Design method and device of casing centralizer for cementing and casing centralizer for cementing

Abstract

This invention discloses a design method for a casing centralizer used in cementing and a casing centralizer for cementing. The method includes: generating a wellbore-centralizer model based on a data set of multiple main control factors affecting centralizer performance and calculating the corresponding horizontal well cement displacement efficiency value and swirl section length; training a neural network based on the data set of multiple main control factors and the horizontal well cement displacement efficiency value and swirl section length to obtain a centralizer optimization design database model; inputting the design data of multiple main control factors of the centralizer to be designed into the centralizer optimization design database model; determining and outputting qualified design data based on the displacement efficiency value and swirl section length output by the model. This invention predicts the displacement efficiency and swirl section length corresponding to different design parameters through the centralizer optimization design database model, and selects qualified centralizer design parameters accordingly, which can ensure the maximization of horizontal well displacement efficiency and provide accurate guidance for centralizer design.

Description

Technical Field

[0001] This invention relates to the field of oil and gas field development technology, and in particular to a design method and device for a cementing casing centralizer and a cementing casing centralizer. Background Technology

[0002] Cementing, a crucial operation in drilling and completion engineering, is a key technological process in the drilling process. In horizontal well cementing operations, many factors influence cementing quality, among which maintaining a high casing centering and displacement efficiency in the horizontal well section is critical. Casing centralizers are an indispensable completion string tool for improving casing centering and displacement efficiency, especially in horizontal well sections where the casing's gravity makes it difficult to center within the horizontal wellbore, severely impacting cementing displacement efficiency and cementing quality.

[0003] In the existing technology, rigid roller centralizers, hydraulic centralizers, and semi-rigid centralizers have been developed and applied to address the problems of difficulty in running and centering horizontal well casings, which to some extent meet the requirements for smooth running of horizontal well casings. However, horizontal well sections often require high casing centering and displacement efficiency. How to meet this requirement is a research hotspot in this field. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed to provide a design method and apparatus for a cementing casing centralizer and a cementing casing centralizer that overcomes or at least partially solves the above problems.

[0005] In a first aspect, embodiments of the present invention provide a design method for a casing centralizer for cementing, characterized in that it includes:

[0006] Determine the operating parameters of the horizontal well section using cementing data;

[0007] Based on the engineering parameters of the horizontal well section, the physical parameters of the casing centralizer for cementing are determined; the centralizer is a stamped semi-rigid spiral centralizing rib structure.

[0008] Multiple key control factors affecting the performance of the centralizer are determined from the physical parameters, and multiple key control factor data groups are generated within a preset range. Each key control factor data group contains data of the multiple key control factors, and the data sizes of the multiple key control factors in different key control factor data groups are not completely equal.

[0009] For each set of main control factor data, a corresponding wellbore-centralizer model is generated, and the cement displacement efficiency value and swirl section length of the horizontal well corresponding to the wellbore-centralizer model are calculated.

[0010] Based on multiple control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length, a pre-architected neural network is trained to obtain the centralizer optimization design database model.

[0011] The design data of multiple key control factors of the centralizer to be designed are input into the centralizer optimization design database model, and the displacement efficiency value and swirl section length of the centralizer to be designed corresponding to the key control factor data group are output.

[0012] Based on the output displacement efficiency value and swirl section length, determine whether the design data of the multiple main control factors are qualified, and use the qualified design data of the multiple main control factors as the design parameters of the centralizer to be designed.

[0013] In one embodiment, determining the engineering parameters of the horizontal well section using cementing data includes:

[0014] The trajectory, wellbore radius, casing radius, annular fluid density, and construction displacement of the horizontal well section are determined by cementing data. The six-velocity value of the cementing annular fluid is measured by a six-velocity rotary viscometer, and the consistency coefficient, yield stress, and flow index are obtained by fitting the six-velocity value according to the Herba model.

[0015] In one embodiment, the physical parameters of the casing centralizer for cementing include:

[0016] The centralizer's inner diameter, outer diameter, length, number of edges, edge helix angle, and height, centralizer volume fraction, as well as the centralizer's flow capacity and swirl section length.

[0017] In one embodiment, multiple key factors affecting the performance of the centralizer are determined from the physical parameters, and multiple key factor data sets are generated within a preset range, including:

[0018] From the physical parameters, the number of edges, the edge spiral angle, and the height of the stabilizer are selected as the main control factors. Within the range of 2-8 edges N, 30-60° edge spiral angle θ, and 180-260mm stabilizer height L, multiple data sets containing the number of edges, edge spiral angle, and stabilizer height are generated.

[0019] In one embodiment, calculating the cement displacement efficiency and swirl section length of the horizontal well corresponding to the wellbore-centralizer model includes:

[0020] In the preset fluid dynamics simulation software, based on the force balance analysis of fluid micro-elements, cementing displacement is constructed based on the fluid volume method. The displacement motion model corresponding to the wellbore-centralizer model is composed of the eccentric annular geometric equation, continuity equation, momentum equation, Herba model and interface motion equation.

[0021] Determine the initial and boundary conditions for cement displacement annulus flow in horizontal wells;

[0022] Based on the initial and boundary conditions, the pressure-velocity coupling algorithm is used to numerically solve the displacement motion model, and the horizontal well cementing displacement efficiency and swirl section length are calculated for each wellbore-centralizer model.

[0023] In one embodiment, the initial condition is: the annulus is filled with drilling fluid, and the pre-flush fluid and cement slurry flow in from the inlet at a certain initial velocity; the boundary condition is a wall-slip-free boundary condition.

[0024] In one embodiment, the pre-architected neural network is a BP neural network; the neural network includes an input layer, a hidden layer, and an output layer; wherein, the input layer is used to input vectors of each controlling factor data in multiple controlling factor data groups; the hidden layer is used to characterize the mapping function relationship between the number of edges, the edge helix angle, and the centralizer height and the displacement efficiency value and the swirl section length; the output layer is used to output the horizontal well cement displacement efficiency value and the swirl section length;

[0025] Based on multiple key control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length, a pre-architected neural network is trained to obtain the centralizer optimization design database model, including:

[0026] The multiple sets of main control factor data, along with the corresponding horizontal well cement displacement efficiency values ​​and swirl section lengths, are used to generate multiple sets of training data. The following steps are then iteratively executed: the training data is input into the BP neural network for forward propagation, the value of the loss function is calculated, and backpropagation is performed based on the value of the loss function to update the parameters of the neural network until the value of the loss function reaches a preset convergence state, thereby obtaining the centralizer optimization design database model.

[0027] Secondly, embodiments of the present invention provide a design device for a casing centralizer for cementing, comprising:

[0028] The operating condition parameter determination module is used to determine the operating condition parameters of the horizontal well section based on cementing data.

[0029] The centralizer physical parameter determination module is used to determine the operating parameters of the horizontal well section based on cementing data;

[0030] The main control factor determination module is used to determine multiple main control factors affecting the performance of the centralizer from the physical parameters, and generate multiple main control factor data groups within a preset range. Each main control factor data group contains data of the multiple main control factors, and the data sizes of the multiple main control factors in different main control factor data groups are not completely equal.

[0031] The wellbore-centralizer model generation module is used to generate a corresponding wellbore-centralizer model for each set of key control factor data.

[0032] The wellbore-centralizer model calculation module is used to calculate the cement displacement efficiency value and swirl section length of the horizontal well corresponding to the wellbore-centralizer model.

[0033] The neural network model training module is used to train a pre-architected neural network based on multiple main control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length, so as to obtain the centralizer optimization design database model.

[0034] The centralizer optimization design database model module is used to input data of multiple main control factors of the centralizer to be designed, and output the displacement efficiency value and swirl section length of the centralizer to be designed corresponding to the main control factor data group.

[0035] The design parameter determination module is used to determine whether the data of the multiple main control factors are qualified based on the output displacement efficiency value and swirl section length, and to use the qualified data of the multiple main control factors as the design parameters of the centralizer to be designed.

[0036] Thirdly, embodiments of the present invention provide a computing device, including a processor and a memory for storing processor-executable commands; wherein the processor is configured to execute the aforementioned design method for a casing centralizer for cementing.

[0037] Fourthly, embodiments of the present invention provide a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the design method for a cementing casing centralizer as described above.

[0038] Fifthly, embodiments of the present invention provide a casing centralizer for cementing, wherein the casing centralizer is a stamped semi-rigid spiral centralizer structure; the number of ridges, the spiral angle of the ridges, and the height of the centralizer are obtained by the design method for the casing centralizer for cementing as described above.

[0039] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0040] The cementing casing centralizer design method and device, and the cementing casing centralizer provided in this invention embodiment, construct an integrated centralizer-wellbore model by considering multiple main control factors affecting centralizer performance. A BP neural network is used to incorporate different basic data of the centralizer, exploring the influence of different combinations of centralizer design parameters on the centralizer displacement efficiency and swirl section length. A centralizer optimization design database model trained by the BP neural network predicts the centralizer displacement efficiency and swirl section length corresponding to different design parameters. Based on this, qualified centralizer design parameters are selected, ensuring that the selected design parameters maximize the displacement efficiency of horizontal wells, providing accurate guidance for on-site centralizer design.

[0041] The embodiments of the present invention can meet the requirements of casing centering and cementing displacement efficiency for different well diameters and different fluids in horizontal well sections. The designed cementing casing centralizer has the characteristics of simple structure and low construction risk.

[0042] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0043] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0044] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0045] Figure 1 This is a flowchart illustrating the design method of a casing centralizer for cementing in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram illustrating the prediction of displacement efficiency and swirl section length by a centralizer optimization design database model obtained through BP neural network training in an embodiment of the present invention.

[0047] Figure 3 This is a schematic diagram illustrating the correspondence between the centralizer wellbore displacement efficiency value and the centralizer height calculated in Embodiment 1 of the present invention.

[0048] Figure 4 This is a structural block diagram of the cementing casing centralizer design device in an embodiment of the present invention. Detailed Implementation

[0049] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0050] To address the current issues of casing centering and displacement efficiency in horizontal well sections, this invention provides a design method for a casing centralizer used in cementing.

[0051] The design method for a cementing casing centralizer provided in this embodiment of the invention refers to... Figure 1 As shown, it includes the following steps:

[0052] S11. Determine the operating parameters of the horizontal well section using cementing data;

[0053] S12. Determine the physical parameters of the casing centralizer for cementing based on the engineering parameters of the horizontal well section; the centralizer is a stamped semi-rigid spiral centralizer structure.

[0054] The stamped semi-rigid spiral centralizing rib structure has multiple spiral ribs. The centralizing ribs are usually long strip-shaped structures that are raised and regularly arranged on the circumference of the centralizer body. Their cross-sectional shape is commonly rectangular, and when viewed from the side, they look like "ribs" extending vertically or at a certain spiral angle along the outer wall of the centralizer; there are also centralizing ribs with trapezoidal cross-sections. The hypotenuse of the trapezoid can play a guiding role to a certain extent, making it easier for the centralizer to be lowered into the well.

[0055] There are usually multiple straightening ridges, which are evenly wrapped around the straightener.

[0056] During drilling, the drill string is situated in a complex downhole environment, making it prone to tilting and eccentricity. The centering ribs, in contact with the wellbore, rely on their rigid structure to support the drill string from multiple directions, keeping it as centered as possible in the wellbore. This ensures the accuracy of subsequent drilling direction and prevents excessive wellbore trajectory deviation or curvature. Furthermore, the gaps between the centering ribs create specific flow channels, optimizing the annular flow of drilling mud within the wellbore. This results in more uniform mud distribution, better removal of cuttings, and improved drilling efficiency.

[0057] The specific form of the stamped semi-rigid spiral straightening rib structure can be referred to existing technology.

[0058] S13. Determine multiple main control factors affecting the performance of the centralizer from the physical parameters, and generate multiple main control factor data groups within a preset range. Each main control factor data group contains data of the multiple main control factors, and the data sizes of the multiple main control factors in different main control factor data groups are not completely equal.

[0059] S14. For each group of main control factor data, generate the corresponding wellbore-centralizer model, and calculate the cement displacement efficiency value and swirl section length of the horizontal well corresponding to the wellbore-centralizer model.

[0060] S15. Based on multiple control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length, the pre-architected neural network is trained to obtain the centralizer optimization design database model.

[0061] S16. Input the design data of multiple main control factors of the centralizer to be designed into the centralizer optimization design database model, and output the displacement efficiency value and swirl section length of the centralizer to be designed corresponding to the main control factor data group.

[0062] S17. Based on the output displacement efficiency value and swirl section length, determine whether the design data of multiple main control factors are qualified, and use the qualified design data of multiple main control factors as the design parameters of the centralizer to be designed.

[0063] In one embodiment, the determination of engineering parameters for the horizontal well section using cementing data in step S11 above can be achieved in the following manner:

[0064] The trajectory of the horizontal well section, wellbore radius R1, casing radius R2, annular fluid density ρ, and construction displacement Q are determined by cementing data. The six-speed value of the cementing annular fluid is measured by a six-speed rotational viscometer, and the consistency coefficient K, yield stress τ0, and flow index n are obtained by fitting the six-speed value according to the Herba model.

[0065] In one embodiment, the physical parameters of the cementing casing centralizer in step S12 above include: the centralizer inner diameter D. m Outer diameter D n Length H, number of edges N, edge helix angle θ, and centralizer height L, centralizer volume fraction V f , as well as the flow capacity of the centralizer and the length of the swirl section.

[0066] Among them, B f The formula for expressing the current-carrying capacity of the centralizer is as follows:

[0067]

[0068] S represents the length of the vortex section, which is the axial distance from the end face of the centralizer to the vortex surface. This parameter is related to the aforementioned wellbore radius R1, casing radius R2, and centralizer inner diameter D. m Outer diameter D n The construction displacement Q, yield stress τ0, consistency coefficient K, flow index n, annular fluid density ρ, centralizer height L, and prism helix angle θ exhibit a certain functional relationship, which can be expressed as the following expression:

[0069] S=f(D n D m Formula 2;

[0070] In one embodiment, in step S13 above, the number of edges, the edge spiral angle, and the height of the stabilizer are selected from the physical parameters as the multiple main control factors, and multiple data sets containing the number of edges, the edge spiral angle, and the stabilizer height are generated within the range of 2-8 edges N, 30-60° edge spiral angle θ, and 180-260mm.

[0071] The values ​​for the number of edges, edge spiral angle, and straightener height contained in different data sets are not entirely equal.

[0072] In one embodiment, based on the multiple control factor data sets generated in the aforementioned step S13, an integrated wellbore-centralizer model can be constructed, for example, using ICEM software.

[0073] In one embodiment, the calculation of the cement displacement efficiency and swirl section length of the horizontal well corresponding to the wellbore-centralizer model can be achieved in the following manner:

[0074] 1.1) In the preset fluid dynamics simulation software, based on the force balance analysis of fluid micro-elements, cementing displacement is constructed based on the fluid volume method. The displacement motion model corresponding to the wellbore-centralizer model is composed of the eccentric annular geometric equation, continuity equation, momentum equation, Herba model and interface motion equation.

[0075] The above eccentric annular geometric equations are:

[0076]

[0077] Where H is the annular space clearance, e is the casing eccentricity, and θ is the circumferential angle;

[0078] R1 is the wellbore radius, R2 is the casing radius, and ε is the casing eccentricity.

[0079] The continuity equation above is:

[0080]

[0081] Where v is velocity, t is time, f is force per unit mass of fluid, ρ is fluid density, and σ is total stress.

[0082] The momentum equation is:

[0083]

[0084] Where ρ is density, v is velocity, t is time, divT is surface tensile stress, and T is the stress tensor matrix, which includes normal stress and tangential stress.

[0085] The interface motion equations are determined in the following manner:

[0086] The VOF fluid volume method is used to establish the interface tracer equation under the Eulerian grid. Within each control volume, the sum of the volume fractions of all fluid phases is 1, then α1 + α2 + α3 = 1. The variable within any given control volume is determined by the phase volume fraction, which dictates whether fluid mixing exists within it. That is, in the computational cell, if the volume fraction of the q-th phase fluid is α... q ,but:

[0087] (a)α q =0, indicating that there is no q-th phase fluid within the computational unit;

[0088] (b)α q =1, the computational unit is filled with the q-th phase fluid;

[0089] (c)0<α q <1, the calculation unit contains the q-th phase fluid and other single-phase or multi-phase fluids.

[0090] In the VOF model, the physical properties of each phase of the fluid within the control volume are determined by its volume fraction. In a multiphase system, the volume fraction average density equation is:

[0091] ρ=∑α q ρ q Formula Six;

[0092] The Herba model is:

[0093] τ=τ y +K′γ n′ Formula 7;

[0094] Where τ y Let τ be the static shear force, K′ be the consistency coefficient, n′ be the flow index, τ be the shear stress (dependent variable), and γ be the shear rate (independent variable).

[0095] In one embodiment, the fluid dynamics simulation software may be, for example, FLUENT software.

[0096] 1.2) Determine the initial and boundary conditions for cement injection to displace the annulus in horizontal wells;

[0097] In one embodiment, the initial conditions in this step are: the annulus is filled with drilling fluid, and the pre-flush fluid and cement slurry flow in from the inlet at a certain initial velocity; the boundary condition is a wall-slip-free boundary condition.

[0098] 1.3) Based on the initial and boundary conditions, the pressure-velocity coupling algorithm is used to numerically solve the displacement motion model, and the horizontal well cementing displacement efficiency and swirl section length are calculated for each wellbore-centralizer model.

[0099] In one embodiment, in step S15 above, the pre-architected neural network is a backpropagation (BP) neural network.

[0100] The BP neural network includes an input layer, a hidden layer, and an output layer. The input layer is used to input vectors of the main control factor data from multiple main control factor data groups. The hidden layer is used to represent the mapping function relationship between the number of edges, the edge helix angle, and the centralizer height with the displacement efficiency value and the swirl section length. The output layer is used to output the cement displacement efficiency value and the swirl section length of the horizontal well.

[0101] Reference Figure 2 As shown, the structure of a BP neural network includes an input layer, a hidden layer, and an output layer connected in sequence.

[0102] The input layer is used to input factors 1 to factors n;

[0103] The output layer is used to replace efficiency and swirl section length.

[0104] The training process of the above-mentioned BP neural network can be implemented, for example, in the following way:

[0105] The multiple sets of main control factor data are combined with the corresponding horizontal well cement displacement efficiency value and swirl section length to generate multiple sets of training data;

[0106] The following steps are performed iteratively: input the training data into the BP neural network for forward propagation, calculate the value of the loss function, and backpropagate based on the value of the loss function to update the parameters of the neural network until the value of the loss function reaches the preset convergence state, thereby obtaining the positive stabilizer optimization design database model.

[0107] Finally, the trained BP neural network, i.e., the centralizer optimization design database model, is used to predict the displacement efficiency and swirl section length of the given design parameters.

[0108] Reference Figure 2As shown, for example, the design data of multiple key control factors of the centralizer to be designed are input into the centralizer optimization design database model, and the predicted values ​​of displacement efficiency and swirl section length are output. If the displacement efficiency value is obtained... If the flow rate is greater than 95% and the swirl section length S is greater than 5m, the centralizer design parameters are valid and the design parameters are output; otherwise, the centralizer parameters are redesigned.

[0109] The implementation process of S11-S14 in the above-mentioned cementing casing centralizer design method provided by the present invention will be described below with several embodiments. The steps of training the BP neural network after Embodiment 1 and Embodiment 2, and determining qualified design parameters using the trained centralizer optimization design database model, can be referred to the foregoing embodiments.

[0110] Example 1:

[0111] Step (1): In this embodiment, the casing cementing parameters of a vertical well in the oil layer are selected as the basis for calculation. The basic conditions of the well are as follows: the casing diameter is 139.7 mm, the drill bit size is 215.9 mm, considering the well diameter enlargement rate of 4%, the wellbore size is 225 mm, and the drilling displacement is 1.5 m³ / h. 3 / min. For ease of calculation, the horizontal section of the wellbore is assumed to be 10m long (one casing length), and a centralizer is installed. The fluid properties are shown in Table 1.

[0112] Table 1. Physical properties of cementing annulus fluids

[0113]

[0114] Step (2): Calculate the edge height to ensure the casing is centered by more than 67% using the casing radius and wellbore radius. There are 4 edges, each with an angle of 30°. The calculated outer diameter of the centralizer is 208mm. Using the centralizer height as the dependent variable, two sets of centralizer models with diameters of 180mm and 245mm are randomly generated.

[0115] Step (3): Based on the generated data set, two integrated models of wellbore-centralizer are established using ICEM software.

[0116] Step (4): Input the above parameters and the constructed model into the FLUENT software for calculation, which can be divided into the following steps:

[0117] Step (4-1): Based on the force balance analysis of the fluid micro-element, a cement displacement is constructed based on the fluid volume method. The displacement motion model consists of the eccentric annular geometric equation, continuity equation, momentum equation, Herba model, and interface motion equation.

[0118] Step (4-2): Determine the initial and boundary conditions for cement injection to displace the annulus flow in the horizontal well.

[0119] Step (4-3): The pressure-velocity coupled Coupled algorithm is used for numerical solution. The displacement efficiency of the wellbore with a centralizer placement height of 180mm is 93.6%, and the displacement efficiency of the centralizer model with a height of 245mm is 95.2%. Figure 3 As shown.

[0120] Example 2:

[0121] Step 1: In this embodiment, the casing cementing parameters of a vertical well in the oil layer are selected as the basis for calculation. The basic conditions of the well are as follows: casing vertical diameter is 139.7mm, drill bit size is 215.9mm, considering a wellbore enlargement rate of 10%, wellbore size is 237.5mm, and drilling displacement is 1.5m³. 3 / min. For ease of calculation, the length of the horizontal section of the wellbore is considered to be 10m, the length of one casing, and a centralizer is installed. The physical properties of the fluid are shown in Table 2.

[0122] Table 2 Physical properties of cementing annulus fluids

[0123]

[0124] Step (2): Calculate the casing radius and wellbore radius to ensure that the casing is centered at a height greater than 67%. The height of the centralizer is 245mm and the angle of the edges is 30°. The outer diameter of the centralizer is calculated to be 213mm. The number of edges of the centralizer is used as the dependent variable to randomly generate two sets of centralizer models with 3 edges and 5 edges respectively.

[0125] Step (3): Based on the generated data set, two integrated models of wellbore-centralizer are established using ICEM software.

[0126] Step (4): Input the above parameters and the constructed model into the FLUENT software for calculation, which can be divided into the following steps:

[0127] Step (4-1): Based on the force balance analysis of the fluid micro-element, a cement displacement is constructed based on the fluid volume method. The displacement motion model consists of the eccentric annular geometric equation, continuity equation, momentum equation, Herba model, and interface motion equation.

[0128] Step (4-2): Determine the initial and boundary conditions for cement injection to displace the annulus flow in the horizontal well.

[0129] Step (4-3): The pressure-velocity coupled Coupled algorithm is used for numerical solution. The displacement efficiency of the wellbore with 3 ridges is 92.1%, and the displacement efficiency of the wellbore with 5 ridges is 95.4%.

[0130] Based on the same inventive concept, embodiments of the present invention also provide a design device for a cementing casing centralizer and a cementing casing centralizer. Since the principle by which these devices solve the problem is similar to the aforementioned design method for a cementing casing centralizer, the implementation of the device can refer to the implementation of the aforementioned method, and the repeated parts will not be described again.

[0131] This invention provides a design device for a casing centralizer for cementing, referring to... Figure 4 As shown, it includes:

[0132] The operating condition parameter determination module 41 is used to determine the operating condition parameters of the horizontal well section through cementing data;

[0133] The centralizer physical parameter determination module 42 is used to determine the operating parameters of the horizontal well section through cementing data;

[0134] The main control factor determination module 43 is used to determine multiple main control factors affecting the performance of the centralizer from the physical parameters, and generate multiple main control factor data groups within a preset range. Each main control factor data group contains data of the multiple main control factors, and the data sizes of the multiple main control factors in different main control factor data groups are not completely equal.

[0135] The wellbore-centralizer model generation module 44 is used to generate a corresponding wellbore-centralizer model for each group of main control factor data.

[0136] The wellbore-centralizer model calculation module 45 is used to calculate the cement displacement efficiency value and swirl section length of the horizontal well corresponding to the wellbore-centralizer model.

[0137] The neural network model training module 46 is used to train the pre-structured neural network based on multiple main control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length to obtain the centralizer optimization design database model.

[0138] The centralizer optimization design database model module 47 is used to input data of multiple main control factors of the centralizer to be designed, and output the displacement efficiency value and swirl section length of the centralizer to be designed corresponding to the main control factor data group.

[0139] The design parameter determination module 48 is used to determine whether the data of the multiple main control factors are qualified based on the output displacement efficiency value and swirl section length, and to use the qualified data of the multiple main control factors as the design parameters of the centralizer to be designed.

[0140] An embodiment of the present invention provides a computing device, including a processor and a memory for storing processor-executable commands; wherein the processor is configured to execute the aforementioned design method for a casing centralizer for cementing.

[0141] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned design method for a cementing casing centralizer.

[0142] The present invention provides a computer program product, which includes a computer program that, when executed by a processor, implements the design method for a cementing casing centralizer as described above.

[0143] This invention provides a casing centralizer for cementing, wherein the casing centralizer is a stamped semi-rigid spiral centralizing rib structure; the number of ribs, the spiral angle of the ribs, and the height of the centralizer are obtained by the design method of the casing centralizer for cementing as described above.

[0144] Regarding the design device for the casing centralizer in the above embodiments, the specific methods by which each module performs its operation have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0145] The cementing casing centralizer design method and device, and the cementing casing centralizer provided in this invention embodiment, construct an integrated centralizer-wellbore model by constructing multiple main control factors affecting centralizer performance. A BP neural network is used to incorporate different basic data of the centralizer, exploring the influence of different combinations of centralizer design parameters on the centralizer displacement efficiency and swirl section length. A centralizer optimization design database model trained by the BP neural network predicts the centralizer displacement efficiency and swirl section length corresponding to different design parameters. Based on this, qualified centralizer design parameters are selected, ensuring that the selected design parameters maximize the displacement efficiency of horizontal wells, providing accurate guidance for on-site centralizer design.

[0146] The embodiments of the present invention can meet the requirements of casing centering and cementing displacement efficiency for different well diameters and different fluids in horizontal well sections. The designed cementing casing centralizer has the characteristics of simple structure and low construction risk.

[0147] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 and optical storage) containing computer-usable program code.

[0148] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0149] 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.

[0150] 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.

[0151] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method of designing a casing centralizer for cementing, characterized by, include: ； Determine the operating parameters of the horizontal well section using cementing data; Based on the engineering parameters of the horizontal well section, the physical parameters of the casing centralizer for cementing are determined; the centralizer is a stamped semi-rigid spiral centralizing rib structure. Multiple key control factors affecting the performance of the centralizer are determined from the physical parameters, and multiple key control factor data groups are generated within a preset range. Each key control factor data group contains data of the multiple key control factors, and the data sizes of the multiple key control factors in different key control factor data groups are not completely equal. For each set of main control factor data, a corresponding wellbore-centralizer model is generated, and the cement displacement efficiency value and swirl section length of the horizontal well corresponding to the wellbore-centralizer model are calculated. Based on multiple control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length, a pre-architected neural network is trained to obtain the centralizer optimization design database model. The design data of multiple key control factors of the centralizer to be designed are input into the centralizer optimization design database model, and the displacement efficiency value and swirl section length of the centralizer to be designed corresponding to the key control factor data group are output. Based on the output displacement efficiency value and swirl section length, determine whether the design data of the multiple main control factors are qualified, and use the qualified design data of the multiple main control factors as the design parameters of the centralizer to be designed.

2. The method of claim 1, wherein, Determine the engineering parameters of the horizontal well section using cementing data, including: The trajectory, wellbore radius, casing radius, annular fluid density, and construction displacement of the horizontal well section are determined by cementing data. The six-velocity value of the cementing annular fluid is measured by a six-velocity rotary viscometer, and the consistency coefficient, yield stress, and flow index are obtained by fitting the six-velocity value according to the Herba model.

3. The method of claim 1, wherein, The physical parameters of the casing centralizer for cementing include: The centralizer's inner diameter, outer diameter, length, number of edges, edge helix angle, and height, centralizer volume fraction, as well as the centralizer's flow capacity and swirl section length.

4. The method of claim 1, wherein, Multiple key factors affecting the performance of the centralizer are identified from the physical parameters, and multiple key factor data sets are generated within a preset range, including: From the physical parameters, the number of edges, the edge spiral angle, and the height of the stabilizer are selected as the main control factors. Within the range of 2-8 edges N, 30-60° edge spiral angle θ, and 180-260mm stabilizer height L, multiple data sets containing the number of edges, edge spiral angle, and stabilizer height are generated.

5. The method of claim 1, wherein, Calculate the cement displacement efficiency and swirl section length of the horizontal well corresponding to the wellbore-centralizer model, including: In the preset fluid dynamics simulation software, based on the force balance analysis of fluid micro-elements, cementing displacement is constructed based on the fluid volume method. The displacement motion model corresponding to the wellbore-centralizer model is composed of the eccentric annular geometric equation, continuity equation, momentum equation, Herba model and interface motion equation. Determine the initial and boundary conditions for cement displacement annulus flow in horizontal wells; Based on the initial and boundary conditions, the pressure-velocity coupling algorithm is used to numerically solve the displacement motion model, and the horizontal well cementing displacement efficiency and swirl section length are calculated for each wellbore-centralizer model.

6. The method of claim 5, wherein, The initial conditions are: the annulus is filled with drilling fluid, and the pre-flush fluid and cement slurry flow in from the inlet at a certain initial velocity; the boundary conditions are non-slip wall boundary conditions.

7. The method according to any one of claims 1 to 6, wherein The pre-architected neural network is a BP neural network; the neural network includes an input layer, a hidden layer, and an output layer; wherein, the input layer is used to input the vectors of each main control factor data in multiple main control factor data groups; the hidden layer is used to characterize the mapping function relationship between the number of edges, the edge helix angle, and the centralizer height and the displacement efficiency value and the swirl section length; the output layer is used to output the horizontal well cement displacement efficiency value and the swirl section length; Based on multiple key control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length, a pre-architected neural network is trained to obtain the centralizer optimization design database model, including: The multiple sets of main control factor data, along with the corresponding horizontal well cement displacement efficiency values ​​and swirl section lengths, are used to generate multiple sets of training data. The following steps are then iteratively executed: the training data is input into the BP neural network for forward propagation, the value of the loss function is calculated, and backpropagation is performed based on the value of the loss function to update the parameters of the neural network until the value of the loss function reaches a preset convergence state, thereby obtaining the centralizer optimization design database model.

8. A design device for a casing centralizer for cementing, characterized in that, include: The operating condition parameter determination module is used to determine the operating condition parameters of the horizontal well section based on cementing data. The centralizer physical parameter determination module is used to determine the operating parameters of the horizontal well section based on cementing data; The main control factor determination module is used to determine multiple main control factors affecting the performance of the centralizer from the physical parameters, and generate multiple main control factor data groups within a preset range. Each main control factor data group contains data of the multiple main control factors, and the data sizes of the multiple main control factors in different main control factor data groups are not completely equal. The wellbore-centralizer model generation module is used to generate a corresponding wellbore-centralizer model for each set of key control factor data. The wellbore-centralizer model calculation module is used to calculate the cement displacement efficiency value and swirl section length of the horizontal well corresponding to the wellbore-centralizer model. The neural network model training module is used to train a pre-architected neural network based on multiple main control factor data sets and the calculated horizontal well cement displacement efficiency value and swirl section length, so as to obtain the centralizer optimization design database model. The centralizer optimization design database model module is used to input data of multiple main control factors of the centralizer to be designed, and output the displacement efficiency value and swirl section length of the centralizer to be designed corresponding to the main control factor data group. The design parameter determination module is used to determine whether the data of the multiple main control factors are qualified based on the output displacement efficiency value and swirl section length, and to use the qualified data of the multiple main control factors as the design parameters of the centralizer to be designed.

9. A computing device, comprising: It includes a processor and a memory for storing processor-executable commands; wherein the processor is configured to execute the cementing casing centralizer design method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the design method for a cementing casing centralizer as described in any one of claims 1-7.

11. A computer program product, characterised in that, The computer program product includes a computer program that, when executed by a processor, implements the design method for a cementing casing centralizer as described in any one of claims 1-7.

12. A casing centralizer for cementing, characterized by The cementing casing centralizer is a stamped semi-rigid spiral centralizer structure; the number of ridges, the spiral angle of the ridges, and the height of the centralizer are obtained by the cementing casing centralizer design method as described in any one of claims 1-7.

Images