Method and device for predicting build-up rate of rotary steering system

Abstract

The invention relates to the technical field of petroleum and natural gas engineering, in particular to a method and device for predicting the build-up rate of a rotary steering system. The method comprises the steps that the operation proportion between a directional deflecting mode and a stable deflecting mode in the drilling process is determined; first values of various drilling parameters of the rotary steering system are collected; according to the first values of the multiple drilling parameters, a proxy model is utilized to predict a first build-up rate and a second build-up rate, the first build-up rate is a limit build-up rate in a directional deflecting mode, and the second build-up rate is a limit build-up rate in a stable deflecting mode; the proxy model is used for representing an association relationship between the multiple drilling parameters of the rotary steering system and a build-up rate; and according to an operation proportion, fusing the first build-up rate and the second build-up rate to obtain a composite working condition build-up rate. According to the embodiment of the invention, the build-up rate of the rotary steering system can be quickly and accurately determined.

Description

Technical Field

[0001] This specification relates to the field of oil and gas engineering technology, and in particular to a method and apparatus for predicting the inclination rate of a rotary steering system. Background Technology

[0002] With the continuous development of unconventional oil and gas, and deep and ultra-deep oil and gas resources, directional wells and horizontal wells are playing an increasingly prominent role in oil and gas exploration and development. Rotary Steerable System (RSS) drilling technology, as an important development direction of directional drilling technology, has been widely used in complex formations and efficient drilling operations due to its advantages such as continuous rotary drilling, good wellbore quality, and high trajectory control accuracy.

[0003] In related technologies, the calculation methods for the build-up rate of rotary steerable systems include geometric methods and mechanical analysis methods. Geometric methods typically refer to the three-point circle method, which treats the drill bit, lower stabilizer, and upper tangent point of the rotary steerable system as three concyclic points, approximating the curvature of the resulting arc as the build-up rate. However, this method does not consider the influence of drill string stiffness and drilling parameters. The build-up rate obtained through geometric methods is inaccurate and has low precision. Mechanical analysis methods typically include the equilibrium curvature method, the limiting curvature method, and the drilling trend angle method. These methods, through force analysis of the bottom drill string assembly, can obtain more accurate build-up rate calculations, but the equations are highly nonlinear, making the solution difficult, time-consuming, and inefficient. Summary of the Invention

[0004] This specification provides a method and apparatus for predicting the tilt rate of a rotary steering system, which is used to quickly and accurately determine the tilt rate of the rotary steering system.

[0005] This specification provides an embodiment of a method for predicting the tilt rate of a rotary steering system, including:

[0006] Determine the operational ratio between directional drilling mode and stabilization mode during the drilling process;

[0007] Collect the first values ​​of various drilling parameters of the rotary steering system;

[0008] Based on the first values ​​of the various drilling parameters, a surrogate model is used to predict the first build-up rate and the second build-up rate. The first build-up rate is the limiting build-up rate in the directional build-up mode, and the second build-up rate is the limiting build-up rate in the stable build-up mode. The surrogate model is used to represent the correlation between the various drilling parameters of the rotary steering system and the build-up rate.

[0009] Based on the operating ratio, the first ramp rate and the second ramp rate are combined to obtain the composite operating condition ramp rate.

[0010] This specification also provides an embodiment of a rotary steering system slope prediction device, comprising:

[0011] The determination unit is used to determine the operational ratio between directional drilling mode and stabilization mode during the drilling process;

[0012] The acquisition unit is used to acquire the first values ​​of various drilling parameters of the rotary steering system;

[0013] The prediction unit is used to predict a first build-up rate and a second build-up rate based on the first values ​​of the various drilling parameters using a surrogate model. The first build-up rate is the limiting build-up rate in the directional build-up mode, and the second build-up rate is the limiting build-up rate in the stable build-up mode. The surrogate model is used to represent the correlation between the various drilling parameters of the rotary steering system and the build-up rate.

[0014] The fusion unit is used to fuse the first ramp rate and the second ramp rate according to the operation ratio to obtain the composite ramp rate.

[0015] This specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described slope prediction method.

[0016] This specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described slope prediction method.

[0017] This specification also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described slope prediction method.

[0018] The technical solution of this specification embodiment can determine the operating ratio between directional drilling mode and stable drilling mode during drilling; it can collect first values ​​of various drilling parameters of the rotary steerable system; based on the first values ​​of the various drilling parameters, it can use a surrogate model to predict a first build-up rate and a second build-up rate, where the first build-up rate is the limiting build-up rate in directional drilling mode and the second build-up rate is the limiting build-up rate in stable drilling mode; the surrogate model is used to represent the correlation between the various drilling parameters of the rotary steerable system and the build-up rate; based on the operating ratio, the first build-up rate and the second build-up rate can be fused to obtain a composite working condition build-up rate. Therefore, this specification embodiment, for both directional drilling and stable drilling conditions, uses a surrogate model to predict the first and second build-up rates corresponding to the two working conditions, and then fuses the first and second build-up rates based on the operating ratio of the two working conditions to obtain a build-up rate conforming to the disclosure. This specification embodiment, for the two working conditions that exist in actual rotary steerable systems, can quickly and accurately determine the build-up rate of the rotary steerable system through a surrogate model. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the method for predicting the tilt rate of the rotary guide system in the embodiments of this specification.

[0021] Figure 2 This is a schematic diagram of the tilt prediction process of the rotary guide system in the embodiments of this specification;

[0022] Figure 3 This is a schematic diagram of the structure of the tilt prediction device of the rotary guide system in the embodiments of this specification;

[0023] Figure 4 This is a schematic diagram illustrating the relationship between drill pressure and build-up rate in the embodiments of this specification;

[0024] Figure 5 This is a schematic diagram illustrating the relationship between drill bit anisotropy and build-up rate in the embodiments of this specification;

[0025] Figure 6 This is a schematic diagram illustrating the relationship between the dip angle and the pitching rate in the embodiments of this specification;

[0026] Figure 7This is a schematic diagram showing the relationship between the outer diameter of the lower stabilizer and the inclination rate in the embodiments of this specification;

[0027] Figure 8 This is a schematic diagram showing the relationship between the outer diameter of the upper stabilizer and the inclination rate in the embodiments of this specification;

[0028] Figure 9 This is a schematic diagram illustrating the relationship between the centralizer distance and the inclination rate in the embodiments of this specification;

[0029] Figure 10 This is a schematic diagram illustrating the relationship between drill bit anisotropy and build-up rate in the embodiments of this specification. Detailed Implementation

[0030] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. The specific embodiments described herein are only used to explain this disclosure, and not to limit this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure are within the scope of protection of this disclosure. In addition, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0031] A bottom hole assembly (BHA) includes the drill bit, stabilizer, and rotary steerable system. A rotary steerable system is a drilling system that simultaneously guides drilling while the drill string rotates, significantly reducing friction, increasing drilling speed, improving wellbore conditions, and substantially increasing wellbore extension. Rotary steerable systems can include point-the-bit rotary steerable systems (RSS) and push-type rotary steerable systems. A rotary steerable system may include an offset actuator, measurement-while-drilling (MWD) components (e.g., sensors), a power unit, and a control unit.

[0032] The build-up rate is used to represent the bending strength of the borehole trajectory. It refers to the total bending angle of the borehole trajectory per unit depth during drilling. The build-up rate of a rotary steerable system refers to the build-up rate of a downhole drilling assembly consisting of rotary steerable tools.

[0033] Please see Figure 1 and Figure 2 This specification provides a method for predicting the tilt rate of a rotary steering system. The method can be applied to computer equipment. The computer equipment may include personal computers, smartphones, tablets, laptops, servers, server clusters comprising multiple servers, etc. Please refer to... Figure 1 The method may include the following steps.

[0034] Step 11: Determine the ratio of operation between directional drilling mode and stabilization mode during the drilling process.

[0035] In some embodiments, the rotary steering system operates in two modes: a directional drilling mode and a stabilization mode. In the directional drilling mode, the rotary steering system continuously generates a net lateral force or a drill bit deflection angle, causing the wellbore trajectory's inclination angle and / or azimuth angle to change at a certain rate. In the stabilization mode, the rotary steering system dynamically adjusts its generated net lateral force to counteract the natural formation drift and other disturbances, thereby maintaining a stable wellbore trajectory's inclination angle and azimuth angle. The operating ratio between the directional drilling mode and the stabilization mode can be determined at specified well depths during drilling. The specified well depth is the actual length of the wellbore trajectory, for example, 100m, 200m, etc.

[0036] In some embodiments, a specified well depth includes one or more well sections. During drilling, the operation mode of the current well section can be identified; the operation ratio can be calculated at specified well depths, based on the operation mode of each well section within the specified well depth.

[0037] During drilling with a rotary steerable system, drilling parameters such as inclination angle, azimuth angle, tool face angle, drilling pressure, rotational speed, pump rate, well depth, formation dip angle, and inclination rate are collected through a measurement-while-drilling (MWD) module and a surface monitoring system. Operating commands for the directional rotary steerable system are also recorded. Based on the collected drilling parameters and / or operating commands, it can be determined whether the current well section is in directional build-up mode or stabilization mode. For example, it can be determined whether the tool face angle remains near a set value, the inclination trend, and operating commands. Specifically, for example, if the inclination angle changes at a certain rate, it can be determined that the current well section is in directional build-up mode. If the inclination angle remains stable, it can be determined that the current well section is in stabilization mode.

[0038] It can calculate the length of the wellbore trajectory obtained since the last determination of the working ratio. If the wellbore trajectory length reaches a specified well depth, the working ratio can be calculated based on the working patterns of each well section within the specified well depth. For example, it can be calculated using the formula... Calculate the task ratio. L represents the task ratio. This indicates the operation time for the directional tilting mode. B represents the operation time of the stabilization mode. Therefore, the operation ratio represents the ratio between the operation time of the directional drilling mode and the operation time at a specified well depth. The operation ratio represents the relative contribution of the directional drilling mode and the stabilization mode at a specified well depth. Of course, the formula for calculating the operation ratio above is only an example; other formulas can be used in practice. For example, .

[0039] Step 12: Collect the first values ​​of various drilling parameters of the rotary steering system.

[0040] In some embodiments, the number of drilling parameters may be one or more. For example, drilling parameters may include drill pressure, inclination angle, formation anisotropy, bit anisotropy, formation dip, bend angle, lower stabilizer outer diameter, upper stabilizer outer diameter, distance from lower stabilizer to drill bit, and distance between stabilizers. Drill pressure refers to the axial force acting on the drill bit, causing it to cut and break the rock. Inclination angle refers to the angle between the tangent direction at a point on the wellbore trajectory and the perpendicular direction at that point. Formation anisotropy refers to the property that the mechanical or drilling properties of the rock (such as drillability and shear strength) differ with different directions. For example, the difference in drillability of a formation in the direction perpendicular to the bedding plane versus the direction parallel to the bedding plane. Bit anisotropy refers to the characteristic that the drill bit has different cutting efficiencies in the axial and lateral directions. Formation dip refers to the angle between the bedding plane and the horizontal plane. Bend angle, also known as pointing angle, refers to the angle by which the drill bit axis deflects relative to the axis of the rotary steering system or the BHA axis. During drilling, the size and direction of the pointing angle can be dynamically changed according to a preset trajectory or real-time commands to achieve complex trajectory control. A centralizer, also known as a stabilizer, is used. The lower centralizer is the one closest to the drill bit in a BHA (Boiler Alignment) system. The upper centralizer is the one furthest from the drill bit in a BHA system.

[0041] In some embodiments, the values ​​of the various drilling parameters during the actual drilling process can be collected as the first values. For example, the first values ​​of the various drilling parameters can be collected through a measurement-while-drilling (MWD) assembly and a surface monitoring system.

[0042] Step 13: Based on the first values ​​of the various drilling parameters, use a surrogate model to predict the first build-up rate and the second build-up rate. The first build-up rate is the limit build-up rate in the directional build-up mode, and the second build-up rate is the limit build-up rate in the stable build-up mode. The surrogate model is used to represent the correlation between the various drilling parameters of the rotary steering system and the build-up rate.

[0043] In some embodiments, after acquiring first values ​​of multiple drilling parameters, the difference between the first value and a second value of each drilling parameter can be calculated. The acquisition time of the second value is adjacent to and earlier than the acquisition time of the first value. Therefore, the second value is the previously acquired drilling parameter value.

[0044] The difference between each drilling parameter can be compared with a first set threshold to determine if the difference is greater than or equal to the first set threshold. If the difference is greater than or equal to the first set threshold, it indicates that the value of the drilling parameter has changed significantly. If the difference is less than the first set threshold, it indicates that the value of the drilling parameter has not changed significantly. The number of drilling parameters whose difference is greater than or equal to the first set threshold can be counted among the various drilling parameters. If the counted number of drilling parameters meets the prediction conditions, it indicates that the operating state of the rotary steerable system has changed significantly, and a surrogate model can be used to predict the first and second build-up rates. The prediction conditions may include, for example, the number of drilling parameters being greater than or equal to a certain value. Therefore, using a surrogate model to predict the build-up rate when the operating state of the rotary steerable system changes significantly can avoid excessive computational burden caused by frequent calls to the surrogate model, and can also avoid control command lag caused by computational delays, resulting in decreased wellbore trajectory control accuracy or increased drilling risk.

[0045] In some embodiments, the surrogate model is a machine learning model capable of representing the correlation between various drilling parameters of the rotary steerable system and the build-up rate. Surrogate models include gradient boosting trees, random forests, regression models, neural network models, etc.

[0046] In some embodiments, the surrogate model may include a first surrogate model and a second surrogate model. The first surrogate model corresponds to the directional drilling mode and is used to represent the correlation between drilling parameters and the build-up rate under the directional drilling mode. The second surrogate model corresponds to the stable drilling mode and is used to represent the correlation between drilling parameters and the build-up rate under the stable drilling mode. First values ​​of the various drilling parameters can be input into the first surrogate model to obtain a first build-up rate. The first build-up rate is the build-up rate of the rotary steerable system under the directional drilling mode. The second build-up rate is the build-up rate of the rotary steerable system under the stable drilling mode.

[0047] Step 14: Based on the operating ratio, the first ramp rate and the second ramp rate are fused to obtain the composite operating condition ramp rate.

[0048] In some embodiments, considering that in practice, directional drilling and stable drilling often combine in a composite process, the first build-up rate and the second build-up rate can be merged to obtain the composite build-up rate. Specifically, the first build-up rate and the second build-up rate can be merged using the work ratio to obtain the composite build-up rate. The composite build-up rate can be used for trajectory control, drill string assembly optimization, and directional parameter design, etc.

[0049] For example, through formula Calculate the slope inclination rate under combined working conditions. This indicates the slope inclination under combined operating conditions. Indicates the first slope. L represents the second slope, and L represents the proportion of work. This represents the conversion factor. The first and second build-up rates predicted by the surrogate model are the limiting build-up rates. The limiting build-up rate is the wellbore curvature corresponding to zero lateral drilling rate. The limiting build-up rate refers to the extreme state reached by the drill string during directional drilling. The limiting build-up rate is closely related to the values ​​of the aforementioned drilling parameters. The limiting build-up rate can be converted using the conversion factor to obtain the converted build-up rate as the composite working condition build-up rate. The conversion factor is related to the geological parameters (e.g., geological type) of the drilling area.

[0050] In some embodiments, each of the above-mentioned drilling parameters may have a range of values.

[0051] For example, the range of drilling parameters is shown in Table 1 below.

[0052] Table 1

[0053]

[0054] The range of drilling parameters can be determined based on the correlation between drilling parameters and the limiting build-up rate. This correlation can include functions, curves, etc. Figure 4 The relationship between drilling pressure and ultimate build-up rate at multiple well inclination angles is shown. Figure 5 The relationship between drill bit anisotropy and limiting build-up rate under various drilling pressures is shown. Figure 6 The relationship between formation dip angle and ultimate build-up rate under various drilling pressures is shown. Figure 7 The relationship between the outer diameter of the centralizer and the limiting build-up rate under various drill pressure conditions is shown. Figure 8 The relationship between the outer diameter of the centralizer under various drilling pressures and the ultimate build-up rate is shown. Figure 9 The relationship between the distance of the centralizer under drilling pressure and the ultimate build-up rate is shown in several examples. Figure 10 The relationship between drill bit anisotropy and limiting build-up rate under various drilling pressures is shown.

[0055] In some embodiments, multiple feature data can be constructed based on the value ranges of various drilling parameters. Each feature data may include one value of the various drilling parameters. The values ​​of the same drilling parameter may be the same or different in different feature data. For each drilling parameter, sampling can be performed within the value range of the drilling parameter using methods such as super-Latin sampling to obtain multiple values ​​for the drilling parameter. For each drilling parameter, the multiple values ​​of that drilling parameter can be assigned to multiple feature data, such that each feature data may include one value of that drilling parameter. This results in the construction of multiple feature data.

[0056] For each feature data point, a third and fourth build-up rate can be calculated using the mechanistic model of the rotary steering system. The third build-up rate is the limiting build-up rate in the directional build-up mode, and the fourth build-up rate is the limiting build-up rate in the stable build-up mode. A first surrogate model can be trained based on the feature data and the third build-up rate; a second surrogate model can also be trained based on the feature data and the fourth build-up rate. Thus, by using the feature data as input features and the mechanistically calculated third and fourth build-up rates as output features, and training the first and second surrogate models based on the input and output features, a nonlinear mapping from drilling parameters to the limiting build-up rate is achieved.

[0057] The mechanistic model of a rotary steering system can be considered its mechanical model. By establishing this mechanical model, the inclination rate can be calculated. However, in practical applications, using the mechanistic model to calculate the inclination rate is computationally intensive and complex, making it difficult to meet the needs of rapid inclination rate prediction at construction sites. Furthermore, rotary steering systems operate in both directional inclination and stabilization modes, with frequent switching between operating conditions, making real-time application of the mechanistic model challenging. Additionally, training machine learning models relies on large amounts of training data. The amount of data accumulated at construction sites is relatively small, making it difficult to effectively train machine learning models. Therefore, this embodiment utilizes the mechanistic model of the rotary steering system to generate training data, and then uses this generated training data to train a surrogate model, achieving data-mechanism fusion.

[0058] In some embodiments, the calculation process of the third slope is described below.

[0059] The third slope rate of each feature data can be calculated according to the following formula (1).

[0060] (1)

[0061] in, Indicates the third slope. Indicates the build-up rate on the well inclination plane. This indicates the build-up rate on the azimuth plane. The well inclination plane is a vertical plane, and the azimuth plane is a horizontal plane; the well inclination plane is perpendicular to the azimuth plane.

[0062] The limiting build-up rate is the borehole curvature corresponding to a lateral drilling rate of zero. Based on the definition of the limiting build-up rate, the following nonlinear equation can be established.

[0063] (2)

[0064] Since the wellbore curvature is unknown, Newton's method can be used to solve equation (2) to obtain... and The solution process of formula (2) can be understood as finding a set of... and This makes the lateral drilling rate zero. The parameters used in solving formula (2) (e.g., the parameters in formulas (3) to (9)) can be determined based on the characteristic data. and In the future, it can be based on and The third slope is calculated using formula (1).

[0065] In actual operations, the formation exhibits significant anisotropy, and the drill bit, in addition to axial drilling, also performs lateral cutting. Therefore, the anisotropy between the drill bit and the formation needs to be considered when calculating the build-up rate. The interaction between the drill bit and the formation can be characterized by the following three-dimensional drilling rate equation.

[0066] (3)

[0067] in, R represents the drilling speed component along the drill bit's axial direction. k This represents the drilling rate components in the well inclination plane and azimuth plane. k is selected from 1 and 2. k=1 indicates the well inclination plane. This represents the drilling velocity component on the well inclination plane. k=2 represents the azimuth plane. This represents the drilling velocity component on the azimuth plane. The normal (standard) drilling efficiency is represented by R, which represents the transformation matrix between bottom hole coordinates and formation coordinates, and S represents the transformation matrix between bottom hole coordinates and drill bit coordinates. Indicates the anisotropy index of the stratigraphy. This represents the anisotropy index of the drill bit, and F1 represents the axial force at the drill bit. This indicates the support reaction force at the drill bit.

[0068] Furthermore, the rotary steering system can be viewed as a combination of several longitudinally and transversely curved beams. For example, using the possible contact points of the drill bit, offset mechanism, stabilizers at each span, tubing string, and wellbore as nodes, the rotary steering system can be divided according to the contact conditions. By dividing the rotary steering system into a combination of multiple beam segments, the three-dimensional problem can be simplified to a two-dimensional problem in the inclination plane and azimuth plane. The governing equations for tubing string deformation in the inclination plane and azimuth plane are:

[0069] (4)

[0070] in, Indicates the inclined plane of the well. Indicates the azimuth plane. This indicates the lateral displacement of the tubing string in the inclination plane and azimuth plane of the well. This represents the arc length at any point in the tubular column. Indicates bending stiffness, unit: N·m 2 . This represents axial force, measured in N. This indicates the buoyancy coefficient of the tubular column. . This indicates the density of the drilling fluid, expressed in g / cm³. 3 . This indicates the density of the steel used in the tubular column, expressed in g / cm³. 3 . This represents the components of the tubing line reprojected onto the wellbore inclination plane and azimuth plane. When the tubing line is projected onto the azimuth plane, the gravity component is zero, i.e. It is 0.

[0071] The trial deflection function of the j-th span of the directional drilling tool can be expressed as:

[0072] (5)

[0073] in, These are the undetermined coefficients for drilling tool mechanics problems on the well inclination plane and azimuth plane. This indicates the number of nodes on the navigation tool. .

[0074] The lower boundary condition of the guiding tool is a hinged constraint, and the displacement and bending moment at the drill bit are zero. That is,

[0075] (6)

[0076] The upper end of the drill string lies at the bottom edge of the wellbore, and the boundary conditions at the upper tangent point are:

[0077] (7)

[0078] in, and They represent The first and second derivatives. This represents the projection of the length of the cut section on the drilling tool onto the well inclination plane and azimuth plane. The coefficients are dimensionless (if we take...) Projected onto the well inclination plane, then If projected onto the azimuth plane, then ). This indicates the apparent radius of the wellbore at the upper tangent point. This represents the projection of the dogleg angle from the drill bit to the point of tangency on the drilling tool onto the well inclination plane and azimuth plane. This represents the components of wellbore curvature in the inclination plane and azimuth plane.

[0079] Substituting formula (5) into formula (7), we can obtain the following: The linear equation of . Substituting the above formula (7) into the above formula (4), we can obtain the equation about . The linear equations. Regarding the two equations mentioned above... The linear equations can be solved using an iterative method to obtain the axial force and support reaction force.

[0080] Drill bit location ( axial force and reaction force It can be represented as:

[0081] (8)

[0082] The remaining cross-nodes ( axial force and reaction force It can be represented as:

[0083] (9)

[0084] in, For drilling pressure. Axial force at the drill bit. Equal to drilling pressure. The support reaction force at the drill bit can be expressed as the lateral force in the well inclination plane and azimuth plane at the drill bit. For the first tubular column The arc length of the span. For the tubing string in the inclination plane and azimuth plane of the well... The arc length of the span. For the first tubular column The angle of inclination of the well span.

[0085] In obtaining axial force and support reaction force (e.g., axial force F1 and support reaction force at the drill bit) Afterwards, the axial force and support reaction force can be substituted into the three-dimensional drilling rate equation (3). Using the three-dimensional drilling rate equation (3), Newton's method can be used to solve equation (2) to obtain... and In formula (2), It can be understood as The function can be represented as R k It can be understood as The function can be represented as .

[0086] In some embodiments, the calculation process of the fourth slope is described below. For each feature data, the following steps can be performed to obtain the fourth slope of that feature data:

[0087] Obtain multiple values ​​of the tool face angle within one rotation cycle;

[0088] The slope rate corresponding to each tool face angle value is calculated using formula (10);

[0089] The fourth inclination rate is calculated based on the inclination rates corresponding to the values ​​of multiple tool face angles.

[0090] In directional drilling, the tool face angle remains constant within a certain well section after being set on the ground, equivalent to the drill bit being subjected to a lateral force in a fixed direction. In stable drilling, the continuous rotation of the drill string causes the tool face angle to rotate rapidly within the range of 0 to 2π. Therefore, the tool face angle can be discretized within the range of 0 to 2π within one rotation cycle to obtain multiple values ​​for the tool face angle. Specifically, a uniform discretization method can be used. For example, multiple values ​​for the tool face angle can include 15°, 30°, 45°, 60°, 75°, 90°, 105°, 120°, 135°, 150°, 165°, 180°, 195°, 210°, 225°, 240°, 255°, 270°, 285°, 300°, 315°, 330°, and 345°. Of course, a non-uniform discretization method can also be used. This specification does not specifically limit the discretization method in the embodiments. The rotation cycle refers to the time or angle that the drill string or rotary steerable tool body takes to rotate one revolution.

[0091] Since a moment in a steady-slope working condition can be understood as a directional working condition, the inclination rate corresponding to each tool face angle value can be calculated using the following formula (10).

[0092] (10)

[0093] Where ω represents a value of the tool face angle. This represents the slope rate corresponding to ω. This represents the build-up rate on the inclination plane corresponding to ω. This represents the slope on the azimuth plane corresponding to ω.

[0094] The presence of structural bends causes the working direction line of the BHA tool to form a tool face angle with the pipe column axis, which can be used to characterize the direction of the bend:

[0095] (11)

[0096] in, Indicates a curved angle. These represent the projected values ​​of the bend angle. θ1 represents the projected value of the bend angle on the inclination plane, and θ2 represents the projected value of the bend angle on the azimuth plane.

[0097] As an example, the axial force and support reaction can be calculated using formulas (4)-(7), combined with formulas (11), (8), and (9). This is to obtain the axial force and support reaction (e.g., the axial force F1 and support reaction at the drill bit). Afterwards, the axial force and support reaction force can be substituted into the three-dimensional drilling rate equation (3). Using the three-dimensional drilling rate equation (3), Newton's method can be used to solve formula (12) to obtain... and .according to and It can be calculated using formula (10). .

[0098] (12)

[0099] It can be understood as The function can be represented as R k It can be understood as The function can be represented as The parameters used in solving formula (12) can be determined based on the characteristic data. The process of solving formula (12) is similar to that of solving formula (2), and will not be repeated here.

[0100] As another example, axial force and support reaction can also be calculated using formulas (4)-(7), combined with formulas (11), (13), and (14). Compared to formulas (8) and (9), formulas (13) and (14) consider the equivalent force caused by the bend angle in the steady-state mode, thus the calculated support reaction is more accurate. This is used to obtain axial force and support reaction (e.g., axial force F1 and support reaction at the drill bit). Afterwards, the axial force and support reaction force can be substituted into the three-dimensional drilling rate equation (3). Using the three-dimensional drilling rate equation (3), Newton's method can be used to solve formula (12) to obtain... and .according to and It can be calculated using formula (10). .

[0101] In this example, at the drill bit ( axial force and reaction force It can also be expressed as:

[0102] (13)

[0103] In this example, the remaining cross-nodes ( axial force and reaction force It can also be expressed as:

[0104] (14)

[0105] The above examples demonstrate how to obtain the slope rate corresponding to each tool facet angle value. In the future, the slope rates corresponding to multiple tool face angle values ​​can be added together to obtain the fourth slope rate corresponding to this feature data.

[0106] In some embodiments, multiple feature data and their corresponding third slopes are used to construct a first training dataset. The first training dataset includes multiple first training data, each of which includes feature data and a corresponding third slope. Multiple feature data and their corresponding fourth slopes are used to construct a second training dataset. The second training dataset includes multiple second training data, each of which includes feature data and a corresponding third slope. Thus, a first surrogate model can be trained using the first training dataset, and a second surrogate model can be trained using the second training dataset.

[0107] For example, feature data from the first training data can be input into the first surrogate model; the loss information of the first surrogate model can be calculated based on the output of the first surrogate model and the third slope in the first training data; the parameters of the first surrogate model can be adjusted based on the loss information of the first surrogate model, thereby achieving the training of the first surrogate model.

[0108] For example, feature data from the second training data can be input into the second proxy model; the loss information of the second proxy model can be calculated based on the output of the second proxy model and the fourth slope in the second training data; the parameters of the second proxy model can be adjusted based on the loss information of the second proxy model, thereby achieving the training of the second proxy model.

[0109] The first surrogate model can be trained directly using the first training dataset. Alternatively, the first training data in the first training dataset can be preprocessed. The preprocessed first training dataset can then be used to train the first surrogate model. Similarly, the second surrogate model can be trained directly using the second training dataset. Alternatively, the second training data in the second training dataset can be preprocessed. The preprocessed second training dataset can then be used to train the first surrogate model. Preprocessing may include outlier removal, normalization, etc.

[0110] In some embodiments, as well depth increases, there may be a deviation between the predicted composite build-up rate and the actual build-up rate. Therefore, the predicted composite build-up rate can be compared with the actual build-up rate. If the difference between the predicted composite build-up rate and the actual build-up rate exceeds a preset threshold, the surrogate model can be corrected. Specifically, if the difference between the predicted composite build-up rate and the actual build-up rate exceeds the preset threshold, the current state of directional build-up or stable build-up mode can be identified based on the collected drilling parameters and / or operation instructions. If in directional build-up mode, the corresponding limiting build-up rate can be calculated based on the actual build-up rate; the first values ​​of various collected drilling parameters can be used as feature data; the feature data and the corresponding limiting build-up rate can be added to the first training dataset as new first training data. The first surrogate model can be trained using the new first training dataset to correct the first surrogate model. If the drilling is in a stable build-up mode, the corresponding limiting build-up rate can be calculated based on the actual build-up rate. The first values ​​of various collected drilling parameters can be used as feature data. The feature data and the corresponding limiting build-up rate can be added to the second training dataset as new second training data. The second surrogate model can be trained using this new second training dataset to correct its performance. This continuously improves the surrogate model's adaptability to the current block and the current drill string combination.

[0111] The actual slope rate can be divided by the conversion factor to obtain the corresponding limiting slope rate.

[0112] The technical solution of this specification embodiment can determine the operating ratio between directional drilling mode and stable drilling mode during drilling; it can collect first values ​​of various drilling parameters of the rotary steerable system; based on the first values ​​of the various drilling parameters, it can use a surrogate model to predict a first build-up rate and a second build-up rate, where the first build-up rate is the limiting build-up rate in directional drilling mode and the second build-up rate is the limiting build-up rate in stable drilling mode; the surrogate model is used to represent the correlation between the various drilling parameters of the rotary steerable system and the build-up rate; based on the operating ratio, the first build-up rate and the second build-up rate can be fused to obtain a composite working condition build-up rate. Therefore, this specification embodiment, for both directional drilling and stable drilling conditions, uses a surrogate model to predict the first and second build-up rates corresponding to the two working conditions, and then fuses the first and second build-up rates based on the operating ratio of the two working conditions to obtain a build-up rate conforming to the disclosure. This specification embodiment, for the two working conditions that exist in actual rotary steerable systems, can quickly and accurately determine the build-up rate of the rotary steerable system through a surrogate model.

[0113] The technical solution of this specification provides a data-mechanism fusion method for predicting the build-up rate of a rotary steerable drilling system. This method, based on fully utilizing the mechanical characteristics of the drill string assembly and the drill bit-formation interaction mechanism, introduces an operational ratio parameter to characterize directional build-up and stabilization conditions. It also trains a data proxy model by generating training data offline using a mechanistic model, enabling real-time prediction and online correction of the build-up rate during rotary steerable drilling. Because the data proxy model is trained using offline training data generated from the mechanistic model, the dependence on large-scale real-world drilling data during model training is reduced, while still maintaining high prediction accuracy for the proxy model.

[0114] The embodiments described in this specification also have the following technical effects.

[0115] The present invention may also include the following beneficial effects:

[0116] (1) For the dual operation modes of directional tilting and stabilization of the rotary guide system, a dual-condition limit tilting rate model was established and operation ratio parameters were introduced to realize the prediction of tilting rate under composite conditions, which is conducive to truly reflecting the actual operation process.

[0117] (2) A large amount of training data is generated offline through the mechanism model and fused with limited field data for training, so that high prediction accuracy can still be maintained when the scale of field data is limited or the working conditions change greatly, thus reducing the dependence on large-scale actual drilling data.

[0118] (3) An online correction mechanism is introduced, which can dynamically update the build-up rate prediction model according to parameter fluctuations and working condition switching during the drilling process. It is highly adaptable and suitable for complex wellbore trajectory control and real-time trajectory optimization.

[0119] Please see Figure 3 This specification provides an embodiment of a rotary guide system slope prediction device, comprising the following units.

[0120] Unit 31 is used to determine the operating ratio between directional drilling mode and stabilization mode during the drilling process;

[0121] Acquisition unit 32 is used to acquire the first values ​​of various drilling parameters of the rotary steering system;

[0122] Prediction unit 33 is used to predict a first build-up rate and a second build-up rate based on the first values ​​of the various drilling parameters using a surrogate model. The first build-up rate is the limiting build-up rate in the directional build-up mode, and the second build-up rate is the limiting build-up rate in the stable build-up mode. The surrogate model is used to represent the correlation between the various drilling parameters of the rotary steering system and the build-up rate.

[0123] The fusion unit 34 is used to fuse the first ramp rate and the second ramp rate according to the operation ratio to obtain the composite ramp rate.

[0124] This specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described slope prediction method.

[0125] This specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described slope prediction method.

[0126] This specification also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described slope prediction method.

[0127] Those skilled in the art will understand that this specification can be provided as a method, system, or computer program product. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may 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.

[0128] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments thereof. It should 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. The computer may be a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0129] The functional units in the embodiments of this specification can be integrated into one processing unit, or each functional unit can exist physically separately, or two or more functional units can be integrated into one processing unit.

[0130] Those skilled in the art will understand that the descriptions of the various embodiments in this specification have different focuses, and parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. Furthermore, it is understood that those skilled in the art, after reading this specification, can conceive of any combination of some or all of the embodiments listed in this specification without creative effort, and such combinations are also within the scope of disclosure and protection of this specification.

[0131] Although this specification has been described through embodiments, those skilled in the art will understand that the above embodiments are merely illustrative of the core ideas of this specification. Those skilled in the art will appreciate that many variations and modifications are possible with this specification. It is intended that the appended claims encompass these variations and modifications without departing from the spirit of this specification.

Claims

1. A method for predicting the tilt rate of a rotary steering system, characterized in that, include: Determine the operational ratio between directional drilling mode and stabilization mode during the drilling process; Collect the first values ​​of various drilling parameters of the rotary steering system; Based on the first values ​​of the various drilling parameters, a surrogate model is used to predict the first build-up rate and the second build-up rate. The first build-up rate is the limiting build-up rate in the directional build-up mode, and the second build-up rate is the limiting build-up rate in the stable build-up mode. The surrogate model is used to represent the correlation between the various drilling parameters of the rotary steering system and the build-up rate. Based on the operating ratio, the first ramp rate and the second ramp rate are combined to obtain the composite operating condition ramp rate.

2. The method according to claim 1, characterized in that, Determining the operational ratio between directional drilling mode and stabilization mode during drilling includes: Identify the current well section's operating mode, which is selected from directional drilling mode and inclination stabilization mode; At each specified well depth interval, the operation ratio is calculated based on the operation mode of each well section within the specified well depth.

3. The method according to claim 1, characterized in that, The method of using a surrogate model to predict the first and second slope rates includes: Calculate the difference between a first value and a second value for each drilling parameter, wherein the acquisition time of the second value is adjacent to and earlier than the acquisition time of the first value; The number of drilling parameters whose statistical differences are greater than or equal to the first set threshold; If the number of drilling parameters counted meets the prediction conditions, the first and second build-up rates are predicted using a surrogate model.

4. The method according to claim 1, characterized in that, The proxy model includes a first proxy model and a second proxy model. The first proxy model corresponds to the directional tilting mode, and the second proxy model corresponds to the tilting stabilization mode. The method of using a surrogate model to predict the first and second slope rates includes: The first values ​​of the various drilling parameters are input into the first surrogate model to obtain the first build-up rate; The first values ​​of the various drilling parameters are input into the second proxy model to obtain the second build-up rate.

5. The method according to claim 4, characterized in that, The method further includes: Feature data is constructed based on the value range of various drilling parameters. The feature data includes one value of each of the various drilling parameters. Based on each feature data, the third and fourth inclination rates are calculated using the mechanism model of the rotary steering system. The third inclination rate is the limiting inclination rate in the directional inclination mode, and the fourth inclination rate is the limiting inclination rate in the steady inclination mode. The first surrogate model is trained based on the feature data and the third slope. The second surrogate model is trained based on the feature data and the fourth slope.

6. The method according to claim 5, characterized in that, The mechanism model of the rotary guide system calculates the third slope, including: According to the formula Calculate the third slope; where, Indicates the third slope. Indicates the build-up rate on the well inclination plane. Indicates the slope on the azimuth plane; and Through formula Calculated; This represents the drilling speed component along the drill bit's axial direction, where k is selected from 0 and 1. Represents the drilling rate component on the well inclination plane. This represents the drilling velocity component on the azimuth plane; , Let R represent the normal drilling efficiency, R represent the transformation matrix between bottom hole coordinates and formation coordinates, and S represent the transformation matrix between bottom hole coordinates and drill bit coordinates. Indicates the anisotropy index of the stratigraphy. This represents the anisotropy index of the drill bit, and F1 represents the axial force at the drill bit. This indicates the support reaction force at the drill bit.

7. The method according to claim 5, characterized in that, The mechanism model of the rotary guide system calculates the fourth slope, including: Obtain multiple values ​​of the tool face angle within one rotation cycle; Through formula Calculate the slope rate corresponding to each tool face angle value; This represents a value of the tool face angle. Indicates the value of the tool face angle The corresponding slope, Indicates the value of the tool face angle The corresponding build-up rate on the well inclination plane, Indicates the value of the tool face angle The slope of the corresponding azimuth plane; The fourth inclination rate is calculated based on the inclination rates corresponding to the values ​​of multiple tool face angles.

8. The method according to claim 1, characterized in that, The fusion of the first slope rate and the second slope rate includes: Using formula The first and second slope rates are fused together; Indicates the slope of the composite working condition. Indicates the first slope. λ represents the second slope, λ represents the conversion factor, and l represents the operation ratio.

9. A device for predicting the inclination rate of a rotary guide system, characterized in that, include: The determination unit is used to determine the operational ratio between directional drilling mode and stabilization mode during the drilling process; The acquisition unit is used to acquire the first values ​​of various drilling parameters of the rotary steering system; The prediction unit is used to predict a first build-up rate and a second build-up rate based on the first values ​​of the various drilling parameters using a surrogate model. The first build-up rate is the limiting build-up rate in the directional build-up mode, and the second build-up rate is the limiting build-up rate in the stable build-up mode. The surrogate model is used to represent the correlation between the various drilling parameters of the rotary steering system and the build-up rate. The fusion unit is used to fuse the first ramp rate and the second ramp rate according to the operation ratio to obtain the composite ramp rate.

10. A computer device, characterized in that, The computer device includes a processor and memory; The memory is used to store a computer program that can run on the processor, which, when executing the computer program, implements the instructions of the method according to any one of claims 1-8.

Images