Casing collapse resistance prediction methods, systems, devices, and media

Abstract

The present application belongs to the technical field of oil and gas development, and provides a casing collapse strength prediction method, system, electronic device and storage medium. The method comprises: acquiring casing working environment parameters and historical loss data, measuring the size of the casing that meets the preset condition, obtaining the collapse strength parameter and size data that affect the casing; performing an external pressure collapse experiment on the casing to obtain experimental data of the collapse strength; based on the collapse strength parameter and the size data, performing a numerical simulation experiment on the casing to generate simulation data of the collapse strength of the casing; performing consistent processing on the experimental data and the simulation data, establishing an intelligent database of the collapse strength of the casing, and obtaining a model for predicting the collapse strength of the casing. The model for predicting the collapse strength of the casing can realize prediction of unknown data, further guide the study of casing strength, and alleviate the casing damage problem.

Description

Technical Field

[0001] This invention belongs to the field of oil and gas development technology, and particularly relates to a method, system, electronic device and storage medium for predicting the crush resistance strength of casing. Background Technology

[0002] Casing is a steel pipeline that protects the wellbore and its equipment, isolates fluids from different layers, and ensures the normal operation of oil, gas, and water wells. As a key component in oil and gas well development and production, casing must withstand not only high axial tensile or compressive loads, as well as internal and external pressure loads, but also harsh operating environments such as high temperatures at the bottom of the well and acid corrosion. Once damaged, it will not only reduce oil and gas production but also severely damage the reservoir, affecting normal exploration, development, and production. During its service life, the strength performance of casing will continuously change due to changes in the mechanical environment and downhole conditions. When the external load exceeds its own strength limit, the casing will be damaged. Crushing failure is one of the most common forms of damage caused by the continuous decline in the casing's own strength.

[0003] Early API standards used to guide the calculation of crush resistance ignored manufacturing defects in the casing itself. In terms of external load, the load on the tubing string was treated as a uniform load, without taking into account the randomness of the load source and distribution. Gradually, it could no longer meet the guidance requirements for casing research under complex well conditions at the present stage, and the problem of casing damage still exists, affecting the work inside the oil and gas well. Summary of the Invention

[0004] To address the aforementioned issues, this disclosure provides a method, system, electronic device, and storage medium for predicting the crush resistance strength of casing. It considers the inherent non-uniform defects in the casing's strength performance during operation and the highly random and poorly controllable nature of external loads. External pressure crushing experiments were conducted in a laboratory environment targeting the main influencing parameters of the casing's inherent strength performance, supplemented by numerical simulation experiments, yielding a certain amount of data. Based on this, leveraging the advantages of neural networks in handling multi-factor problems, this method is combined with the study of crush resistance strength to train a model that can predict the crush resistance strength of casing. This enables the prediction of unknown data, further guiding the research on casing strength and improving the accuracy of non-API casing strength prediction.

[0005] To address the aforementioned technical problems, the first aspect of this invention proposes a method for predicting the crush resistance strength of casing, the method comprising:

[0006] Obtain the working environment parameters and historical loss data of the casing, measure the size of the casing that meets the preset conditions, and obtain the parameters and size data that affect the extrusion strength of the casing.

[0007] An external pressure crushing test was conducted on the sleeve to obtain experimental data on its crush resistance strength.

[0008] Based on the extrusion resistance strength parameters and the dimensional data, a numerical simulation experiment was conducted on the casing to generate simulated data on the extrusion resistance strength of the casing.

[0009] The experimental data and the simulation data are processed to be consistent, and an intelligent database of the casing's extrusion resistance strength is established to obtain a model for predicting the casing's extrusion resistance strength.

[0010] According to a preferred embodiment of the present invention, measuring the dimensions of the sleeve that meet preset conditions includes:

[0011] Inherent defects in the manufacturing process of the sleeve cause the sleeve to have ellipticity;

[0012] The casing is subjected to different loads in different well sections, so the external load on the casing is non-uniform.

[0013] According to a preferred embodiment of the present invention, the external pressure crushing test includes:

[0014] The tubing section of the sleeve is ground and welded to obtain a sample;

[0015] The tube segment of the sample is placed into the external pressure crushing cylinder and sealed;

[0016] The sealed pipe section of the sample was pressurized by adding water as an external pressure medium to conduct an external pressure crushing test, and experimental data on the crushing strength were obtained.

[0017] According to a preferred embodiment of the present invention, the numerical simulation experiment on the sleeve includes:

[0018] The crushing process was simulated using numerical simulation experiments based on finite element analysis software.

[0019] The crushing process is simulated by setting external pressure loads in the X and Y directions to simulate the non-uniform external extrusion acting on the casing, thereby obtaining simulated data on the crushing strength.

[0020] According to a preferred embodiment of the present invention, obtaining the model for predicting the extrusion resistance strength of the casing includes:

[0021] The intelligent database is divided into a training set, a validation set, and a test set according to a preset ratio;

[0022] Training data for the training, validation, and test sets;

[0023] When the coefficient of determination reaches its maximum value and the actual error is less than the preset error, the model training ends.

[0024] To address the aforementioned technical problems, a second aspect of this invention proposes a casing anti-extrusion strength prediction system, characterized in that the system comprises: a data acquisition module, an external force experiment module, a simulation experiment module, and a model building module;

[0025] The data acquisition module is used to acquire the working environment parameters and historical loss data of the casing, measure the size of the casing that meets the preset conditions, and obtain the parameters and size data that affect the extrusion strength of the casing.

[0026] The external force test module is used to conduct an external pressure crushing test on the casing to obtain experimental data on its crush resistance strength.

[0027] The simulation experiment module is used to conduct numerical simulation experiments on the casing based on the extrusion strength parameters and the size data, and generate simulation data of the extrusion strength of the casing.

[0028] The model building module is used to unify the experimental data with the simulation data, establish an intelligent database of the casing's extrusion resistance strength, and obtain a model for predicting the casing's extrusion resistance strength.

[0029] According to a preferred embodiment of the present invention, it includes:

[0030] Inherent defects in the manufacturing process of the sleeve in the data acquisition module cause the sleeve to have ellipticity;

[0031] The casing in different well sections of the data acquisition module is subjected to different loads, so the external load on the casing is non-uniform.

[0032] According to a preferred embodiment of the present invention, it includes:

[0033] The external force testing module is also used to grind and weld the pipe section of the sleeve to obtain a sample;

[0034] The external force testing module is also used to place the tube section of the sample into the external pressure crushing cylinder and seal it;

[0035] The external force test module is also used to apply pressure to the sealed pipe section of the sample by adding external pressure medium water, and to conduct an external pressure crushing test to obtain experimental data on the crushing strength.

[0036] To address the aforementioned technical problems, a third aspect of the present invention provides an electronic device, comprising:

[0037] processor;

[0038] And a memory storing computer-executable instructions, which, when executed, cause the processor to perform the method described in any of the above embodiments.

[0039] To address the aforementioned technical problems, a fourth aspect of the present invention provides a computer storage medium, wherein the computer storage medium stores one or more programs, which, when executed by a processor, implement the method described in any of the above embodiments.

[0040] Compared with existing technologies, this invention has the following advantages: This invention considers the inherent non-uniform defects in the casing's strength performance during service, as well as the strong randomness and poor controllability of external loads. In a laboratory environment, external pressure crushing experiments were conducted on the main influencing parameters of the casing's strength performance, supplemented by numerical simulation experiments, obtaining a certain amount of data. Based on this, leveraging the advantages of neural networks in handling multi-factor problems, this is combined with research on crush resistance strength to train a model that can predict the casing's crush resistance strength, enabling prediction of unknown data and further guiding research on casing strength to alleviate casing damage problems. Moreover, this invention requires less computation, improving work efficiency and enabling rapid prediction of the casing's crush resistance strength, further facilitating the use and maintenance of the casing by personnel.

[0041] 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 pointed out in the description, claims and drawings. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A schematic flowchart of a method for predicting the extrusion resistance of casing according to an embodiment of the present invention is shown;

[0044] Figure 2 A second schematic diagram of a method for predicting the extrusion resistance of casing according to an embodiment of the present invention is shown.

[0045] Figure 3 A schematic flowchart of a method for predicting the extrusion resistance of casing according to an embodiment of the present invention is shown in part three.

[0046] Figure 4 A schematic flowchart of a method for predicting the extrusion resistance of casing according to an embodiment of the present invention is shown in Figure 4.

[0047] Figure 5A schematic flowchart of a method for predicting the extrusion resistance of casing according to an embodiment of the present invention is shown in Figure 5.

[0048] Figure 6 A structural diagram of a casing extrusion resistance prediction system according to an embodiment of the present invention is shown;

[0049] Figure 7 A schematic diagram of an electronic device structure according to an embodiment of the present invention is shown. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] The same reference numerals in the accompanying drawings denote the same or similar elements, components, or parts, and therefore, repeated descriptions of the same or similar elements, components, or parts may be omitted below. It should also be understood that although terms such as first, second, third, etc., indicating numbers may be used herein to describe various devices, elements, components, or parts, these devices, elements, components, or parts should not be limited by these terms. That is, these terms are only used to distinguish one from another. For example, a first device may also be referred to as a second device, without departing from the essential technical solution of the invention. Furthermore, the terms "and / or" and "and / or" refer to all combinations including any one or more of the listed items.

[0052] Please see Figure 1 , Figure 1 This is a schematic diagram of one of the methods for predicting the extrusion resistance strength of casing provided by the present invention, as shown below. Figure 1 As shown, the method includes:

[0053] S11. Obtain the working environment parameters and historical loss data of the casing, measure the size of the casing that meets the preset conditions, and obtain the parameters and size data that affect the extrusion strength of the casing.

[0054] In this embodiment, the factors affecting the extrusion resistance of the casing can be mainly divided into natural geological factors, engineering factors, and the casing's own performance defects.

[0055] In this embodiment, the formation stress sources are complex and varied, and are greatly affected by the natural environment; engineering factors mainly come from the additional loads brought about by downhole operations such as perforation, high-pressure water injection, and fracturing; the casing's own performance defects mainly refer to certain original defects in the casing during the manufacturing stage due to process or design, which make it difficult to achieve the expected load-bearing capacity in later use.

[0056] In this embodiment, given that natural geology and engineering development are uncontrollable factors with strong randomness and uncertainty, the study and improvement of the performance of the casing itself becomes the key to alleviating the casing loss problem.

[0057] In this embodiment, the outer diameter and wall thickness of the casing are mainly measured in the full-size measurement, and the parameters and dimensional data affecting the casing's extrusion resistance are calculated.

[0058] S12. An external pressure crushing test is performed on the sleeve to obtain experimental data on its crush resistance strength.

[0059] In this embodiment, the casing's resistance to crushing is a key parameter for ensuring the casing's quality and safe use during the external pressure crushing test.

[0060] In this embodiment, the test of the casing's crush resistance performance was carried out in accordance with the requirements of ISO 11960 / API RP 5C3 standard. The standard stipulates that for pipes with a nominal outer diameter (D) less than or equal to 9-5 / 8in, the minimum specimen length is 8 times the nominal outer diameter (D), and for pipes with a nominal outer diameter (D) greater than 9-5 / 8in, the minimum specimen length is 7 times the nominal outer diameter (D).

[0061] S13. Based on the extrusion resistance strength parameters and the dimensional data, a numerical simulation experiment is conducted on the casing to generate simulated data of the casing's extrusion resistance strength.

[0062] In this embodiment, based on full-size measurements, a numerical simulation experiment of the casing is conducted and compared with an external pressure crushing experiment to supplement the simulation data of the casing's crush resistance strength.

[0063] S14. The experimental data and the simulation data are processed to be consistent, and an intelligent database of the casing's extrusion resistance strength is established to obtain a model for predicting the casing's extrusion resistance strength.

[0064] In this embodiment, data consistency processing involves dimensionlessly processing different parameters affecting extrusion strength, including outer diameter, wall thickness, diameter-to-thickness ratio, ellipticity, wall thickness uniformity, and yield strength, so that the parameters characterizing different attributes have consistency, forming an intelligent database.

[0065] In this embodiment, the data consistency processing method includes min-max normalization, also known as deviation normalization, which is a linear transformation of the original data to map the result value to the range [0-1].

[0066] Specifically,

[0067] Among them, X * X represents the standardized result, X represents the original data, max represents the maximum value of the sample data, and min represents the minimum value of the sample data.

[0068] In this embodiment, the drawback of the min-max normalization method is that once new data is added, it may cause changes in max and min, so they need to be redefined.

[0069] In this embodiment, the data consistency processing method includes Z-score standardization, which standardizes the data based on the mean and standard deviation of the original data. The processed data conforms to a standard normal distribution, i.e., the mean is 0 and the standard deviation is 1.

[0070] Specifically,

[0071] Among them, X * Let X be the standardized result, μ be the original data, μ be the mean of all sample data, and σ be the standard deviation of all sample data.

[0072] Please see Figure 2 , Figure 2 This is a second schematic diagram of a method for predicting the extrusion resistance strength of casing provided by the present invention, as shown below. Figure 2 As shown, the method includes:

[0073] S21. Inherent defects in the manufacturing process of the sleeve cause the sleeve to have ellipticity.

[0074] In this embodiment, the ellipticity is calculated using a formula.

[0075] Specifically,

[0076] Where D is the ellipticity, D max The maximum measured outer diameter value on the same cross section, D min This represents the smallest measured outer diameter value on the same cross-section.

[0077] S22. The casing is subjected to different loads in different well sections, so the external load on the casing is non-uniform.

[0078] In this embodiment, the wall thickness non-uniformity is calculated using a formula.

[0079] Specifically,

[0080] Where t is the wall thickness non-uniformity, t max The maximum wall thickness measured on the same cross section, t min This represents the minimum wall thickness measured on the same cross-section.

[0081] Please see Figure 3 , Figure 3 This is a schematic diagram of the third step in the process of predicting the extrusion resistance strength of casing provided by the present invention. Figure 3 As shown, the method includes:

[0082] S31. Grind and weld the pipe section of the sleeve to obtain a sample.

[0083] In this embodiment, it is necessary to determine the basic dimensions of the experimental column and perform full-size measurements.

[0084] In this embodiment, the mechanical properties of the tubing need to be tested. The residual stress of the tubing is detected using the stress ring method, and the residual stress specimen should be cut from the adjacent part of the crushed specimen. The minimum tubing length should be twice the outer diameter of the tubing (L / D≥2).

[0085] Specifically,

[0086] Where σ is the stress (positive value is tensile stress, negative value is compressive stress), Et = 2.1e5MPa, μ = 0.3, D i To cut the outer diameter, D f This is the outer diameter of the sample after it has been cut open.

[0087] S32. Place the tube section of the sample into the external pressure crushing cylinder and seal it.

[0088] In this embodiment, the prepared sample is placed into an external pressure crushing cylinder and the tube end is sealed.

[0089] S33. Apply pressure to the sealed pipe section of the sample by adding external pressure medium water, and conduct an external pressure crushing test to obtain experimental data on the crushing strength.

[0090] In this embodiment, water, an external pressure medium, is added to apply pressure, and an external pressure crushing experiment is completed to obtain experimental data on the crushing resistance strength.

[0091] Please see Figure 4 , Figure 4 This is a schematic diagram (fourth) of the process for predicting the extrusion resistance strength of casing provided by the present invention. Figure 4 As shown, the method includes:

[0092] S41. The crushing process is simulated through numerical simulation experiments using finite element analysis software.

[0093] In this embodiment, based on full-size measurements, a numerical simulation experiment of the casing is conducted and compared with an external pressure crushing experiment to supplement the simulation data of the casing's crush resistance strength.

[0094] S42. The crushing process is simulated by setting external pressure loads in the X and Y directions to simulate the non-uniform external extrusion process on the casing, thereby obtaining simulation data of the crushing strength.

[0095] In this embodiment, the numerical simulation mainly uses finite element analysis software to simulate the crushing process. By setting external pressure loads in the X and Y directions, the process of non-uniform external extrusion acting on the tubular column is simulated, thereby obtaining numerical simulation data of the crushing strength.

[0096] Please see Figure 5 , Figure 5 This is a schematic diagram (5) of a method for predicting the extrusion resistance strength of casing provided by the present invention. Figure 5 As shown, the method includes:

[0097] S51. Divide the intelligent database into a training set, a validation set, and a test set according to a preset ratio.

[0098] In this embodiment, the database is allocated appropriately for training and testing the Bayesian artificial neural network model. Reserved testing data is substituted into the finally trained model for verification. If the output error between the predicted result and the known experimental data meets a preset range, it indicates that the model can predict unknown results. If the error is large, it indicates that the model cannot effectively predict the crush strength of the tubular column, and another tubular column sample should be selected for re-testing to obtain data and complete the model training and testing.

[0099] In this embodiment, the database is mainly divided into a training set and a test set. The training set is used to train the neural network model for predicting the casing's crush resistance strength, while the test set is used to verify the reliability of the obtained model. The neural network input includes six parameters that directly affect the casing's crush resistance strength: outer diameter, wall thickness, diameter-to-thickness ratio, ellipticity, wall thickness uniformity, and yield strength. The output is the casing's crush resistance strength. In terms of algorithm selection, the traditional backpropagation (BP) algorithm is prone to overfitting, while the Bayesian algorithm has better generalization ability.

[0100] S52, training data for the training set, validation set, and test set.

[0101] In this embodiment, the BRANN model uses the objective function F, including the mean squared error function E. D and weight decay function E wMinimize the combination of , and determine the optimal weights and objective function parameters in a probabilistic manner.

[0102] Specifically, F = βE D +αE w ;

[0103]

[0104] Where F is the objective function, α and β are hyperparameters, and E D The mean square error function, E w Here, ω is the weight decay function, m is the number of weights, D = (xi, ti) represents the data of the training set i = 1, 2, ..., N, N is the total number of training sets, and yi represents the output value of ith corresponding to the ith training set.

[0105] In this embodiment, the initial weights in BRANN are randomly set. With these initial weights, the weight density function can be updated according to the Bayer rule.

[0106] Specifically,

[0107] Where P(ω|D,α,β,M) is the density function of the weights, M is the specific neural network architecture used, P(w|α,M) is the prior density, P(D|w,β,M) is the likelihood function, and P(D|α,β,M) is the normalization factor.

[0108] In this embodiment, the prior density represents the knowledge of the weights before data collection, and the likelihood function is the probability of the data occurring given the weights.

[0109] Specifically,

[0110] In this embodiment, if we assume that the noise of the training set data and weights is Gaussian distributed, the probability density can be calculated using a formula.

[0111] Specifically,

[0112] Substitute the probability density into the equation

[0113]

[0114] In this embodiment, in BRANN, determining the optimal weights means maximizing the posterior probability P(w|D, α, β, M), which is to minimize the regularization objective function F.

[0115] Specifically,

[0116] Where P(α, β / D, M) is the joint posterior density.

[0117] In this embodiment, maximizing the joint posterior density can be determined by maximizing the likelihood function P(D / α, β, M).

[0118] Specifically,

[0119] Where n is the number of observations and m is the total number of network parameters.

[0120] In this embodiment, parameter Z F (α, β) depends on the Hessian matrix of the objective function.

[0121] Specifically,

[0122] Where the subscript "max" represents the maximum posterior probability. The Hessian matrix (H) is calculated from the Jacobian matrix (J).

[0123] Specifically, H = J T J.

[0124] In this embodiment, the Jacobian matrix contains the first derivative of the network error with respect to the network parameters.

[0125] S53. The coefficient of determination reaches its maximum value, the actual error is less than the preset error, and the model training ends.

[0126] In this embodiment, the model training ends when the determination coefficient R2 of the prediction result reaches its maximum value; otherwise, the number of hidden layer neurons should be adjusted and the model should be retrained until R2 reaches its maximum value.

[0127] In this embodiment, after the model training is completed, the test group data is imported into the model, and the original output of the test group data is compared with the output value predicted by the model. If the error is less than the preset error, which can be 5%, it indicates that the model is reliable and can predict the unknown crush resistance strength.

[0128] Please see Figure 6 , Figure 6 This is a structural diagram of a casing anti-crushing strength prediction system provided by the present invention, as shown in the figure. Figure 6 As shown, the system includes: a data acquisition module, an external force experiment module, a simulation experiment module, and a model building module.

[0129] In this embodiment, the data acquisition module is specifically used to acquire the working environment parameters and historical loss data of the casing, measure the size of the casing that meets the preset conditions, and obtain the parameters and size data that affect the extrusion strength of the casing.

[0130] In this embodiment, the external force test module is specifically used to conduct an external pressure crushing test on the sleeve to obtain experimental data on its crush resistance strength.

[0131] In this embodiment, the simulation experiment module is specifically used to conduct a numerical simulation experiment on the casing based on the extrusion strength parameter and the size data, and generate simulated data of the extrusion strength of the casing.

[0132] In this embodiment, a model building module is specifically used to unify the experimental data with the simulation data, establish an intelligent database of the casing's extrusion resistance strength, and obtain a model for predicting the casing's extrusion resistance strength.

[0133] In this embodiment, an inherent defect in the manufacturing process of the sleeve in the data acquisition module causes the sleeve to have ellipticity.

[0134] In this embodiment, the casing in different well sections of the data acquisition module is subjected to different loads, so the external load on the casing is non-uniform.

[0135] In this embodiment, the external force test module is specifically used to grind and weld the pipe section of the sleeve to obtain a sample.

[0136] In this embodiment, the external force test module is specifically used to place the tube segment of the sample into the external pressure crushing cylinder and seal it.

[0137] In this embodiment, the external force test module is specifically used to apply pressure to the sealed pipe section of the sample by adding external pressure medium water, to conduct an external pressure crushing test and obtain experimental data on the crushing strength.

[0138] like Figure 7 As shown, this embodiment of the invention provides an electronic device, including a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140.

[0139] Memory 1130 is used to store computer programs;

[0140] When the processor 1110 executes the program stored in the memory 1130, it implements any of the above-described determination methods.

[0141] The electronic device provided in this embodiment of the invention includes a processor 1110 that executes a program stored in a memory 1130 to obtain the fluid flow rate of each branch under different switching states and determines the initial volumetric flow rate of each branch; it corrects the initial volumetric flow rate based on the pipe parameters and fluid parameters of each branch when it is in operating condition and standard condition to obtain the standard condition volumetric flow rate of each branch; it obtains multiple total standard condition volumetric flow rates based on the standard condition volumetric flow rates of each branch under different switching states, and determines the optimal switching state of each branch by using the switching state of each branch when the total standard condition volumetric flow rate reaches a preset target.

[0142] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, it is shown in the figure with only one thick line, but this does not indicate that there is only one bus or one type of bus.

[0143] The communication interface 1120 is used for communication between the above-mentioned electronic device and other devices.

[0144] The memory 1130 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1130 may also be at least one storage device located remotely from the aforementioned processor 1110.

[0145] The processor 1110 mentioned above can be a general-purpose processor 1110, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0146] This invention provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors 1110 to implement the determination method of any of the above embodiments.

[0147] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0148] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for predicting the crush resistance strength of casing, characterized in that, The method includes: Obtain the working environment parameters and historical loss data of the casing, measure the size of the casing that meets the preset conditions, and obtain the parameters and size data that affect the extrusion strength of the casing. An external pressure crushing test was conducted on the sleeve to obtain experimental data on its crush resistance strength. Based on the extrusion resistance strength parameters and the dimensional data, a numerical simulation experiment was conducted on the casing to generate simulated data on the extrusion resistance strength of the casing. The experimental data and the simulation data are processed to be consistent, and an intelligent database of the casing's extrusion resistance strength is established to obtain a model for predicting the casing's extrusion resistance strength.

2. The prediction method according to claim 1, characterized in that, The measurement of the sleeve dimensions that meet preset conditions includes: Inherent defects in the manufacturing process of the sleeve cause the sleeve to have ellipticity; The casing is subjected to different loads in different well sections, so the external load on the casing is non-uniform.

3. The prediction method according to claim 1, characterized in that, The external pressure crushing test includes: The tubing section of the sleeve is ground and welded to obtain a sample; The tube segment of the sample is placed into the external pressure crushing cylinder and sealed; The sealed pipe section of the sample was pressurized by adding water as an external pressure medium to conduct an external pressure crushing test, and experimental data on the crushing strength were obtained.

4. The prediction method according to claim 1, characterized in that, The numerical simulation experiment on the sleeve includes: The crushing process was simulated using numerical simulation experiments based on finite element analysis software. The crushing process is simulated by setting external pressure loads in the X and Y directions to simulate the non-uniform external extrusion acting on the casing, thereby obtaining simulated data on the crushing strength.

5. The prediction method according to claim 1, characterized in that, The model for predicting the extrusion resistance of the casing includes: The intelligent database is divided into a training set, a validation set, and a test set according to a preset ratio; Training data for the training, validation, and test sets; When the coefficient of determination reaches its maximum value and the actual error is less than the preset error, the model training ends.

6. A casing extrusion resistance prediction system, characterized in that, The system includes: a data acquisition module, an external force experiment module, a simulation experiment module, and a model building module; The data acquisition module is used to acquire the working environment parameters and historical loss data of the casing, measure the size of the casing that meets the preset conditions, and obtain the parameters and size data that affect the extrusion strength of the casing. The external force test module is used to conduct an external pressure crushing test on the sleeve to obtain experimental data on its crush resistance strength. The simulation experiment module is used to conduct numerical simulation experiments on the casing based on the extrusion strength parameters and the dimensional data, and generate simulation data of the extrusion strength of the casing. The model building module is used to unify the experimental data with the simulation data, establish an intelligent database of the casing's extrusion resistance strength, and obtain a model for predicting the casing's extrusion resistance strength.

7. The prediction system according to claim 6, characterized in that, include: Inherent defects in the manufacturing process of the sleeve in the data acquisition module cause the sleeve to have ellipticity; The casing in different well sections of the data acquisition module is subjected to different loads, so the external load on the casing is non-uniform.

8. The prediction system according to claim 6, characterized in that, include: The external force testing module is also used to grind and weld the pipe section of the sleeve to obtain a sample; The external force testing module is also used to place the tube section of the sample into the external pressure crushing cylinder and seal it; The external force test module is also used to apply pressure to the sealed pipe section of the sample by adding external pressure medium water, and to conduct an external pressure crushing test to obtain experimental data on the crushing strength.

9. An electronic device, characterized in that, include: processor; And a memory storing computer-executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1-5.

10. A computer storage medium, characterized in that, in, The computer storage medium stores one or more programs, which, when executed by a processor, implement the method of any one of claims 1-5.

Images