A method for screening phase change materials in deep-sea cementing and its application

Abstract

This invention relates to the field of machine learning technology and discloses a method and terminal for screening phase change materials (PCMs) in deep-sea cementing. The method includes: establishing a mathematical analysis model of deep-sea cementing; establishing a dataset based on the mathematical analysis model; establishing a surrogate model of the mathematical analysis model as a temperature prediction model based on the dataset; and screening PCMs in the deep-sea cementing based on the temperature prediction model. This invention establishes a mathematical analysis model for deep-sea cementing and obtains a large amount of simulated data based on the results of the data analysis model, thereby establishing a dataset that meets the requirements of neural networks. A surrogate model is then trained based on the dataset to train the neural network, enabling rapid screening of PCMs to meet the needs of complex and variable construction environments.

Description

Technical Field

[0001] This invention relates to the field of machine learning technology, and in particular to a method for screening phase change materials in deep-sea cementing, a terminal, and a readable storage medium. Background Technology

[0002] Before deep-sea oil and gas extraction, cement needs to be injected into the gap between the casing and the formation to stabilize the well. During the hydration process, the cement releases a large amount of heat of hydration, causing the system temperature to rise. In shallow deep-sea layers, there are often hydrate layers. Hydrates are mainly composed of solidified methane and are stable under high pressure and specific low-temperature conditions (usually not higher than 18°C). Once the temperature exceeds its equilibrium temperature boundary value, the hydrates will decompose, releasing a large amount of gas. This can easily form gas channeling channels in the cement sheath, affecting the cementing quality and, in severe cases, causing cementing failure and formation collapse.

[0003] Therefore, temperature control is necessary. Traditionally, the heat of hydration and maximum temperature are usually adjusted chemically using low-activity cementitious materials and inert fillers, such as fly ash, slag, and silica sand. However, reducing the heat of hydration of cement chemically often leads to a decrease in material strength, especially in the early stages. Furthermore, to control the heat of hydration and temperature distribution of cement paste as much as possible, the amount of fly ash and slag used typically accounts for 50-60% of the total cementitious materials, which also increases the cost of cement paste. Moreover, there are significant differences between fly ash and slag from different manufacturers and batches, making stable temperature control difficult.

[0004] In recent years, phase change materials (PCMs) have been increasingly used to control the heat of hydration and temperature rise of building concrete. However, it has also been found that molten PCMs have a significant impact on the mechanical properties and permeability of building concrete. To address this, existing technologies employ microencapsulation of PCMs with different shell materials to overcome the negative impact of PCMs on cement slurry performance. Microcapsule phase change materials (MPCMs) have been widely used in the field of building concrete; however, their application in oil well cementing is relatively limited. Research often focuses on verifying the effectiveness of PCMs in temperature control under hypothetical operating conditions, but the deep-sea oil well environment is complex and variable, deviating significantly from ideal conditions. Therefore, existing technologies cannot meet the complex and variable engineering requirements of deep-sea oil well environments. Summary of the Invention

[0005] The purpose of this invention is to provide a method for screening phase change materials in deep-sea cementing, aiming to solve the problem that existing methods for selecting phase change materials cannot meet the needs of the complex and variable environment of deep-sea oil wells.

[0006] The technical solution adopted by this invention to solve the technical problem is as follows:

[0007] This invention provides a method for screening phase change materials in deep-sea cementing cement, the method specifically comprising:

[0008] Establish a mathematical analysis model for deep-sea cementing.

[0009] A dataset is established based on the mathematical analysis model, and a surrogate model of the mathematical analysis model is established based on the dataset as a temperature prediction model.

[0010] Phase change materials in deep-sea cementing are screened based on the temperature prediction model.

[0011] Furthermore, the establishment of the mathematical analysis model for deep-sea cementing specifically includes:

[0012] Establish thermal conduction models for the deep-sea cementing cement and the formation;

[0013] An exothermic model was established for the cement hydration process of the deep-sea cementing material.

[0014] Based on the heat conduction model and the heat release model, a mathematical analysis model with the peak temperature as the output is established.

[0015] Furthermore, the establishment of the thermal conduction model for the deep-sea cementing and the thermal conduction model for the formation specifically includes:

[0016] Establish a specific heat model for deep-sea cementing:

[0017] ρ eff c p,eff (T)=φ c ρ c c p,c (T)+φ s ρ s c p,s +(1-φ c -φ s )ρ m c p,m ;

[0018] Where T is the independent variable, temperature, ρ represents density, and c p,eff (T) represents the specific heat of cement containing phase change materials, ρ eff φ represents the density of cement containing phase change materials. c ρ represents the volume fraction of the nucleus. c c represents the density of the nucleus. p,c (T) represents the specific heat of the nucleus, φ s ρ represents the volume fraction of the shell.s c represents the density of the shell. p,s ρ represents the specific heat of the shell. m c represents the density of the cement matrix. p,m Indicates the specific heat of the cement matrix;

[0019] Among them, the specific heat of the nucleus c p,c (T) is:

[0020]

[0021] Among them, T melting h is the melting temperature of the phase change material. sf For latent heat of fusion, ΔT melting For the melting temperature window, c p,c,s For the solid phase heat of phase change materials, c p,c,l The phase change material is a liquid phase heat;

[0022] Establish a thermal conductivity model for deep-sea cementing:

[0023]

[0024] Where, k eff k represents the effective thermal conductivity of cement containing phase change materials. m k represents the thermal conductivity of the cement matrix. c k represents the thermal conductivity of the core of a phase change material. s This indicates the thermal conductivity of the shell of the phase change material;

[0025] A heat conduction model for deep-sea cementing is established based on the specific heat model and the thermal conductivity model:

[0026]

[0027] in, This represents the heat production rate per unit volume of cement at location r at time t, expressed in W / m³. 3 ), c p,eff (T) represents the relationship between the effective specific heat in the cement ring and temperature;

[0028] Establish a thermal conduction model for the formation:

[0029]

[0030] Where r represents the position inside the cement ring at a distance r from the center, ρ h c represents the density of the formation. p,h T represents the specific heat of the formation. h K represents the formation temperature. h This indicates the thermal conductivity of the formation.

[0031] Furthermore, the establishment of the exothermic model for the cement hydration process of the deep-sea cementing specifically includes:

[0032] Establish an equivalent age model for the cement hydration process:

[0033]

[0034] Where t represents time, E a T represents the activation energy of the hydration reaction, R represents the ideal gas constant, and T represents the activation energy of the hydration reaction. ref t represents the reference temperature. eq (r,t) represents the equivalent age t. eq T(r,t) is a function of temperature T changing with time t and position r.

[0035] A hydration degree model is established based on the aforementioned equivalent age model:

[0036]

[0037] Where, θ ∞ B and τ are the experimentally measured hydration curve parameters, and θ(t) eq ) represents the equivalent age t eq Degree of hydration at time;

[0038] Based on the aforementioned hydration degree model, a model for the total heat released per unit volume during the hydration process is established:

[0039] Q(t eq ) = C c ΔHθ(t eq );

[0040] Where Q(t) eq ) indicates that cement hydration has developed to the point where t eq The total heat released per unit volume at age , C c ΔH represents the cement content per unit volume, and ΔH represents the enthalpy of cement hydration.

[0041] Based on the total heat model, establish a model for the heat production rate of cement per unit volume:

[0042]

[0043] in, This represents the heat production rate per unit volume of cement at position r at time t.

[0044] Furthermore, the screening of phase change materials in the deep-sea cementing material based on the temperature prediction model specifically includes:

[0045] The temperature peak values ​​corresponding to multiple phase change materials are obtained based on the temperature prediction model.

[0046] Obtain the hydrate hydrolysis temperature of the formation where the deep-sea cementing well is located;

[0047] Based on the hydrolysis temperature of the hydrate and the corresponding temperature peak of each phase change material, each phase change material is screened.

[0048] Furthermore, obtaining the temperature peaks corresponding to multiple phase change materials based on the temperature prediction model specifically includes:

[0049] The initial cementing temperature, hydrate saturation, and formation porosity, as well as the melting temperature, volume fraction, and latent heat of each phase change material, are obtained. The initial cementing temperature, hydrate saturation, formation porosity, melting temperature, volume fraction, and latent heat of each phase change material are then input into the temperature prediction model.

[0050] The temperature prediction model outputs the peak temperature of each phase change material.

[0051] Furthermore, obtaining the hydrate hydrolysis temperature of the formation where the deep-sea cementing well is located specifically includes:

[0052] Obtain the hydrate three-phase equilibrium model, formation temperature, hydrate saturation, and formation porosity, and input the formation temperature, hydrate saturation, and formation porosity into the hydrate three-phase equilibrium model;

[0053] The three-phase equilibrium model of the hydrate outputs the hydrolysis temperature of the hydrate.

[0054] Furthermore, the step of screening each phase change material based on the hydrate hydrolysis temperature and the corresponding temperature peak of each phase change material specifically includes:

[0055] For each phase change material, determine whether the corresponding temperature peak is lower than the hydrate hydrolysis temperature;

[0056] If the peak temperature is lower than the hydrolysis temperature of the hydrate, the corresponding phase change material is retained.

[0057] If the peak temperature is not less than the hydrolysis temperature of the hydrate, then the corresponding phase change material is filtered out.

[0058] In addition, to achieve the above objectives, the present invention also provides a terminal, the terminal comprising: a memory, a processor, and a screening program for phase change materials in deep-sea cementing stored in the memory and executable on the processor, wherein when the screening program for phase change materials in deep-sea cementing is executed by the processor, the terminal controls the terminal to implement the steps of the screening method for phase change materials in deep-sea cementing as described above.

[0059] In addition, to achieve the above objectives, the present invention also provides a readable storage medium storing a screening program for phase change materials in deep-sea cementing, wherein when the screening program for phase change materials in deep-sea cementing is executed by a processor, the program implements the steps of the screening method for phase change materials in deep-sea cementing as described above.

[0060] The present invention, by employing the above technical solution, has the following effects:

[0061] This invention establishes a mathematical analysis model for deep-sea cementing and obtains a large amount of simulation data based on the results of the data analysis model. This results in the creation of a dataset that meets the requirements of neural networks. The neural network is then trained based on the dataset to establish a surrogate model, which enables rapid screening of phase change materials to meet the needs of complex and ever-changing construction environments. Attached Figure Description

[0062] Figure 1 This is a flowchart of the steps in a preferred embodiment of the present invention for screening phase change materials in deep-sea cementing.

[0063] Figure 2 This is a schematic diagram of a deep-sea cementing model in a preferred embodiment of the present invention;

[0064] Figure 3 This is a schematic diagram of the distribution of the maximum radial temperature in a preferred embodiment of the present invention;

[0065] Figure 4 This is a schematic diagram of the sample space in a preferred embodiment of the present invention;

[0066] Figure 5 A schematic diagram of the temperature prediction model in a preferred embodiment of the present invention;

[0067] Figure 6 A schematic diagram of the training and testing results of the temperature prediction model in a preferred embodiment of the present invention;

[0068] Figure 7 A schematic diagram of the generalization test results of the temperature prediction model in a preferred embodiment of the present invention;

[0069] Figure 8 A schematic diagram of the weighting analysis in a preferred embodiment of the present invention;

[0070] Figure 9 A schematic diagram of the sample distribution for additive causality analysis in a preferred embodiment of the present invention;

[0071] Figure 10 A schematic diagram of the phase change material screening process in a preferred embodiment of the present invention;

[0072] Figure 11A schematic diagram of the screening results in the first sea area in a preferred embodiment of the present invention;

[0073] Figure 12 A schematic diagram of the screening results in the second sea area in a preferred embodiment of the present invention;

[0074] Figure 13 A schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0075] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0076] Example 1

[0077] Please see Figure 1 Embodiment 1 of this application is a method for screening phase change materials in deep-sea cementing, which includes the following steps:

[0078] S1. Establish a mathematical analysis model for deep-sea cementing.

[0079] In this embodiment, a finite element analysis model of deep-sea cementing is specifically established. Since the temperature gradient in the depth direction is significantly smaller than the temperature gradient in the radial direction, heat conduction in the depth direction can be ignored, and only heat conduction in the radial direction is considered.

[0080] First, a heat conduction model for deep-sea cementing needs to be established. Please refer to [the relevant documentation / reference]. Figure 2 , Figure 2 This is a schematic diagram of heat transfer in deep-sea cementing. The cylinder contains drilling fluid, and from the radial direction outwards, it consists of steel casing, cement sheath, and hydrate layer. Phase change material capsules are randomly distributed within the cement sheath. According to previous studies, the effective specific heat of composite materials can be expressed as the weighted average of the components. That is, the effective specific heat of cement containing phase change material can be expressed as the weighted average of the specific heat of the phase change material core, the specific heat of the phase change material shell, and the specific heat of the cement matrix.

[0081] ρ eff c p,eff (T)=φ c ρ c c p,c (T)+φ s ρ s c p,s +(1-φ c -φ s )ρ m c p,m ;

[0082] Where T is the independent variable, temperature, ρ represents density, and cp,eff ρ represents the specific heat of cement containing phase change materials. eff c represents the density of cement containing phase change materials. p,eff (T) represents the effective specific heat of cement containing phase change materials as a function of temperature, φ c ρ represents the volume fraction of the nucleus. c c represents the density of the nucleus. p,c c represents the specific heat of the nucleus. p,c (T) represents the specific heat of the nucleus as a function of temperature, φ s ρ represents the volume fraction of the shell. s c represents the density of the shell. p,s ρ represents the specific heat of the shell. m c represents the density of the cement matrix. p,m This indicates the specific heat of the cement matrix.

[0083] Among them, the specific heat c of the core of the phase change material p,c (T) can be described as:

[0084]

[0085] Among them, T melting h is the melting temperature of the phase change material. sf For latent heat of fusion, ΔT melting For the melting temperature window, c p,c,s For the solid phase heat of phase change materials, c p,c,l The phase change material is the liquid phase heat. According to the effective medium theory, the effective thermal conductivity of cement containing phase change materials can be calculated using Felske's model:

[0086]

[0087] Where, k eff k represents the effective thermal conductivity of a composite material, specifically cement containing phase change materials. m k represents the thermal conductivity of the cement matrix. c k represents the thermal conductivity of the core of a phase change material. s This indicates the thermal conductivity of the shell of the phase change material.

[0088] The one-dimensional heat conduction equation within the cement ring is:

[0089]

[0090] in, This represents the heat production rate per unit volume of cement at location r at time t, expressed in W / m³. 3 ), c p,eff (T) represents the relationship between the effective specific heat within the cement ring and temperature.

[0091] The one-dimensional heat conduction equation in the strata is:

[0092]

[0093] Where, ρ h c represents the density of the formation. p,h T represents the specific heat of the formation. h K represents the formation temperature. h This indicates the thermal conductivity of the formation.

[0094] The initial conditions are set as follows:

[0095] T(r,0)=T h (r,0)=T init ;

[0096] Where T(r,0) represents the temperature inside the cement ring at an initial time, r away from the center. h (r,0) represents the formation temperature at an initial time r away from the center, T. init This represents the initial temperature, T. init Due to the geothermal gradient dT melting The depth h of the strata determines:

[0097] T init =dT melting *h;

[0098] Next, the boundary conditions of the model were set. The upper and lower interfaces of the strata were considered to be thermally insulated. An infinite element domain was set at the outermost interface along the radial direction with a geometric stretch of 10,000 times. The innermost interface was for static water convection.

[0099] Then, an exothermic model for the cement hydration process is established. The cement hydration process is highly temperature-dependent, and the equivalent age model can effectively measure the degree of cement hydration. The equivalent age t of cement... eq for:

[0100]

[0101] Where r represents the positional variable within the cement, a one-dimensional heat conduction positional variable located at a point r away from the center within the cement ring, and t represents the time variable, specifically the equivalent age t. eq Both position x and temperature T are functions of position x and time t. T(r,t) represents the function of temperature T changing with time and position, where t eq (r,t) represents the equivalent age t. eq E is a function that varies with time and location. a The value represents the activation energy of the hydration reaction, R = 8.314 J / mol·K is the ideal gas constant, and T represents the activation energy of the hydration reaction. ref =20℃ is the reference temperature for the laboratory.

[0102] The degree of hydration θ can be approximated as a function of the equivalent age:

[0103]

[0104] Where θ(t) eq ) represents the equivalent age t eq hydration degree at time θ ∞ B and τ are the parameters of the experimentally measured hydration curve.

[0105] The total heat Q released per unit volume during cement hydration is a function of the equivalent age:

[0106] Q(t eq ) = C c ΔHθ(t eq );

[0107] Where Q(t) eq ) indicates that cement hydration has developed to the point where t eq The total heat released per unit volume at age , C c ΔH represents the cement content per unit volume, and ΔH is the enthalpy of cement hydration reaction, 475 kJ / kg.

[0108] The heat production rate per unit volume of cement can be considered as the derivative of the total heat released per unit volume of cement with respect to time:

[0109]

[0110] Among them, E a R = 8.314 J / mol·K is the activation energy for the hydration reaction and is the ideal gas constant.

[0111] S2. Establish a dataset based on the mathematical analysis model, and establish a surrogate model of the mathematical analysis model based on the dataset as a temperature prediction model.

[0112] After establishing the heat transfer and heat release models, finite element analysis can be performed, and the results are as follows: Figure 3 As shown, the temperature peak occurs before 50 hours as the cement hydration reaction proceeds. The temperature decreases with increasing distance between the observation point and the cement sheath; therefore, the observation point closest to the cement sheath is a critical point for cementing, and controlling the temperature rise at this point is essential to ensure the safety of the cementing process. In this study, the peak temperature at this point is used as the research object, and whether the peak temperature exceeds the decomposition temperature of formation hydrates is used to determine whether the selected phase change material can guarantee the safety of the cementing process.

[0113] Furthermore, based on the analysis results of finite element analysis, six key parameters (characteristics) affect the cementing process: phase change material melting temperature, phase change material volume fraction, phase change material latent heat, initial cementing temperature, hydrate saturation, and porosity. Please refer to... Figure 4 , Figure 4 The middle arrow indicates the feature direction, and the scale on the arrow indicates the uniform value in that direction. The area within {} represents the value range of the feature. The area enclosed by the hexagon is the sample space, which contains 11,520 samples. Applying these samples to the finite element heat transfer model yields the corresponding peak temperatures (labels) for these samples, resulting in a temperature prediction database.

[0114] That is, in this embodiment, 11,520 sets of datasets are established, with the melting temperature of phase change material, volume fraction of phase change material, latent heat of phase change material, initial cementing temperature, hydrate saturation and formation porosity as samples, and peak temperature as label, to train a neural network, and to establish a surrogate model of finite element analysis as a temperature prediction model.

[0115] In this embodiment, please refer to Figure 5 A Forward Neural Network (FNN) model is used as the temperature prediction model, consisting of 5 hidden layers, each containing 10 pre-trained neurons after hyperparameter tuning. This model can be used to construct a mapping from the sample space to temperature peaks.

[0116]

[0117] Where NN represents a neural network, s are the parameters of the input sample space, and θ are the weights of the model. This represents the peak temperature output by the model.

[0118] The training process of a model is essentially the process of optimizing the weights.

[0119]

[0120] T peak θ represents the true value calculated by the finite element model. * This represents the weights of the optimal model obtained through training.

[0121] The training results of the model are as follows Figure 6 As shown, during the training process, the model exhibits uniform convergence on both the training and validation sets, proving that the model does not suffer from overfitting. On the test set, R0... 2 =0.995, proving that the model's prediction error is very low. By resampling and taking new eigenvalues ​​both within and outside the sample space for finite element analysis, 2700 sets of interpolated datasets and 1440 sets of expanded datasets were obtained. For example... Figure 7As shown, the model performs excellently on both datasets, demonstrating that it can also predict situations that have not occurred before, indicating good generalization ability and suitability for deployment.

[0122] In this embodiment, after training is completed, Shapley Additive Explanations based on game theory are used to explain how the neural network processes the data, making the model's predictions more reliable and secure.

[0123] The average result of the additive causality analysis for the Shapley values ​​is as follows: Figure 8 As shown, Figure 8 It characterizes the average impact of different features on the results in the dataset. Figure 8 In this table, temp_place represents the initial temperature, phi_sc represents the volume fraction of the phase change material (PCM), poro represents the formation porosity, phi_h represents the hydrate saturation, PCM_melting represents the melting temperature of the PCM, and hsf represents the latent heat of the PCM. Analysis of the Shapley average values ​​reveals the importance of these parameters for temperature control. It can be seen that the initial temperature (temp_place) has the greatest impact on the peak temperature; that is, the deeper the formation and the greater the geothermal gradient, the higher the peak temperature during the cementing process.

[0124] Please refer to Figure 9 , Figure 9 The graph shows the scatter distribution of Shapley values ​​for all samples, with the x-axis representing the Shapley values ​​and the y-axis representing the order of features. Figure 9 and Figure 8 The order corresponds in the diagram. Positive Shapley values ​​represent promoting the outcome, while negative values ​​represent inhibiting the outcome. Each row represents the scatter distribution of a feature. The more scatter points with the same Shapley value, the wider the band appears. Since the samples are not randomly selected, many bands with concentrated scatter points are presented. The color of the scatter points changes from red to blue, indicating that the feature value decreases. It can be seen that an increase in initial temperature promotes an increase in the peak cementing temperature, while a larger volume fraction of phase change material results in a smaller peak cementing temperature. Furthermore, the volume fraction of phase change material does not promote the peak cementing temperature. It can be seen that the rules learned by deep learning revealed by Shapley game theory are intuitive and understandable.

[0125] S3. Screening phase change materials in the deep-sea cementing material based on the temperature prediction model.

[0126] Please refer to Figure 10 , Figure 10This flowchart illustrates the screening process for phase change materials (PCMs). By deploying a temperature prediction model into the screening program, rapid screening of PCMs can be achieved. During the screening process, the program iterates through the collected PCM property tables, finding the corresponding material name and its thermophysical properties (melting temperature, latent heat of fusion), and then assigns a volume fraction. For the formation to be studied, formation temperature, hydrate saturation, and formation porosity need to be input. The program uses these parameters to calculate the maximum temperature during the cementing process using the temperature prediction model. On the other hand, the seawater depth, formation depth, and formation thickness of the formation are input, and the program calculates the hydrolysis temperature of the hydrate in that formation based on the three-phase equilibrium condition. Finally, the program determines whether to store the material's serial number and the volume fraction to be used by checking if the maximum temperature exceeds the hydrate hydrolysis temperature. In this process, a step-by-step method is used to find the minimum usable volume fraction for the material.

[0127] Please refer to Figure 11 and Figure 12 , Figure 11 and Figure 12 The screening results of phase change materials in two different sea areas were recorded. Figure 11 Record the screening results for the first sea area. Figure 12 Record the screening results for the second sea area. Figure 11 The figure shows the screening results of the natural gas extraction site in the first offshore area. It records the phase change materials and their volume fractions for the site, as well as the melting temperature of the materials, for the geological conditions of the site. Since there are many materials screened, the horizontal axis cannot record all the serial numbers, so the serial numbers are omitted. Figure 12 The results of using this screening procedure to select mining sites in the second sea area are presented. The selected materials and their quantities can be used as a reference in practical engineering projects.

[0128] Example 2

[0129] Please see Figure 13 Based on the above method, the present invention also provides a terminal, which includes a processor 10, a memory 20, and a display 30. However, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0130] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard drive or RAM. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a phase change material screening program 40 for deep-sea cementing, which can be executed by the processor 10 to realize the terminal described in this application.

[0131] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing related programs for a method of screening phase change materials in deep-sea cementing.

[0132] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface.

[0133] In one embodiment, when the processor 10 executes a screening program 40 for phase change materials in deep-sea cementing in the memory 20, it implements the steps of a screening method for phase change materials in deep-sea cementing as described above.

[0134] Example 3

[0135] This embodiment provides a storage medium that stores a screening program for phase change materials in deep-sea cementing. When the screening program for phase change materials in deep-sea cementing is executed by a processor, it implements the steps of a screening method for phase change materials in deep-sea cementing as described above.

[0136] In summary, this invention establishes a mathematical analysis model for deep-sea cementing and obtains a large amount of simulation data based on the results of the data analysis model, thereby establishing a dataset that can meet the needs of neural networks. Based on the dataset, a neural network is trained to establish a surrogate model, which is then used to achieve rapid screening of phase change materials to meet the needs of complex and ever-changing construction environments.

[0137] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0138] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a memory, magnetic disk, optical disk, etc.

[0139] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for screening phase change materials in deep-sea cementing, characterized in that, The method for screening phase change materials in deep-sea cementing specifically includes: Establish a mathematical analysis model for deep-sea cementing. A dataset is established based on the mathematical analysis model, and a surrogate model of the mathematical analysis model is established based on the dataset as a temperature prediction model. The phase change materials in the deep-sea cementing are screened based on the temperature prediction model. The mathematical analysis model for establishing deep-sea cementing specifically includes: Establish thermal conduction models for the deep-sea cementing cement and the formation; An exothermic model was established for the cement hydration process of the deep-sea cementing material. Based on the thermal conduction model of deep-sea cementing, the thermal conduction model of the formation, and the heat release model, a mathematical analysis model with peak temperature as the output is established. The screening of phase change materials in deep-sea cementing based on the temperature prediction model specifically includes: The temperature peak values ​​corresponding to multiple phase change materials are obtained based on the temperature prediction model. Obtain the hydrate hydrolysis temperature of the formation where the deep-sea cementing well is located; Based on the hydrolysis temperature of the hydrate and the corresponding temperature peak of each phase change material, each phase change material is screened.

2. The method for screening phase change materials in deep-sea cementing as described in claim 1, characterized in that, The establishment of the thermal conduction model for the deep-sea cementing and the thermal conduction model for the formation specifically includes: Establish a specific heat model for deep-sea cementing: in, Temperature is the independent variable. Indicates density, This indicates the relationship between the effective specific heat within the cement ring and temperature. This indicates the density of cement containing phase change materials. This represents the volume fraction of the nucleus in a phase change material. This represents the density of the core in a phase change material. This represents the specific heat of the core in a phase change material. This indicates the volume fraction of the shell in a phase change material. This indicates the density of the shell of the phase change material. This represents the specific heat of the shell of a phase change material. Indicates the density of the cement matrix. Indicates the specific heat of the cement matrix; Among them, the specific heat of the core of the phase change material for: in, This refers to the melting temperature of the phase change material. For latent heat of fusion, For melting temperature window, For phase change materials, solid-phase heat. The phase change material is a liquid phase heat; Establish a thermal conductivity model for deep-sea cementing: in, This indicates the effective thermal conductivity of cement containing phase change materials. Indicates the thermal conductivity of the cement matrix. This represents the thermal conductivity of the core in a phase change material. This indicates the thermal conductivity of the shell of the phase change material; A heat conduction model for deep-sea cementing is established based on the specific heat model and the thermal conductivity model: in, Indicates position cement over time The heat production rate of cement per unit volume at time, in units of , This indicates the relationship between the effective specific heat within the cement ring and temperature. Establish a thermal conduction model for the formation: in, This indicates that the distance from the center of the cement ring is... The location, Indicates the density of the formation. Indicates the specific heat of the formation. Indicates formation temperature. This indicates the thermal conductivity of the formation.

3. The method for screening phase change materials in deep-sea cementing as described in claim 2, characterized in that, The establishment of the exothermic model for the cement hydration process of the deep-sea cementing concrete specifically includes: Establish an equivalent age model for the cement hydration process: in, Indicates time, Indicates the activation energy of the hydration reaction. Represents the ideal gas constant. Indicates reference temperature. Indicates equivalent age Over time And a function of position r change, Indicates temperature Over time and location A changing function; A hydration degree model is established based on the aforementioned equivalent age model: in The parameters of the hydration curve were measured experimentally. Indicates equivalent age Degree of hydration at time; Based on the aforementioned hydration degree model, a model for the total heat released per unit volume during the hydration process is established: in, This indicates that cement hydration has developed to the point where The total heat released per unit volume at age 7 The cement content per unit volume. The enthalpy of reaction for cement hydration; Based on the total heat model, establish a model for the heat production rate of cement per unit volume:

4. The method for screening phase change materials in deep-sea cementing as described in claim 1, characterized in that, The step of obtaining the temperature peak values ​​corresponding to multiple phase change materials based on the temperature prediction model specifically includes: The initial cementing temperature, hydrate saturation, and formation porosity, as well as the melting temperature, volume fraction, and latent heat of each phase change material, are obtained. The initial cementing temperature, hydrate saturation, formation porosity, melting temperature, volume fraction, and latent heat of each phase change material are then input into the temperature prediction model. The temperature prediction model outputs the peak temperature of each phase change material.

5. The method for screening phase change materials in deep-sea cementing as described in claim 1, characterized in that, The method of obtaining the hydrate hydrolysis temperature of the formation where the deep-sea cementing well is located specifically includes: Obtain the hydrate three-phase equilibrium model, formation temperature, hydrate saturation, and formation porosity, and input the formation temperature, hydrate saturation, and formation porosity into the hydrate three-phase equilibrium model; The three-phase equilibrium model of the hydrate outputs the hydrolysis temperature of the hydrate.

6. The method for screening phase change materials in deep-sea cementing as described in claim 1, characterized in that, The step of screening each phase change material based on the hydrolysis temperature of the hydrate and the corresponding temperature peak of each phase change material specifically includes: For each phase change material, determine whether the corresponding temperature peak is lower than the hydrate hydrolysis temperature; If the peak temperature is lower than the hydrolysis temperature of the hydrate, the corresponding phase change material is retained. If the peak temperature is not less than the hydrolysis temperature of the hydrate, then the corresponding phase change material is filtered out.

7. A terminal, characterized in that, The terminal includes: a memory, a processor, and a screening program for phase change materials in deep-sea cementing stored in the memory and executable on the processor. When the screening program for phase change materials in deep-sea cementing is executed by the processor, the terminal controls the implementation of the steps of the screening method for phase change materials in deep-sea cementing as described in any one of claims 1-6.

8. A readable storage medium, characterized in that, The readable storage medium stores a screening program for phase change materials in deep-sea cementing, which, when executed by a processor, implements the steps of a screening method for phase change materials in deep-sea cementing as described in any one of claims 1-6.

Images