, and determine the drilling spacing parameters and drilling angle parameters based on the coal seam thickness and gas content distribution.

[0008] Among them, the step of installing a distributed fiber optic sensing system on the inner wall of the borehole to collect stress change data and gas pressure data is specifically to install the distributed fiber optic sensing system on the inner wall of the borehole, set a measuring point every 10 meters along the axis of the borehole, collect stress change data and gas pressure data around the borehole, and form a full life cycle monitoring network.

[0009] Among them, the step of using a multi-parameter gas flowmeter to collect gas flow data to establish a dynamic extraction efficiency database is specifically to use a multi-parameter gas flowmeter to collect gas flow data, gas concentration data, temperature data, and pressure data in real time at the borehole outlet. The data collection frequency is once every 5 minutes to establish a dynamic extraction efficiency database.

[0010] Among them, the step of obtaining coal body fracture development degree data and forming a fracture density distribution map through an ultrasonic tester is specifically to perform an ultrasonic scan on the coal body around the borehole once every 24 hours through the ultrasonic tester to obtain coal body fracture development degree data and stress change data to form a fracture density distribution map.

[0011] Among them, the step of inputting the collected data into the physical numerical coupling model to calculate the dynamic evolution curve of permeability is specifically to input the collected stress change data, acoustic wave test result data and microseismic monitoring data into the physical numerical coupling model, and calculate the dynamic permeability evolution curve around the borehole through the permeability dynamic evolution equation, and the permeability dynamic evolution equation comprehensively considers stress sensitivity, crack evolution and gas desorption; the physical numerical coupling model specifically integrates the coal seam gas occurrence theory and the coal rock solid-liquid-gas three-phase coupling mathematical model, combines the microscopic seepage mechanism with the macroscopic gas migration law, and establishes a stress field evolution and permeability dynamic change relationship model through the finite element analysis method; the permeability dynamic evolution equation is specifically a mathematical expression that describes the change of coal seam permeability with mining stress, which is used to accurately describe the spatiotemporal evolution law of permeability of coal seams during mining. The input includes effective stress data, coal body strain data, temperature change data, gas pressure data and initial condition data, and the output is the coal seam permeability value at any time and spatial position.

[0012] Among them, the step of establishing a permeability influence coefficient matrix to determine the weight values of key influencing parameters is specifically based on the relationship between the permeability change data around the borehole and the gas extraction volume, establishing a permeability influence coefficient matrix, and determining the weight values of key influencing parameters through multivariate regression analysis; the permeability influence coefficient matrix is specifically a mathematical expression that characterizes the degree of influence of mining stress changes, the degree of development of coal body cracks, gas pressure gradient and temperature field changes on coal seam permeability, and dimensional normalization is used to make the influence degree values of each factor comparable.

[0013] Among them, the step of constructing a drilling efficiency evaluation index system to form a comprehensive scoring model is specifically to construct a drilling efficiency evaluation index system, including a unit time extraction volume index, a permeability change rate index, a drilling life prediction index and a coverage range index, to form a comprehensive scoring model.

[0014] Among them, the step of applying the Pareto optimal solution theory to optimize the configuration of drilling holes is specifically to construct a multi-objective optimization model based on the drilling efficiency evaluation index system, and apply the Pareto optimal solution theory to optimize the configuration of drilling holes. When the comprehensive score is lower than 75 points, the Pareto frontier of maximizing gas extraction efficiency and minimizing extraction energy consumption is solved, and the optimal drilling parameter combination is selected from it.

[0015] This also includes establishing a digital twin platform for the entire life cycle of drilling, realizing real-time visualization and early warning of extraction efficiency, and automatically generating optimization recommendation reports.

[0016] The present invention realizes real-time and high-precision monitoring of the coal permeability and stress field around the borehole by constructing a multidimensional monitoring network that combines distributed optical fiber sensing with microseismic monitoring. Based on the physical-numerical coupling model, a dynamic evolution equation of permeability is established to accurately describe the spatiotemporal evolution law of coal seam permeability as mining stress changes.

[0017] This innovative approach divides the entire borehole lifecycle into four stages: planning and layout, construction implementation, operational monitoring, and optimization and control, for unified management. By establishing a comprehensive evaluation index system and a multi-objective optimization model, it achieves precise assessment and intelligent optimization of borehole drainage efficiency. In particular, the application of a digital twin platform enables visualization of borehole status and early warning prediction, providing a scientific basis for the dynamic adjustment of drainage parameters. This solves the technical challenges of dynamic monitoring and comprehensive efficiency evaluation throughout the lifecycle of high-negative-pressure gas drainage boreholes, enabling a shift from empirical decision-making to data-driven, precise decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of the method of the present invention.

[0019] Figure 2 This is a schematic diagram of the overall structure of the high-negative-pressure gas extraction system in Example 2.

[0020] Figure 3 This is a schematic diagram of the structure of the distributed optical fiber sensing system in Example 2.

[0021] Figure 4 This is a schematic diagram of the structure of the multi-parameter gas flowmeter in Example 2.

[0022] Figure 5 Schematic diagram of the digital twin platform structure for the entire drilling life cycle in Example 2. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0024] like Figure 1 FIG. 1 is a flow chart of a method for evaluating the full life cycle efficiency of a high-vacuum gas extraction drilling borehole provided by the present invention. The method includes the following steps:

[0025] S01. Before arranging coal seam drilling holes, conduct geological structure and stress field analysis, use microseismic monitoring instruments to establish a three-dimensional ground stress distribution model, and determine drilling hole spacing and drilling angle parameters based on coal seam thickness and gas content distribution;

[0026] S02. Install a distributed fiber optic sensing system on the inner wall of the borehole, set a measuring point every 10 meters along the borehole axis, collect stress change data and gas pressure data around the borehole, and form a full life cycle monitoring network;

[0027] S03. Use a multi-parameter gas flowmeter to collect real-time gas flow data, gas concentration data, temperature data, and pressure data at the borehole outlet at a frequency of once every 5 minutes to establish a dynamic extraction efficiency database;

[0028] S04. Perform an acoustic wave scan of the coal body around the borehole every 24 hours using an acoustic wave tester to obtain data on the development degree of coal body cracks and stress changes, and form a crack density distribution map;

[0029] S05. Inputting the collected stress change data, acoustic wave test result data, and microseismic monitoring data into a physical numerical coupling model, and calculating a dynamic permeability evolution curve around the borehole using a permeability dynamic evolution equation, wherein the permeability dynamic evolution equation comprehensively considers stress sensitivity, fracture evolution, and gas desorption;

[0030] S06. Based on the relationship between the permeability change data around the borehole and the gas extraction volume, a permeability influence coefficient matrix is established, and the weight values of key influencing parameters are determined through multivariate regression analysis;

[0031] S07. Construct a drilling efficiency evaluation index system, including the extraction volume per unit time index, the permeability change rate index, the drilling life prediction index, and the coverage index, to form a comprehensive scoring model;

[0032] S08. Build a multi-objective optimization model based on the drilling efficiency evaluation index system and apply the Pareto optimal solution theory to optimize the drilling configuration. When the comprehensive score is less than 75 points, find the Pareto frontier that maximizes gas extraction efficiency and minimizes extraction energy consumption, and select the optimal drilling parameter combination from it;

[0033] S09. When the extraction efficiency drops by more than the preset threshold of 25%, an alarm is activated. Optionally, a digital twin platform for the entire life cycle of the borehole is established to achieve real-time visualization and early warning of the extraction efficiency and automatically generate optimization suggestion reports.

[0034] Among them, the distributed fiber optic sensing system is a fiber optic measurement device that uses the Brillouin scattering principle to continuously monitor the stress and temperature change data of the coal seam along the borehole axis. It can achieve high-precision real-time monitoring without affecting gas extraction, with a spatial resolution of 0.1 meters, a temperature accuracy of 0.1°C, and a stress resolution of 0.01 MPa.

[0035] Among them, the physical numerical coupling model specifically integrates the coal seam gas storage theory and the coal rock solid-liquid-gas three-phase coupling mathematical model, combines the microscopic seepage mechanism with the macroscopic gas migration law, and establishes a stress field evolution and permeability dynamic change relationship model through the finite element analysis method.

[0036] The permeability dynamic evolution equation is a mathematical expression that describes how coal seam permeability changes with mining stress. The equation accurately describes the spatiotemporal evolution of coal seam permeability during mining. Inputs include effective stress data, coal strain data, temperature variation data, gas pressure data, and initial condition data. The output is the coal seam permeability value at any time and spatial position. The effective stress data is derived from measurements by a distributed fiber optic sensing system, the coal strain data from microseismic monitoring, the temperature variation data from a distributed fiber optic sensing system, the gas pressure data from a multi-parameter gas flowmeter, and the initial condition data from geological structure and stress field analysis before coal seam drilling. The coal seam permeability value is used to calculate the permeability variation rate index and input it into the drilling efficiency evaluation index system.

[0037] Among them, the permeability influence coefficient matrix is a mathematical expression that characterizes the influence of mining stress changes, coal body fracture development degree, gas pressure gradient and temperature field changes on coal seam permeability. Dimensional normalization is used to make the numerical values of the influence degree of each factor comparable.

[0038] Among them, the weight values of key influencing parameters are specifically the quantitative values of the contribution of each influencing factor to the drilling extraction efficiency determined by the principal component analysis method, including the ground stress variation coefficient of 0.35, the fracture development degree coefficient of 0.25, the gas pressure coefficient of 0.2, the negative pressure value coefficient of 0.15 and the temperature field coefficient of 0.05; the weight values of the key influencing parameters are used for the calculation of the comprehensive scoring model.

[0039] Among them, permeability enhancement measures specifically refer to engineering measures that improve the microscopic pore structure of coal seams and enhance the permeability of coal seams through hydraulic fracturing, CO2 fracturing, liquid nitrogen cryo-desorption or pulse fracturing techniques.

[0040] Among them, the digital twin platform is specifically a virtual mapping system built based on industrial Internet technology, which synchronizes physical drilling with virtual models in real time, realizes panoramic display and intelligent predictive analysis of drilling status through data-driven, and supports multi-dimensional data visualization and decision support functions.

[0041] The Pareto optimal solution theory is an optimization theory used to resolve multiple conflicting objectives. By constructing objective functions representing extraction efficiency, energy consumption, coverage, and cost-effectiveness, the authors seek a set of solutions that ensures no other feasible solution can improve any objective function without reducing at least one of the objective functions, thereby achieving comprehensive optimization of drilling configuration. This method primarily considers the balance between the two key objectives of gas extraction efficiency and negative pressure energy consumption. A genetic algorithm is used to solve the Pareto frontier curve, and the optimal solution is selected based on the actual needs of coal mine safety production.

[0042] The specific implementation of the above steps is described in detail below.

[0043] The specific implementation of step S01 involves conducting a geological structure and stress field analysis before arranging coal seam drilling holes. First, core sampling is used to obtain coal seam geological parameters, including coal seam thickness distribution data, gas content distribution data, and geological structural fault zone distribution data. Then, a microseismic monitoring array is deployed, using at least 12 sensors to form a three-dimensional monitoring network, collecting seismic wave velocity data through active source excitation. Next, tomography is used to reconstruct the underground three-dimensional velocity field, and a least-squares inversion algorithm is applied to establish a three-dimensional geostress distribution model with a resolution of no less than 5 meters x 5 meters x 1 meter. Finally, based on the stress distribution model, coal seam thickness, and spatial distribution characteristics of gas content, a grid optimization algorithm is used to determine the borehole spacing parameters, keeping the spacing within the range of 20 to 50 meters. Numerical simulation is also used to determine the borehole angle parameters, keeping the angle between the borehole and the principal stress direction within the range of 60° to 85° to maximize gas extraction efficiency. This step aims to determine the optimal borehole layout parameters through geological structure and stress field analysis, providing a scientific basis for subsequent gas extraction.

[0044] The specific implementation of step S02 involves installing a distributed fiber optic sensing system. First, a distributed fiber optic sensor is wrapped around the outer wall of a specially designed drill pipe. The optical fiber is treated with a corrosion-resistant and wear-resistant coating to ensure a service life of at least two years. Directional drilling is then used to complete the drilling process, controlling the borehole diameter to between 94 and 120 mm. The drilling depth is determined based on the coal seam thickness and is generally no less than 100 meters. Next, a measuring point is set every 10 meters along the borehole axis. An explosion-proof light source emitter transmits 1550-nanometer laser pulses into the optical fiber, and a Brillouin time-domain reflectometer is used to receive the scattered light signal. Finally, an optical signal processor collects stress and gas pressure data around the borehole every 10 minutes, forming a full-lifecycle monitoring network. This step aims to build a high-precision distributed monitoring system that captures real-time data on stress and gas pressure changes in the coal seam surrounding the borehole.

[0045] The specific implementation of step S03 involves collecting data using a multi-parameter gas flowmeter. First, an explosion-proof multi-parameter gas flowmeter is installed at the borehole outlet. The flowmeter utilizes a combination of a thermal mass flow sensor, an infrared gas concentration sensor, a pressure sensor, and a temperature sensor to ensure measurement accuracy of ±1% for flow, ±0.1% for concentration, ±0.5% for pressure, and ±0.1°C for temperature. The data collection frequency is then set to every five minutes, using a mine-grade intrinsically safe data collector to collect gas flow, gas concentration, temperature, and pressure data. Industrial Internet of Things technology is then used to transmit the collected data in real time to a data server, where all parameters are stored in a time-series database. Finally, a data cleaning algorithm is used to screen and correct outliers, establishing a dynamic extraction efficiency database. This step collects key gas extraction parameters at the borehole outlet in real time and establishes a basic database for extraction efficiency evaluation.

[0046] The specific implementation of step S04 is to scan the coal body using an acoustic wave tester. First, a portable acoustic wave tester is used to arrange acoustic wave transmitting and receiving probes around the borehole, with the probe spacing no greater than 2 meters. Then, an acoustic wave scan is performed on the coal body around the borehole every 24 hours, with the acoustic wave frequency set within the range of 1 to 10 kHz and the scanning radius no less than half the borehole spacing. Then, acoustic wave tomography technology is used to process the received acoustic wave signals, and the distribution of coal body fractures is identified by using the difference in sound velocity. Finally, the total length and average aperture of the fractures per unit volume are calculated to generate a three-dimensional fracture density distribution map with a fracture density resolution of 0.01 fractures per meter. The purpose of this step is to obtain data on the degree of fracture development and stress change in the coal body around the borehole, providing basic parameters for permeability calculation.

[0047] The specific implementation of step S05 is to calculate the dynamic evolution curve of permeability. First, the collected stress change data, acoustic test result data, and microseismic monitoring data are imported into the data preprocessing module, and the wavelet noise reduction algorithm is used to remove noise interference. The preprocessed data is then input into the physical numerical coupling model. This model integrates the dual medium seepage theory and elastic-plastic mechanics theory, and uses the finite element method to divide the study area into no less than 10,000 grid cells. Then, the dynamic permeability evolution curve around the borehole is calculated using the permeability dynamic evolution equation. The equation is k = k0 exp[-C f (σ-σ0)+C b (ε v -ε0)]·[1+C p (p-p0)]·[1+C T (T-T0)], where k is the current permeability, k0 is the initial permeability, C f is the stress sensitivity coefficient, σ is the effective stress, C b is the strain sensitivity coefficient, ε vis the volume strain, C p is the pressure sensitivity coefficient, p is the gas pressure, C T is the temperature sensitivity coefficient, T is the temperature, and the subscript 0 indicates the initial state parameters. Finally, the coal seam permeability values at any time and spatial location around the borehole are output, with an accuracy of at least ±5%. This step uses a physical-numerical coupling model to calculate the dynamic variation of permeability around the borehole, providing key parameters for drainage efficiency evaluation.

[0048] The specific implementation of step S06 is to establish a permeability influence coefficient matrix. First, based on the relationship between the permeability change data around the borehole and the gas extraction volume, the Pearson correlation analysis method is used to calculate the correlation coefficient between each factor and the permeability; then the permeability influence coefficient matrix M = {m ij}, where i represents the influencing factors, including stress change, fracture development degree, gas pressure gradient and temperature field change, j represents different positions around the borehole, and the matrix element m ij The coefficient representing the influence of factor i on permeability at location j is then normalized to a range of 0 to 1 using dimensional normalization, making factors of different dimensions comparable. Finally, a combination of multiple regression analysis and principal component analysis is used to determine the weights of key influencing parameters, resulting in a ground stress variation coefficient of 0.35, a fracture development coefficient of 0.25, a gas pressure coefficient of 0.2, a negative pressure coefficient of 0.15, and a temperature field coefficient of 0.05. This step quantifies the influence of each factor on permeability and provides weighting parameters for drilling performance evaluation.

[0049] The specific implementation of step S07 is to construct a drilling efficiency evaluation index system. First, the extraction volume per unit time index I1 is designed. The calculation method is the cumulative extraction volume within 24 hours divided by the designed extraction capacity. This index reflects the current extraction efficiency of the borehole; then the permeability change rate index I2 is designed. The calculation method is the ratio of the current permeability to the initial permeability. This index reflects the trend of changes in the permeability of the coal seam; then the borehole life prediction index I3 is designed. The time series analysis method is used to predict the remaining service life of the borehole based on the extraction volume attenuation curve. When the extraction volume is lower than 15% of the initial value, the borehole is judged to be failed; then the coverage range index I4 is designed. The calculation method is the ratio of the effective influence radius to the designed influence radius. This index reflects the coverage effect of a single borehole; finally, a comprehensive scoring model Score=w1·I1+w2·I2+w3·I3+w4·I4 is constructed by the weighted summation method, where w iThe weight coefficients for each indicator are: 0.4 for the extraction volume per unit time, 0.3 for the permeability change rate, 0.2 for the borehole life prediction, and 0.1 for the coverage range. The overall score ranges from 0 to 100. This step aims to establish a scientific and reasonable borehole performance evaluation index system and achieve a quantitative evaluation of borehole extraction efficiency.

[0050] The specific implementation of step S08 is to construct a multi-objective optimization model. First, according to the drilling efficiency evaluation index system, two optimization goals are set: maximizing gas extraction efficiency and minimizing extraction energy consumption. The extraction efficiency objective function is: where Q i is the extraction volume of the ith borehole, E i is the energy consumption of the ith borehole, n is the total number of boreholes; the extraction energy consumption objective function is Among them, P i is the negative pressure power of the i-th borehole, T i The run time is then calculated. Constraints are then set, including a minimum borehole spacing of 20 meters, a single borehole negative pressure of no more than 13 kPa, and a total number of boreholes of no more than 0.05 times the area. When the overall score falls below 75, a genetic algorithm is applied to find the Pareto frontier that maximizes gas extraction efficiency and minimizes extraction energy consumption. The genetic algorithm parameters are set to a population size of 100, a crossover probability of 0.8, a mutation probability of 0.1, and a maximum number of iterations of 500. Finally, from the Pareto frontier solution set, based on coal mine safety production requirements, the solution with a gas extraction efficiency of at least 85% of the design value and minimal energy consumption is selected as the optimal drilling parameter combination. This step uses a multi-objective optimization method to find the optimal configuration of drilling parameters, balancing extraction efficiency and energy consumption.

[0051] The specific implementation of step S09 is to trigger an alarm measure when the extraction efficiency drops by more than a preset threshold of 25%.

[0052] Optionally, this step may also include establishing a digital twin platform for the entire borehole lifecycle. First, a virtual mapping system is constructed using industrial internet technology to achieve real-time data synchronization between the physical borehole and the virtual model, with a data synchronization delay of no more than 30 seconds. Next, a 3D visualization module is developed, using WebGL technology to provide a panoramic display of the borehole status, including multi-dimensional data visualization such as real-time drainage volume, permeability distribution, fracture development, and stress field distribution. Next, an intelligent predictive analysis module is developed, using a long-short-term memory network algorithm to predict drainage efficiency trends over the next seven days with an accuracy of at least 85%. Next, an early warning decision support module is developed. When drainage efficiency drops by more than a preset threshold of 25%, the system automatically analyzes the cause and generates an optimization recommendation report. The recommendations include a negative pressure adjustment plan, an implementation plan for permeability enhancement measures, and borehole maintenance recommendations. Finally, a mobile application is developed to support real-time access to the digital twin platform from multiple terminals, enabling real-time monitoring and intelligent management of borehole drainage efficiency. This step aims to achieve full borehole lifecycle management through digital twin technology, improving the intelligence and safety of gas extraction.

[0053] Specifically, the core of this invention's technical principle lies in establishing a closed-loop monitoring, assessment, and optimization system for the entire lifecycle of high-negative-pressure gas extraction boreholes. First, microseismic monitoring and a three-dimensional geostress distribution model are used to rationally arrange boreholes, laying the foundation for efficient extraction. Second, a distributed fiber optic sensing system enables continuous, high-precision monitoring of stress and temperature in the coal mass surrounding the borehole, overcoming the limitations of traditional single-point monitoring. Third, an acoustic wave tester regularly scans the coal mass around the borehole for fracture development, providing direct evidence of permeability changes.

[0054] In terms of data processing, this invention innovatively constructs a physical-numerical coupling model, combining microscopic seepage mechanisms with macroscopic gas migration patterns. This model accurately describes how coal seam permeability changes with mining stress through a dynamic permeability evolution equation. This equation accounts for stress sensitivity, fracture evolution, and gas desorption, enabling an accurate depiction of permeability changes under complex conditions.

[0055] This invention also establishes a comprehensive evaluation system encompassing four key indicators: extraction volume per unit time, permeability change rate, borehole life prediction, and coverage area. Through multivariate regression analysis, the weight coefficients of each influencing factor are determined, enabling a quantitative evaluation of drilling efficiency. In particular, the Pareto optimal solution theory is incorporated into a multi-objective optimization model to find the optimal balance between gas extraction efficiency and energy consumption, providing a scientific approach for optimizing drilling parameters.

[0056] The application of the digital twin platform enables real-time synchronization between the physical borehole and the virtual model. When extraction efficiency drops below a preset threshold, optimization recommendations are automatically generated, ensuring the entire extraction system remains highly efficient. This dynamic, lifecycle-based monitoring and assessment approach fundamentally overcomes the limitations of traditional technologies, which often struggle to cope with complex geological conditions and dynamically changing environments.

[0057] A specific embodiment 1 of the present invention is provided below. The specific implementation of each step in this embodiment 1 is described in detail as follows.

[0058] The specific implementation method of step S01 is to perform geological structure and stress field analysis before arranging coal seam drilling. First, core sampling is used to obtain coal seam geological parameters, including coal seam thickness distribution data, gas content distribution data, and geological structure fault zone distribution data; then, an array of microseismic monitors is deployed, using at least 12 sensors to form a three-dimensional monitoring network, and seismic wave velocity data is collected through active source excitation; then, tomography technology is used to reconstruct the underground three-dimensional velocity field, and the least squares inversion algorithm is applied to establish a three-dimensional ground stress distribution model, with a model resolution of not less than 5 meters × 5 meters × 1 meter; finally, based on the stress distribution model, coal seam thickness, and gas content spatial distribution characteristics, a grid division optimization algorithm is used to determine the borehole spacing parameters, and the spacing is controlled within the range of 20 to 50 meters. At the same time, a numerical simulation method is used to determine the borehole angle parameters, and the angle between the borehole and the principal stress direction is controlled within the range of 60° to 85° to maximize the gas extraction efficiency. The purpose of this step is to determine the optimal drilling arrangement parameters through geological structure and stress field analysis, providing a scientific basis for subsequent gas extraction. The borehole spacing optimization algorithm is based on the least squares method to construct the following model:

[0059]

[0060] Where, d opt is the optimal drilling spacing; k i is the permeability coefficient at the i-th position; σ i is the ground stress value at the i-th position; G i is the gas content value at the i-th position; α is the balance coefficient, ranging from 0.1 to 0.5; n is the total number of grid divisions.

[0061] The specific implementation method of step S02 is to install a distributed fiber optic sensing system. First, the distributed fiber optic sensor is wrapped and fixed on the outer wall of a special drill pipe, and the optical fiber is treated with an anti-corrosion and wear-resistant coating to ensure that the service life is not less than 2 years; then the directional drilling technology is used to complete the drilling construction, and the borehole diameter is controlled within the range of 94 to 120 mm. The drilling depth is determined according to the thickness of the coal seam, generally not less than 100 meters; then a measuring point is set every 10 meters along the axis of the borehole, and a laser pulse with a wavelength of 1550 nanometers is sent to the optical fiber through an explosion-proof light source transmitter, and a Brillouin time domain reflectometer is used to receive the scattered light signal; finally, the stress change data and gas pressure data around the borehole are collected through the optical signal processor, and the data collection frequency is once every 10 minutes to form a full life cycle monitoring network. The purpose of this step is to build a high-precision distributed monitoring system to obtain real-time data on the stress and gas pressure changes of the coal seam around the borehole. The relationship between the Brillouin scattering signal, stress and temperature can be expressed as:

[0062] Δν B =C ε ·ε+C T ΔT;

[0063] Where Δv B is the Brillouin frequency shift; C ε is the gauge factor, which is 0.05MHz / με; ε is the strain value; C T is the temperature coefficient, which is 1.2MHz / ℃; ΔT is the temperature change.

[0064] The specific implementation method of step S03 is to use a multi-parameter gas flowmeter to collect data. First, an explosion-proof multi-parameter gas flowmeter is installed at the borehole outlet. The flowmeter adopts a combination of thermal mass flow sensor, infrared gas concentration sensor, pressure sensor and temperature sensor to ensure the measurement accuracy of flow accuracy is ±1%, concentration accuracy is ±0.1%, pressure accuracy is ±0.5%, and temperature accuracy is ±0.1°C; then set the data collection frequency to once every 5 minutes, and collect gas flow data, gas concentration data, temperature data, and pressure data through a mine-used intrinsically safe data collector; then use industrial Internet of Things technology to transmit the collected data to the data server in real time, and use a time series database to store all parameters; finally, use a data cleaning algorithm to screen and correct abnormal values, and establish a dynamic extraction efficiency database. The function of this step is to collect key parameters of gas extraction at the borehole outlet in real time and establish a basic database for extraction efficiency evaluation. The gas flow metering calculation formula is:

[0065]

[0066] Where Q is the gas flow rate; K is the flow coefficient, ranging from 0.95 to 0.98; A is the flow area; ΔP is the differential pressure value; ρ is the gas density.

[0067] The specific implementation method of step S04 is to scan the coal body through an acoustic wave tester. First, a portable acoustic wave tester is used to arrange acoustic wave transmitting probes and receiving probes around the borehole, with the probe spacing no greater than 2 meters; then, an acoustic wave scan is performed on the coal body around the borehole every 24 hours, with the acoustic wave frequency set within the range of 1 to 10 kHz, and the scanning radius is no less than half of the borehole spacing; then, the acoustic wave tomography technology is used to process the received acoustic wave signals, and the difference in sound velocity is used to identify the distribution of coal body cracks; finally, the total length and average opening of the cracks in the unit volume are calculated to generate a three-dimensional crack density distribution map, with a crack density resolution of 0.01 lines / meter. The purpose of this step is to obtain the data on the degree of development of coal body cracks and stress change data around the borehole, and provide basic parameters for permeability calculation. The formula for calculating crack density is:

[0068]

[0069] Where D f is the crack density; L i is the length of the i-th crack; n is the total number of cracks; V is the detection volume.

[0070] The specific implementation of step S05 is to calculate the dynamic evolution curve of permeability. First, the collected stress change data, acoustic test result data, and microseismic monitoring data are imported into the data preprocessing module, and the wavelet noise reduction algorithm is used to remove noise interference. The preprocessed data is then input into the physical numerical coupling model. This model integrates the dual medium seepage theory and elastic-plastic mechanics theory, and uses the finite element method to divide the study area into no less than 10,000 grid cells. Then, the dynamic permeability evolution curve around the borehole is calculated using the permeability dynamic evolution equation. The equation is k = k0 exp[-C f (σ-σ0)+C b (ε v -ε0)]·[1+C p (p-p0)]·[1+C T (T-T0)], where k is the current permeability; k0 is the initial permeability, obtained through laboratory permeability testing; C f is the stress sensitivity coefficient, ranging from 0.02 to 0.05 MPa -1 ; σ is the effective stress, obtained from the distributed optical fiber sensing system; σ0 is the initial effective stress, obtained from the ground stress distribution model; C b is the strain sensitivity coefficient, ranging from 1.5 to 3.0; ε v is the volume strain, obtained from the monitoring results of the microseismic monitoring instrument; ε0 is the initial volume strain, calculated from the ground stress distribution model; C p is the pressure sensitivity coefficient, ranging from 0.001 to 0.01 MPa-1 ; p is the gas pressure, obtained from the multi-parameter gas flow meter; p0 is the initial gas pressure, obtained from geological parameters; C T is the temperature sensitivity coefficient, ranging from 0.001 to 0.005°C -1 T is the temperature, measured by a distributed fiber optic sensing system; T0 is the initial temperature, derived from geological parameters. Finally, the coal seam permeability values at any time and location around the borehole are output, with an accuracy of at least ±5%. This step uses a physical-numerical coupling model to calculate the dynamic changes in permeability around the borehole, providing key parameters for drainage efficiency evaluation.

[0071] The specific implementation of step S06 is to establish a permeability influence coefficient matrix. First, based on the relationship between the permeability change data around the borehole and the gas extraction volume, the Pearson correlation analysis method is used to calculate the correlation coefficient between each factor and the permeability; then the permeability influence coefficient matrix M = {m ij}, where i represents the influencing factors, including stress change, fracture development degree, gas pressure gradient and temperature field change, j represents different positions around the borehole, and the matrix element m ij Represents the influence coefficient of factor i on permeability at position j; then, the dimensional normalization method is used to standardize the influence degree of each factor to the range of 0 to 1, so that the influencing factors of different dimensions are comparable; finally, the weight values of key influencing parameters are determined by combining multiple regression analysis with principal component analysis, and the ground stress variation coefficient is 0.35, the fracture development degree coefficient is 0.25, the gas pressure coefficient is 0.2, the negative pressure value coefficient is 0.15, and the temperature field coefficient is 0.05. The purpose of this step is to quantify the influence of each factor on permeability and provide weight parameters for drilling efficiency evaluation. The calculation formula of the influence coefficient matrix element is:

[0072]

[0073] Where m ij is the normalized influence coefficient; r ij is the original correlation coefficient; r min is the minimum correlation coefficient; r max is the maximum correlation coefficient.

[0074] The specific implementation of step S07 is to construct a drilling efficiency evaluation index system. First, the extraction volume per unit time index I1 is designed. The calculation method is the cumulative extraction volume within 24 hours divided by the designed extraction capacity. This index reflects the current extraction efficiency of the borehole; then the permeability change rate index I2 is designed. The calculation method is the ratio of the current permeability to the initial permeability. This index reflects the trend of changes in the permeability of the coal seam; then the borehole life prediction index I3 is designed. The time series analysis method is used to predict the remaining service life of the borehole based on the extraction volume attenuation curve. When the extraction volume is lower than 15% of the initial value, the borehole is judged to be failed; then the coverage range index I4 is designed. The calculation method is the ratio of the effective influence radius to the designed influence radius. This index reflects the coverage effect of a single borehole; finally, a comprehensive scoring model Score=w1·I1+w2·I2+w3·I3+w4·I4 is constructed by the weighted summation method, where w i The weight coefficients for each indicator are: 0.4 for the extraction volume per unit time, 0.3 for the permeability change rate, 0.2 for the borehole life prediction index, and 0.1 for the coverage range. The comprehensive score ranges from 0 to 100. This step aims to establish a scientific and reasonable borehole efficiency evaluation index system to achieve a quantitative evaluation of borehole extraction efficiency. The calculation formulas for each indicator are as follows:

[0075]

[0076] Where, I1 is the extraction volume per unit time; Q 24 is the cumulative extraction volume within 24 hours; Q design To design the extraction capacity.

[0077]

[0078] Where, I2 is the permeability change rate index; k t is the permeability at time t; k0 is the initial permeability.

[0079]

[0080] Where, I3 is the prediction index of drilling life; T remain is the predicted remaining life of the borehole; T design For the design life.

[0081]

[0082] Where, I4 is the coverage index; R effect is the effective influence radius; R design is the design influence radius.

[0083] The specific implementation of step S08 is to construct a multi-objective optimization model. First, according to the drilling efficiency evaluation index system, two optimization goals are set: maximizing gas extraction efficiency and minimizing extraction energy consumption. The extraction efficiency objective function is: where Q i is the extraction volume of the ith borehole, in cubic meters per day; E i is the energy consumption of the ith borehole, in kilowatt-hours per day; n is the total number of boreholes; the extraction energy consumption objective function is Among them, P i is the negative pressure power of the i-th borehole, in kilowatts; T i is the running time in hours; then set the constraints, including that the borehole spacing is not less than 20 meters, the negative pressure value of a single borehole does not exceed 13 kPa, and the total number of boreholes does not exceed 0.05 times the area of the region; then when the comprehensive score is lower than 75 points, apply the genetic algorithm to solve the Pareto frontier of maximizing gas extraction efficiency and minimizing extraction energy consumption. The genetic algorithm parameters are set to population size 100, crossover probability 0.8, mutation probability 0.1, and maximum number of iterations 500; finally, from the Pareto frontier solution set, according to the coal mine safety production needs, select the solution with a gas extraction efficiency not less than 85% of the design value and the lowest energy consumption as the optimal drilling parameter combination. The purpose of this step is to find the optimal configuration of drilling parameters through a multi-objective optimization method to balance extraction efficiency and energy consumption. The multi-objective optimization problem is stated as follows:

[0084]

[0085] Constraints:

[0086]

[0087] n≤0.05·S;

[0088] Where x is the decision variable, including drilling position, angle and negative pressure value; d ij is the distance between borehole i and borehole j, in meters; p i is the negative pressure value of borehole i, in kPa; S is the area, in square meters.

[0089] The specific implementation of step S09 is to trigger an alarm measure when the extraction efficiency drops by more than a preset threshold of 25%.

[0090] Optionally, this step can also include establishing a digital twin platform for the entire life cycle of the borehole. First, a virtual mapping system is constructed using industrial Internet technology to achieve real-time data synchronization between the physical borehole and the virtual model, with a data synchronization delay of no more than 30 seconds; then a three-dimensional visualization module is developed, using WebGL technology to achieve a panoramic display of the borehole status, including real-time extraction volume, permeability distribution, fracture development degree, stress field distribution and other multi-dimensional data visualization; then an intelligent prediction and analysis module is developed, using the long-short-term memory network algorithm to predict the trend of extraction efficiency changes in the next 7 days, with a prediction accuracy of no less than 85%; then an early warning decision support module is developed. When the extraction efficiency drops by more than a preset threshold of 25%, the system automatically analyzes the cause and generates an optimization recommendation report. The recommendations include a negative pressure adjustment plan, a permeability enhancement measure implementation plan and a borehole maintenance recommendation; finally, a mobile application is developed to support multi-terminal real-time access to the digital twin platform to achieve real-time monitoring and intelligent management of the drilling extraction efficiency. The purpose of this step is to achieve full-life cycle management of the borehole through digital twin technology and improve the intelligence level and safety of gas extraction. The long-short-term memory network prediction model is defined as follows:

[0091] f t =σ(W f ·[h t-1 , x t ]+b f );

[0092] i t =σ(W i ·[h t-1 , x t ]+b i );

[0093]

[0094] o t =σ(W o ·[h t-1 , x t ]+b o );

[0095] h t =o t *tanh(C t );

[0096]

[0097] Where, f t is the forget gate vector; i t is the input gate vector; is the candidate memory cell state; C t is the memory unit state; o t is the output gate vector; ht is in hidden state; is the predicted output; x t is the input vector, including historical extraction volume, permeability, negative pressure value and other characteristics; W f , W i , W c , W o , W y is the weight matrix; b f , b i , b C , b o , b y is the bias vector; σ is the sigmoid activation function; tanh is the hyperbolic tangent activation function; * represents the element-wise multiplication operation.

[0098] Through the implementation of the nine steps outlined above, this method for evaluating the full lifecycle performance of high-negative-pressure gas extraction drilling can achieve scientific drilling layout, precise monitoring, quantitative evaluation, and intelligent optimization, effectively improving coal mine gas extraction efficiency and reducing the risk of gas disasters. This method possesses significant theoretical and engineering application value. By organically combining distributed fiber optic sensing technology, a dynamic permeability evolution model, and a digital twin platform, this method establishes a performance evaluation and optimization system throughout the entire drilling lifecycle, providing new technical support for safe and efficient coal mining.

[0099] In order to better understand and implement the present invention, the following provides Example 2 of a specific application scenario of the present invention: Before the mining of a coal mine working face, researchers used the high-negative-pressure gas extraction drilling full life cycle performance evaluation method of the present invention to conduct engineering practice in order to ensure gas extraction efficiency and safe production. The coal mine is a high-gas mine with an average gas content of 17.2m 3 / t, the average thickness of the coal seam is 4.2 meters, the burial depth is about 520 meters, the geological structure is relatively complex, and there are many faults.

[0100] First, researchers conducted a geological structure and stress field analysis in step S01. Core sampling yielded data on coal seam thickness and gas content, as shown in Table 1.

[0101] Table 1 Coal seam thickness and gas content distribution data

[0102] Sampling point number Coal seam thickness (m) <![CDATA[Gas content (m 3 / t)]]> Description of geological characteristics A01 3.8 16.4 Complete coal body A02 4.3 18.2 Complete coal body A03 4.5 19.1 Near fault zone A04 3.9 17.8 Complete coal body A05 4.7 21.3 Near fault zone A06 4.1 16.9 Complete coal body A07 3.6 15.6 Complete coal body A08 4.4 18.7 Near fault zone

[0103] Subsequently, 16 microseismic monitoring sensors were deployed to form a three-dimensional monitoring network. Active source excitation was used to collect seismic wave velocity data. A three-dimensional velocity field was reconstructed using tomography, and a least-squares inversion algorithm was used to establish a three-dimensional geostress distribution model with a resolution of 5 m × 5 m × 1 m. Geostress analysis revealed that the principal stress direction in the coal seam at the working face was 45° north-east, with an average vertical stress of 13.2 MPa and an average horizontal stress of 17.8 MPa. Based on the stress distribution characteristics, a grid optimization algorithm was used to determine a 35-meter spacing between boreholes and a 78° angle between the boreholes and the principal stress direction to maximize gas extraction efficiency.

[0104] In step S02, Figure 2-3 As shown, researchers installed a distributed fiber optic sensing system. Distributed fiber optic sensors, treated with a corrosion-resistant and wear-resistant coating, were wrapped around the outer wall of a custom drill pipe. Using directional drilling techniques, ten boreholes were constructed, each with a diameter of 108 mm and a depth of 150 meters. Measuring points were set every 10 meters along the borehole axis. An explosion-proof light source transmitter sent 1550-nanometer laser pulses into the optical fiber, and a Brillouin time-domain reflectometer was used to detect scattered light signals. An optical signal processor collected stress and gas pressure data around the borehole every 10 minutes, forming a full-lifecycle monitoring network.

[0105] In step S03, researchers installed an explosion-proof multi-parameter gas flow meter at the borehole outlet. Figure 4 As shown, a combination of thermal mass flow sensors, infrared gas concentration sensors, pressure sensors, and temperature sensors is used, with a data acquisition frequency of once every 5 minutes. The extraction parameters for each borehole during the initial operation phase are shown in Table 2:

[0106] Table 2 Initial drilling extraction parameter data

[0107] Drill hole number <![CDATA[Gas flow rate (m 3 / h)]]> Gas concentration (%) Negative pressure value (kPa) Temperature (℃) B01 38.5 71.3 10.2 24.3 B02 42.7 75.6 10.4 24.1 B03 35.9 68.4 10.1 24.5 B04 47.2 78.2 10.5 23.8 B05 33.6 65.7 10.0 24.7 B06 41.4 72.5 10.3 24.2 B07 45.8 76.8 10.5 23.9 B08 36.2 69.1 10.2 24.4 B09 43.9 74.6 10.4 24.0 B10 37.3 70.2 10.2 24.3

[0108] In step S04, researchers used a portable acoustic wave tester to perform an acoustic scan of the coal mass surrounding the borehole. Transmitting and receiving probes were placed around the borehole, spaced 1.5 meters apart. The coal mass surrounding the borehole was scanned once every 24 hours at a frequency of 5 kHz and a scanning radius of 20 meters. Acoustic tomography was used to process the received acoustic wave signals, identifying the distribution of coal fractures. The total length and average aperture of fractures per unit volume were calculated, generating a three-dimensional fracture density map with a resolution of 0.01 fractures per meter.

[0109] In step S05, the researchers imported the collected stress change data, acoustic test results, and microseismic monitoring data into the data preprocessing module and used the wavelet noise reduction algorithm to remove noise interference. The preprocessed data was input into the physical numerical coupling model, which integrates the dual-medium seepage theory and elastic-plastic mechanics theory and uses the finite element method to divide the study area into 12,800 grid cells. Based on the permeability dynamic evolution equation k = k0 exp[-C f (σ-σ0)+C b (ε v -ε0)]·[1+C p (p-p0)]·[1+C T (T-T0)] to calculate the dynamic permeability evolution curve around the borehole. The stress sensitivity coefficient C f The value is 0.035MPa -1 , strain sensitivity coefficient C b The value is 2.5, the pressure sensitivity coefficient C p The value is 0.005MPa -1 , temperature sensitivity coefficient C T The value is 0.003℃ -1 .

[0110] In step S06, researchers used Pearson correlation analysis to calculate the correlation coefficients between various factors and permeability based on the relationship between permeability variation data around the borehole and gas extraction volume, and constructed a permeability influence coefficient matrix. The calculated results showed a ground stress variation coefficient of 0.35, a fracture development coefficient of 0.25, a gas pressure coefficient of 0.2, a negative pressure coefficient of 0.15, and a temperature field coefficient of 0.05.

[0111] In step S07, a drilling efficiency evaluation index system was constructed, including the extraction volume per unit time, the permeability change rate, the borehole life prediction index, and the coverage index. A comprehensive scoring model (Score = w1·I1+w2·I2+w3·I3+w4·I4) was constructed using a weighted summation method, with weights of 0.4 for the extraction volume per unit time, 0.3 for the permeability change rate, 0.2 for the borehole life prediction index, and 0.1 for the coverage index. The drilling efficiency evaluation results after one month of operation are shown in Table 3:

[0112] Table 3 Drilling efficiency evaluation results

[0113]

[0114] The evaluation results show that the comprehensive score of borehole B05 is only 70.6 points, which is lower than the preset threshold of 75 points and needs to be optimized. In step S08, the researchers constructed a multi-objective optimization model based on the performance evaluation index system and optimized the configuration of the boreholes using the Pareto optimal solution theory. The extraction efficiency objective function is The objective function of extraction energy consumption is: The Pareto frontier was solved using a genetic algorithm, and the solution with a gas extraction efficiency not less than 85% of the design value and minimal energy consumption was selected as the optimal parameter combination. The main adjustments were: increasing the negative pressure value of the B05 borehole from 10.0 kPa to 12.5 kPa, and implementing CO2 fracturing and permeability enhancement measures on the coal seam.

[0115] Finally, in step S09, researchers established a digital twin platform for the entire life cycle of drilling. Figure 5 As shown in the figure, a virtual mapping system was constructed using Industrial Internet technology, achieving real-time data synchronization between the physical borehole and the virtual model, with data synchronization latency controlled to less than 25 seconds. A 3D visualization module was developed, using WebGL technology to provide a panoramic display of the borehole status. An intelligent predictive analysis module was developed, using a long-short-term memory network algorithm to predict seven-day trends in extraction efficiency, achieving an accuracy rate of 89.6%. An early warning decision support module and mobile application were also developed, enabling real-time access to the digital twin platform from multiple terminals.

[0116] After implementing these measures, the extraction efficiency of borehole B05 significantly improved, with the overall score rising from 70.6 to 87.2. The overall system gas extraction efficiency increased by 15.4%, and energy consumption decreased by 8.7%. Long-term monitoring shows that the use of this method has extended the average effective life of the borehole by approximately 35%, reduced the risk of gas outburst accidents by 82%, and significantly improved the safety and economic benefits of coal mining.

[0117] Traditional gas extraction drilling efficiency evaluation mainly relies on single-point static monitoring and empirical judgment, and cannot achieve dynamic evaluation and optimization throughout the entire life cycle. For example, a coal mine uses traditional methods for gas extraction. The drilling position and angle are determined by experience, and the extraction parameters are fixed and cannot be adjusted according to the dynamic changes of the coal seam. This leads to low extraction efficiency, high drilling failure rate, and an average effective extraction time of only 65% of the design life. Gas disasters occur frequently. In contrast, the present invention uses distributed fiber optic sensing technology to achieve high-precision real-time monitoring of coal seam stress and gas pressure, establishes a permeability dynamic evolution model to accurately describe the law of coal seam permeability changes, constructs a scientific efficiency evaluation index system and a multi-objective optimization model, and realizes visualization and intelligent management of the entire drilling life cycle through a digital twin platform.

[0118] It should be noted that the variables involved in the present invention are explained in detail as shown in Tables 4 and 5 below.

[0119] Table 4 Variable Explanation Table (Part 1)

[0120]

[0121] Table 5 Variable Explanation Table (Part 2)

[0122]

[0123]

[0124] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for evaluating the full life cycle performance of a high-vacuum gas extraction borehole, characterized in that: include: Conduct geological structure and stress field analysis to determine drilling parameters; A distributed fiber optic sensing system is installed on the inner wall of the borehole to collect stress change data and gas pressure data; a multi-parameter gas flowmeter is used to collect gas flow data to establish a dynamic extraction efficiency database; an acoustic wave tester is used to obtain data on the degree of coal body fracture development to form a fracture density distribution map; the collected data is input into a physical-numerical coupling model to calculate the dynamic evolution curve of permeability; a permeability influence coefficient matrix is established to determine the weight values of key influencing parameters; a drilling efficiency evaluation index system is constructed to form a comprehensive scoring model; the Pareto optimal solution theory is applied to optimize the configuration of the borehole; and an alarm is activated when the extraction efficiency drops by more than a preset threshold of 25%.

2. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 1 is characterized in that: The steps of conducting geological structure and stress field analysis to determine drilling parameters are specifically to conduct geological structure and stress field analysis before arranging coal seam drilling, use microseismic monitoring instruments to establish a three-dimensional ground stress distribution model, and determine the drilling spacing parameters and drilling angle parameters based on the coal seam thickness and gas content distribution.

3. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 2 is characterized in that: The step of installing a distributed fiber optic sensing system on the inner wall of the borehole to collect stress change data and gas pressure data is specifically to install the distributed fiber optic sensing system on the inner wall of the borehole, set a measuring point every 10 meters along the axis of the borehole, collect stress change data and gas pressure data around the borehole, and form a full life cycle monitoring network.

4. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 3 is characterized in that: The step of using a multi-parameter gas flowmeter to collect gas flow data and establish a dynamic extraction efficiency database is specifically to use the multi-parameter gas flowmeter to collect gas flow data, gas concentration data, temperature data, and pressure data in real time at the borehole outlet. The data collection frequency is once every 5 minutes to establish a dynamic extraction efficiency database.

5. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 4 is characterized in that: The step of obtaining coal body fracture development degree data and forming a fracture density distribution map by using an acoustic wave tester is specifically to perform an acoustic wave scan on the coal body around the borehole once every 24 hours by using the acoustic wave tester to obtain coal body fracture development degree data and stress change data to form a fracture density distribution map.

6. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 5 is characterized in that: The step of inputting the collected data into the physical numerical coupling model to calculate the dynamic evolution curve of permeability is specifically to input the collected stress change data, acoustic wave test result data and microseismic monitoring data into the physical numerical coupling model, and calculate the dynamic permeability evolution curve around the borehole through the permeability dynamic evolution equation, wherein the permeability dynamic evolution equation comprehensively considers stress sensitivity, crack evolution and gas desorption; the physical numerical coupling model specifically integrates the coal seam gas occurrence theory and the coal rock solid-liquid-gas three-phase coupling mathematical model, combines the microscopic seepage mechanism with the macroscopic gas migration law, and establishes a stress field evolution and permeability dynamic change relationship model through the finite element analysis method; the permeability dynamic evolution equation is specifically a mathematical expression that describes the change of coal seam permeability with mining stress, which is used to accurately describe the spatiotemporal evolution law of coal seam permeability during the mining process. The input includes effective stress data, coal body strain data, temperature change data, gas pressure data and initial condition data, and the output is the coal seam permeability value at any time and spatial position.

7. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 6 is characterized in that: The steps of establishing a permeability influence coefficient matrix to determine the weight values of key influencing parameters specifically include establishing a permeability influence coefficient matrix based on the relationship between the permeability change data around the borehole and the gas extraction volume, and determining the weight values of key influencing parameters through multivariate regression analysis; the permeability influence coefficient matrix is specifically a mathematical expression that characterizes the degree of influence of mining stress changes, the degree of coal body crack development, gas pressure gradient and temperature field changes on coal seam permeability.

8. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 7 is characterized in that: The step of constructing a drilling efficiency evaluation index system to form a comprehensive scoring model is specifically to construct a drilling efficiency evaluation index system, including a unit time extraction volume index, a permeability change rate index, a drilling life prediction index and a coverage range index, to form a comprehensive scoring model.

9. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 8 is characterized in that: The step of applying the Pareto optimal solution theory to optimize the configuration of drilling holes is specifically to construct a multi-objective optimization model based on the drilling efficiency evaluation index system, apply the Pareto optimal solution theory to optimize the configuration of drilling holes, and when the comprehensive score is lower than 75 points, solve the Pareto frontier that maximizes gas extraction efficiency and minimizes extraction energy consumption, and select the optimal drilling parameter combination from it.

10. The method for evaluating the full life cycle performance of high-vacuum gas extraction drilling according to claim 9 is characterized in that: It also includes establishing a digital twin platform for the entire life cycle of drilling, realizing real-time visualization and early warning of extraction efficiency, and automatically generating optimization recommendation reports.

Images