Pipeline corrosion prediction method, device and system suitable for high-flow-rate liquid

Abstract

The invention is suitable for the technical field of intelligent injection and production engineering, and provides a pipeline corrosion prediction method, device and system suitable for high-flow-rate liquid. The corrosion prediction model is used for representing the corrosion speed under the influence of the corrosion medium flow velocity, the corrosion medium sand content, the CO2 partial pressure and the temperature at the same time, obtaining the influence weight of a single influence factor on the prediction model, obtaining the influence weight of a composite influence factor on the prediction model, and based on the corrosion prediction model, calculating the corrosion speed of the corrosion medium. And predicting the corrosion speed of the production water reinjection well pipe column. The corrosion effect of composite influence factors such as high temperature, acid gas (such as CO2) and high flow rate specific in a production water reinjection environment on the production water tubular column material is considered, corrosion prediction is more accurate, the service life of the material can be evaluated more accurately, and potential safety hazards are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent injection and production engineering, and in particular relates to a pipeline corrosion prediction method, device and system suitable for high-flow rate liquids. Background Art

[0002] Produced water reinjection technology is a water resource management and formation pressure maintenance technology commonly used in oil and gas field development. It mainly refers to the process of reinjecting produced water (including associated water, sewage, etc.) separated during oil and gas production into underground formations after treatment. Its main purpose is to effectively solve the problem of produced water treatment and reduce the impact on the environment.

[0003] With the deepening of oilfield development, the amount of reinjected water increases year by year, especially under large-volume reinjection conditions, the performance requirements for water injection well pipes are more stringent. However, during the production water reinjection process, water injection well pipes are susceptible to the dual effects of erosion and corrosion, especially the production water containing salt and acidic gas has a significant corrosive effect on the pipe string material. Under high flow rates, the erosion of the reinjection well pipe string and screen pipe by the production water will also be aggravated. The failure of the reinjection well pipe string will not only lead to a decrease in the water injection volume in the well area, but also destroy the well network distribution, affecting the production operation of the entire oil field.

[0004] Existing corrosion prediction models, such as the De Waard-Millis model and the De Waard-Lotz-Dugstad model, can take into account the influence of temperature, CO 2 The influence of partial pressure and flow rate on corrosion rate. However, although these models perform well in corrosion prediction under laboratory and low flow rate conditions, their applicability is limited when faced with complex production conditions such as large displacement, high flow rate, high temperature, and high sediment content, and their prediction accuracy is low in actual engineering environments.

[0005] Therefore, it is necessary to improve the existing corrosion prediction methods. Summary of the invention

[0006] The purpose of the embodiments of the present application is to provide a pipeline corrosion prediction method suitable for high-flow liquids, aiming to solve the problem that the existing prediction methods are limited in applicability when faced with complex production conditions such as large displacement, high flow rate, high temperature, and high sediment content, and have low prediction accuracy in actual engineering environments.

[0007] The embodiment of the present application is implemented by providing a pipeline corrosion prediction method applicable to high-flow liquids, the method comprising:

[0008] A corrosion prediction model under multiple influencing factors is constructed. The corrosion prediction model is used to characterize the corrosion medium flow rate, the sand content of the corrosive medium, CO 2Corrosion rate under the influence of partial pressure and temperature:

[0009]

[0010] in, Indicates the corrosion rate; represents temperature; v is the flow rate of the corrosive medium; For CO 2 partial pressure; w is the sand content of the corrosive medium; a, b, l, n are four correlation coefficients to be determined; represents the interaction effect correction term;

[0011] Based on the influence data of a single influencing factor on the corrosion rate, the influence weight of the single influencing factor on the prediction model is obtained to obtain correlation coefficients a, b, l, and n;

[0012] Based on the influence data of the composite influencing factors on the corrosion rate, the influence weight of the composite influencing factors on the prediction model is obtained to obtain the interaction influence correction term ;

[0013] Based on the corrosion prediction model, the corrosion rate of the produced water reinjection well pipe string is predicted.

[0014] Preferably, based on the influence data of a single influencing factor on the corrosion rate, the influence weight of the single influencing factor on the prediction model is obtained, and the method for obtaining the correlation coefficients a, b, l, and n is:

[0015] Construct the influence models of single influencing factors on corrosion rate respectively:

[0016] ,

[0017] ,

[0018] ,

[0019] ,

[0020] Based on variable control, temperature, CO 2 The single factor functional relationship between partial pressure, medium flow rate and medium sand content and the erosion corrosion;

[0021] Based on the single factor functional relationship, the correlation coefficients a, b, l, and n are obtained.

[0022] Preferably, based on the influence data of the composite influencing factors on the corrosion rate, the influence weight of the composite influencing factors on the prediction model is obtained to obtain the interaction influence correction term The method is:

[0023] Acquire a plurality of data sets consisting of a plurality of composite influencing factor values ​​and the corrosion rate values, and construct them into a composite database;

[0024] Normalizing the data in the composite database, and dividing the composite database into a training set, a validation set, and a test set;

[0025] Constructing a support vector regression model, training the support vector regression model based on the training set, the validation set and the test set, using the radial basis function kernel in the support vector regression model to capture the nonlinear relationship between the data, performing importance analysis on the generated composite features, and then obtaining the influence weight of each composite feature;

[0026] The composite features are weighted and summed based on the influence weights of each composite feature to obtain the interaction influence correction term.

[0027] Preferably, the composite feature includes the following interactive features: ;

[0028] in, Represents the composite characteristics of temperature and flow rate, Indicates temperature and CO 2 Partial pressure compound characteristics; Indicates the composite characteristics of temperature and sand content; It represents the composite characteristics of sand content and flow velocity; Indicates CO 2 Composite characteristics of partial pressure and sediment content; Indicates flow rate and CO 2 Partial pressure composite characteristics.

[0029] Preferably, the composite feature includes at least the following high-level features: ;

[0030] in, represents the second-order characteristic of temperature, represents the second-order characteristics of flow velocity, Indicates CO 2 The second-order characteristic of voltage division, Represents the second-order characteristics of sand content.

[0031] Preferably, the method of performing importance analysis on the generated composite features and then obtaining the influence weight of each composite feature is:

[0032] Based on the recursive elimination method, remove the feature that contributes the least to the model prediction each time, and record the impact of the feature on the system performance;

[0033] The impact weight is obtained according to the fluctuation range of the system performance after the feature is removed.

[0034] Another object of an embodiment of the present application is to provide a pipeline corrosion prediction system applicable to high-flow liquids. When the system is running, the steps of the pipeline corrosion prediction method applicable to high-flow liquids as described above are executed.

[0035] Another object of an embodiment of the present application is to provide a pipeline corrosion prediction device applicable to high-flow liquids, the device being used to collect the influence data of the single influencing factor on the corrosion rate and / or the influence data of the composite influencing factor on the corrosion rate in the pipeline corrosion prediction method applicable to high-flow liquids as described above, the pipeline corrosion prediction device applicable to high-flow liquids comprising:

[0036] Reactor, gas supply unit, rotary stirring unit and temperature adjustment unit;

[0037] The reactor is used to perform corrosion rate test on the experimental samples, and is provided with a hanging plate fixture, and the hanging plate fixture is used to hold the experimental samples;

[0038] The gas supply unit is used to introduce reaction gas into the reactor;

[0039] The temperature adjustment unit is used to adjust the reaction temperature in the reactor;

[0040] The rotary stirring unit is provided with stirring blades located in the reactor for controlling the flow rate of the corrosive medium.

[0041] Preferably, the experimental sample is a woven fabric containing a plurality of warp threads and weft threads of the same diameter, wherein the warp threads and the weft threads are mutually interwoven and arranged perpendicularly to form a mesh structure, and the quality characterization of the corrosion rate of the experimental sample is obtained by:

[0042]

[0043] in, A qualitative characterization of the corrosion rate of the experimental sample, represents the initial weight of the experimental sample, represents the weight of the test sample after removing the erosion-corrosion products, represents the surface area of ​​the experimental sample, and t represents the test time;

[0044] Among them, the surface area S of the experimental sample is obtained as follows:

[0045] ;

[0046] ;

[0047] , ;

[0048] in, Indicates the number of warp threads, represents the length of the experimental sample, Indicates the warp density, represents the width of the experimental sample, Indicates the length of the warp. represents the number of weft threads, d represents the weft thread diameter, Indicates the length of the weft. represents the distance between the holes, and c is the thickness of the experimental sample.

[0049] Preferably, the depth characterization of the corrosion of the experimental sample is set as the corrosion rate of the experimental sample;

[0050] The corrosion rate of the experimental sample is obtained as follows:

[0051]

[0052] in, represents the corrosion rate, Represents the density of the experimental sample.

[0053] The present invention provides a pipeline corrosion prediction method for high-flow liquids. The outstanding advantage is that, compared with the existing corrosion prediction methods and systems, the present invention takes into account the high temperature and acidic gases (such as CO) that are unique to the produced water reinjection environment. 2 ), high flow rate and other composite influencing factors on the corrosion of production water pipe column materials, the prediction of corrosion is more accurate, so that the life of the material can be evaluated more accurately, avoiding excessive use or premature scrapping of materials, and thus improving the coefficient of the safety system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A flow chart of a pipeline corrosion prediction method applicable to high-flow liquids provided in an embodiment of the present application;

[0055] Figure 2 is a block diagram of the internal structure of a computer device in one embodiment;

[0056] Figure 3 A structural diagram of a pipeline corrosion prediction device applicable to high-flow rate liquids provided in an embodiment of the present application;

[0057] Figure 4 A diagram of an experimental sample structure provided in an embodiment of the present application;

[0058] Figure 5 A diagram of an experimental sample weaving method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first script may be referred to as a second script, and similarly, a second script may be referred to as a first script without departing from the scope of this application.

[0061] like Figure 1 As shown, in one embodiment, a pipeline corrosion prediction method suitable for high-flow liquid is proposed, which may specifically include the following steps:

[0062] Step S10, constructing a corrosion prediction model under multiple influencing factors, wherein the corrosion prediction model is used to characterize the corrosion medium flow rate, the sand content of the corrosion medium, CO 2 Corrosion rate under the influence of partial pressure and temperature:

[0063]

[0064] in, Indicates the corrosion rate; represents temperature; v is the flow rate of the corrosive medium; For CO 2 partial pressure; w is the sand content of the corrosive medium; a, b, l, n are four correlation coefficients to be determined; represents the interaction effect correction term.

[0065] Step S20, based on the influence data of the single influencing factor on the corrosion rate, obtain the influence weight of the single influencing factor on the prediction model to obtain the correlation coefficients a, b, l, and n.

[0066] Step S30, based on the impact data of the composite influencing factors on the corrosion rate, obtain the impact weight of the composite influencing factors on the prediction model, and obtain the interaction impact correction term .

[0067] Step S40: predicting the corrosion rate of the produced water reinjection well pipe string based on the corrosion prediction model.

[0068] In the embodiment of the present application, there may be multiple types of acidic gases. As a reference and example, it is understandable that when other types of acidic gases are present, the corrosion rate can also be measured by this method. The influence data of single influencing factors and composite influencing factors can be composite influencing factor coupling test data of orthogonal design, historical database formed by historical sampling data under real hydrological environment, single variable experimental data of single influencing factor variation experiment, literature data, simulation data generated in simulation system, etc., which need not be limited here.

[0069] Those skilled in the art will know that with the deepening of oil field development, the amount of reinjected water increases year by year, especially under the condition of large-volume reinjection, the performance requirements for water injection well pipes are more stringent. However, during the reinjection of produced water, water injection well pipes are easily subjected to multiple effects of complex factors such as erosion and corrosion. For example, pipes containing a large amount of impurities such as sand and gravel, salt, acidic gases (such as CO 2 ) has a significant corrosive effect on the tubing material. Under high flow rates, the erosion of the production water on the reinjection well tubing and screen will also be aggravated. The coupled effect of erosion-corrosion greatly increases the risk of well pipe failure. The failure of the well pipe will not only lead to a decrease in production in the well area, but also destroy the well network distribution and affect the production operation of the entire oil field. Therefore, how to effectively predict and prevent the erosion-corrosion coupling risk under large-volume reinjection conditions has become a technical difficulty in the safe and efficient development of oil and gas fields. Existing corrosion prediction models such as the De Waard-Millis model, the De Waard-Lotz-Millis model and the De Waard-Lotz-Dugstad model, although they take into account temperature, CO 2 The influence of factors such as partial pressure and flow rate on the corrosion rate. Although these models perform well in corrosion prediction in the laboratory and under low flow rate conditions, their applicability is limited when faced with actual production conditions of large displacement and high flow rate. For the prediction of erosion rate, early studies focused on the conditions of curved pipe flow and jet flow, and developed models such as the Finnie micro-cutting theoretical model and the Bitter deformation grinding theoretical model. However, in the straight pipe flow environment of large-volume reinjection, the applicability of existing models is poor, and experimental data is relatively scarce. The API RP 14E specification is currently a more commonly used erosion rate prediction tool, but the value of its empirical coefficient C is controversial in practical applications. Therefore, the existing erosion rate prediction model has many problems such as conservatism and lack of applicability under large-volume reinjection conditions. Therefore, in the embodiments of the present application, the coupling effect of multiple influencing factors on the corrosion rate under actual conditions is taken into account.

[0070] At the same time, since the present application finds that the high-speed fluid destroys the protective film layer formed on the surface of the pipe while eroding it, the exposure area of ​​the pipe to the corrosive medium is increased, thereby aggravating the corrosion process; conversely, the weakening of the material by corrosion further enhances the effect of erosion. Due to the lack of comprehensive consideration of the composite coupling corrosion effect, the existing prediction model is often difficult to accurately assess the degree of damage to the pipe in practical applications, especially in the complex oil field reinjection environment. This error will lead to deviations in the prediction results and increase the risk of pipe failure. For large-volume production water reinjection wells, there is a lack of effective means to predict the risk of oil pipe and screen loss under multiple coupling effects. Under the combined influence of factors such as pipe string material, anti-corrosion process, reinjection production water components and water injection conditions, the ambiguity of the empirical constant value in the existing model, the existing model has limited applicability to the erosion-corrosion coupling risk of large-volume production water reinjection wells. Therefore, the present application also takes into account the interaction effects between multiple influencing factors, which are often not linear superpositions of single influencing factors. For example, at high temperatures, the increase in sediment volume will further increase the corrosion effect, and the relationship between the two is not a linear superposition relationship. Therefore, the corrosion prediction model provided by this application also introduces the influence of composite factors, for example, the influence of any two variables changing simultaneously on the corrosion rate in a system with multiple variables. Through the data under composite influencing factors, the interaction correction term can be obtained , thereby further increasing the prediction accuracy.

[0071] In a preferred embodiment, based on the influence data of a single influencing factor on the corrosion rate, the influence weight of the single influencing factor on the prediction model is obtained, and the method for obtaining the correlation coefficients a, b, l, and n is as follows:

[0072] Construct the influence models of single influencing factors on corrosion rate respectively:

[0073] ,

[0074] ,

[0075] ,

[0076] ,

[0077] Based on variable control, temperature, CO 2 The single factor functional relationship between partial pressure, medium flow rate and medium sand content and the erosion corrosion; based on the single factor functional relationship, the correlation coefficients a, b, l, n are obtained.

[0078] In the present application, based on a single factor variation test, CO 2The quantitative relationship between partial pressure, temperature, flow rate and sand content and corrosion rate is analyzed. Based on experimental parameters or historical data, the correlation coefficients a, b, l, and n can be obtained.

[0079] In one embodiment, due to the corrosion rate and , , , The variables formed by these four single factors are often roughly proportional to each other, so the correlation coefficient a can be obtained by combining and superimposing the influencing factors.

[0080] In a preferred embodiment, based on the influence data of the composite influencing factors on the corrosion rate, the influence weight of the composite influencing factors on the prediction model is obtained to obtain the interaction influence correction term The method is:

[0081] Acquire a plurality of data sets consisting of a plurality of composite influencing factor values ​​and the corrosion rate values, and construct them into a composite database;

[0082] Normalizing the data in the composite database, and dividing the composite database into a training set, a validation set, and a test set;

[0083] Constructing a support vector regression model, training the support vector regression model based on the training set, the validation set and the test set, using the radial basis function kernel in the support vector regression model to capture the nonlinear relationship between the data, performing importance analysis on the generated composite features, and then obtaining the influence weight of each composite feature;

[0084] The composite features are weighted and summed based on the influence weights of each composite feature to obtain the interaction influence correction term.

[0085] In the embodiment of the present application, the data is divided into a training set, a validation set, and a test set in a ratio of 7:2:1, which is suitable for processing by a machine learning algorithm for multidimensional nonlinear problems. In order to improve the adaptability and prediction accuracy of the model under complex conditions, multiple influencing variables are fully considered. This model can more accurately reflect the corrosion-erosion rate of the water reinjection well string under complex working conditions, providing a scientific basis for engineering applications.

[0086] In a preferred embodiment, the composite feature includes the following interactive features: ;

[0087] in, Represents the composite characteristics of temperature and flow rate, Indicates temperature and CO 2 Partial pressure compound characteristics; Indicates the composite characteristics of temperature and sand content; It represents the composite characteristics of sand content and flow velocity; Indicates CO 2 Composite characteristics of partial pressure and sediment content; Indicates flow rate and CO 2 Partial pressure composite characteristics.

[0088] In a preferred embodiment, the composite feature includes at least the following high-level features: ;

[0089] in, represents the second-order characteristic of temperature, represents the second-order characteristics of flow velocity, Indicates CO 2 The second-order characteristic of voltage division, Represents the second-order characteristics of sand content.

[0090] In the embodiments of the present application, the high-order features may be expressed in the form of second order or higher order, and the correlation coefficient may not be an integer, but since the influence of higher-order composite features is limited, and in order to reduce the computational intensity, only second-order features and binary composite features are used for example analysis. In order to capture high-order and interactive factors, the method is to first generate a feature polynomial, use the PolynomialFeatures function to expand the original features into a high-order interactive form, and use the radial basis function kernel RBF Kernel to capture nonlinear relationships.

[0091] In a preferred embodiment, the method of performing importance analysis on the generated composite features and then obtaining the influence weight of each composite feature is as follows:

[0092] Based on the recursive elimination method, remove the feature that contributes the least to the model prediction each time, and record the impact of the feature on the system performance;

[0093] The impact weight is obtained according to the fluctuation range of the system performance after the feature is removed.

[0094] In the embodiment of the present application, the fluctuation amplitude may refer to the degree of performance degradation of the system. Based on the above method, the weight of the above composite feature may be quantified, and each influencing factor may be weighted and then summed to obtain an accurate interaction correction term. .

[0095] Figure 2The internal structure diagram of a computer device in one embodiment is shown. The computer device can be specifically used to execute the pipeline corrosion prediction method for high-flow rate liquid provided in the embodiment of the present application. As shown in 2, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected by a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and can also store a computer program. When the computer program is executed by the processor, the processor can implement a pipeline corrosion prediction method for high-flow rate liquid. The internal memory can also store a computer program. When the computer program is executed by the processor, the processor can execute a pipeline corrosion prediction method for high-flow rate liquid. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0096] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0097] In one embodiment, the pipeline corrosion prediction device for high-velocity liquid provided by the present application can be implemented in the form of a computer program. The computer program can be used in Figure 2 The computer device is shown in the figure. The memory of the computer device can store various program modules constituting the pipeline corrosion prediction device suitable for high-flow liquid.

[0098] In one embodiment, a pipeline corrosion prediction system applicable to high-flow liquid is provided. When the system is running, the system executes the steps of the pipeline corrosion prediction method applicable to high-flow liquid as described above.

[0099] In the embodiment of the present application, the system can be a computer software or program system, which runs in the hardware containing the processing device, and when the above system is running, the corresponding method is executed. For the description of the above pipeline corrosion prediction method applicable to high flow rate liquid, please refer to the above text, which will not be repeated here.

[0100] In the embodiment of the present application, the outstanding advantage of the system is that, compared with the existing corrosion prediction methods and systems, the present application takes into account the high temperature and acidic gases (such as CO) unique to the production water injection well pipe string environment. 2), high flow rate and other composite influencing factors on the corrosion of production water pipe column materials, the prediction of corrosion is more accurate, so that the life of the material can be evaluated more accurately, avoiding excessive use or premature scrapping of materials, and thus improving the coefficient of the safety system.

[0101] In a preferred embodiment, if Figure 3 As shown, a pipeline corrosion prediction device suitable for high-flow liquid is provided, characterized in that the device is used to collect the influence data of the single influencing factor on the corrosion rate and / or the influence data of the composite influencing factor on the corrosion rate in the pipeline corrosion prediction method suitable for high-flow liquid as described above, and the pipeline corrosion prediction device suitable for high-flow liquid includes:

[0102] Reactor, gas supply unit, rotary stirring unit and temperature adjustment unit;

[0103] The reactor is used to perform corrosion rate test on the experimental samples, and is provided with a hanging plate fixture, and the hanging plate fixture is used to hold the experimental samples;

[0104] The gas supply unit is used to introduce reaction gas into the reactor;

[0105] The temperature adjustment unit is used to adjust the reaction temperature in the reactor;

[0106] The rotary stirring unit is provided with stirring blades located in the reactor for controlling the flow rate of the corrosive medium.

[0107] In this embodiment, the temperature adjustment device may include a heating device and a thermometer. The heating device may be a heating plate, a heating belt, etc., which is attached to the side wall of the reactor. The thermometer is used to measure the temperature in the reactor in real time. The gas supply device is used to introduce the corresponding gas into the reactor. The introduced gas is CO 2 and N 2 , and a pressure gauge is set to measure the pressure in the reactor; the rotary stirring device includes a rotary motor and a stirring blade connected to the power output end of the motor. Through this device, experiments can be carried out to obtain test data of composite or single influencing factors.

[0108] like Figure 4 and Figure 5 As shown, a structural diagram and a weaving diagram of an experimental sample are given. The experimental sample is a woven fabric containing a number of warp threads and weft threads of the same diameter. The warp threads and the weft threads are interwoven perpendicularly to each other to form a mesh structure. The quality characterization of the corrosion rate of the experimental sample is obtained by:

[0109]

[0110] in, A qualitative characterization of the corrosion rate of the experimental sample, represents the initial weight of the experimental sample, represents the weight of the test sample after removing the erosion-corrosion products, represents the surface area of ​​the experimental sample, and t represents the test time;

[0111] Among them, the surface area S of the experimental sample is obtained as follows:

[0112] ;

[0113] ;

[0114] , ;

[0115] in, Indicates the number of warp threads, represents the length of the experimental sample, Indicates the warp density, represents the width of the experimental sample, Indicates the length of the warp. represents the number of weft threads, d represents the weft thread diameter, Indicates the length of the weft. represents the distance between the holes, and c is the thickness of the experimental sample.

[0116] In this embodiment, The unit is g / (cm 2 ﹒ h); The unit is g; The unit is g; Unit: m 2 ; t is the test time, in h.

[0117] In one embodiment, the depth characterization of the corrosion of the experimental sample is set as the corrosion rate of the experimental sample;

[0118] The corrosion rate of the experimental sample is obtained as follows:

[0119]

[0120] in, represents the corrosion rate, Represents the density of the experimental sample.

[0121] In this embodiment, the depth of the corrosion rate can be obtained, and the depth value of the corrosion rate can be used as a composite corrosion rate judgment standard to obtain an evaluation that is closer to reality.

[0122] As a preferred embodiment of the present application, the corrosion rate data under the composite influencing factors can also be obtained by the following method:

[0123] The experiment was conducted based on the above device and samples. The stirring blades used were U-shaped stirring blades, with a stirring diameter of 11.5 cm and a blade width of 1 cm; the experimental samples can be made of N80 material oil pipe hanging pieces, with the following specifications:

[0124] Specification Specific parameters Length(m) 0.05 Width(m) 0.03 Thickness(mm) 2 Hanging hole diameter (mm) 4

[0125] The experimental samples can be made of 13Cr-L80 material or 316L material screen hanging sample, and its specifications are:

[0126] Specification Specific parameters Mesh 200 Pore ​​size (μm) 74 Test piece length (mm) 72.4 Width of test piece (mm) 11.5 Wire diameter (μm) 53 Thickness(mm) 0.5

[0127] The structure of the experimental sample can be a full-cover twill weave, the structural diagram is as follows Figure 3 As shown, the compilation method is as follows Figure 4 As shown. The corrosive medium can be N 2 and CO 2 Mix the gas and simulate the formation water sample. The simulated formation water sample can be a formation water sample configured with deionized water according to density, pH value, mineralization, ion concentration. The test conditions are set as follows: fluid stirring by electromagnetic coupling, with a speed range of 0-3000rpm (corresponding to a linear speed of 0.6-18m / s). The stirring blade rotates at high speed to drive the sand particles in the corrosive medium to simulate the impact and erosion of the fixed hanging piece. Due to the high speed (turbulence), it can be assumed that the sand particle flow rate is similar to the linear speed of the blade rotation, which is 0.6-18m / s (corresponding to a speed of 100-3000rpm). The reactor has a diameter of 160mm, a height of 180mm, a maximum working pressure of 15MPa, and is heated by a constant temperature water bath cycle, with a maximum working temperature of 100℃.

[0128] The corrosion test adopts a rotating differential erosion corrosion simulation test. The process of the rotating differential erosion corrosion simulation test is as follows:

[0129] First, the hanging piece was fixed vertically at the bottom of the reactor, the formation water sample was injected into the reactor, and a set weight of sand was added to seal it. Secondly, the reactor was evacuated and CO was injected. 2 Gas to set CO 2 pressure, and then inject N 2The gas is set to the pressure set in the reactor, preferably, it can be set to 10MPa; the temperature of the reactor is adjusted to the set value; then, the stirring time is set, the stirring is turned on, the temperature is lowered and the exhaust is performed after the stirring is completed, and the hanging piece is taken out; specifically, the stirring time that can be set in this step is 72 hours; finally, the hanging piece is immersed in 15% concentration of hydrochloric acid to remove minerals and corrosive substances, and the washed hanging piece is immediately immersed in sodium hydroxide solution to neutralize the acidity, and then immersed in clean anhydrous ethanol after being taken out, and the filter paper is wiped dry, and then the surface of the hanging piece is gently polished with fine sandpaper until the metal color is exposed, and then weighed to calculate the hanging piece loss rate.

[0130] In order to simulate the actual water injection conditions of large-volume production water reinjection wells, an orthogonal design test scheme was used to carry out a corrosion test with four factors and four levels. The parameters were set as follows:

[0131] factor Level 1 Level 2 Level 3 Level 4 <![CDATA[CO 2 Partial pressure (MPa)]]> 0 0.24 0.48 0.72 Temperature(℃) 52 62 72 82 <![CDATA[Silt content (kg / m 3 )]]> 0 0.15 0.30 0.45 Flow rate (m / s) 3.3 4.3 5.3 6.3

[0132] The test results of the orthogonal experiment are:

[0133] Serial number Flow rate (m / s) <![CDATA[Silt content (kg / m 3 )]]> Temperature(℃) <![CDATA[CO 2 Partial pressure (MPa)]]> Corrosion rate 1 4.3 0.3 72 0.48 5.926641 2 4.3 0 52 0 2.398147 3 4.3 0.15 62 0.24 4.824545 4 4.3 0.45 82 0.72 6.834667 5 3.3 0.3 52 0.24 4.382462 6 3.3 0 72 0.72 6.197811 7 3.3 0.15 82 0.48 5.551476 8 3.3 0.45 62 0 2.449115 9 5.3 0.3 62 0.72 6.935275 10 5.3 0 82 0.24 5.440109 11 5.3 0.15 72 0 3.081354 12 5.3 0.45 52 0.48 6.114214 13 6.3 0.3 82 0 3.499499 14 6.3 0 62 0.48 6.472784 15 6.3 0.15 52 0.72 7.087469 16 6.3 0.45 72 0.24 6.032474

[0134] The orthogonal test results were brought into the prediction model, and the unknown coefficients were determined by using the multivariate linear regression method.

[0135] In this embodiment, the considered temperature, The corrosion rate prediction model affected by partial pressure, flow velocity and sand content is:

[0136]

[0137] In order to further verify the accuracy of the above model, the prediction results of the established model were compared with the orthogonal test results:

[0138] Serial number Measured value (mm / a) Predicted value (mm / a) error(%) Serial number Measured value (mm / a) Predicted value (mm / a) Error value (%) 1 5.9267 5.5365 6.58 9 6.9353 7.2117 3.99 2 2.3981 2.6103 8.85 10 5.4401 5.1230 5.83 3 4.8245 4.3697 9.43 11 3.0814 3.2213 4.54 4 6.8347 7.2064 5.44 12 6.1142 6.6625 8.97 5 4.3825 3.9847 9.08 13 3.4995 3.6627 4.66 6 6.1978 5.6625 8.64 14 6.4728 6.7577 4.40 7 5.5515 5.2114 6.13 15 7.0875 7.5769 6.91 8 2.4491 2.5300 3.30 16 6.0325 5.7013 5.49

[0139] From the above results, it can be seen that the error between the model prediction and the test results is between 3.30% and 9.43%, indicating that the established corrosion rate prediction model of composite influencing factors has good accuracy within the target oil pipe operating parameter range.

[0140] It should be understood that, although each step in the flow chart of each embodiment of the present application is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0141] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0142] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0143] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A pipeline corrosion prediction method suitable for high-velocity liquids, characterized in that: The method comprises: A corrosion prediction model under multiple influencing factors is constructed, and the corrosion prediction model is used to characterize the corrosion rate under the influence of the flow velocity of the corrosive medium, the sand content of the corrosive medium, the CO2 partial pressure and the temperature at the same time: in, Indicates the corrosion rate; represents temperature; v is the flow rate of the corrosive medium; is the partial pressure of CO2; w is the sand content of the corrosive medium; a, b, l, n are four correlation coefficients to be determined; represents the interaction effect correction term; Based on the influence data of a single influencing factor on the corrosion rate, the influence weight of the single influencing factor on the prediction model is obtained to obtain correlation coefficients a, b, l, and n; Based on the influence data of the composite influencing factors on the corrosion rate, the influence weight of the composite influencing factors on the prediction model is obtained to obtain the interaction influence correction term ; Based on the corrosion prediction model, the corrosion rate of the produced water reinjection well pipe string is predicted.

2. A pipeline corrosion prediction method suitable for high-velocity liquid according to claim 1, characterized in that: Based on the influence data of a single influencing factor on the corrosion rate, the influence weight of the single influencing factor on the prediction model is obtained, and the method for obtaining the correlation coefficients a, b, l, and n is as follows: Construct the influence models of single influencing factors on corrosion rate respectively: ， ， ， ， Based on variable control, the single factor functional relationship between temperature, CO2 partial pressure, medium flow rate and medium sand content and the erosion corrosion is obtained respectively; Based on the single factor functional relationship, the correlation coefficients a, b, l, and n are obtained.

3. A pipeline corrosion prediction method suitable for high-velocity liquid according to claim 1, characterized in that: Based on the influence data of the composite influencing factors on the corrosion rate, the influence weight of the composite influencing factors on the prediction model is obtained to obtain the interaction influence correction term The method is: Acquire a plurality of data sets consisting of a plurality of composite influencing factor values ​​and the corrosion rate values, and construct them into a composite database; Normalizing the data in the composite database, and dividing the composite database into a training set, a validation set, and a test set; Constructing a support vector regression model, training the support vector regression model based on the training set, the validation set and the test set, using the radial basis function kernel in the support vector regression model to capture the nonlinear relationship between the data, performing importance analysis on the generated composite features, and then obtaining the influence weight of each composite feature; The composite features are weighted and summed based on the influence weights of each composite feature to obtain the interaction influence correction term.

4. A pipeline corrosion prediction method applicable to high-velocity liquid according to claim 3, characterized in that: The composite feature includes the following interactive features: ; in, Represents the composite characteristics of temperature and flow rate, It represents the composite characteristics of temperature and CO2 partial pressure; Indicates the composite characteristics of temperature and sand content; It represents the composite characteristics of sand content and flow velocity; It represents the composite characteristics of CO2 partial pressure and sediment content; Represents the composite characteristics of flow rate and CO2 partial pressure.

5. The pipeline corrosion prediction method applicable to high-velocity liquid according to claim 3 is characterized in that: The composite features include at least the following high-level features: ； in, represents the second-order characteristic of temperature, represents the second-order characteristics of flow velocity, represents the second-order characteristic of CO2 partial pressure, Represents the second-order characteristics of sand content.

6. A pipeline corrosion prediction method applicable to high-velocity liquids according to claim 3, characterized in that: The method for analyzing the importance of the generated composite features and obtaining the influence weight of each composite feature is as follows: Based on the recursive elimination method, remove the feature that contributes the least to the model prediction each time, and record the impact of the feature on the system performance; The impact weight is obtained according to the fluctuation range of the system performance after the feature is removed.

7. A pipeline corrosion prediction system suitable for high-velocity liquids, characterized in that: When the system is in operation, the steps of the pipeline corrosion prediction method applicable to high-flow-rate liquids according to any one of claims 1 to 6 are executed.

8. A pipeline corrosion prediction device suitable for high-velocity liquids, characterized in that: The device is used to collect the influence data of the single influencing factor on the corrosion rate and / or the influence data of the composite influencing factor on the corrosion rate in the pipeline corrosion prediction method applicable to high-flow liquid as described in any one of claims 1 to 6; The pipeline corrosion prediction device suitable for high-flow liquid comprises: Reactor, gas supply unit, rotary stirring unit and temperature adjustment unit; The reactor is used to perform corrosion rate test on the experimental samples, and is provided with a hanging plate fixture, and the hanging plate fixture is used to hold the experimental samples; The gas supply unit is used to introduce reaction gas into the reactor; The temperature adjustment unit is used to adjust the reaction temperature in the reactor; The rotary stirring unit is provided with stirring blades located in the reactor for controlling the flow rate of the corrosive medium.

9. A pipeline corrosion prediction device suitable for high-velocity liquid according to claim 8, characterized in that: The experimental sample is a woven fabric containing a number of warp threads and weft threads of the same diameter, wherein the warp threads and the weft threads are interwoven perpendicularly to each other to form a mesh structure. The quality characterization of the corrosion rate of the experimental sample is obtained by: in, A qualitative characterization of the corrosion rate of the experimental sample, represents the initial weight of the experimental sample, represents the weight of the test sample after removing the erosion-corrosion products, represents the surface area of ​​the experimental sample, and t represents the test time; Among them, the surface area S of the experimental sample is obtained as follows: ； ； , ； in, Indicates the number of warp threads, represents the length of the experimental sample, Indicates the warp density, represents the width of the experimental sample, Indicates the length of the warp. represents the number of weft threads, d represents the weft thread diameter, Indicates the length of the weft. represents the distance between the holes, and c is the thickness of the experimental sample.

10. A pipeline corrosion prediction device suitable for high-velocity liquid according to claim 9, characterized in that: The depth representation of the corrosion of the experimental sample is set as the corrosion rate of the experimental sample; The corrosion rate of the experimental sample is obtained as follows: in, represents the corrosion rate, Represents the density of the experimental sample.

Images