Top drive torsional pendulum parameter control method and device and storage medium

Abstract

The invention relates to the technical field of drilling engineering, in particular to a top drive torsional pendulum parameter control method and device and a storage medium. The method comprises the following steps: based on well track, top drive torque and screw tool pressure difference data, determining a first depth of a neutral point of shaft bottom drill string reaction torque and shaft bottom torque with reserved safety margin; a top drive torque theoretical value is determined by combining the well track, the drill column structure, the well body structure and the operation parameters; establishing a relation model of a torsion angle and a torque, calculating a theoretical total torsion angle, performing field control to obtain an actually measured torque, and minimizing a deviation between the actually measured torque and a material mechanical model calculation value containing an optimizable coefficient through a Bayesian optimization algorithm to obtain an optimized total torsion angle; the optimized angle and other drilling state parameters are input into a control model based on reinforcement learning training, a top drive torsional pendulum angle control instruction is generated, model parameters are continuously updated according to execution feedback, and intelligent calculation and control of torsional pendulum parameters are achieved.

Description

Technical Field

[0001] This application relates to the field of drilling engineering technology, and specifically to a method, device and storage medium for controlling top drive torsional oscillation parameters. Background Technology

[0002] In modern oil and gas exploration and production, top drive (i.e., top-driven drilling rig) is a widely used and important drill pipe drive system that significantly improves drilling capability and efficiency. During directional well sliding drilling, due to the significant frictional resistance between the drill string and the wellbore or casing, the drilling pressure applied from the surface is difficult to effectively transmit to the drill bit, easily leading to sticking. Sticking not only affects cuttings carrying and wellbore cleanliness but also increases the risk of differential pressure stuck pipe. Once the sticking is suddenly released, the accumulated axial force and torque are released instantaneously, causing severe fluctuations in the tool face, exacerbating fatigue damage to downhole tools, and severely restricting drilling efficiency.

[0003] Currently, a common approach to solving such problems is top drive torsion oscillation technology. This technology controls the top drive to periodically twist the drill string left and right, reducing friction and improving pressure transmission. However, existing top drive torsion oscillation technologies rely on subjective experience, requiring manual calculation and setting of parameters. Therefore, they suffer from a lack of real-time adjustment capabilities, large errors, and frequent failures. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, and storage medium for controlling the top drive torsion swing parameters, in order to solve the problem in the prior art where the top drive torsion swing parameters rely on manual experience to set, lack real-time feedback and adaptive adjustment capabilities, resulting in a large deviation between the measured torque and the theoretical prediction.

[0005] To achieve the above objectives, the first aspect of this application provides a method for controlling the parameters of a top drive torsional yaw, comprising: Acquire wellbore trajectory data, top drive torque data, and screw differential pressure data; Based on the screw differential pressure data, the screw motor counter-torque is calculated, and the first depth of the bottom hole torque neutral point with a safety margin is determined. Based on wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, the theoretical value of the top drive torque is calculated according to the soft rod model and the piecewise infinitesimal method. Based on the theoretical value of the top drive torque and the first depth, a relationship model between the torsion angle and the top drive torque is established, and the theoretical total torsion angle is calculated. The theoretical total torsion angle is applied to the on-site top drive control to obtain the measured torque. The deviation between the measured torque and the theoretical torque value calculated by the material mechanics model with optimizable coefficients is minimized by the Bayesian optimization algorithm to obtain the optimized total torsion angle. The drilling state parameters, including the optimized total torsion angle, are input into the control model trained based on the reinforcement learning algorithm to generate the top drive torsion angle control command. The parameters of the control model are updated according to the state feedback after the control command is executed, so as to realize the adaptive closed-loop control of the top drive torsion parameters.

[0006] In this embodiment of the application, calculating the screw motor counter-torque based on screw differential pressure data and determining the first depth of the bottom hole torque neutral point with a safety margin includes: determining the screw motor counter-torque based on the screw differential pressure data, combined with the screw motor efficiency, screw motor displacement per revolution, and screw motor efficiency. The screw motor counter-torque is determined based on the following formula:

[0007] in, For the reverse torque of the screw motor, This refers to the displacement per revolution of the screw motor. For screw motor efficiency, The screw pressure differential data is used; based on the screw motor counter-torque, the torque neutral point depth is determined so that the drill string friction torque from the bottom of the well to the torque neutral point depth is equal to the screw motor counter-torque; a preset safety margin is subtracted from the torque neutral point depth to determine the first bottom-hole torque neutral point depth with a safety margin.

[0008] In this embodiment, the theoretical value of the top drive torque calculated based on the soft rod model and the segmented micro-element method, using wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, includes: acquiring wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, wherein the wellbore trajectory data includes at least well depth, inclination angle, and azimuth angle; the drill string structure data includes at least the outer diameter of the tubing string and its own weight; the wellbore structure data includes at least the segmented wellbore diameter used to confirm the contact relationship; and the operating parameters include at least the circumferential friction coefficient; dividing the drill string into multiple micro-element segments along the well depth direction according to a preset micro-element segment length; acquiring the inclination angle and azimuth angle of each micro-element segment based on the wellbore trajectory data; determining the inclination angle change rate and azimuth angle change rate; and calculating the contact force between each micro-element segment and the wellbore wall based on the axial force at the lower end of the micro-element segment and the component of the tubing string's own weight along the normal direction of the well wall. The contact force is determined based on the following formula:

[0009] in, For contact force, The axial force at the lower end of the infinitesimal segment. The azimuth rate of change The rate of change of well inclination angle. The component of the tubing string's self-weight along the wellbore normal is given. The torque at the top and bottom of the micro-element segment is obtained. Based on the contact force, tubing string outer diameter, and circumferential friction coefficient, the friction torque increment from the first depth to the surface is calculated segment by segment using the micro-element torque transmission formula. These increments are then summed to determine the theoretical value of the top drive torque. The friction torque increment is determined based on the following formula:

[0010] in, The torque at the top of the micro-element segment, This refers to the torque at the bottom of the micro-element segment. The coefficient of friction is the circumferential friction factor. The outer diameter of the tubular column, is the length of the infinitesimal segment.

[0011] In this embodiment of the application, a relationship model between the torsion angle and the top drive torque is established based on the theoretical value of the top drive torque and the first depth. The calculation of the theoretical total torsion angle includes: determining the torsion angle of the micro-segment based on the top torque of the micro-segment, the length of the micro-segment, the shear modulus of the drill string material, and the polar moment of inertia of the drill string, wherein the polar moment of inertia is calculated based on the outer diameter and inner diameter of the drill string; and determining the theoretical total torsion angle by integrating the torsion angle of all micro-segments along the well depth direction from the first depth to the surface.

[0012] In this embodiment, the torsion angle of the micro-element at well depth x is determined based on the following formula:

[0013] in, Let x be the torsion angle of the micro-element at well depth x. The torque at the top of the micro-element segment, The length of the infinitesimal segment. Let be the shear modulus of the drill string material. Let be the polar moment of inertia of the drill string; The polar moment of inertia of the drill string is determined based on the following formula:

[0014] in, The outer diameter of the drill string. The inner diameter of the drill string; The theoretical total torsional angle is determined based on the following formula:

[0015] in, For the theoretical total angle of twist, This is the first depth.

[0016] In this embodiment, the theoretical total torsion angle is applied to the field top drive control to obtain the measured torque. The deviation between the measured torque and the theoretical torque value calculated by the material mechanics model containing optimizable coefficients is minimized using a Bayesian optimization algorithm to obtain the optimized total torsion angle. This process includes: driving the drill string torsion based on the theoretical total torsion angle and acquiring the corresponding measured torque through the top drive torque sensor; establishing an objective function to measure the deviation between the measured torque and the theoretical torque, iteratively adjusting the optimizable coefficients using a Bayesian optimization algorithm to minimize the objective function value; determining the total torsion angle calculation formula based on the optimizable coefficients minimized by the objective function, and calculating the optimized total torsion angle. The optimized total torsion angle is determined based on the following formula:

[0017] in, The optimized total torsion angle, For the first depth, For optimizable coefficients, The torque at the top of the micro-element segment, Let be the shear modulus of the drill string material. Let be the polar moment of inertia of the drill string. is the length of the infinitesimal segment.

[0018] In this embodiment, the drilling state parameters, including the optimized total torsion angle, are input into a control model trained based on a reinforcement learning algorithm to generate a top drive torsion angle control command. The parameters of the control model are then updated based on the state feedback after executing the control command, achieving adaptive closed-loop control of the top drive torsion angle parameters. This includes: using the current drilling state vector as input to a strategy network; outputting the mean and standard deviation of the top drive torsion angle action through the strategy network; and generating continuous torsion angle actions using reparameterization techniques. The drilling state vector includes wellbore trajectory parameters and the optimized total torsion angle output by the Bayesian optimization module. The system calculates the torsional angle; estimates the state value function through a value network, and determines the advantage function based on the state value function and the immediate reward obtained after the action; constructs a trust region objective function based on generalized advantage estimation, and updates the policy network parameters by maximizing the trust region objective function; uses the measured torque, wellbore trajectory parameters, and tool face state obtained after executing the torsional angle action as state feedback for updating the control model parameters in the next round; during the control process, it integrates real-time acquired data and historical operating condition data to construct a two-dimensional experience pool for model training and parameter adjustment, realizing closed-loop updating and control of the top drive torsional angle parameters.

[0019] In this embodiment, the advantage function is constructed based on the state value function:

[0020] in, For the dominant function, The immediate reward obtained after performing an action. For state The value estimate, For state Value estimation; The trust region objective function for maximizing generalized advantage estimation is:

[0021] in, For the trust region objective function, The probability of generating action 'a' for the current policy network. The probability of generating action 'a' for the old policy network. For the clipping function, This is a pruning parameter used to control the step size of policy updates.

[0022] A second aspect of this application provides a top drive torsional yaw parameter control device, comprising: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing instructions, to implement a top-drive yaw parameter control method for either of these.

[0023] A third aspect of this application provides a machine-readable storage medium storing instructions for causing a machine to execute any one of the top drive yaw parameter control methods.

[0024] Through the above technical solution, this application first obtains wellbore trajectory data, top drive torque data, and screw tool differential pressure data; calculates the bottom hole drill string counter-torque based on the screw tool differential pressure data, and determines the first depth of the bottom hole torque neutral point with a safety margin; then, combining the wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, the theoretical value of the top drive torque is calculated using a soft rod model and a piecewise infinitesimal method; subsequently, a relationship model between the torsion angle and the top drive torque is established based on the theoretical value and the first depth, thereby calculating the theoretical total torsion angle; this theoretical total torsion angle is applied to the field top drive control to obtain the measured torque, and the deviation between the measured torque and the theoretical torque value calculated by the material mechanics model containing optimizable coefficients is minimized using a Bayesian optimization algorithm, thereby obtaining the optimized total torsion angle; finally, the drilling state parameters, including the optimized total torsion angle, are input into the control model trained based on a reinforcement learning algorithm, which generates a top drive torsion angle control command, and continuously updates the model parameters based on the state feedback after executing the command, thereby achieving adaptive control of the top drive torsion parameters.

[0025] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0026] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 The illustration shows a schematic flowchart of a top drive torsional yaw parameter control method according to an embodiment of this application; Figure 2 This illustration schematically shows a top drive torsional yaw parameter control method architecture according to an embodiment of this application; Figure 3 The schematic diagram illustrates a structural block diagram of a top drive torsion oscillating parameter control device according to an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0028] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0029] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0030] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0031] Figure 1 The illustration schematically shows a flowchart of a top drive torsional yaw parameter control method according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a method for controlling the top drive torsional yaw parameter, which may include the following steps.

[0032] Step 110: Obtain wellbore trajectory data, top drive torque data, and screw differential pressure data.

[0033] A screw motor is a type of bottom-hole power drilling tool, and its working principle is based on positive displacement hydraulic transmission. When high-pressure drilling fluid flows into the screw motor, a pressure difference is formed between the stator and rotor of the motor, driving the rotor to perform planetary motion within the stator, thereby converting the pressure energy of the fluid into mechanical energy and driving the drill bit to rotate. In the embodiments of this application, wellbore trajectory data is acquired in real time by MWD (Measurement While Drilling) sensors, including well depth, inclination angle, and azimuth angle; top drive torque data is acquired in real time by a torque sensor installed on the top drive spindle; screw differential pressure data is acquired by pressure sensors installed at the inlet and outlet of the screw motor, and combined with the drilling fluid discharge to determine the working status of the bottom-hole power drilling tool.

[0034] Step 120: Based on the screw differential pressure data, calculate the screw motor counter-torque and determine the first depth of the bottom hole torque neutral point to retain a safety margin.

[0035] In this embodiment, based on the working principle of the screw motor, the processor calculates and determines the screw motor's counter-torque by combining the screw motor's differential pressure data with its efficiency, displacement per revolution, and other parameters. Then, the torque distribution on the drill string is calculated segment by segment from the bottom of the well upwards. When the cumulative frictional torque at a certain depth of the drill string equals the screw motor's counter-torque, that location is the bottom-hole torque neutral point. After considering a preset safety margin, the first depth can be confirmed.

[0036] Specifically, in this embodiment, the screw motor counter-torque is determined based on the following formula:

[0037] in, For the reverse torque of the screw motor, This refers to the displacement per revolution of the screw motor. For screw motor efficiency, This is the screw pressure differential data.

[0038] To ensure safety, a preset safety margin is introduced in this embodiment. After determining the theoretical depth of the bottom torque neutral point, the preset safety margin is deducted to determine the first depth.

[0039] Step 130: Based on wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, calculate the theoretical value of the top drive torque according to the soft rod model and the segmented infinitesimal method.

[0040] In this embodiment, the processor determines the torsion angle of the micro-segment based on the torque at the top of the micro-segment, the length of the micro-segment, the shear modulus of the drill string material, and the polar moment of inertia of the drill string, wherein the polar moment of inertia is calculated based on the outer diameter and inner diameter of the drill string; then, the processor integrates the torsion angles of all micro-segments along the well depth direction from the first depth to the surface to determine the theoretical total torsion angle.

[0041] Specifically, in this embodiment, the processor first acquires wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters. The wellbore trajectory data includes at least well depth, inclination angle, and azimuth angle; the drill string structure data includes at least the outer diameter of the tubing and its own weight; the wellbore structure data includes at least the segmented wellbore diameter used to confirm contact relationships; and the operating parameters include at least the circumferential friction coefficient. Further, the processor divides the drill string along the well depth direction into multiple micro-segments of a preset micro-segment length. Based on the wellbore trajectory data, it acquires the inclination angle and azimuth angle of each micro-segment, determines the rate of change of the inclination angle and the rate of change of the azimuth angle, and calculates the contact force between each micro-segment and the wellbore wall based on the axial force at the lower end of the micro-segment and the component of the tubing's own weight along the normal direction of the well wall. Finally, the processor acquires the torque at the top and bottom of the micro-segment, and calculates the incremental friction torque from the first depth to the surface segment by segment based on the contact force, the outer diameter of the tubing, and the circumferential friction coefficient, according to the micro-segment torque transmission formula, and accumulates these to determine the theoretical value of the top drive torque.

[0042] Furthermore, in this embodiment, the contact force is determined based on the following formula:

[0043] in, For contact force, The axial force at the lower end of the infinitesimal segment. The azimuth rate of change The rate of change of well inclination angle. This is the component of the tubing string's self-weight along the normal direction of the wellbore; The friction torque increment is determined based on the following formula:

[0044] in, The torque at the top of the micro-element segment, This refers to the torque at the bottom of the micro-element segment. The coefficient of friction is the circumferential friction factor. The outer diameter of the tubular column, is the length of the infinitesimal segment.

[0045] This application divides the drill string into multiple micro-segments along the well depth direction. The length of each micro-segment is adaptively divided according to the wellbore trajectory variation rate and drill string structure variation. For each micro-segment, based on the soft rod model, its buckling state in the wellbore (including no buckling, sinusoidal buckling, or helical buckling) is considered. Combining the well inclination angle and azimuth angle in the wellbore trajectory data, the inner and outer diameters, linear weight, and elastic modulus of the segmented tubing in the drill string structure data, the segmented wellbore diameter in the wellbore structure data, and the friction coefficient and drilling fluid density in the operating parameters, the normal contact force between the micro-segment and the wellbore is calculated. Using this contact force, combined with the tubing outer diameter and circumferential friction coefficient, the circumferential friction torque is accumulated upward segment by segment using the segmented micro-element method. Finally, the total friction torque from the bottom hole torque neutral point with a safety margin to the surface is obtained as the theoretical value of the top drive torque.

[0046] Step 140: Establish a relationship model between the torsion angle and the top drive torque based on the theoretical value of the top drive torque and the first depth, and calculate the theoretical total torsion angle.

[0047] In this embodiment, the processor determines the torsion angle of the micro-segment based on the torque at the top of the micro-segment, the length of the micro-segment, the shear modulus of the drill string material, and the polar moment of inertia of the drill string, wherein the polar moment of inertia is calculated based on the outer diameter and inner diameter of the drill string; the processor then integrates the torsion angles of all micro-segments along the well depth direction from the first depth to the surface to determine the theoretical total torsion angle.

[0048] Specifically, in the embodiments of this application, the torsion angle of the micro-element segment at well depth x can be determined based on the following formula:

[0049] in, Let x be the torsion angle of the micro-element at well depth x. The torque at the top of the micro-element segment, The length of the infinitesimal segment. Let be the shear modulus of the drill string material. Let be the polar moment of inertia of the drill string; The polar moment of inertia of the drill string can be determined based on the following formula:

[0050] in, The outer diameter of the drill string. The inner diameter of the drill string; The theoretical total torsional angle can be determined based on the following formula:

[0051] in, For the theoretical total angle of twist, This is the first depth.

[0052] By integrating the entire well section from the first depth to the surface, the processor can accurately quantify the cumulative torsional effect caused by the torque applied by the top drive in the wellbore. This embodiment fully considers the geometric changes of the drill string structure along the well depth direction and the influence of material properties on torsional stiffness, thereby ensuring that the theoretical total torsional angle accurately reflects the actual downhole stress conditions and serves as the initial input parameter for subsequent control.

[0053] Step 150: Apply the theoretical total torsion angle to the on-site top drive control to obtain the measured torque, and use the Bayesian optimization algorithm to minimize the deviation between the measured torque and the theoretical torque value calculated by the material mechanics model with optimizable coefficients to obtain the optimized total torsion angle.

[0054] In this embodiment, the processor drives the drill string to oscillate based on the theoretical total torsion angle and collects the corresponding measured torque through the top drive torque sensor. Furthermore, the processor establishes an objective function to measure the degree of deviation between the measured torque and the theoretical torque, and uses a Bayesian optimization algorithm to iteratively adjust the optimizable coefficients to minimize the value of the objective function. Finally, the processor determines the formula for calculating the total torsion angle based on the optimizable coefficients that minimize the objective function, and calculates the optimized total torsion angle.

[0055] Specifically, in this embodiment, the optimized total torsion angle is determined based on the following formula:

[0056] in, The optimized total torsion angle, For the first depth, For optimizable coefficients, The torque at the top of the micro-element segment, Let be the shear modulus of the drill string material. Let be the polar moment of inertia of the drill string. is the length of the infinitesimal segment.

[0057] It is understood that by introducing optimizable coefficients in the embodiments of this application to compensate for complex on-site factors that are not fully considered in the theoretical model, the control consistency between the torsion angle and the measured torque is effectively improved.

[0058] Step 160: Input the drilling state parameters, including the optimized total torsion angle, into the control model trained based on the reinforcement learning algorithm to generate the top drive torsion angle control command, and update the parameters of the control model according to the state feedback after executing the control command to achieve adaptive closed-loop control of the top drive torsion parameters.

[0059] In this embodiment, the processor first uses the current drilling state vector as input to the policy network, outputs the mean and standard deviation of the top drive torsional angle action through the policy network, and generates continuous torsional angle actions using reparameterization techniques. The drilling state vector includes wellbore trajectory parameters and the optimized total torsional angle output by the Bayesian optimization module. Further, the processor estimates the state value function through a value network and determines the dominance function based on the state value function and the immediate reward obtained after executing the action. Then, a trust region objective function is constructed based on generalized dominance estimation, and the processor updates the policy network parameters by maximizing the trust region objective function. The measured torque, wellbore trajectory parameters, and tool face state obtained after executing the torsional angle action are used as state feedback for updating the control model parameters in the next round. Simultaneously, during the control process, the processor integrates real-time acquired data and historical operating condition data to construct a two-dimensional experience pool for model training and parameter adjustment, realizing closed-loop updating and control of the top drive torsional parameters.

[0060] Preferably, in this embodiment, the advantage function is constructed based on the state value function:

[0061] in, For the dominant function, The immediate reward obtained after performing an action. For state The value estimate, For state Value estimation; The trust region objective function for maximizing generalized advantage estimation is:

[0062] in, For the trust region objective function, The probability of generating action 'a' for the current policy network. The probability of generating action 'a' for the old policy network. For the clipping function, This is a pruning parameter used to control the step size of policy updates.

[0063] In this way, the control model can continuously optimize the output strategy of the top drive torsional yaw angle while taking into account the complex downhole mechanical environment and real-time operating condition changes. After each torsional yaw action, the system compares the actual drilling status with the expected target, generates an error signal, and uses it to adjust the parameters of the strategy network and value network, ultimately improving control accuracy and stability.

[0064] Figure 2 The illustration schematically shows a top drive torsional yaw parameter control method architecture according to an embodiment of this application. Figure 2 As shown in the embodiment of this application, the input data includes wellbore trajectory, drill string structure, wellbore structure, and riser pressure; the riser pressure is input to the screw tool model to calculate the anti-torque depth B, which, combined with the safety margin, determines the depth A; the wellbore trajectory, drill string structure, and wellbore structure data are input to the BHA friction torque model, and the top drive torque parameters are calculated based on the depth A; the top drive torque parameters and the depth A are input together to the drill string friction torque model to determine the theoretical total torsion angle; the theoretical total torsion angle is input to the torsion yaw parameter optimization model, which outputs the corrected torsion angle; the corrected torsion angle is input to the torsion yaw parameter control model to generate the final torsion yaw parameter application command, thereby realizing closed-loop control of the top drive torsion yaw parameters.

[0065] This application provides a top drive torsional yaw parameter control method. First, it acquires wellbore trajectory data, top drive torque data, and screw tool differential pressure data to calculate the bottom hole drill string counter-torque, and determines the first depth of the bottom hole torque neutral point with a safety margin. Then, combining wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, it calculates the theoretical value of the top drive torque using a soft rod model and a piecewise infinitesimal element method. Subsequently, based on this theoretical value and the first depth, it establishes a relationship model between the torsion angle and the top drive torque, thereby calculating the theoretical total torsion angle. This theoretical total torsion angle is applied to the field top drive control to obtain the measured torque, and a Bayesian optimization algorithm is used to minimize the deviation between the measured torque and the theoretical torque value calculated by the material mechanics model containing optimizable coefficients. The difference is calculated to obtain the optimized total torsion angle. Finally, the drilling state parameters, including the optimized total torsion angle, are input into the control model trained based on the reinforcement learning algorithm. The model generates the top drive torsion angle control command and continuously updates the model parameters based on the state feedback after executing the command, realizing adaptive closed-loop control of the top drive torsion parameters. This effectively solves the problems of existing technologies where top drive torsion parameters rely on manual experience and lack real-time feedback and adaptive adjustment capabilities. It realizes intelligent calculation, automatic error correction, and precise dynamic control of torsion parameters, thereby significantly improving the stability of the tool face during sliding drilling, effectively suppressing pressure drag, reducing the risk of differential pressure stuck pipe and downhole tool fatigue damage, and improving the efficiency and safety of directional drilling operations.

[0066] Figure 3 A schematic block diagram of a top drive torsional yaw parameter control device according to an embodiment of this application is shown. Figure 3 As shown in the figure, this application embodiment provides a top drive torsional yaw parameter control device 300, which may include: Memory 310 is configured to store instructions; The processor 320 is configured to retrieve instructions from the memory 310 and, when executing the instructions, to implement the aforementioned method for controlling the top drive yaw parameters.

[0067] This application also provides a machine-readable storage medium storing instructions for causing a machine to perform the above-described method for controlling the top drive yaw parameters.

[0068] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0073] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0074] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0075] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0076] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for controlling the parameters of a top-drive torsional yaw mechanism, characterized in that, include: Acquire wellbore trajectory data, top drive torque data, and screw differential pressure data; Based on the screw differential pressure data, the screw motor counter-torque is calculated, and the first depth of the bottom hole torque neutral point with a safety margin is determined. Based on the wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, the theoretical value of the top drive torque is calculated according to the soft rod model and the piecewise infinitesimal method. Based on the theoretical value of the top drive torque and the first depth, a relationship model between the torsion angle and the top drive torque is established, and the theoretical total torsion angle is calculated. The theoretical total torsion angle is applied to the field top drive control to obtain the measured torque. The deviation between the measured torque and the theoretical torque value calculated by the material mechanics model with optimizable coefficients is minimized using the Bayesian optimization algorithm to obtain the optimized total torsion angle. The drilling state parameters, including the optimized total torsion angle, are input into the control model trained based on the reinforcement learning algorithm to generate the top drive torsion angle control command. The parameters of the control model are updated according to the state feedback after executing the control command, thereby realizing adaptive closed-loop control of the top drive torsion parameters.

2. The top drive torsional oscillating parameter control method according to claim 1, characterized in that, The process of calculating the screw motor counter-torque based on the screw differential pressure data and determining the first depth of the bottom hole torque neutral point with a safety margin includes: Based on the screw pressure difference data, combined with the screw motor efficiency, screw motor displacement per revolution, and screw motor efficiency, the screw motor reverse torque is determined. The screw motor reverse torque is determined based on the following formula: in, This is the counter-torque of the screw motor. The displacement per revolution of the screw motor is [missing information]. The efficiency of the screw motor is... The differential pressure data of the screw; Based on the reverse torque of the screw motor, the torque neutral point depth is determined so that the drill string friction torque from the bottom of the well to the torque neutral point depth is equal to the reverse torque of the screw motor; The first depth of the bottom torque neutral point with a safety margin is determined by subtracting the preset safety margin from the torque neutral point depth.

3. The top drive torsional oscillating parameter control method according to claim 1, characterized in that, The theoretical value of the top drive torque calculated based on the wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters, according to the soft rod model and the piecewise infinitesimal method, includes: The wellbore trajectory data, drill string structure data, wellbore structure data, and operating parameters are acquired. The wellbore trajectory data includes at least well depth, inclination angle, and azimuth angle. The drill string structure data includes at least the outer diameter of the tubing string and the weight of the tubing string. The wellbore structure data includes at least the segmented wellbore diameter used to confirm the contact relationship. The operating parameters include at least the circumferential friction coefficient. The drill string is divided into multiple micro-segments along the well depth direction according to a preset micro-segment length. Based on the wellbore trajectory data, the inclination angle and azimuth angle of each micro-segment are obtained, and the inclination angle change rate and azimuth angle change rate are determined. Furthermore, based on the axial force at the lower end of each micro-segment and the component of the drill string's self-weight along the normal direction of the well wall, the contact force between each micro-segment and the well wall is calculated. The contact force is determined based on the following formula: in, The contact force, The axial force at the lower end of the micro-element segment. The azimuth rate of change, The rate of change of the well inclination angle, This is the component of the tubing string's self-weight along the normal direction of the wellbore; Obtain the torque at the top and bottom of the micro-segment. Based on the contact force, the outer diameter of the tubing, and the circumferential friction coefficient, calculate the incremental friction torque from the first depth to the ground segment by segment according to the micro-segment torque transmission formula. Accumulate these values ​​to determine the theoretical value of the top drive torque. The incremental friction torque is determined based on the following formula: in, The torque at the top of the micro-element segment is... The torque at the bottom end of the micro-element segment is... The circumferential friction coefficient is... The outer diameter of the tubular column, The length of the micro-element segment is given.

4. The top drive torsional oscillating parameter control method according to claim 1, characterized in that, The step of establishing a relationship model between the torsion angle and the top drive torque based on the theoretical value of the top drive torque and the first depth, and calculating the theoretical total torsion angle, includes: The torsional angle of the micro-segment is determined based on the tip torque of the micro-segment, the length of the micro-segment, the shear modulus of the drill string material, and the polar moment of inertia of the drill string, wherein the polar moment of inertia is calculated based on the outer diameter and inner diameter of the drill string. The theoretical total torsion angle is determined by integrating the torsional angles of all micro-segments along the well depth direction from the first depth to the surface.

5. The top drive torsional oscillating parameter control method according to claim 4, characterized in that, The torsional angle of the micro-element at well depth x is determined based on the following formula: in, The torsion angle of the micro-element segment at the well depth x. The torque at the top of the micro-element segment is... The length of the micro-element segment is... The shear modulus of the drill string material. Let be the polar moment of inertia of the drill string; The polar moment of inertia of the drill string is determined based on the following formula: in, The outer diameter of the drill string. The inner diameter of the drill string; The theoretical total torsional angle is determined based on the following formula: in, The total torsional angle is the theoretical value stated above. This is the first depth.

6. The top drive torsional oscillating parameter control method according to claim 1, characterized in that, The theoretical total torsion angle is applied to the on-site top drive control to obtain the measured torque. A Bayesian optimization algorithm is used to minimize the deviation between the measured torque and the theoretical torque value calculated from a material mechanics model containing optimizable coefficients. The optimized total torsion angle includes: The drill string is driven to twist and oscillate based on the theoretical total torsion angle, and the corresponding measured torque is collected by the top drive torque sensor. A target function is established to measure the deviation between the measured torque and the theoretical torque. The optimizable coefficients are iteratively adjusted using a Bayesian optimization algorithm to minimize the value of the target function. The formula for calculating the total torsion angle is determined based on the optimizable coefficients that minimize the objective function. The optimized total torsion angle is then calculated based on the following formula: in, The optimized total torsion angle is... For the first depth, For optimizable coefficients, The torque at the top of the micro-element segment, Let be the shear modulus of the drill string material. Let be the polar moment of inertia of the drill string. is the length of the infinitesimal segment.

7. The top drive torsional oscillating parameter control method according to claim 1, characterized in that, The step of inputting drilling state parameters, including the optimized total torsion angle, into a control model trained based on a reinforcement learning algorithm to generate a top drive yaw angle control command, and updating the parameters of the control model based on the state feedback after executing the control command, thereby achieving adaptive closed-loop control of the top drive yaw parameters, includes: The current drilling state vector is used as the input of the strategy network. The strategy network outputs the mean and standard deviation of the top drive torsional angle action and uses the reparameterization technique to generate continuous torsional angle action. The drilling state vector includes wellbore trajectory parameters and the optimized total torsional angle output by the Bayesian optimization module. The state value function is estimated through a value network, and the advantage function is determined based on the state value function and the immediate reward obtained after performing the action. A trust region objective function is constructed based on generalized advantage estimation, and the policy network parameters are updated by maximizing the trust region objective function. The measured torque, wellbore trajectory parameters, and tool face status obtained after performing the torsional angle action are used as status feedback for updating the control model parameters in the next round. During the control process, a two-dimensional experience pool is constructed by integrating real-time acquired data and historical operating condition data for model training and parameter adjustment, thereby realizing closed-loop updating and control of the top drive torsion yaw parameters.

8. The top drive torsional oscillating parameter control method according to claim 7, characterized in that, The advantage function is constructed based on the state value function: in, For the aforementioned advantage function, The immediate reward obtained after performing an action. For state The value estimate, For state Value estimation; The trust region objective function for maximizing generalized advantage estimation is: in, Let the trust region objective function be... The probability of generating action 'a' for the current policy network. The probability of generating action 'a' for the old policy network. For the clipping function, This is a pruning parameter used to control the step size of policy updates.

9. A top-drive torsional oscillating parameter control device, characterized in that, include: The memory is configured to store instructions; The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the top drive yaw parameter control method according to any one of claims 1 to 8.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the top drive yaw parameter control method according to any one of claims 1 to 8.

Images