Method, system and equipment for predicting and safety evaluating pipe erosion under stress

Abstract

The application discloses a stress-affected pipe erosion prediction and safety evaluation method, system and equipment, and belongs to the technical field of oil and gas pipelines. The evaluation method comprises the following steps: acquiring a key parameter range of a fracturing elbow; based on the key parameter range, carrying out a stress-affected material erosion test of the fracturing elbow under different working conditions; based on the erosion test result, establishing a stress-affected erosion mathematical model; based on the erosion mathematical model, carrying out erosion simulation on the fracturing elbow to obtain a simulation result of the maximum erosion rate of the fracturing elbow under different working conditions; based on the simulation result of the maximum erosion rate of the fracturing elbow under different working conditions, using a machine learning algorithm to carry out high internal pressure fracturing elbow erosion prediction to obtain a fracturing elbow erosion prediction model; and based on the fracturing elbow erosion prediction model, carrying out safety evaluation on the fracturing elbow. The application combines simulation and a machine learning algorithm, and the prediction result is fast, accurate and reliable, and is convenient for field industrial application.

Description

Technical Field

[0001] This invention belongs to the field of oil and gas pipeline technology, and specifically relates to methods, systems and equipment for predicting and assessing the erosion of pipe fittings under stress. Background Technology

[0002] Currently, the development and utilization of unconventional oil and gas resources such as shale gas, tight oil and gas, and coalbed methane have become a hot topic in the petroleum industry. Unlike conventional oil and gas extraction, shale gas production enhancement employs large-scale fracturing operations in a well factory setting. Under conditions of deep burial, high pressure, multiple layers, and dense geological structures, fracturing equipment faces severe challenges of ultra-high pressure, large flow rates, and long operating cycles. The fracturing manifold is a key piece of equipment in the shale gas fracturing process. Its function is to deliver high-pressure fracturing fluid to the wellbore, creating artificial microfractures in the low-porosity and ultra-low-permeability shale reservoir, thereby improving recovery rates. Under large-scale fracturing, the fracturing manifold is subjected to enormous stress caused by internal pressures of tens to hundreds of megapascals for extended periods. This makes it prone to erosion damage at fracturing bends, and under continuous high stress, cracks can be induced. Once these cracks extend to the outer surface, they can cause sudden pipe punctures and ruptures, resulting in high-pressure fluid leakage and serious safety accidents, severely threatening the safety of personnel and equipment on site. Existing research on erosion wear has been limited to the interaction between impact particles and the target surface, neglecting the influence of the overall stress state of the target material on erosion. In recent years, studies have shown that stress on high-pressure flow pipe fittings such as fracturing elbows under high internal pressure conditions exacerbates erosion wear, and the erosion rate increases exponentially with increasing stress level. This indicates that stress is a crucial and undeniable factor influencing erosion wear.

[0003] In the field of erosion prediction, numerous scholars have proposed over 200 empirical / semi-empirical mathematical models for erosion based on relevant research. Applying these mathematical models to conduct computational fluid dynamics (CFD) erosion simulations of pipe fittings under different working conditions is an effective approach to predict erosion. However, existing erosion mathematical models do not yet consider the impact of complex loads on erosion, making it difficult to accurately assess the erosion performance of fracturing elbows under real high internal pressure environments, which may have significant shortcomings in guiding the erosion-resistant design of pipe fittings.

[0004] Furthermore, fracturing elbows operate under extremely harsh conditions, and pipe rupture accidents are frequent during actual fracturing processes. Fracturing elbows face enormous erosion damage risks, and their failures are highly sudden and have extremely serious consequences, making them a critical weak link in large-scale fracturing surface process systems. However, due to the lack of accurate erosion prediction methods and the difficulty in timely detection of fracturing elbow wall thickness, sudden failures and ruptures of fracturing elbows are commonplace. Therefore, there is an urgent need to propose a method for predicting and assessing the erosion of fracturing elbows.

[0005] In response, Chinese patent (publication number CN117131805A) discloses a method for predicting the liquid-solid two-phase flow erosion rate of a fracturing manifold transition bend, and proposes a fitting calculation formula for erosion of the fracturing bend specifically for the transition bend in the fracturing manifold:

[0006]

[0007] In the formula, E is the maximum erosion rate, mm / s; X1 is the ratio of particle size to reference particle size; X2 is the ratio of inlet velocity to reference inlet velocity; X3 is the ratio of transition bend diameter to reference bend diameter; and X4 is the ratio of particle flow rate to reference particle flow rate.

[0008] The aforementioned patent considers the influence of flow velocity, particle size, pipe diameter, and particle flow rate on elbow erosion, but it does not consider the impact of stress caused by the high internal pressure actually borne by the fracturing elbow on elbow erosion. Therefore, neglecting the stress effect in the above calculation formula will lead to the predicted results being lower than the actual results, resulting in dangerous situations. In addition, the data fitting in the above patent comes from field fracturing elbow monitoring data. Since actual field fracturing conditions are difficult to control as easily as laboratory tests (e.g., flow velocity, particle size, and particle flow rate fluctuate within a certain range during a fracturing operation, and it is difficult to obtain the maximum erosion wall thickness reduction at the elbow location in the field), the method is not very practical. Summary of the Invention

[0009] To address the above problems, this invention discloses a method for predicting and evaluating the safety of pipe fittings under stress, including:

[0010] Obtain the key parameter ranges for fracturing elbows;

[0011] Based on the range of key parameters, erosion tests were conducted on fracturing elbow materials under different working conditions under stress.

[0012] Based on the results of erosion tests, a mathematical model of erosion under the influence of stress is established.

[0013] Based on the mathematical model of erosion, erosion simulation of fracturing elbow was carried out to obtain the simulation results of the maximum erosion rate of fracturing elbow under different working conditions.

[0014] Based on the simulation results of the maximum erosion rate of fracturing elbows under different working conditions, machine learning algorithms are used to predict the erosion of fracturing elbows under high internal pressure, and a fracturing elbow erosion prediction model is obtained.

[0015] Based on the erosion prediction model of fracturing elbows, a safety assessment of fracturing elbows is conducted.

[0016] Furthermore, the key parameters include the dimensions of the fracturing elbow, material properties, and flow field parameters;

[0017] The dimensions of the fracturing elbow include outer diameter, wall thickness, and bending radius;

[0018] The material performance parameters include the material yield strength and Brinell hardness;

[0019] The flow field parameters include the flow velocity, internal pressure, particle type, particle mass fraction, and particle size inside the pipe.

[0020] Furthermore, the variable factors in the erosion test include flow velocity, impact angle, particle type, particle mass fraction, particle size, and applied stress value;

[0021] The flow velocity is 5-30 m / s;

[0022] The impact angle is 0-90°;

[0023] The types of particles include quartz sand and ceramsite sand;

[0024] The particle mass fraction is 1-20%;

[0025] The particle size is 0.1-0.9 mm;

[0026] The loading stress value is the circumferential stress of the fracturing elbow under different internal pressures; wherein, the internal pressure is 0-120MPa.

[0027] Furthermore, the mathematical model of erosion is expressed as follows:

[0028] ER=CBH -0.59 u n f(c p )f(d p )F s F E (α)F σ (P)

[0029] Where ER is the erosion rate; C is the coefficient; BH is the Brinell hardness of the fracturing elbow material; u is the fluid velocity; n is the velocity index; f(c p ) is the particle mass fraction correction function; c p f(d) represents the particle mass fraction; p ) represents the particle size correction function; d p For particle size; F s F is the particle shape factor; E (α) is the impact angle function; α is the impact angle; F σ (P) is the erosion function amplified by internal pressure; P is the internal pressure.

[0030] Furthermore, the simulation of erosion of the fracturing elbow based on the erosion mathematical model to obtain the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions includes the following steps:

[0031] A three-dimensional flow field model of the fracturing elbow was established based on the dimensions of the fracturing elbow on site.

[0032] The three-dimensional flow field model of the fracturing elbow is meshed, the discrete particle model in the fluid is set, the boundary conditions are defined, and the erosion mathematical model is defined.

[0033] Based on the three-dimensional flow field model of the fracturing elbow, the motion trajectory of discrete phase particles in the solid-liquid two-phase flow and the erosion results of the fracturing elbow were simulated, and the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions were obtained.

[0034] Furthermore, the parameters set in the discrete particle model include particle type, particle mass fraction, and particle size;

[0035] The boundary conditions include the flow velocity and internal pressure inside the pipe.

[0036] Furthermore, the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions, and the prediction of erosion of the fracturing elbow under high internal pressure using machine learning algorithms, to obtain the fracturing elbow erosion prediction model, include the following steps:

[0037] A dataset was created based on simulation results of the maximum erosion rate of fracturing elbows under different working conditions;

[0038] The dataset is randomly divided into a training set and a test set;

[0039] The simulation results of different fracturing conditions and corresponding maximum erosion rates of fracturing elbows in the training set are input into the machine learning algorithm to train the machine learning algorithm and obtain the fracturing elbow erosion prediction model.

[0040] Input the parameters of different fracturing conditions in the test set into the fracturing elbow erosion prediction model, output the prediction result of the maximum erosion rate of the fracturing elbow, and compare the prediction result with the simulation result in the test set. If the accuracy is higher than the threshold, the fracturing elbow erosion prediction model is established; otherwise, increase the number of samples in the dataset and re-optimize the model parameters of the fracturing elbow erosion prediction model until the accuracy is higher than the threshold.

[0041] Furthermore, the safety assessment of fracturing elbows based on the fracturing elbow erosion prediction model includes the following steps:

[0042] The fracturing operating parameters are input into the fracturing elbow erosion prediction model to obtain the prediction result of the maximum erosion rate of the fracturing elbow;

[0043] Multiply the prediction result by the service time of the fracturing elbow to obtain the maximum thinning of the fracturing elbow wall.

[0044] If the maximum reduction in wall thickness of the fracturing elbow does not exceed the set threshold, the fracturing elbow is considered to be in a safe state; otherwise, it is considered unsafe.

[0045] This invention also discloses a system for predicting and assessing the safety of pipe fittings under stress, comprising:

[0046] The acquisition unit is used to obtain the key parameter range of the fracturing elbow.

[0047] The erosion unit is used to conduct erosion tests on fracturing elbow materials under different working conditions under stress, based on the range of key parameters.

[0048] Establish a unit to build a mathematical model of erosion based on the results of erosion tests, which is influenced by stress.

[0049] The simulation unit is used to perform erosion simulation on fracturing elbows based on the erosion mathematical model, and obtain simulation results of the maximum erosion rate of fracturing elbows under different working conditions.

[0050] The model unit is used to predict the erosion of the fracturing elbow under high internal pressure based on the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions and the machine learning algorithm.

[0051] The evaluation unit is used to conduct a safety evaluation of fracturing elbows based on the fracturing elbow erosion prediction model.

[0052] The present invention also discloses an electronic 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 method for predicting and assessing the erosion of pipe fittings under stress.

[0053] Compared with the prior art, the embodiments of the present invention have at least the following advantages: The present invention realizes the prediction of the erosion rate of fracturing elbows considering the influence of stress. By combining simulation and machine learning algorithms, the prediction results are fast, accurate and reliable, which is convenient for field industrial application. It has important guiding significance for ensuring the safe development of unconventional oil and gas and ensuring the safe service of fracturing elbows under high pressure conditions.

[0054] Other features and advantages of the invention will be set forth in the following description, 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 can be realized and obtained by means of the structures pointed out in the description and the drawings. Attached Figure Description

[0055] 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.

[0056] Figure 1 A flowchart of a method for predicting and evaluating the safety of pipe fittings under stress according to an embodiment of the present invention is shown;

[0057] Figure 2 A schematic diagram of the testing machine structure according to an embodiment of the present invention is shown;

[0058] Figure 3 A schematic diagram of the erosion chamber structure of the testing machine according to an embodiment of the present invention is shown;

[0059] Figure 4 A schematic diagram of finite element mesh generation for a fracturing elbow according to an embodiment of the present invention is shown;

[0060] Figure 5 A schematic diagram of finite element simulation of circumferential stress in a fracturing elbow according to an embodiment of the present invention is shown.

[0061] Figure 6 The following are curves showing the variation of material erosion rate at different flow rates according to an embodiment of the present invention;

[0062] Figure 7 The following are curves showing the material erosion rate variation under different impact angles according to an embodiment of the present invention;

[0063] Figure 8 The following are curves showing the variation of material erosion rate under different particle mass fractions according to an embodiment of the present invention;

[0064] Figure 9 The following are curves showing the material erosion rate variation under different particle sizes according to an embodiment of the present invention;

[0065] Figure 10 The following are curves showing the variation of material erosion rate under different internal pressures according to an embodiment of the present invention;

[0066] Figure 11 A schematic diagram of the particle trajectory of a fracturing bend according to an embodiment of the present invention is shown;

[0067] Figure 12 A schematic diagram of the simulation results of erosion of a fracturing elbow according to an embodiment of the present invention is shown;

[0068] Figure 13A schematic diagram of a pipe erosion prediction and safety evaluation system under stress according to an embodiment of the present invention is shown.

[0069] Reference numerals: 1. Air compressor; 2. Mud pump; 3. Sand mixing tank; 4. Erosion chamber; 401. Tensile sensor; 402. Hydraulic tensile pump; 403. Sample; 404. Cavity; 405. Nozzle; 5. Pneumatic-hydraulic pump; 6. Flow meter; 7. Control cabinet. Detailed Implementation

[0070] 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.

[0071] like Figure 1 As shown, the present invention proposes a method for predicting and evaluating the safety of pipe fittings under stress, comprising:

[0072] S101: Obtain the range of key parameters such as the size parameters, material performance parameters, and flow field parameters of the fracturing elbow used in the field. The size parameters of the fracturing elbow include: outer diameter, wall thickness, and bending radius; the material performance parameters include: material yield strength and Brinell hardness; and the flow field parameters include: flow velocity in the pipe, internal pressure, particle type, particle mass fraction, and particle size.

[0073] S102: Based on the key parameters obtained, conduct erosion tests on fracturing elbow materials under stress conditions. During the test, the main factors considered are flow velocity, impact angle, particle type, particle mass fraction, particle size, and applied stress value. The erosion rate is measured by the weight loss method and expressed as a dimensionless erosion rate.

[0074] During the experiment, the apparatus used, such as Figure 2 As shown, the device is a solid-liquid two-phase jet erosion and wear testing machine that can apply tensile loads. It mainly includes: an air compressor 1, a mud pump 2, a sand mixing tank 3, an erosion chamber 4, a pneumatic-hydraulic pump 5, a flow meter 6, and a control cabinet 7.

[0075] Air compressor 1 is connected to pneumatic hydraulic pump 5, and pneumatic hydraulic pump 5 is connected to erosion chamber 4;

[0076] The sand mixing tank 3 is located below the erosion chamber 4 and is connected to the bottom of the erosion chamber 4 via a pipeline; the sand mixing tank 3 is equipped with an agitator;

[0077] The sand mixing tank 3 is connected to one end of the mud pump 2, and the other end of the mud pump 2 is connected to the erosion chamber 4 through a pipeline.

[0078] Multiple flow meters 6 are installed on the pipeline between the mud pump 2 and the erosion chamber 4;

[0079] The control cabinet 7 is connected to the air compressor 1, mud pump 2, sand mixing tank 3, erosion chamber 4, pneumatic hydraulic pump 5 and flow meter 6 respectively.

[0080] like Figure 3 As shown, the erosion chamber 4 is mainly composed of a tensile sensor 401, a hydraulic tensile pump 402, a sample 403, a chamber 404, and a nozzle 405.

[0081] The sample 403 is installed inside the cavity 404, and the sample 403, tensile sensor 401, and hydraulic tensile pump 402 are connected in sequence. The mud pump 2 is connected to the nozzle 405 through a pipeline.

[0082] The hydraulic tensile pump 402 is connected to the pneumatic hydraulic pump 5 and is used to apply axial stress to the specimen 403.

[0083] Specifically, during the experiment:

[0084] (a) The variables considered in the experiment are:

[0085] 1) The flow velocity is considered to vary between 5m / s and 30m / s, and can be set to 5m / s, 10m / s, 15m / s, 20m / s, 25m / s, and 30m / s;

[0086] 2) The impact angle is considered to vary between 0-90°, and can be set to 0°, 15°, 30°, 45°, 60°, 75° and 90°;

[0087] 3) The particle type can be selected as quartz sand or ceramsite sand, and the particle mass fraction (the percentage of a certain component in the mixture to the total mass) is 1-20%, which can be set to 1%, 5%, 10%, 15%, or 20%; the particle size is 0.1-0.9 mm, which can be set to 0.1 mm, 0.3 mm, 0.5 mm, 0.7 mm, or 0.9 mm;

[0088] 4) The applied stress value is the maximum circumferential stress caused by the internal pressure borne by the fracturing elbow. A finite element simulation model of the fracturing elbow is constructed using ANSYS or ABAQUS software. A geometric model is established based on the dimensional parameters of the fracturing elbow (outer diameter, wall thickness, bending radius). The upstream and downstream pipe walls of the fracturing elbow are fixed and constrained. Different internal pressures are applied to the inner wall of the fracturing elbow, ranging from 0 to 120 MPa. Considering internal pressures of 0, 30 MPa, 60 MPa, 90 MPa, and 120 MPa, the circumferential stress of the fracturing elbow under different internal pressures is obtained. For example, the finite element mesh generation of the fracturing elbow is as follows: Figure 4As shown; the finite element simulation results of the circumferential stress of the fracturing elbow under internal pressure of 60 MPa are as follows. Figure 5 As shown, the maximum circumferential stress at the fracture elbow wall occurs on the inner side of the elbow, and the circumferential stress in the local area of ​​the fracture elbow always exhibits tensile stress. Therefore, during the erosion test, tensile stress can be applied to specimen 403 to simulate the local circumferential stress caused by high internal pressure. This equivalent method not only allows for a better indoor reproduction of the coupled erosion test environment of proppant-carrying fluid impact and stress during fracturing operations, but also avoids the high risks and costs associated with using high-pressure fluid equipment. During the test, the calculated maximum circumferential stress value of 216 MPa was applied to both ends of specimen 403.

[0089] (b) The erosion rate was determined by the weight loss method, that is, the sample 403 was weighed before and after the test, and the dimensionless erosion rate ER obtained from the test was calculated as follows:

[0090]

[0091] In the formula, ER is the dimensionless erosion rate, mg / mg; m e The mass loss of sample 403 before and after erosion; m p The mass of particles consumed in the erosion test.

[0092] (c) The test procedure is as follows: using a solid-liquid two-phase jet erosion wear testing machine capable of applying tensile loads:

[0093] (1) Clean the erosion test machine and add a certain amount of clean water and erosion particles to the sand mixing tank 3.

[0094] (2) Select sample 403 and number it. Clean the surface of sample 403 with acetone. After cleaning, dry it with a hot air blower. Weigh it using a high-precision electronic balance and record the mass of sample 403. Weigh each sample 403 three times and take the average value of the result as m1.

[0095] (3) Install the sample 403 and adjust the tilt angle of the sample 403 to the set impact angle.

[0096] (4) Start the air compressor 1, adjust the output oil pressure of the pneumatic hydraulic pump 5, and apply tensile stress to the sample 403 through the hydraulic tensile pump 402. The magnitude of the tensile stress is adjusted according to the test requirements.

[0097] (5) Turn on mud pump 2 and adjust the flow rate to the set flow rate according to the flow meter 6.

[0098] (6) Start the test and stop when the test period is reached. The test period is set to 1 hour.

[0099] (7) After the erosion is completed, remove the sample 403, rinse the sand and gravel on the surface of the sample 403 with clean water, then clean the stains with acetone, and finally dry it with a hot air blower.

[0100] (8) Weigh the eroded sample 403 three times using a balance, and take the average value as m2. The weight of m can be obtained from m1-m2. e .

[0101] (9) Calculate the ER of the fracturing elbow under this working condition according to formula (1) and record it.

[0102] Based on the aforementioned testing machine and testing procedures, the ER under different working conditions was obtained to establish an erosion mathematical model. The ER variation under different working conditions is as follows: Figures 6-10 As shown (particle type is ceramsite sand). For example... Figure 6 As shown, the material erosion test parameters at different flow rates are as follows: impact angle 30°; particle mass fraction 10%; particle size 0.5 mm; internal pressure considered 60 MPa; flow rates set to 5 m / s, 10 m / s, 15 m / s, 20 m / s, 25 m / s, and 30 m / s. With increasing flow rate, the erosion rate of sample 403 increases exponentially.

[0103] like Figure 7 As shown, the test parameters for material erosion rate at different impact angles are as follows: flow velocity 20 m / s; particle mass fraction 10%; particle size 0.5 mm; internal pressure considered 60 MPa; impact angles set to 0°, 15°, 30°, 45°, 60°, 75°, and 90°. With increasing impact angle, the erosion rate first increases and then decreases, with the maximum erosion rate corresponding to an impact angle of 30°.

[0104] like Figure 8 As shown, the test parameters for material erosion rate under different particle mass fractions are as follows: flow velocity 20 m / s; impact angle 30°; particle size 0.5 mm; internal pressure 60 MPa; particle mass fractions of 1%, 5%, 10%, 15%, and 20%. The material erosion rate decreases with increasing particle mass fraction.

[0105] like Figure 9 As shown, the test parameters for material erosion rate under different particle sizes are as follows: flow velocity 20 m / s; impact angle 30°; particle mass fraction 10%; internal pressure considered 60 MPa; particle size set to 0.1 mm, 0.3 mm, 0.5 mm, 0.7 mm, and 0.9 mm. The erosion rate increases with increasing particle size.

[0106] like Figure 10As shown, the test parameters for material erosion rate under different internal pressure conditions are as follows: flow velocity 20 m / s; impact angle 30°; particle mass fraction 10%; particle size 0.5 mm; considered internal pressures of 0, 30 MPa, 60 MPa, 90 MPa, and 120 MPa. With increasing internal pressure, the applied circumferential stress increases, leading to an increase in the material erosion rate.

[0107] S103: Based on the erosion test results under different working conditions, an erosion mathematical model considering the influence of stress is established, and its mathematical expression is as follows:

[0108] ER=CBH -0.59 u n f(c p )f(d p )F s F E (α)F σ (P) (2)

[0109] In the formula, C is a coefficient, i.e., an empirical constant of the model obtained from experiments; BH is the Brinell hardness of the fracturing elbow material; u is the liquid flow velocity, in m / s; n is the velocity exponent; c p This represents the particle mass fraction, expressed as %, f(c) p ) is the particle mass fraction correction function; d p f(d) represents the particle size in mm. p ) is the particle size correction function; F s This is the particle shape coefficient; if the particles are quartz sand, this coefficient is 1; if the particles are ceramsite sand, this coefficient is 0.2. F E (α) is the impact angle function obtained after correction based on experimental results, where α is the impact angle; F σ (P) is the erosion function amplified by internal pressure, where P is the internal pressure.

[0110] In formula (2), the value of C can be determined based on test data under different working conditions (e.g., Figures 6-10 The value of n can be obtained by fitting the data; for n, its value can be obtained by fitting the erosion test results at different flow rates. Generally, for metallic materials, the value of n varies between 1.8 and 2.6; for f(c) p The formula can be derived by fitting the erosion test results at different particle mass fractions, based on... Figure 8 As a result, for example: f(c p This can be expressed as:

[0111]

[0112] For f(d) p The formula can be derived by fitting the erosion test results under different particle sizes, based on... Figure 9As a result, for example: f(d p This can be expressed as:

[0113] f(d p )=0.51ln(d p )+1.36 (4)

[0114] For F E (α), whose formula can be obtained by fitting the erosion test results at different impact angles, according to Figure 7 As a result, exemplarily: F E (α) can be expressed as:

[0115] F E (α)=-7×10 -8 α 4 +2×10 -5 α 3 -2.3×10 -3 α 3 +0.082α 2 -0.0067 (5)

[0116] For F σ (P), whose formula can be obtained by fitting the erosion test results under different internal pressures, according to Figure 10 As a result, exemplarily: F σ (P) can be expressed as:

[0117] F σ (P)=0.601e 0.0085P (6)

[0118] S104: Based on the established erosion mathematical model, erosion simulation of the fracturing elbow was performed to obtain simulation results of the maximum erosion rate of the fracturing elbow under different working conditions; the main implementation steps are as follows:

[0119] 1) Establish a three-dimensional physical model (flow field model) based on the dimensions of the fracturing elbow on site (outer diameter, wall thickness, and bending radius of the fracturing elbow);

[0120] 2) Mesh the three-dimensional flow field model of the fracturing bend, set the discrete particle model in the fluid (particle type, particle mass fraction, particle size), define the boundary conditions (set the inlet velocity and the outlet pressure), and define the erosion mathematical model (using formula (2) in step 103).

[0121] 3) Based on the three-dimensional flow field model of the fracturing elbow, the motion trajectory of discrete phase particles in the solid-liquid two-phase flow and the erosion results of the fracturing elbow were simulated, and the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions were obtained.

[0122] The above-mentioned erosion simulation of fracturing elbows can be achieved using ANSYS.FLUENT software.

[0123] For example, the particle trajectory of the fracturing bend is as follows: Figure 11 As shown, the erosion results are as follows Figure 12 As shown, the maximum erosion rate output is EMAX, which has a value of 0.101 mm / d.

[0124] S105: Based on the simulation results of the maximum erosion rate of fracturing elbows under different working conditions, machine learning algorithms are used to predict the erosion of fracturing elbows under high internal pressure, resulting in a fracturing elbow erosion prediction model; the main implementation steps are as follows:

[0125] 1) Obtain simulation results of the maximum erosion rate of the fracturing bend under different fracturing conditions (fracturing bend size, particle type, particle mass fraction, particle size, flow velocity, internal pressure), with at least 1000 sets, to form a dataset;

[0126] 2) Randomly divide the dataset, with 70% used as the training set and 30% as the test set;

[0127] 3) Input the simulation results of different fracturing conditions parameters and corresponding maximum erosion rate of fracturing elbows from the training set into the machine learning algorithm, train the machine learning algorithm, and form a fracturing elbow erosion prediction model.

[0128] 5) Input the parameters of different fracturing conditions in the test set into the fracturing elbow erosion prediction model, output the prediction result of the maximum erosion rate of the fracturing elbow, and compare the prediction result with the simulation result of the maximum erosion rate of the fracturing elbow in the test set. If the accuracy is higher than 90%, the fracturing elbow erosion prediction model is established. Otherwise, increase the number of samples in the data set and re-optimize the model parameters of the fracturing elbow erosion prediction model until the accuracy of the output prediction result of the maximum erosion rate of the fracturing elbow with the simulation result in the test set is higher than 90%.

[0129] Specifically, the accuracy calculation method described above is as follows:

[0130]

[0131] In the formula, R is the model accuracy; N is the number of test set samples; EMAX O The simulation results for the maximum erosion rate of the fracturing elbow are in mm / d; EMAX P The maximum erosion rate prediction result for fracturing elbows is in mm / d; EMAX M The value is the average of the simulation results for the maximum erosion rate of the fracturing elbow, in mm / d.

[0132] S106: Based on the fracturing elbow erosion prediction model, the erosion safety status of the fracturing elbow is evaluated. The implementation method is as follows: input the fracturing operating parameters into the fracturing elbow erosion prediction model described in S105, and predict the maximum erosion rate EMAX of the fracturing elbow under the operating condition based on the output results. P Multiplying this value by the service time of the pipe fitting will give the maximum reduction in wall thickness of the fracturing elbow. If this value does not exceed 20% of the wall thickness of the fracturing elbow, the fracturing elbow is considered to be in a safe state; otherwise, it is considered unsafe.

[0133] This invention proposes a method for predicting and evaluating the safety of pipe fittings under stress, based on a combination of indoor experiments, mathematical models, erosion simulation, and machine learning. First, key parameters such as the dimensions, material properties, and flow field parameters of the fracturing elbows used in the field are obtained. Then, multi-condition material experiments on fracturing elbows considering stress are conducted. Based on the results of numerous controllable indoor erosion tests, a mathematical model of material erosion considering the influence of stress is established. This model considers the elbow material hardness, flow velocity, particle mass fraction, particle shape, impact angle, and internal pressure parameters. Based on the established model, erosion simulations of real fracturing elbows are performed. Numerical simulations are used to establish a database of the maximum erosion rate of pipe fittings under different service conditions of fracturing elbows. Machine learning algorithms are used to establish a erosion prediction model for fracturing elbows under high internal pressure. Finally, the erosion prediction model is used to predict actual fracturing conditions, obtaining the predicted value of the maximum wall thinning of the fracturing elbow under these conditions, thereby determining the safety status of the fracturing elbow. This invention enables the prediction of the maximum erosion rate of fracturing elbows considering the influence of stress. By combining simulation and machine learning algorithms, the prediction results are fast, accurate and reliable, which is convenient for field industrial application. It has important guiding significance for ensuring the safe development of unconventional oil and gas and ensuring the safe service of fracturing elbows under high pressure conditions.

[0134] like Figure 13 As shown, based on the above-mentioned method for predicting and evaluating the erosion of pipe fittings under stress, this embodiment proposes a system for predicting and evaluating the erosion of pipe fittings under stress, including:

[0135] The acquisition unit is used to obtain the key parameter range of the fracturing elbow.

[0136] The erosion unit is used to conduct erosion tests on fracturing elbow materials under different working conditions under stress, based on the range of key parameters.

[0137] Establish a unit to build a mathematical model of erosion based on the results of erosion tests, which is influenced by stress.

[0138] The simulation unit is used to perform erosion simulation on fracturing elbows based on the erosion mathematical model, and obtain simulation results of the maximum erosion rate of fracturing elbows under different working conditions.

[0139] The model unit is used to predict the erosion of the fracturing elbow under high internal pressure based on the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions and the machine learning algorithm.

[0140] The evaluation unit is used to conduct a safety evaluation of fracturing elbows based on the fracturing elbow erosion prediction model.

[0141] The present invention also discloses an electronic 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 method for predicting and assessing the erosion of pipe fittings under stress.

[0142] The present invention also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for predicting and assessing the erosion of pipe fittings under stress.

[0143] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

[0144] 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, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] 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.

[0146] 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 functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus 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.

[0147] Although the present invention 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 these 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 invention.

Claims

1. A method for predicting and assessing the safety of pipe fittings under stress, characterized in that, include: Obtain the key parameter ranges for fracturing elbows; Based on the range of key parameters, erosion tests were conducted on fracturing elbow materials under different working conditions under stress. Based on the results of erosion tests, a mathematical model of erosion under the influence of stress is established. Based on the mathematical model of erosion, erosion simulation of fracturing elbow was carried out to obtain the simulation results of the maximum erosion rate of fracturing elbow under different working conditions. Based on the simulation results of the maximum erosion rate of fracturing elbows under different working conditions, machine learning algorithms are used to predict the erosion of fracturing elbows under high internal pressure, and a fracturing elbow erosion prediction model is obtained. Based on the erosion prediction model of fracturing elbows, a safety assessment of fracturing elbows is conducted.

2. The method for predicting and evaluating the safety of pipe fittings under stress according to claim 1, characterized in that, The key parameters include the dimensions of the fracturing elbow, material properties, and flow field parameters; The dimensions of the fracturing elbow include outer diameter, wall thickness, and bending radius; The material performance parameters include the material yield strength and Brinell hardness; The flow field parameters include the flow velocity, internal pressure, particle type, particle mass fraction, and particle size inside the pipe.

3. The method for predicting and evaluating the safety of pipe fittings under stress according to claim 1, characterized in that, The variable factors in the erosion test include flow velocity, impact angle, particle type, particle mass fraction, particle size, and applied stress value. The flow velocity is 5-30 m / s; The impact angle is 0-90°; The types of particles include quartz sand and ceramsite sand; The particle mass fraction is 1-20%; The particle size is 0.1-0.9 mm; The loading stress value is the circumferential stress of the fracturing elbow under different internal pressures; wherein, the internal pressure is 0-120MPa.

4. The method for predicting and evaluating the safety of pipe fittings under stress according to claim 1, characterized in that, The mathematical model of erosion is expressed as follows: ER=CBH -0.59 u n f(c p )f(d p )F s F E (α)F σ (P) Where ER is the erosion rate; C is the coefficient; BH is the Brinell hardness of the fracturing elbow material; u is the fluid velocity; n is the velocity index; f(c p ) is the particle mass fraction correction function; c p f(d) represents the particle mass fraction; p ) represents the particle size correction function; d p For particle size; F s F is the particle shape factor; E (α) is the impact angle function; α is the impact angle; F σ (P) is the erosion function amplified by internal pressure; P is the internal pressure.

5. The method for predicting and evaluating the safety of pipe fittings under stress according to claim 1, characterized in that, The simulation of erosion of fracturing elbows based on erosion mathematical models to obtain simulation results of the maximum erosion rate of fracturing elbows under different working conditions includes the following steps: A three-dimensional flow field model of the fracturing elbow was established based on the dimensions of the fracturing elbow on site. The three-dimensional flow field model of the fracturing elbow is meshed, the discrete particle model in the fluid is set, the boundary conditions are defined, and the erosion mathematical model is defined. Based on the three-dimensional flow field model of the fracturing elbow, the motion trajectory of discrete phase particles in the solid-liquid two-phase flow and the erosion results of the fracturing elbow were simulated, and the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions were obtained.

6. The method for predicting and evaluating the safety of pipe fittings under stress according to claim 5, characterized in that, The parameters set in the discrete particle model include particle type, particle mass fraction, and particle size. The boundary conditions include the flow velocity and internal pressure inside the pipe.

7. The method for predicting and evaluating the safety of pipe fittings under stress according to claim 1, characterized in that, The simulation results of the maximum erosion rate of the fracturing elbow under different working conditions are used to predict the erosion of the fracturing elbow under high internal pressure using machine learning algorithms. The resulting fracturing elbow erosion prediction model includes the following steps: A dataset was created based on simulation results of the maximum erosion rate of fracturing elbows under different working conditions; The dataset is randomly divided into a training set and a test set; The simulation results of different fracturing conditions and corresponding maximum erosion rates of fracturing elbows in the training set are input into the machine learning algorithm to train the machine learning algorithm and obtain the fracturing elbow erosion prediction model. Input the parameters of different fracturing conditions in the test set into the fracturing elbow erosion prediction model, output the prediction result of the maximum erosion rate of the fracturing elbow, and compare the prediction result with the simulation result in the test set. If the accuracy is higher than the threshold, the fracturing elbow erosion prediction model is established; otherwise, increase the number of samples in the dataset and re-optimize the model parameters of the fracturing elbow erosion prediction model until the accuracy is higher than the threshold.

8. The method for predicting and evaluating the safety of pipe fittings under stress according to claim 1, characterized in that, The safety assessment of fracturing elbows based on the erosion prediction model includes the following steps: The fracturing operating parameters are input into the fracturing elbow erosion prediction model to obtain the prediction result of the maximum erosion rate of the fracturing elbow; Multiply the prediction result by the service time of the fracturing elbow to obtain the maximum thinning of the fracturing elbow wall. If the maximum reduction in wall thickness of the fracturing elbow does not exceed the set threshold, the fracturing elbow is considered to be in a safe state; otherwise, it is considered unsafe.

9. A system for predicting and assessing the erosion of pipe fittings under stress, characterized in that, include: The acquisition unit is used to obtain the key parameter range of the fracturing elbow. The erosion unit is used to conduct erosion tests on fracturing elbow materials under different working conditions under stress, based on the range of key parameters. Establish a unit to build a mathematical model of erosion based on the results of erosion tests, which is influenced by stress. The simulation unit is used to perform erosion simulation on fracturing elbows based on the erosion mathematical model, and obtain simulation results of the maximum erosion rate of fracturing elbows under different working conditions. The model unit is used to predict the erosion of the fracturing elbow under high internal pressure based on the simulation results of the maximum erosion rate of the fracturing elbow under different working conditions and the machine learning algorithm. The evaluation unit is used to conduct a safety evaluation of fracturing elbows based on the fracturing elbow erosion prediction model.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for predicting and evaluating the erosion of pipe fittings under stress as described in any one of claims 1-8.

Images