Stratum groutability while drilling evaluation method and system based on deep learning

Abstract

The invention provides a stratum groutability while-drilling evaluation method and system based on deep learning, and relates to the technical field of ground grouting evaluation.The method comprises the steps that a grouting area is determined, and the track and distribution of grouting drill holes are designed; drilling parameters and ground monitoring data in the drilling process and grouting parameters in the grouting process are obtained; the drilling parameters, the ground monitoring data and the grouting parameters are input into a stratum groutability evaluation model, and the predicted stratum grout absorption amount is obtained; wherein the drilling parameters comprise drill bit torque, counter-force data, drilling speed data, temperature data, vibration data and drill bit rotating speed in the drilling process, and the vibration data is obtained by converting a time domain signal into a frequency domain signal from three-axis acceleration of a drill bit through fast Fourier transform and taking an average amplitude value to represent the vibration condition.

Description

Technical Field

[0001] The present disclosure relates to the technical field of ground grouting assessment, and in particular to a method and system for assessing the injectability of a formation while drilling based on deep learning. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Ground grouting technology is a commonly used ground reinforcement technology, which is often used in underground engineering sudden water inrush control, ground pre-reinforcement and other projects. The process of ground grouting treatment includes grouting scheme design → installation of ground drilling and grouting construction equipment → improvement of grouting pipelines → trial operation of grouting system and pipeline pressure test → drilling → water pressure test → formulation of single-hole grouting scheme → improvement of grouting pipelines → grouting → stop grouting when the final pressure and final hole standards are reached → flushing the borehole with clean water → checking the grouting effect.

[0004] In the construction of ground grouting, testing the injectability of the stratum is an important part. The conventional method is to use water pressure test. According to the three-stage water pressure test method adopted in the standard "Drilling Water Pressure Test Regulations" (DZ / T 0132 94), the water pressure test requires washing the hole, lifting the drill, installing the water stop plug, and connecting the water pump. However, the experimental steps are cumbersome and the experimental cycle is long. At the same time, for non-vertical boreholes, such as L-shaped holes, curved trajectory holes and long-distance boreholes, conventional water pressure tests are difficult to conduct. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and system for evaluating the injectability of formations while drilling based on deep learning. By acquiring rock mechanical parameters and rock structure information during the drilling process, a mapping relationship model between the monitoring parameters while drilling and the amount of grouting absorbed by the formation is constructed to realize the evaluation of the injectability of formations while drilling.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions:

[0007] The deep learning-based method for evaluating formation injectability while drilling includes:

[0008] Determine the grouting area and design the trajectory and distribution of grouting holes;

[0009] Obtain drilling parameters and ground monitoring data during the drilling process, and grouting parameters during the grouting process;

[0010] Inputting the drilling parameters, ground monitoring data and grouting parameters into a formation injectability evaluation model to obtain a predicted formation grouting amount;

[0011] Among them, the drilling parameters include drill bit torque, reaction force data, drilling speed data, temperature data, vibration data and drill bit speed during drilling. The vibration data is obtained by converting the time domain signal of the drill bit's three-axis acceleration into a frequency domain signal using fast Fourier transform, and taking the average amplitude to characterize the vibration condition.

[0012] According to some embodiments, the present disclosure adopts the following technical solutions:

[0013] The deep learning-based formation injectability while drilling assessment system includes:

[0014] Data acquisition module, used to determine the grouting area and design the trajectory and distribution of grouting holes;

[0015] Obtain drilling parameters and ground monitoring data during the drilling process, and grouting parameters during the grouting process;

[0016] A prediction module, used for inputting the drilling parameters, ground monitoring data and grouting parameters into a formation injectability evaluation model to obtain a predicted formation grouting amount;

[0017] Among them, the drilling parameters include drill bit torque, reaction force data, drilling speed data, temperature data, vibration data and drill bit speed during drilling. The vibration data is obtained by converting the time domain signal of the drill bit's three-axis acceleration into a frequency domain signal using fast Fourier transform, and taking the average amplitude to characterize the vibration condition.

[0018] According to some embodiments, the present disclosure adopts the following technical solutions:

[0019] A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the deep learning-based formation injectability while drilling assessment method is implemented.

[0020] According to some embodiments, the present disclosure adopts the following technical solutions:

[0021] An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the deep learning-based formation injectability while drilling assessment method.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] The deep learning-based while-drilling assessment method for formation injectability disclosed in the present invention establishes a formation injectability evaluation model through a deep neural network, and takes the formation grouting amount as an evaluation index of the formation injectability. The input parameters of the model include drill bit torque, reaction force, drilling speed, temperature, vibration, drill bit rotation speed, drilling fluid loss rate, drilling fluid loss amount, pump pressure, pump flow, grouting pressure, grouting flow, grouting time and rock integrity (coring) and other parameters. The output parameter of the model is the grouting amount of the formation. The deep neural network is used to automatically analyze and process a large amount of while-drilling data, which reduces the risk of manual operation errors and improves the automation level of the construction process.

[0024] The deep learning-based while-drilling assessment method for formation injectability disclosed in the present invention evaluates the injectability of the formation in real time through while-drilling monitoring data, avoiding tedious steps in water pressure testing, such as hole washing, drill lifting, and installation of water-stop plugs, thereby simplifying the work process, shortening the construction period, and improving construction efficiency.

[0025] The deep learning-based method for evaluating the injectability of formations while drilling is disclosed. Traditional water pressure tests are difficult to carry out in long-distance boreholes, curved boreholes and non-vertical boreholes, while the method disclosed in the present invention can adapt to various complex drilling trajectories, such as L-shaped holes and other non-vertical holes; it can evaluate the injectability of formations in real time, and can guide the adjustment of single-hole grouting schemes and the detection of grouting effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0027] Figure 1 The present invention is a flowchart of a specific implementation process of the method disclosed herein. DETAILED DESCRIPTION

[0028] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0029] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0030] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0031] Example 1

[0032] The present invention discloses a method for evaluating the injectability of a formation while drilling based on deep learning. The method evaluates the injectability of a formation through monitoring data while drilling, avoids cumbersome water pressure test steps, solves the problem that the water pressure test is not applicable to long-distance drilling and curved drilling, and improves the efficiency of ground grouting treatment of broken formations, including:

[0033] Step 1: Determine the grouting area and design the trajectory and distribution of grouting drilling holes;

[0034] Step 2: Obtain drilling parameters and ground monitoring data during the drilling process, and grouting parameters during the grouting process;

[0035] Step 3: input the drilling parameters, ground monitoring data and grouting parameters into the formation injectability evaluation model to obtain the predicted formation grouting amount;

[0036] Among them, the drilling parameters include drill bit torque, reaction force data, drilling speed data, temperature data, vibration data and drill bit speed during drilling. The vibration data is obtained by converting the time domain signal of the drill bit's three-axis acceleration into a frequency domain signal using fast Fourier transform, and taking the average amplitude to characterize the vibration condition.

[0037] As an embodiment, the present invention discloses a method for evaluating the injectability of a formation while drilling based on deep learning. The principle is that when the drill bit drills in the formation, the rock and the drill bit have mechanical contact, and the rock mechanical parameters and rock mass structure information will be reflected in the drill bit's drilling speed, reaction force, torque, vibration and other while drilling parameters. Drilling fluid leakage can also reflect the permeability of formation fractures. By establishing a mapping relationship model between while drilling monitoring parameters and formation slurry absorption, the while drilling evaluation of the injectability of the formation is realized. The specific implementation process is as follows:

[0038] 1. Determine the grouting area based on geological exploration data, geological drilling, and geological disaster evolution, design the trajectory and distribution of grouting drilling holes, select 25% of the holes as test holes, and the remaining 75% of the holes as application holes.

[0039] 2. Use a directional drill for drilling, and install a drilling parameter monitoring module between the downhole power drill and the drill bit to monitor the drill bit torque, reaction force, drilling speed, vibration, temperature, three-axis acceleration, drill bit speed and other data during the drilling process, and transmit them to the ground through the data transmission system.

[0040] 3. Ground monitoring of drilling fluid loss rate, drilling fluid loss volume, pump pressure, pump flow and other data.

[0041] 4. Carry out drilling and water pressure tests on 25% of the test holes, carry out grouting construction, record the grouting pressure, grouting flow, grouting time, slurry viscosity, slurry consolidation time, and calculate the grouting absorption volume of the grouting section.

[0042] 5. Based on the existing deep neural network model, a model is established between the drilling pressure, drill pipe torque, drill pipe vibration, pump pressure, pump flow, drilling speed, compressive strength, rock integrity (coring), drilling fluid loss rate, drilling fluid loss amount, grouting pressure, grouting flow, grouting time, slurry viscosity, consolidation time, grouting amount of the previous formation and other data and the grouting amount of the formation.

[0043] 6. After the model is trained, the formation grouting volume is predicted for the subsequent 75% of the applied boreholes to achieve formation injectability evaluation.

[0044] Directional drilling rigs are used for drilling, and the drill bit, screw motor, and pump are selected according to the needs of the project. There are mature products on the market for near-drill bit parameter monitoring modules, and data transmission uses mud pulse transmission.

[0045] A deep neural network algorithm is used to establish a formation injectability evaluation model, and parameter parameters are obtained through a near-drill bit monitoring device. The input parameters include drill bit torque, reaction force, drilling speed, temperature, vibration, drill bit speed, drilling fluid loss rate, drilling fluid loss amount, pump pressure, pump flow, grouting pressure, grouting flow, grouting time, and rock integrity (coring) during drilling. The above parameters are used to train the model, and the output is the predicted grouting amount of the formation.

[0046] Furthermore, torque (unit: N·m), reaction force (unit: N), and drilling speed (unit: m / s) are monitored and obtained through a near-drill-bit parameter measurement device. Vibration is obtained through a near-drill-bit parameter measurement device to obtain triaxial acceleration, and the time domain signal is converted into a frequency domain signal using a fast Fourier transform. The average amplitude of 0-500 Hz is taken to characterize the vibration. The specific calculation process is as follows:

[0047] Assume that the time domain signals obtained from the near-bit parameter measurement device are x(t), y(t) and z(t), which represent the acceleration in three directions. Perform fast Fourier transform on the time domain signal in each direction to obtain the corresponding frequency domain signals X(f), Y(f), and Z(f):

[0048] X(f)=FFT(x(t))

[0049] Y(f)=FFT(y(t))

[0050] Z(f)=FFT(z(t))

[0051] Furthermore, the average amplitude in the range of 0-500 Hz is calculated for each direction.

[0052]

[0053] Where k = 500, f i is a frequency point in the range of 0 to 500 Hz.

[0054] Furthermore, the drill bit speed (unit: rpm) is calculated by the drill rod speed n1 and the screw motor speed n2.

[0055]

[0056] Among them, the screw motor speed n2 is obtained through the pump displacement and screw motor parameter table.

[0057] Furthermore, the drilling fluid loss rate q1(t) is monitored by placing a liquid level sensor in the mud pool, and the unit is L / s. The drilling fluid loss rate V1 is obtained by integrating the loss rate. The drilling fluid loss V1 in the time interval [t1, t2] can be calculated by the following integral formula:

[0058]

[0059] Furthermore, parameters such as pump pressure (unit: MPa), pump flow (unit: L / s), grouting pressure (unit: MPa), and grouting flow (unit: L / s) are obtained through sensors provided by the equipment.

[0060] Furthermore, the rock mass integrity (coring) depends on whether there is coring drilling near the grouting hole. If there is coring drilling, then

[0061]

[0062] If no core drilling is performed, this value is 0.

[0063] Furthermore, the predicted grouting volume of the formation and the grouting volume of the grouting section can be output and calculated by the grouting flow rate and the grouting time.

[0064]

[0065] Among them, V2 is the amount of grouting absorbed by the formation, t1 and t2 are the start and end time of grouting, and q2 is the grouting flow rate.

[0066] Example 2

[0067] In one embodiment of the present disclosure, a system for evaluating formation injectability while drilling based on deep learning is provided, comprising:

[0068] Data acquisition module, used to determine the grouting area and design the trajectory and distribution of grouting holes;

[0069] Obtain drilling parameters and ground monitoring data during the drilling process, and grouting parameters during the grouting process;

[0070] A prediction module, used for inputting the drilling parameters, ground monitoring data and grouting parameters into a formation injectability evaluation model to obtain a predicted formation grouting amount;

[0071] Among them, the drilling parameters include drill bit torque, reaction force data, drilling speed data, temperature data, vibration data and drill bit speed during drilling. The vibration data is obtained by converting the time domain signal of the drill bit's three-axis acceleration into a frequency domain signal using fast Fourier transform, and taking the average amplitude to characterize the vibration condition.

[0072] Example 3

[0073] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the deep learning-based formation injectability while drilling assessment method is implemented.

[0074] Example 4

[0075] In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the deep learning-based formation injectability while drilling assessment method.

[0076] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A deep learning-based method for assessing formation injectability while drilling, characterized in that: include: Determine the grouting area and design the trajectory and distribution of grouting holes; Obtain drilling parameters and ground monitoring data during the drilling process, and grouting parameters during the grouting process; Inputting the drilling parameters, ground monitoring data and grouting parameters into a formation injectability evaluation model to obtain a predicted formation grouting amount; Among them, the drilling parameters include drill bit torque, reaction force data, drilling speed data, temperature data, vibration data and drill bit speed during drilling. The vibration data is obtained by converting the time domain signal of the drill bit's three-axis acceleration into a frequency domain signal using fast Fourier transform, and taking the average amplitude to characterize the vibration condition.

2. The method for evaluating formation injectability while drilling based on deep learning according to claim 1, characterized in that: The surface monitoring data includes drilling fluid loss rate, drilling fluid loss volume, pump pressure and pump flow rate.

3. The method for evaluating formation injectability while drilling based on deep learning according to claim 1, characterized in that: The grouting parameters during the grouting process include grouting pressure, grouting flow, grouting time, rock integrity, slurry viscosity, consolidation time and grouting volume of the previous stratum.

4. The method for evaluating formation injectability while drilling based on deep learning according to claim 1, characterized in that: The time domain signals x(t), y(t) and z(t) of the three-axis acceleration of the drill bit are monitored and obtained through the near-bit parameter measurement device, which represent the acceleration in three directions respectively. The time domain signal in each direction is subjected to fast Fourier transform to obtain the corresponding frequency domain signal, including: X(f)=FFT(x(t)) Y(f)=FFT(y(t)) Z(f)=FFT(z(t)).

5. The method for evaluating formation injectability while drilling based on deep learning according to claim 1, characterized in that: Calculate the average amplitude in the range 0-500Hz for each direction, including: Where k = 500, f i is a frequency point in the range of 0 to 500 Hz.

6. The method for evaluating formation injectability while drilling based on deep learning according to claim 1, characterized in that: The drill bit speed is calculated by the drill rod speed and the screw motor speed, including: Among them, n1 is the drill pipe rotation speed, n2 is the screw motor rotation speed, and the screw motor rotation speed is obtained through the pump displacement and screw motor parameter table.

7. The method for evaluating formation injectability while drilling based on deep learning according to claim 1, characterized in that: The drilling fluid loss rate is monitored by placing a liquid level sensor in the mud pool. The drilling fluid loss rate is obtained by integrating the loss rate. The drilling fluid loss amount is calculated in the time interval [t1, t2] by the following integral formula: Among them, V1 is the drilling fluid loss loss, and q1(t) is the drilling fluid loss rate.

8. A deep learning-based formation injectability while drilling assessment system, characterized in that: include: Data acquisition module, used to determine the grouting area and design the trajectory and distribution of grouting holes; Obtain drilling parameters and ground monitoring data during the drilling process, and grouting parameters during the grouting process; A prediction module, used for inputting the drilling parameters, ground monitoring data and grouting parameters into a formation injectability evaluation model to obtain a predicted formation grouting amount; Among them, the drilling parameters include drill bit torque, reaction force data, drilling speed data, temperature data, vibration data and drill bit speed during drilling. The vibration data is obtained by converting the time domain signal of the drill bit's three-axis acceleration into a frequency domain signal using fast Fourier transform, and taking the average amplitude to characterize the vibration condition.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the deep learning-based formation injectability while drilling assessment method as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the deep learning-based formation injectability while drilling assessment method as described in any one of claims 1 to 7.

Images