Three-dimensional imaging gas extraction drilling construction scheme design method
Through three-dimensional imagery technology and convolutional neural network simulation, the problems of poor adaptability of coal mine gas extraction drilling design and unintuitive two-dimensional drawings in the existing technology are solved, and the precise simulation of coal seam drilling trajectory and extraction blank belts are realized. The demonstration improves construction efficiency and design accuracy.
Patent Information
- Application Number
- CN202410914388.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-12
AI Technical Summary
The existing coal mine gas extraction drilling design is difficult to adapt to coal seams with unstable allocation and large inclination changes, and the two-dimensional drawings are not intuitive, resulting in low construction efficiency and cumbersome parameter design, making it difficult to achieve drilling design that strictly complies with the regulations.
Using three-dimensional imagery technology, coal-rock storage information is obtained through well logging, and a virtual three-dimensional coal seam model is generated using a convolutional neural network. Combining physical strength and mechanical properties detection, the drilling trajectory is calculated and simulated, providing an intuitive three-dimensional construction solution design , reduce operation difficulty and improve efficiency.
It realizes the simulation of the precise drilling trajectory of coal seams and the intuitive display of the extraction gap belt, improves the construction efficiency and the accuracy of parameter design, provides a drilling solution with high success rate, stability and fault tolerance, and reduces drilling risk.
Smart Images

Figure CN118940462A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of coal mine gas extraction, and specifically is a three-dimensional image gas extraction drilling construction plan design method. Background Art
[0002] Coal is the main energy source in mineral resources, and is also an important industrial raw material for industries such as electricity, steel, and chemicals. It has a very important strategic position in economic construction. According to statistics, coal accounts for more than 75% of one-time energy consumption. With the global energy crisis, the status of coal as the main energy source will be difficult to change for a long time. As a clean energy source, coal-associated gas has been widely valued by major coal-producing countries. Major coal-producing countries in the world are actively carrying out gas exploration and development. At the same time, gas is one of the main disasters that restrict coal mine safety production. Therefore, efficient gas mining is a fundamental measure to achieve mine disaster management and resource utilization. Among them, the drilling and extraction of coal seam gas technology has a significant effect in mine gas mining and management. In practical applications, according to the regional characteristics of coal seam gas storage, accurately determining the drilling layout parameters is an important technical step to achieve efficient extraction of coal seam gas.
[0003] Specifically, the design of coal mine extraction drilling holes is mainly carried out by the designers of the extraction department based on their experience or using prepared design templates. However, the above extraction drilling hole design is only applicable to near-horizontal coal seams with stable occurrence and little change in occurrence, and extraction drilling holes with low requirements for drilling hole design. However, the extraction drilling hole design for coal seams with unstable occurrence and large inclination changes, and protruding coal seams with strict requirements on the drilling control range, has poor adaptability, and it is difficult to achieve a drilling design that strictly complies with the regulations and has no extraction blank zone. At the same time, the existing graphical presentation of the extraction drilling hole design is only two two-dimensional drawings of the plane and the section, and the drilling hole offset trajectory, the extraction range of the target layer and the blank zone are not graphically presented. Therefore, for the current situation where the front-line operators in coal mines generally have low educational qualifications, the existing extraction drilling hole design method is not intuitive enough, difficult to understand, and has low construction efficiency. For this reason, it is necessary to propose a three-dimensional graphical gas extraction drilling hole construction scheme design method that can calculate the coal seam extraction blank zone and the drilling hole trajectory offset, and intuitively display it. Summary of the invention
[0004] In order to solve the above problems, the purpose of the present invention is to provide a three-dimensional image gas extraction drilling construction plan design method, which can combine three-dimensional technology to obtain a three-dimensional stereoscopic image of the drilling site, borehole, and coal seam, and intuitively display the drilling construction plan.
[0005] In order to achieve the above object, the technical solution of the present invention is as follows: a three-dimensional image gas extraction drilling construction plan design method, comprising:
[0006] Step 1: Collect information about coal seams through several well logging operations, obtain coal-rock occurrence information and geological anomaly information, and mark coal-rock borehole sections;
[0007] Step 2: preparing a trained convolutional neural network, the convolutional neural network is trained based on the coal-rock structure training model, and the convolutional neural network is used to generate a virtual three-dimensional coal seam model based on the annotated coal-rock occurrence information and geological anomaly information;
[0008] Step 3: Conduct physical strength and mechanical property tests on coal seams, rock strata, geological anomalies and drilling tools, and collect gravity acceleration in the coal seam area;
[0009] Step 4: Bind the detected physical strength, mechanical property information and gravity acceleration to the virtual 3D coal seam model, input the drilling site information, and the virtual 3D coal seam model is calculated based on the preset formula to generate the drilling trajectory and construction parameters;
[0010] Step 5: Intercept the attached area of the drilling offset trajectory of the virtual three-dimensional coal seam model, conduct several coal seam structure simulation tests in the attached area based on the convolutional neural network, generate the drilling offset trajectory with the same construction parameters under different coal seam structure simulations, compare the simulation test results with the original trajectory, and show the relationship between the offset amount and the offset probability at different drilling depths.
[0011] The following beneficial effects are achieved by adopting the above scheme:
[0012] 1. Logging of coal seams and information collection. Collect coal-rock occurrence information and geological anomaly information. Coal-rock occurrence information includes the distribution, dip, inclination and thickness of coal seams and rock strata, which can directly feedback the geological conditions of the operation area.
[0013] 2. Information collection has blind spots and the degree of refinement is not high. Therefore, the use of convolutional neural networks for machine learning can make up for the refinement problems caused by the lack of geological information. Construct a virtual three-dimensional coal seam model as the basis for the design of the scheme.
[0014] 3. Physical strength and mechanical property tests are performed on coal seams, rock strata, geological anomalies and drilling tools respectively, so that the three-dimensional physical model of the virtual three-dimensional coal seam can be bound to perform mechanical simulation and simulate the drilling trajectory. To restore the real drilling trajectory. During the drilling process, the actual drilling trajectory is a curve. Due to the friction between the drill bit and the coal seam and rock strata, gravity and other factors during the drilling process, the drill hole will deviate, and as the depth increases, the torque increases, and the deviation will become more and more obvious. Due to different geological compositions, the deviation of the drill bit in different geological environments is also different. Therefore, after binding the physical strength and mechanical properties to the virtual three-dimensional coal seam model, a simulation trajectory that is more in line with the actual drilling trajectory can be generated.
[0015] 4. Users can generate drilling trajectories by inputting drilling site information, so as to analyze the design scheme and assist users in designing schemes. However, there is a gap between the simulation process and the actual situation, which is specifically reflected in the accuracy of virtual three-dimensional coal seam construction and the simulation of drilling trajectories. The accuracy of virtual three-dimensional coal seam construction will inevitably deviate, and the friction caused by the friction between the drill bit and the coal seam and rock layer in the drilling trajectory is in a random direction, and the deviation direction cannot be completely determined. Therefore, in order to make the scheme more executable, accurate and practical, the probabilistic randomness of convolutional neural networks can be used to build multiple simulation models based on collected information, and conduct drilling trajectory simulation tests multiple times to obtain the probability distribution of different drilling trajectories. The test results can be reflected in the trajectory distribution of multiple drillings under different refined geological structures, so that users can perform trajectory analysis based on probability distribution, and thus formulate drilling schemes with high success rate, stability and fault tolerance. Intercepting the attachment area of the drilling offset trajectory of the virtual three-dimensional coal seam model can reduce the computing power requirements of the convolutional neural network and reduce the difficulty of implementation.
[0016] 5. In addition to assisting users in formulating construction plans, the virtual 3D coal seam model can also demonstrate plans to frontline operators, considering that frontline operators in coal mines generally have low educational qualifications. The 3D graphical construction plan can reduce the difficulty for workers to understand and improve construction efficiency.
[0017] Compared with the existing technology, it solves the problems of cumbersome design of extraction drilling parameters and the lack of intuitiveness of two-dimensional drawings. The virtual three-dimensional coal seam model is used to simulate the drilling trajectory to achieve the effect of simulating the real drilling trajectory. In the past, the design method based on two-dimensional drawings simplified the drilling trajectory into a straight line, and it was impossible to simulate the drilling curve trajectory, which resulted in great uncertainty. Through the establishment of a three-dimensional model, more parameters and information can be provided for curve trajectory simulation, which can effectively avoid abnormal terrain such as collapse columns and bubbles, and reduce drilling risks. And by using the random filling characteristics of convolutional neural networks, its simulation function is expanded, and multiple iterations are used to simultaneously solve the problems of refinement defects and trajectory deviation randomness, providing the ability to formulate drilling plans with high success rate, stability and fault tolerance.
[0018] Furthermore, in step one, seismic waves are first used to detect the distribution of coal seam thickness, and well logging is planned. The areas where drill stuck, rock is seen, gas eruption and water are produced during the logging drilling process are marked as geological abnormal areas.
[0019] Beneficial effects: Seismic waves can obtain underground geological distribution, facilitate planning of logging locations, and collect accurate information on coal seam geology based on logging.
[0020] Furthermore, the physical strength, mechanical property testing and gravitational acceleration in step 3 are all accurate to 10 -3 .
[0021] Beneficial effect: Simulation requires higher precision, but excessively high precision increases the computing power burden exponentially, so adaptive precision settings can achieve a balance between computing power and demand.
[0022] Furthermore, after the virtual three-dimensional coal seam model is bound in step four, the logging drilling trajectory is restored, and the marked coal-rock occurrence information and geological anomaly information position are corrected based on the output logging drilling trajectory to update the virtual three-dimensional coal seam model.
[0023] Beneficial effects: Although logging is used as a standard for basic information collection, it is also a curved trajectory during the drilling process, which will cause the actual data marking points to shift. Therefore, it is necessary to perform inversion after binding the physical strength and mechanical properties to restore the actual logging trajectory, thereby correcting the virtual three-dimensional coal seam.
[0024] Furthermore, the construction parameters in step 4 include but are not limited to the hole opening position, drilling orientation, inclination, coal hole depth, coal penetration hole depth and hole depth.
[0025] Beneficial effect: By generating construction parameters, construction deployment can be facilitated and the intensity of manual calculation of related parameters can be reduced.
[0026] Furthermore, during the drilling trajectory generation process, the drilling process is divided into a number of length nodes, and the drilling trajectory is generated and spliced in sequence using the length nodes as units.
[0027] Beneficial effect: During the drilling process, the deviation of the drill bit will change the geological contact and stress conditions. Therefore, the node calculation method is used in the calculation. Each trajectory calculation within the length node takes the end of the previous node as the starting point to ensure the accuracy of the simulation.
[0028] Furthermore, the boundaries of coal seams, rock strata, and geological anomalies are all located at the ends of length nodes.
[0029] Beneficial effects: The boundaries of coal seams, rock strata and geological anomalies are all located at the ends of length nodes, which can reduce the calculation error at a single length node and reduce the difficulty of calculation.
[0030] Furthermore, the drilling trajectory is corrected based on the interpolation algorithm during the drilling trajectory generation process.
[0031] Beneficial effect: The generated trajectory is composed of several micro-trajectories, which are not related to each other, so the smoothness is low. The interpolation algorithm can correct the trajectory, improve the continuity of the overall trajectory, and even improve the accuracy of the trajectory.
[0032] Furthermore, the interpolation algorithm is composed of a trained BP network, which is trained based on the drilling trajectory training model. The BP network is used to add interpolation points in the length node, and the coordinates of the interpolation points are:
[0033]
[0034] Where i is the i-th interpolation point, a is the starting point of the trajectory in the current length node, b is the end point of the trajectory in the current length node, α1 is the inclination angle of the xz plane trajectory projection in the current length node, β1 is the interpolation angle of the xz plane trajectory projection in the current length node, α2 is the inclination angle of the yz plane trajectory projection in the current length node, β2 is the interpolation angle of the yz plane trajectory projection in the current length node, and n is the total number of interpolation points.
[0035] Beneficial effects: The interpolation algorithm based on BP network can simulate the trajectory through machine learning. Compared with the common interpolation algorithm, it is corrected through the empirical model, so that its correction result can break away from the limitations brought by the minimum step distance to achieve better accuracy improvement. The interpolation point is set within the length node through the formula to optimize the drilling trajectory curve.
[0036] Furthermore, in step 4, after generating multiple drilling trajectories, the volume of the blank zone extracted between the marked drilling trajectories is calculated.
[0037] Beneficial effects: Gas extraction is carried out by multiple boreholes to ensure that the extraction blank zone can be reduced and the gas extraction volume can be increased. As the borehole density increases, the extraction blank zone will decrease, but the workload will also increase significantly. Therefore, a reasonable density and borehole planning can achieve the best effect by combining the extraction blank zone and workload. Based on the single-hole extraction radius and simulation in the virtual three-dimensional coal seam model, the size of the extraction blank zone between the borehole trajectories can be calculated to assist users in making reasonable drilling density and drilling trajectory planning.
[0038] Furthermore, in step 5, the directional offset and offset probability of the blank zone are extracted, and the expected volume of the blank zone is calculated.
[0039] Beneficial effects: Since there are differences between actual applications and simulations in virtual three-dimensional coal seam models, multiple calculations are performed on blank zone planning with the help of simulation tests to obtain the relationship between the blank zone changes based on the borehole offset and offset probability, thereby calculating the expected volume of the blank zone. Users can plan drilling based on the expected volume of the blank zone.
[0040] Furthermore, in step five, the distribution probability of the drilled products at each drilling depth is output based on the simulation test.
[0041] Beneficial effect: After outputting the distribution probability of the drilled products at each drilling depth, during construction, construction personnel can analyze the accuracy of the simulation in the virtual three-dimensional coal seam model based on the drilling products, and promptly reflect the fit between the construction and the simulation, so as to promptly discover construction errors or simulation distortions so as to make timely modifications to reduce losses.
[0042] Furthermore, in step five, when the distribution probability of the drilled products at each drilling depth is output, the time node at which the drilled products are transported to the ground is inverted based on the depth.
[0043] Beneficial effect: When drilling, the rock cuttings produced by the drill bit will return to the ground through the annular space outside the drill pipe, but there is a certain transportation time difference. Therefore, when outputting the drilling product information, the time difference of returning to the ground needs to be added so that construction personnel can better understand and compare the fit between construction and simulation. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 It is a logical schematic diagram of an embodiment of the present invention.
[0045] Figure 2 This is a logical diagram of step 4 of an embodiment of the present invention.
[0046] Figure 3 This is a logical diagram of step five of an embodiment of the present invention. DETAILED DESCRIPTION
[0047] The following is further described in detail through specific implementation methods:
[0048] The embodiment is basically as shown in the attached Figure 1 To Attachment Figure 3 As shown:
[0049] A three-dimensional image-based gas extraction drilling construction scheme design method, comprising:
[0050] Step 1: Use seismic waves to detect the distribution of coal seam thickness, plan well logging, collect information on coal seams through several well logging, mark the areas where drill stuck, rock visible, gas eruption and water discharge occur during logging drilling as geological anomaly areas, obtain coal-rock occurrence information and geological anomaly information, and mark the coal-rock sections.
[0051] Before building a 3D model, it is necessary to collect information about the coal seam so that the 3D model has a certain degree of restoration capability. Seismic waves use the path, time and wave field of seismic waves excited by artificial seismic sources to propagate in underground rock formations to detect the geometric and physical properties of underground rock formations, such as burial depth and shape. Then, drilling is performed at several points through well logging to obtain detailed information and improve the model restoration degree.
[0052] Step 2: Prepare the trained convolutional neural network. The convolutional neural network is trained based on the coal-rock structure training model. The convolutional neural network is used to generate a virtual three-dimensional coal seam model based on the labeled coal-rock occurrence information and geological anomaly information.
[0053] Although a lot of relevant information can be obtained after the detection in step 1, it is still impossible to restore geological details when constructing a virtual 3D coal seam model. Convolutional neural network model generation is one of the 3D geological modeling methods. By mining the geological laws hidden in the big data of geosciences through geoscience artificial intelligence technology, it can supplement geological details and improve the refinement of the model, thus providing a basis for subsequent trajectory simulation.
[0054] Step 3: Conduct physical strength and mechanical property tests on coal seams, rock strata, geological anomalies and drilling tools, and collect gravity acceleration in the coal seam area. The physical strength, mechanical property tests and gravity acceleration are all accurate to 10 -3 .
[0055] Well logging is used to collect samples from coal seams, rock strata, and geological anomalies, and then sent to the laboratory to test their physical strength and mechanical properties, so as to fill in simulation parameters in the virtual three-dimensional coal seam model. The same test is performed on the drilling tools in the rotating hole to complete the collection of simulation parameters.
[0056] Step 4: Bind the detected physical strength, mechanical property information and gravity acceleration to the virtual 3D coal seam model, restore the logging drilling trajectory, and correct the annotated coal-rock occurrence information and geological anomaly information position based on the output logging drilling trajectory, and update the virtual 3D coal seam model. Input the drilling site information, and the virtual 3D coal seam model is calculated based on the preset formula to generate the drilling trajectory and construction parameters. The construction parameters include but are not limited to the opening position, drilling orientation, inclination, coal-seeing hole depth, coal-penetrating hole depth and hole depth.
[0057] Bind the detected data into the virtual three-dimensional coal seam model. First, perform inversion and restoration of well logging. Although well logging is a standard for basic information collection, it is also a curved trajectory during the drilling process, which will cause the actual data annotation points to be offset. Therefore, it is necessary to perform inversion after binding the physical strength and mechanical properties to restore the real well logging trajectory, thereby correcting the virtual three-dimensional coal seam. Then, based on the corrected virtual three-dimensional coal seam, perform drilling simulation and plan the construction process. It can perform mechanical simulation and simulate the drilling trajectory. To restore the real drilling trajectory. During the drilling process, the actual drilling trajectory is a curve. Due to the friction between the drill bit and the coal seam and rock formation, gravity and other factors during the drilling process, the borehole will deviate, and as the depth increases, the torque increases, and the deviation will become more and more obvious. Due to different geological compositions, the deviation of the drill bit in different geological environments is also different. Therefore, after binding the physical strength and mechanical properties to the virtual three-dimensional coal seam model, a simulation trajectory that is more in line with the actual drilling trajectory can be generated.
[0058] In addition to assisting users in formulating construction plans, the virtual 3D coal seam model can also demonstrate plans to frontline operators, considering that frontline operators in coal mines generally have low educational qualifications. The 3D graphical construction plan can reduce the difficulty for workers to understand and improve construction efficiency.
[0059] During the drilling trajectory generation process, the drilling process is divided into several length nodes, and the drilling trajectory is generated and spliced in units of length nodes. The boundaries of coal seams, rock strata, and geological anomalies are all located at the end of the length nodes. During the drilling trajectory generation process, the drilling trajectory is corrected based on the interpolation algorithm. The interpolation algorithm is composed of a trained BP network. The BP network is trained based on the drilling trajectory training model. The BP network is used to add interpolation points in the length nodes. The coordinates of the interpolation points are:
[0060]
[0061] Where i is the i-th interpolation point, a is the starting point of the trajectory in the current length node, b is the end point of the trajectory in the current length node, α1 is the inclination angle of the xz plane trajectory projection in the current length node, β1 is the interpolation angle of the xz plane trajectory projection in the current length node, α2 is the inclination angle of the yz plane trajectory projection in the current length node, β2 is the interpolation angle of the yz plane trajectory projection in the current length node, and n is the total number of interpolation points.
[0062] During the drilling process, the deviation of the drill bit will change the geological contact and stress conditions. Therefore, the node calculation method is used in the calculation. Each trajectory calculation within a length node starts from the end of the previous node to ensure the accuracy of the simulation. The boundaries of coal seams, rock strata, and geological anomalies are all located at the end of the length node, which can reduce the calculation error at a single length node and reduce the difficulty of calculation.
[0063] The interpolation algorithm is an algorithm used in CNC machining to reduce the approximation error. It reduces the approximation error by adding interpolation points to the middle section of the cutting to correct the arc when forming the arc surface. It is applied to the correction of the drilling trajectory to reduce the error caused by the node degree limitation of the length node, making the trajectory smoother and closer to the actual trajectory. Conventional interpolation algorithms have certain limitations, requiring higher computing power and low smoothness. The interpolation algorithm trained based on the BP network can adapt to complex curve models and has a stronger ability to correct interpolation errors. It can effectively solve the discontinuity problem of adjacent nodes caused by segmented interpolation, and has a smaller computing power burden, which can shorten the interpolation cycle. Placing the interpolation point in the length node can improve the amplitude in a single length node, thereby improving the trajectory fit.
[0064] Step 5: Intercept the attached area of the drilling offset trajectory of the virtual three-dimensional coal seam model, conduct several coal seam structure simulation tests in the attached area based on the convolutional neural network, generate the drilling offset trajectory with the same construction parameters under different coal seam structure simulations, compare the simulation test results with the original trajectory, and show the relationship between the offset amount and the offset probability at different drilling depths.
[0065] There is a gap between the simulation process and the actual situation, which is specifically reflected in the accuracy of the virtual three-dimensional coal seam construction and the simulation of the drilling trajectory. The accuracy of the virtual three-dimensional coal seam construction will inevitably deviate, and the friction caused by the friction between the drill bit and the coal seam and rock layer in the drilling trajectory is in a random direction, and the deviation direction cannot be completely determined. Therefore, in order to make the scheme more executable, accurate and practical, the probabilistic randomness of the convolutional neural network can be used to build multiple simulation models based on the collected information, and conduct multiple drilling trajectory simulation tests to obtain the probability distribution of different drilling trajectories. The test results can be reflected in the trajectory distribution of multiple drillings under different refined geological structures, so that users can perform trajectory analysis based on probability distribution, and thus formulate drilling plans with high success rate, stability and fault tolerance. Intercepting the attachment area of the drilling offset trajectory of the virtual three-dimensional coal seam model can reduce the computing power requirements of the convolutional neural network and reduce the difficulty of implementation.
[0066] In step 4, after generating multiple drilling trajectories, the volume of the blank zone between the marked drilling trajectories is calculated based on the drilling trajectories bound to the corresponding single-hole extraction range.
[0067] Gas extraction is carried out by multiple boreholes to ensure that the extraction blank zone can be reduced and the gas extraction volume can be increased. As the borehole density increases, the extraction blank zone will decrease, but the workload will also increase significantly. Therefore, a reasonable density and drilling planning can achieve the best effect by combining the extraction blank zone and workload. Based on the single-hole extraction radius and simulation in the virtual three-dimensional coal seam model, the size of the extraction blank zone between the drilling trajectories can be calculated to assist users in making reasonable drilling density and drilling trajectory planning.
[0068] In step 5, the directional offset and offset probability of the blank zone are extracted, and the expected volume of the blank zone is calculated.
[0069] Since there are differences between actual applications and simulations in virtual 3D coal seam models, multiple calculations are performed on blank zone planning with the help of simulation tests to obtain the relationship between the blank zone changes based on the borehole offset and offset probability, thereby calculating the expected volume of the blank zone. Users can plan drilling based on the expected volume of the blank zone.
[0070] In step five, the distribution probability of the drilled products at each drilling depth is output based on the simulation test.
[0071] After outputting the distribution probability of the drilled products at each drilling depth, during construction, construction personnel can analyze the accuracy of the simulation in the virtual three-dimensional coal seam model based on the drilling products, and promptly reflect the fit between the construction and the simulation. They can promptly discover construction errors or simulation distortions so that they can be modified in time to reduce losses.
[0072] In step five, when outputting the distribution probability of the drilled products at each borehole depth, the time node at which the drilled products are transported to the ground is inverted based on the depth.
[0073] When drilling, the rock cuttings produced by the drill bit will return to the ground through the annular space outside the drill pipe, but there is a certain transportation time difference. Therefore, the time difference of returning to the ground needs to be added when outputting the drilling product information so that construction personnel can better understand and compare the fit between construction and simulation. During construction, they can directly compare the time node products for fit verification without additional calculation.
[0074] After the construction plan is designed, a probability distribution map of the overall extraction range and blank zone is generated to assist users in evaluating the overall design effect of the construction plan, and to facilitate users to compare the advantages and disadvantages of different construction plans, so as to optimize and adjust the construction plan or select the best construction plan.
[0075] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.
Claims
1. A three-dimensional image-based gas extraction drilling construction scheme design method, Features: include: Step 1: Collect information about coal seams through several well logging, obtain coal-rock occurrence information and geological anomaly information, and mark coal-rock sections; Step 2: preparing a trained convolutional neural network, the convolutional neural network is trained based on the coal-rock structure training model, and the convolutional neural network is used to generate a virtual three-dimensional coal seam model based on the annotated coal-rock occurrence information and geological anomaly information; Step 3: Conduct physical strength and mechanical property tests on coal seams, rock strata, geological anomalies and drilling tools, and collect gravity acceleration in the coal seam area; Step 4: Bind the detected physical strength, mechanical property information and gravity acceleration to the virtual 3D coal seam model, input the drilling site information, and the virtual 3D coal seam model is calculated based on the preset formula to generate the drilling trajectory and construction parameters; Step 5: Intercept the attached area of the drilling offset trajectory of the virtual three-dimensional coal seam model, conduct several coal seam structure simulation tests in the attached area based on the convolutional neural network, generate the drilling offset trajectory with the same construction parameters under different coal seam structure simulations, compare the simulation test results with the original trajectory, and show the relationship between the offset amount and the offset probability at different drilling depths.
2. According to the three-dimensional image gas extraction drilling construction plan design method of claim 1, Features: In step one, seismic waves are first used to detect the distribution of coal seam thickness, and well logging is planned. The areas where drill stuck, rock is seen, gas eruption, and water is produced during the logging drilling process are marked as geological anomaly areas.
3. According to the three-dimensional image gas extraction drilling construction plan design method of claim 2, Features: In step 3, the physical strength, mechanical properties and gravitational acceleration are all accurate to 10 -3 .
4. According to the three-dimensional image gas extraction drilling construction plan design method of claim 3, Features: After binding the virtual three-dimensional coal seam model in step 4, the logging drilling trajectory is restored, and the marked coal-rock occurrence information and geological anomaly information position are corrected based on the output logging drilling trajectory to update the virtual three-dimensional coal seam model.
5. According to the three-dimensional image gas extraction drilling construction plan design method of claim 4, Features: The construction parameters in step 4 include but are not limited to the hole opening position, drilling orientation, inclination, coal hole depth, coal penetration hole depth and hole depth.
6. According to the three-dimensional image gas extraction drilling construction plan design method of claim 5, Features: During the drilling trajectory generation process, the drilling process is divided into several length nodes, and the drilling trajectory is generated and spliced in sequence using the length nodes as units.
7. The three-dimensional image-based gas extraction drilling construction scheme design method according to claim 6, Features: The boundaries of coal seams, rock strata, and geological anomalies are all located at the ends of length nodes.
8. The three-dimensional image-based gas extraction drilling construction scheme design method according to claim 7, Features: The drilling trajectory is corrected based on the interpolation algorithm during the drilling trajectory generation process.
9. The three-dimensional image-based gas extraction drilling construction scheme design method according to claim 8, Features: The interpolation algorithm consists of a trained BP network, which is trained based on the drilling trajectory training model. The BP network is used to add interpolation points in the length node. The coordinates of the interpolation points are: Where i is the i-th interpolation point, a is the starting point of the trajectory in the current length node, b is the end point of the trajectory in the current length node, α 1 is the inclination angle of the xz plane trajectory projection in the current length node, β 1 The interpolation angle of the xz plane trajectory projection within the current length node, α 2 is the projection inclination of the yz plane trajectory in the current length node, β 2 The interpolation angle of the yz plane trajectory projection within the current length node, where n is the total number of interpolation points.
10. The three-dimensional image-based gas extraction drilling construction scheme design method according to claim 9, Features: In step 4, after generating multiple drilling trajectories, the volume of the blank zone between the marked drilling trajectories is calculated.
11. The three-dimensional image-based gas extraction drilling construction scheme design method according to claim 10, Features: In step 5, the directional offset and offset probability of the blank zone are extracted, and the expected volume of the blank zone is calculated.
12. The three-dimensional image-based gas extraction drilling construction scheme design method according to claim 11, Features: In step five, the distribution probability of the drilled products at each drilling depth is output based on the simulation test.
13. The three-dimensional image-based gas extraction drilling construction scheme design method according to claim 12, Features: In step five, when outputting the distribution probability of the drilled products at each borehole depth, the time node at which the drilled products are transported to the ground is inverted based on the depth.
Citation Information
Patent Citations
Mining overlying strata gas accumulation area space identification method and system
CN110334432A
Coal mine gas drainage hole drilling logging geological structure detection method
CN114280676A
Construction and dynamic analysis method and device for high-precision three-dimensional geological model of coal mine
CN115308812A
Intelligent design and three-dimensional visualization method for gas extraction drilling parameters
CN115544894A
Intelligent design method for floor crossing drill hole for correcting drill hole deviation
CN116484749A
Cited By
Intelligent design system for high-position gas extraction drilling
CN119598565A
Method for designing three-dimensional visualized gas drainage borehole construction scheme
WO2026011938A1
