Middle-deep layer geothermal well drilling self-adaptive variable-diameter drilling process based on intelligent regulation and control

Abstract

The invention relates to the technical field of well drilling, and discloses a medium-deep layer geothermal well drilling self-adaptive variable-diameter drilling process based on intelligent regulation and control, which comprises the following steps: S1, before well drilling, collecting stratum geological characteristic data of a well drilling area through a stratum geological data acquisition system; s2, optimizing a drilling path by using an artificial intelligence algorithm according to the stratigraphic geological data, and determining initial drilling parameters; and S3, in the drilling process, on the basis of the real-time drilling parameters, the stratum information and the drill bit abrasion data, an intelligent regulation and control system is adopted to adjust variable diameter parameters in the drilling technology. By combining an artificial intelligence algorithm and an intelligent regulation and control system, a drilling path and process parameters can be optimized in real time, so that the drilling process is more efficient and accurate. By means of stratum geological data and real-time sensor feedback in the drilling process, the system can adjust drill bit reducing and drilling parameters in a self-adaptive mode, the drilling operation speed and the drilling quality are remarkably improved, and errors or low-efficiency operation caused by stratum changes in the drilling process is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling, and in particular to an adaptive variable-diameter drilling process for mid-deep geothermal drilling based on intelligent regulation. Background Art

[0002] In the traditional deep-layer geothermal drilling process, the optimization of drilling paths and process parameters depends on experience and manual judgment, and is often difficult to achieve real-time and precise control due to the complexity and unpredictability of geological conditions. During drilling operations, changes in the formation can lead to problems such as reduced drilling speed, increased drill bit wear, and unstable drilling quality, which directly affect drilling efficiency and cost. In addition, the existing drilling technology cannot effectively respond to changes in the formation when facing complex geological environments, resulting in large uncertainties and errors in the drilling process, affecting the stability and continuity of operations. Although some advanced technologies use sensors to monitor real-time data during drilling, these systems often lack intelligent feedback mechanisms and cannot adaptively adjust drilling paths and process parameters according to dynamic changes in the formation. Therefore, how to achieve efficient control of the drilling process, reduce drill bit wear, improve operation stability, and reduce costs are still difficult problems that need to be solved by current technologies.

[0003] To this end, those skilled in the art have proposed an adaptive variable-diameter drilling process for mid-deep geothermal drilling based on intelligent regulation to solve the above problems. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an adaptive variable-diameter drilling process for mid-deep geothermal drilling based on intelligent regulation, which solves the problems raised in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A medium-deep geothermal drilling adaptive variable diameter drilling process based on intelligent regulation, comprising the following steps: S1. Before drilling, the formation geological characteristic data of the drilling area is collected through the formation geological data acquisition system; S2. Based on the formation geological data, the drilling path is optimized using artificial intelligence algorithms to determine the initial drilling parameters; S3. During the drilling process, based on real-time drilling parameters, formation information and drill bit wear data, an intelligent control system is used to adjust the variable diameter parameters in the drilling process; S4, monitor the formation resistance changes around the drill bit through real-time sensors, and combine machine learning algorithms to make real-time adaptive adjustments to the variable diameter parameters during drilling; S5. When the drilling depth exceeds the preset threshold, the intelligent system automatically adjusts the drill bit diameter to cope with the changes in the characteristics of different formations; S6. After the drilling is completed, the data of the entire drilling process is obtained through inverse analysis method to evaluate the adaptability of the entire drilling process and further optimize future drilling operations.

[0006] Preferably, the formation geological data acquisition system in step S1 includes downhole sensors and surface exploration equipment. The downhole sensors can collect parameters such as formation density, porosity, elastic modulus, compressive strength, formation temperature, and the wear condition of the bit in contact with the formation in real time. The surface exploration equipment conducts auxiliary collection according to the surface geological conditions. The artificial intelligence algorithm in step S2 includes a deep learning model, which automatically adjusts the selection of the drilling path and initial parameters through training on historical drilling data.

[0007] Preferably, the artificial intelligence algorithm in step S2 adopts a method combining deep learning and reinforcement learning to analyze historical drilling data and real-time geological data, so as to predict the best drilling path under different formation conditions and automatically adjust the initial parameters of drilling according to the prediction results, including the type, size, rotation speed, penetration rate of the bit, etc.

[0008] Preferably, the intelligent control system in step 3 includes a drilling data transmission module, a real-time monitoring module, and a data processing module. The data processing module uses a dynamic optimization algorithm to adjust the parameters in the drilling process in real time.

[0009] Preferably, the dynamic optimization algorithm is a multi-objective optimization algorithm based on genetic algorithm. The objective function of the algorithm includes multiple parameters such as drilling speed, bit wear, formation pressure, and energy consumption. The specific algorithm is as follows:

[0010] Among them, $(x)$ is the target value comprehensively obtained according to factors such as drilling speed, bit wear, formation pressure, and energy consumption. $v$ is the drilling speed, indicating the advancing speed of the bit during the drilling process. $w$ is the bit wear, indicating the degree of wear of the bit during the drilling process. $p$ is the formation pressure. $p$ represents the pressure of the underground rock formation. $e$ is the energy consumption, indicating the amount of energy consumed during the drilling process. $, $, and $\alpha$, $\beta$, $\gamma$, and $\delta$ are all weight coefficients.

[0011] Preferably, the real-time sensors in S3 include a bit pressure sensor, a temperature sensor, a displacement sensor, and a vibration sensor. The sensors transmit data to the intelligent control system in real time through a wireless data transmission module. The automatic adjustment method of the bit diameter in S4 includes driving the expansion and contraction of the bit through a servo motor to achieve real-time adjustment of the bit size, and adjusting the driving frequency and force according to the feedback information.

[0012] Preferably, the adjustment process of the bit diameter is optimized based on the relationship between the formation hardness and the bit friction, and is optimized using the following formula:

[0013] where is the current bit diameter, is the adjustment increment, which is calculated based on the formation hardness coefficient and the bit wear condition.

[0014] Preferably, it also includes adjusting the flow rate and viscosity of the drilling fluid during drilling through the intelligent control system. The optimization of the flow rate and viscosity is carried out according to the following formula: = where is the required drilling fluid flow rate, is the rock hardness, is the formation pressure, is the formation temperature, is the porosity, 、 and are empirical constants, which are adjusted according to the fluid requirements of different formation types during drilling.

[0015] Preferably, the real-time sensors in step S5 include a bit pressure sensor, a temperature sensor, a displacement sensor, and a vibration sensor. The sensors transmit data to the intelligent control system in real time through a wireless data transmission module. The sensors can accurately sense the pressure change, temperature fluctuation, displacement change, and vibration signal between the bit and the formation, and transmit the data to the intelligent control system in real time through the wireless data transmission module to ensure that the system can timely obtain and respond to any changes occurring during drilling.

[0016] Preferably, the optimization model in S2 uses the finite element analysis method based on geological information to numerically simulate the stress distribution and deformation under different drilling conditions to obtain the optimal drilling path and parameters.

[0017] The present invention provides an adaptive variable-diameter drilling process for medium-deep geothermal drilling based on intelligent control. It has the following beneficial effects: 1. By integrating artificial intelligence algorithms and intelligent control systems, the present invention can optimize the drilling path and process parameters in real time, making the drilling process more efficient and accurate. Utilizing formation geological data and real-time sensor feedback during drilling, the system can adaptively adjust the bit diameter change and drilling parameters, significantly improving the speed and quality of drilling operations, and reducing errors or inefficient operations caused by formation changes during drilling. At the same time, the use of optimized drilling paths and parameter selection can maintain high stability under complex geological conditions, thereby effectively reducing drilling costs and time.

[0018] 2. By monitoring the bit wear condition in real time and automatically adjusting it in combination with the intelligent control system, the present invention can significantly slow down the wear rate of the bit and extend the service life of the bit. During the drilling process, the intelligent system adjusts parameters such as bit diameter change and the flow rate and viscosity of drilling fluid according to real-time data, thereby reducing the friction between the bit and the formation, reducing the wear of the bit, and avoiding frequent bit replacement and maintenance caused by excessive wear. Such intelligent control technology not only reduces production costs, but also improves the use efficiency of equipment and reduces drilling maintenance and downtime.

[0019] 3. By deeply integrating the intelligent control system and machine learning algorithms, the present invention has a high degree of adaptability. Through the formation data and sensor feedback collected in real time, the system can dynamically adjust various parameters during the drilling process to adapt to changes in different formations and drilling environments. This adaptability enables the drilling operation to be flexibly adjusted under different geological conditions, not only improving the stability and safety of the operation, but also greatly enhancing the intelligent level of the drilling system, laying a foundation for future high-efficiency and precise drilling technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is the general flow chart of the present invention; Figure 2 is the flow chart of the intelligent control system of the present invention; Figure 3 is the flow chart of bit diameter change adjustment and drilling fluid optimization of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] Embodiment 1 Please refer to the attached Figure 1 - attached Figure 3, an embodiment of the present invention provides an adaptive variable-diameter drilling process for medium-deep geothermal wells based on intelligent regulation, including the following steps: S1. Before drilling, collect formation geological characteristic data of the drilling area through a formation geological data acquisition system; The formation geological data acquisition system includes downhole sensors and surface exploration equipment. The downhole sensors can collect parameters such as formation density, porosity, elastic modulus, compressive strength, formation temperature, and wear conditions of the bit in contact with the formation in real time. The surface exploration equipment conducts auxiliary collection according to the surface geological conditions. The artificial intelligence algorithm in the S2 step includes a deep learning model, which automatically adjusts the selection of the drilling path and initial parameters through training on historical drilling data.

[0023] Specifically, in order to ensure the smooth progress of the drilling process and avoid unexpected problems, it is necessary to collect the geological characteristic data of the drilling area. It includes the following contents: Formation density, which reflects the weight of the rock layer, is related to the composition and porosity of the rock, and can help judge the nature of the underground structure.

[0024] Porosity, that is, the proportion of voids in the rock, affects whether fluids (such as oil and gas) can flow or be stored.

[0025] Elastic modulus, which is used to describe the elasticity of the rock layer and determines the response of the rock layer to the drilling tool.

[0026] Compressive strength: that is, the pressure-bearing capacity of the rock layer.

[0027] Formation temperature: helps judge the underground thermal environment conditions.

[0028] S2. According to the formation geological data, use an artificial intelligence algorithm to optimize the drilling path and determine the initial drilling parameters; The artificial intelligence algorithm adopts a method combining deep learning and reinforcement learning to analyze historical drilling data and real-time geological data, thereby predicting the optimal drilling path under different formation conditions and automatically adjusting the initial parameters of drilling according to the prediction results, including the type, size, rotation speed, penetration rate, etc. of the bit.

[0029] The optimization model adopts a finite element analysis method based on geological information to numerically simulate the stress distribution and deformation conditions under different drilling conditions to obtain the optimal drilling path and parameters.

[0030] Specifically, in step S2, an artificial intelligence algorithm is used to optimize the drilling path. Specifically, the artificial intelligence adopts a method that combines deep learning and reinforcement learning. Through the training of historical drilling data, the deep learning model can understand the complex patterns involved in the drilling process. These historical data include cases of successful and failed drilling under different geological conditions. The model learns how to cope with different types of formations and different drilling conditions through these data, so as to predict the optimal drilling path. The reinforcement learning method automatically optimizes and adjusts by simulating the effects of different drilling paths and parameter combinations. The reinforcement learning model can continuously self-adjust according to the real-time collected geological data to find the most favorable drilling path.

[0031] S3. During the drilling process, based on real-time drilling parameters, formation information, and bit wear data, an intelligent control system is used to adjust the variable diameter parameters in the drilling process; The intelligent control system includes a drilling data transmission module, a real-time monitoring module, and a data processing module. The data processing module uses a dynamic optimization algorithm to adjust the parameters in the drilling process in real time.

[0032] Specifically, the intelligent control system is composed of multiple modules, and each module is responsible for different functions to ensure that the entire system can cooperate efficiently to achieve the purpose of dynamically optimizing the drilling process. Specifically, it includes the following main modules: The drilling data transmission module is responsible for transmitting various data generated during the drilling process to the control system in the background in real time. The data includes information such as the drilling depth, bit load, rotation speed, pressure, temperature, etc. The real-time nature of data transmission is crucial because many situations during the drilling process are dynamically changing, and the system needs to obtain this information in a timely manner to make a quick response.

[0033] The real-time monitoring module can monitor various data during the drilling process to help the system understand the working status of the drilling equipment and formation information. For example, it can monitor the bit wear condition, formation hardness change, pressure change, etc. When certain indicators are detected to be abnormal, the monitoring module will send an alarm to the system, indicating that the drilling process needs to be adjusted.

[0034] The data processing module is responsible for processing and analyzing the collected data. Through advanced algorithms, the data processing module can evaluate the parameters in the drilling process in real time and perform dynamic optimization and adjustment according to factors such as formation conditions and bit wear. Using the dynamic optimization algorithm, the system can adjust the drilling parameters according to the continuously changing conditions, such as adjusting the rotation speed, pressure, feed rate of the bit, etc., thereby optimizing the drilling efficiency and extending the service life of the bit.

[0035] The advantages of the intelligent control system are as follows: Improve the drilling efficiency. The intelligent control system can monitor the changes of various parameters in real time during the drilling process and adjust the drilling technology in a timely manner, so that the drilling operation is always in the optimal state, thereby improving the drilling efficiency and shortening the operation time.

[0036] Prolong the service life of the drill bit. By dynamically optimizing the parameters, the system can reduce unnecessary wear and ensure that the drill bit can maintain a good working state for a long time, reducing the maintenance cost of the equipment.

[0037] Reduce the operation risk. Real-time monitoring and adjustment can effectively avoid equipment failures or safety accidents caused by improper parameters, reducing the operation risk.

[0038] Adapt to complex formations. The complexity and variability of the formations require continuous adjustment of drilling parameters. The intelligent control system can make rapid adjustments according to the actual situation to ensure that the drilling operation adapts to the challenges of different formations.

[0039] The dynamic optimization algorithm is a multi-objective optimization algorithm based on the genetic algorithm. The objective function of the algorithm includes multiple parameters such as drilling speed, drill bit wear, formation pressure, and energy consumption. The specific algorithm is as follows:

[0040] Among them, $(x)$ is the target value obtained by comprehensively considering factors such as drilling speed, drill bit wear, formation pressure, and energy consumption. $v$ is the drilling speed, indicating the advancing speed of the drill bit during the drilling process. $w$ is the drill bit wear, indicating the degree of wear of the drill bit during the drilling process. $p$ is the formation pressure. $p$ represents the pressure of the underground rock formation. $e$ is the energy consumption, indicating the amount of energy consumed during the drilling process. $, $, and are all weight coefficients.

[0041] The real-time sensors include a drill bit pressure sensor, a temperature sensor, a displacement sensor, and a vibration sensor. The sensors transmit data to the intelligent control system in real time through a wireless data transmission module. The automatic adjustment method of the drill bit diameter change in S4 includes driving the expansion and contraction of the drill bit through a servo motor to realize real-time adjustment of the drill bit size, and adjusting the driving frequency and force according to the feedback information.

[0042] The adjustment process of the drill bit diameter change is based on the relationship between the formation hardness and the drill bit friction, and is optimized using the following formula:

[0043] Among them, is the current bit diameter, is the adjustment increment, calculated based on the formation hardness coefficient and bit wear condition.

[0044] S4. Monitor the change of formation resistance around the bit through real-time sensors, and combine with machine learning algorithms to perform real-time adaptive adjustment of the variable diameter parameters during the drilling process; The real-time sensors include a bit pressure sensor, a temperature sensor, a displacement sensor, and a vibration sensor. The sensors transmit data to the intelligent control system in real time through a wireless data transmission module. The sensors can accurately sense the pressure change, temperature fluctuation, displacement change, and vibration signal between the bit and the formation, and transmit the data to the intelligent control system in real time through the wireless data transmission module to ensure that the system can timely obtain and respond to any changes occurring during the drilling process.

[0045] Specifically, the data collected by all sensors are transmitted to the intelligent control system in real time through a wireless data transmission module. The wireless transmission module ensures that the data of various sensors can be continuously transmitted to the system during the drilling process for real-time processing and response by the system. The advantage of wireless transmission is that it reduces problems such as poor contact and data loss encountered in traditional wired data transmission, and is also convenient for transmitting data in a complex underground operation environment.

[0046] The intelligent control system is responsible for receiving data from the sensors and performing real-time processing. In particular, the system combines machine learning algorithms, which can deeply analyze the data collected by the sensors and historical drilling data, and predict and adjust various parameters during the drilling process.

[0047] Through training on historical drilling data, the machine learning algorithm can extract rules from historical data and predict the optimal drilling parameters under different formation conditions. For example, by analyzing historical data, the system can learn the optimal bit pressure and penetration rate when encountering a certain rock formation. The algorithm combines real-time data and can automatically adjust the drilling parameters to achieve more efficient and safer drilling.

[0048] During the drilling process, the properties of the formation are changing. The variable diameter parameter refers to the change in the size of the bit or the bit diameter. By real-time sensing the change of formation resistance, the machine learning algorithm can dynamically adjust the size and shape of the bit so that the bit can adapt to the changes of different formations. For example, when encountering a hard rock formation, the system will adjust the bit pressure or speed to avoid excessive resistance causing bit wear; while in a softer formation, the system will increase the feed rate to improve the operation efficiency.

[0049] S5. When the drilling depth exceeds the preset threshold, the intelligent system automatically adjusts the bit variable diameter to cope with the change of characteristics of different formations; Specifically, this function of automatically adjusting the bit diameter not only improves the drilling operation efficiency but also significantly reduces the risks during the drilling process. For example, in hard formations, an oversized bit can lead to a too slow drilling speed or premature wear of the bit, affecting the operation cycle. By adjusting the bit size in real time through the intelligent system, not only can the stability of the drilling process be improved, but also energy can be saved, the service life of the bit can be extended, and thus the overall operation cost can be optimized.

[0050] S6. After the drilling is completed, obtain the data of the whole drilling process through the inverse analysis method, evaluate the adaptability of the entire drilling process, and further optimize future drilling operations.

[0051] Specifically, this data-driven feedback mechanism enables the drilling operation to be carried out more precisely and scientifically. By continuously accumulating and analyzing historical drilling data, the intelligent system can gradually improve the drilling parameters and operation plans, continuously increasing the drilling efficiency and gradually reducing the cost. In addition, the inverse analysis method can also be combined with technologies such as machine learning, enabling the system to self-learn and make more accurate decisions during future drilling processes. This closed-loop optimization not only improves the efficiency of a single operation but also provides impetus for the technological progress and innovation of the entire drilling industry.

[0052] It also includes adjusting the flow rate and viscosity of the drilling fluid through an intelligent control system during the drilling process. The optimization of the flow rate and viscosity is carried out according to the following formula: = where is the required drilling fluid flow rate, is the rock hardness, is the formation pressure, is the formation temperature, is the porosity, 、 and are empirical constants, which are adjusted according to the fluid requirements of different formation types during the drilling process.

[0053] Example 2: Performance of the drilling operation in different formations This example aims to prove the effectiveness and advantages of an adaptive variable-diameter drilling process for medium-deep geothermal wells based on intelligent control. Through practical applications and simulation experiments, the drilling efficiency, bit wear degree, energy consumption, formation pressure and other parameters of this process under different formation conditions were compared and analyzed.

[0054] In this example, two typical formation conditions were selected for the drilling operation, namely soft rock formations and hard rock formations. The adaptive variable-diameter drilling process based on the intelligent control system was used in the experiment and compared with the traditional drilling process. The experimental results are shown in Table 1: Table 1 Analysis of experimental results: Drilling speed: In the drilling of soft rock formations and hard rock formations, the drilling speed using the intelligent control process is higher than that of the traditional process. The drilling speed in the soft rock formation has increased by about 21.9%, and in the hard rock formation, it has increased by about 35.8%. This is because the intelligent control system can adjust the bit diameter change and the footage speed in real time to maximize the drilling efficiency.

[0055] Bit wear: In both formations, the bit wear of the intelligent control process is significantly lower than that of the traditional process. The wear in the soft rock formation has been reduced by 53.1%, and in the hard rock formation, it has been reduced by 47.4%. The intelligent control system can adjust the bit diameter change according to the real-time sensor feedback data, thereby reducing wear and extending the service life of the bit.

[0056] Formation pressure: Under the application of the intelligent control process, the formation pressure is better controlled. Especially in the hard rock formation, the formation pressure has been reduced by 5.6%. This is because the intelligent control system can optimize the drilling path according to the real-time monitoring data and reduce the excessive disturbance to the formation.

[0057] Energy consumption: The intelligent control process shows lower energy consumption than the traditional process in both formations. The energy consumption in the soft rock formation has been reduced by 10.3%, and in the hard rock formation, it has been reduced by 6.9%. The intelligent control system can dynamically optimize energy utilization according to the formation information and drilling parameters, reducing unnecessary energy consumption.

[0058] Drilling fluid flow rate: The intelligent control system dynamically adjusts the flow rate of the drilling fluid according to the formation characteristics. The flow rate increases by 20% in the soft rock formation and 5% in the hard rock formation. This shows that the system can effectively optimize the drilling fluid flow rate according to conditions such as formation pressure and temperature, thereby improving the drilling effect.

[0059] Example 3: Optimization of drilling path and parameter adjustment In this example, the drilling paths under different formation conditions are optimized through deep learning and reinforcement learning algorithms based on artificial intelligence. By comparing the changes in the drilling paths before and after optimization, the effectiveness of the intelligent system is verified. The experimental results are shown in Table 2 as follows: Table 2 According to the results in Table 2, it can be seen that after the optimization of the drilling path, the drilling efficiency in both the soft rock formation and the hard rock formation has been significantly improved. The drilling efficiency in the soft rock formation has increased by 21.9%, and in the hard rock formation, it has increased by 35.8%. This improvement is mainly due to the optimized adjustment of the drilling path by the intelligent control system, effectively reducing unnecessary detours.

[0060] The drilling time is also effectively shortened, with a reduction of approximately 15% in soft rock formations and approximately 20% in hard rock formations. By predicting and adjusting the drilling path through a deep learning model, the intelligent control process can significantly shorten the drilling operation time.

[0061] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive variable-diameter drilling process for medium-deep geothermal wells based on intelligent regulation, characterized in that, Including the following steps: S1. Before drilling, collect the formation geological characteristic data of the drilling area through the formation geological data acquisition system; S2. According to the formation geological data, use the artificial intelligence algorithm to optimize the drilling path and determine the initial drilling parameters; S3. During the drilling process, based on the real-time drilling parameters, formation information and bit wear data, use the intelligent control system to adjust the variable diameter parameters in the drilling process; S4. Monitor the change of formation resistance around the bit through real-time sensors, and combine with the machine learning algorithm to perform real-time adaptive adjustment of the variable diameter parameters during the drilling process; S5. When the drilling depth exceeds the preset threshold, the intelligent system automatically adjusts the bit variable diameter to cope with the characteristic changes of different formations; S6. After the drilling is completed, obtain the data of the whole drilling process through the inversion analysis method, evaluate the adaptability of the whole drilling process, and further optimize the future drilling operations.

2. The self - adaptive variable - diameter drilling process for medium - deep geothermal wells based on intelligent regulation according to claim 1, wherein, In the S1 step, the formation geological data acquisition system includes downhole sensors and surface exploration equipment. The downhole sensors can collect parameters such as formation density, porosity, elastic modulus, compressive strength, formation temperature, and the wear condition of the contact between the bit and the formation in real time. The surface exploration equipment conducts auxiliary collection according to the surface geological conditions. In the S2 step, the artificial intelligence algorithm includes a deep learning model, which automatically adjusts the selection of the drilling path and initial parameters through the training of historical drilling data.

3. An adaptive variable-diameter drilling process for medium-deep geothermal wells based on intelligent regulation according to claim 1, characterized in that, In the S2 step, the artificial intelligence algorithm adopts a method combining deep learning and reinforcement learning to analyze the historical drilling data and real-time geological data, so as to predict the best drilling path under different formation conditions, and automatically adjust the initial drilling parameters according to the prediction results, including the type, size, rotation speed, penetration rate, etc. of the bit.

4. A self - adaptive variable - diameter drilling process for medium - deep geothermal wells based on intelligent control according to claim 1, characterized in that, The intelligent control system in the S3 includes a drilling data transmission module, a real-time monitoring module and a data processing module. The data processing module uses a dynamic optimization algorithm to adjust the parameters during the drilling process in real time.

5. The adaptive variable-diameter drilling process for medium-deep geothermal wells based on intelligent regulation according to claim 4, wherein, The dynamic optimization algorithm is a multi-objective optimization algorithm based on the genetic algorithm. The objective function of the algorithm includes multiple parameters such as drilling speed, bit wear, formation pressure, and energy consumption. The specific algorithm is as follows:

6. Among them, The target value of (x) is obtained comprehensively based on factors such as the drilling speed, bit wear, formation pressure, and energy consumption. is the drilling speed, representing the advancing speed of the bit during the drilling process. is the bit wear, representing the degree of wear of the bit during the drilling process, and is the formation pressure. represents the pressure of the underground rock formation. is the energy consumption, representing the amount of energy consumed during the drilling process. , , and are all weight coefficients.

7. A self - adaptive variable - diameter drilling process for medium - deep geothermal wells based on intelligent regulation according to claim 1, characterized in that, The real-time sensors in the S3 include a bit pressure sensor, a temperature sensor, a displacement sensor and a vibration sensor. The sensors transmit the data to the intelligent control system in real time through the wireless data transmission module. The way for the intelligent system in the S4 to automatically adjust the bit variable diameter includes driving the expansion and contraction of the bit through a servo motor to realize the real-time adjustment of the bit size, and adjusting the driving frequency and force according to the feedback information.

8. The adaptive variable-diameter drilling process for medium-deep geothermal wells based on intelligent regulation according to claim 6, characterized in that, The adjustment process of the bit variable diameter is based on the relationship between the formation hardness and the bit friction force, and is optimized by using the following formula:

9. Among them, is the current bit diameter, is the adjustment increment, which is calculated based on the formation hardness coefficient and the bit wear condition.

10. The self - adaptive variable - diameter drilling process for medium - deep geothermal wells based on intelligent regulation according to claim 1, characterized in that, It also includes adjusting the flow rate and viscosity of the drilling fluid during the drilling process. The optimization of the flow rate and viscosity is carried out according to the following formula:

11. Among them is the required drilling fluid flow rate, is the rock hardness, is the formation pressure, is the formation temperature, is the porosity, , and are empirical constants, which are adjusted according to the fluid requirements of different formation types during the drilling process.

12. The adaptive variable diameter drilling process for medium-deep geothermal wells based on intelligent regulation according to claim 1, wherein, The real-time sensors in step S4 include a bit pressure sensor, a temperature sensor, a displacement sensor, and a vibration sensor. The sensors transmit data to the intelligent control system in real time through a wireless data transmission module. The sensors can accurately sense the pressure changes, temperature fluctuations, displacement changes, and vibration signals between the bit and the formation, and transmit the data to the intelligent control system in real time through the wireless data transmission module to ensure that the system can timely obtain and respond to any changes occurring during the drilling process.

13. The self - adaptive variable - diameter drilling process for medium - deep geothermal wells based on intelligent control according to claim 1, characterized in that, The optimization model in S2 uses the finite element analysis method based on geological information to numerically simulate the stress distribution and deformation conditions under different drilling conditions to obtain the optimal drilling path and parameters.

Images