A method, device and equipment for generating a phase diagram of supercritical carbon dioxide hydrate

Abstract

The present invention provides a supercritical carbon dioxide hydrate phase diagram generation method, device, and equipment, wherein the supercritical carbon dioxide hydrate phase diagram generation method includes: establishing an SC-CO2 hydrate phase data test system based on multi-source monitoring technology, and obtaining a physical data set and an image data set through the SC-CO2 hydrate phase data test system; dividing the physical data set and the image data set into a training data set and a test data set; constructing an SC-CO2 hydrate phase data prediction generation model, and training and optimizing the SC-CO2 hydrate phase data prediction generation model using the training data set and the test data set to obtain an optimal generalization model; obtaining data to be analyzed under different environmental conditions, and predicting the data to be analyzed using the optimal generalization model to obtain a prediction result. Through the present invention, a visualization experiment of the phase evolution of SC-CO2 hydrate is realized, and the generation accuracy and efficiency of the SC-CO2 hydrate phase diagram can also be improved.

Description

Technical Field

[0001] The present invention belongs to the field of carbon dioxide geological storage and machine learning technology, and in particular relates to a method, device and equipment for generating a supercritical carbon dioxide hydrate phase diagram. Background Art

[0002] Deep reservoir CO2 geological storage projects are gaining increasing attention due to the ability of supercritical CO2 (SC-CO2) hydrates to carry large amounts of CO2 in the form of clathrates within a small amount of water for geological storage. CO2 transforms into a supercritical state at temperatures of 31.1°C and 7.38 MPa, significantly altering its physical and mechanical properties. Furthermore, due to the high geothermal, high geostress, and high permeability conditions found in deep reservoirs, the state of SC-CO2 hydrates varies significantly with temperature and pressure. Therefore, calculating the phase diagram of SC-CO2 hydrates significantly impacts the CO2 content stored in deep reservoirs and the safety and stability of CO2 geological storage projects.

[0003] At present, the calculation models of SC-CO2 hydrate phase diagrams mainly include calculation models based on hydrate phase equilibrium and calculation models based on hydrate chemical potential. The former mainly includes the Chen-Guo model and thermodynamic and thermodynamic equilibrium models, while the latter mainly includes the Van der Waals-Platteeuw model. However, both types of models have certain simplified model assumptions, which are different from the actual SC-CO2 hydrate phase state. In addition, since the specific morphology and number of layers of the SC-CO2 hydrate clathrate structure are difficult to determine, they can only predict the solubility of CO2 at different temperatures and pressures, resulting in low calculation accuracy of the SC-CO2 hydrate phase diagram. The shortcomings of these two types of models are specifically manifested in the following aspects:

[0004] (1) The computational models based on hydrate phase equilibrium have a large number of assumptions based on stable equilibrium conditions and different equations of state. They are mostly suitable for predicting hydrate phase equilibrium conditions and are quite different from the actual SC-CO2 hydrate phase evolution.

[0005] (2) The computational model based on the chemical potential of hydrates can only calculate the phase diagram and solubility of CO2 hydrates during the formation and stabilization processes, but cannot calculate the transition critical state of the SC-CO2 hydrate phase evolution process, and therefore cannot construct an accurate SC-CO2 hydrate phase diagram;

[0006] (3) Existing phase diagram calculation studies rarely consider the calculation of hydrate phase diagrams in porous media. However, real CO2 hydrates exist in the porous structure and fractures of deep reservoir rocks. Existing phase diagram experiments and theoretical model studies rarely consider the influence of the heterogeneous structure of reservoir rocks.

[0007] Therefore, existing SC-CO2 hydrate phase diagram calculation studies have many assumptions, low accuracy of phase diagram calculation models, and little consideration of the influence of heterogeneous structure of reservoir rocks. As a result, it is impossible to obtain an accurate SC-CO2 hydrate phase diagram, resulting in unclear understanding of the evolution state and capacity of deep reservoirs during CO2 geological storage, which seriously affects the assessment of reservoir CO2 storage capacity and the safety and stability of CO2 geological storage projects.

[0008] There is currently no effective solution to the problem of poor accuracy of existing hydrate phase diagram generation methods. Summary of the Invention

[0009] The present invention provides a supercritical carbon dioxide hydrate phase diagram generation method, device and equipment, which are used to solve the defect of poor accuracy of existing hydrate phase diagram generation methods.

[0010] In a first aspect, the present invention provides a method for generating a supercritical carbon dioxide hydrate phase diagram, comprising:

[0011] Establishing an SC-CO2 hydrate phase state data testing system based on multi-source monitoring technology, and acquiring physical data sets and image data sets through the SC-CO2 hydrate phase state data testing system;

[0012] Dividing the physical dataset and the image dataset into a training dataset and a test dataset;

[0013] Constructing a SC-CO2 hydrate phase state data prediction generation model, and training and optimizing the SC-CO2 hydrate phase state data prediction generation model using the training data set and the test data set to obtain an optimal generalization model;

[0014] Obtaining data to be analyzed under different environmental conditions, predicting the data to be analyzed using the optimal generalization model to obtain prediction results, and generating an SC-CO2 hydrate phase diagram based on the prediction results.

[0015] According to a supercritical carbon dioxide hydrate phase diagram generation method provided by the present invention, the SC-CO2 hydrate phase data testing system includes an SC-CO2 control generation system, a topology control imaging system and a nuclear magnetic resonance control imaging system; the SC-CO2 hydrate phase data testing system is connected to a data control processing module.

[0016] According to a supercritical carbon dioxide hydrate phase diagram generation method provided by the present invention, the SC-CO2 control generation system includes a gas cylinder, the gas outlet end of the gas cylinder is connected to a high-pressure plunger pump, the output end of the high-pressure plunger pump is connected to a CNC constant temperature water tank, the outside of the CNC constant temperature water tank is provided with a corrosion-resistant container, the output end of the CNC constant temperature water tank is connected to a deionized water bottle through a corrosion-resistant conduit, the corrosion-resistant conduit is provided with a quick-closing valve, and the output end of the deionized water bottle is connected to the topology control imaging module.

[0017] According to a method for generating a supercritical carbon dioxide hydrate phase diagram provided by the present invention, the topological control imaging system includes a base, on which a mounting track is fixed by fastening bolts, and on which a plurality of mutually corresponding X-ray probes and block detection plates are arranged, and the X-ray probes and the block detection plates are connected to the data control processing module via data wires.

[0018] According to a supercritical carbon dioxide hydrate phase diagram generation method provided by the present invention, the mounting track is composed of two semicircular multi-layer grooves, and the X-ray probe and the segmented detection plate are controlled to move freely in each layer of grooves by the data control processing module.

[0019] According to a method for generating a supercritical carbon dioxide hydrate phase diagram provided by the present invention, the nuclear magnetic resonance controlled imaging system includes a magnetic pole system cabin, on which a magnet is provided; the nuclear magnetic resonance controlled imaging system also includes a wavelet signal amplifier, an image conversion generator, and a nuclear magnetic radio frequency source generator, and the nuclear magnetic radio frequency source generator, the magnet, the wavelet signal amplifier, the image conversion generator, and the data control processing module are sequentially connected to form a closed loop;

[0020] The nuclear magnetic resonance controlled imaging system also includes a loading chamber and a porous medium, wherein the porous medium is arranged inside the loading chamber; the loading chamber includes an outer chamber plate and an inner chamber plate, both of which are transparent; a plurality of temperature sensors and heating components are arranged between the outer chamber plate and the inner chamber plate; the nuclear magnetic resonance controlled imaging system also includes a pressure controller, which is connected to the temperature sensor, the heating component and the data control processing module.

[0021] According to a supercritical carbon dioxide hydrate phase diagram generation method provided by the present invention, the SC-CO2 hydrate phase data prediction generation model is trained and optimized using the training data set and the test data set to obtain an optimal generalization model, including:

[0022] Training and fine-tuning the SC-CO2 hydrate phase data prediction generation model using the training data set;

[0023] Inputting the test data set into the SC-CO2 hydrate phase state data prediction generation model to obtain a predicted value;

[0024] The relative error of the SC-CO2 hydrate phase state data prediction generation model is determined according to the predicted value and the true value, and the optimal generalization model is determined according to the relative error.

[0025] According to a supercritical carbon dioxide hydrate phase diagram generation method provided by the present invention, data to be analyzed under different environmental conditions are obtained, the data to be analyzed are predicted using the optimal generalization model to obtain prediction results, and the SC-CO2 hydrate phase diagram is generated based on the prediction results, including:

[0026] Inputting the data to be analyzed into the optimal generalization model, predicting the data to be analyzed using the optimal generalization model, and obtaining critical temperature and critical pressure data of the phase evolution of SC-CO2 hydrate;

[0027] The SC-CO2 hydrate phase diagram is generated according to the critical temperature and the critical pressure data.

[0028] In a second aspect, the present invention further provides a supercritical carbon dioxide hydrate phase diagram generating device, comprising:

[0029] an acquisition module, configured to establish an SC-CO2 hydrate phase state data testing system based on a multi-source monitoring technology, and to acquire a physical data set and an image data set through the SC-CO2 hydrate phase state data testing system;

[0030] A division module, configured to divide the physical dataset and the image dataset into a training dataset and a test dataset;

[0031] an optimization module for constructing a SC-CO2 hydrate phase state data prediction generation model, and training and optimizing the SC-CO2 hydrate phase state data prediction generation model using the training data set and the test data set to obtain an optimal generalization model;

[0032] The generation module is used to obtain data to be analyzed under different environmental conditions, predict the data to be analyzed using the optimal generalization model to obtain prediction results, and generate an SC-CO2 hydrate phase diagram based on the prediction results.

[0033] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for generating a supercritical carbon dioxide hydrate phase diagram as described in the first aspect above is implemented.

[0034] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating a supercritical carbon dioxide hydrate phase diagram as described in the first aspect above.

[0035] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method for generating a supercritical carbon dioxide hydrate phase diagram as described in the first aspect above.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The supercritical carbon dioxide hydrate phase diagram generation method provided by the present invention constructs an adaptive single-layer-double-layer SC-CO2 hydrate phase state short-term memory network (ASD-SC-CO2PS-LSTM), namely, a SC-CO2 hydrate phase state data prediction and generation model. Training and test data are used as inputs to the SC-CO2 hydrate phase state data prediction and generation model, which is trained and optimized to obtain an optimal generalization model. The trained optimal generalization model can directly extract critical data for SC-CO2 hydrate phase state evolution. Using the optimal generalization model to predict the data to be analyzed can improve the accuracy and efficiency of the prediction results. Based on this, the SC-CO2 hydrate phase diagram is generated based on the prediction results.

[0038] In addition, the present invention overcomes the deficiency that the phase evolution of SC-CO2 hydrate cannot be directly observed, and realizes the visualization experiment of the phase evolution of SC-CO2 hydrate, thereby reducing the economic cost of the SC-CO2 hydrate phase evolution observation experiment, and the SC-CO2 hydrate phase diagram can be obtained using a small amount of experimental data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is a flow chart of the method for generating a supercritical carbon dioxide hydrate phase diagram provided by the present invention;

[0041] Figure 2 Schematic diagram of the SC-CO2 hydrate phase data testing system in an embodiment of the present invention;

[0042] Figure 3is a schematic diagram of a topology-controlled imaging system according to an embodiment of the present invention;

[0043] Figure 4 4 is a calculation flow chart of the SC-CO2 hydrate phase data prediction generation model in an embodiment of the present invention;

[0044] Figure 5 2 is a schematic diagram comparing experimental predicted values and true values in an embodiment of the present invention;

[0045] Figure 6 Schematic diagram of the SC-CO2 hydrate phase diagram constructed in an embodiment of the present invention;

[0046] Figure 7 This is a structural block diagram of the supercritical carbon dioxide hydrate phase diagram generating device provided by the present invention;

[0047] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention.

[0048] Reference numerals:

[0049] 1: Gas cylinder; 2: Fluid flow direction; 3: High-pressure plunger pump; 4: Corrosion-resistant container; 5: CNC constant temperature water tank; 6: Corrosion-resistant catheter; 7: Quick-closing valve; 8: Deionized water bottle; 9: Magnetic pole system cabin; 10: Data wire; 11: Magnet; 12: Wavelet signal amplifier; 13: Column; 14: Image conversion generator; 15: Nuclear magnetic radio frequency generator; 16: Data control processing module; 17: Pressure controller; 18: Base; 19: Fastening bolts; 20: Mounting rail; 21: Outer compartment plate; 22: Loading compartment; 23: Injection port; 24: Temperature sensor; 25: Heating assembly; 26: Block detection plate; 27: X-ray probe; 28: Inner compartment plate; 29: Porous medium; 30: Fixing bolts. DETAILED DESCRIPTION

[0050] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0051] The present invention provides a method for generating a supercritical carbon dioxide hydrate phase diagram. Figure 1 This is a flow chart of the method for generating a supercritical carbon dioxide hydrate phase diagram provided by the present invention, such as Figure 1 As shown, the method includes the following steps:

[0052] Step S101: establishing an SC-CO2 hydrate phase state data testing system based on multi-source monitoring technology, and acquiring a physical data set and an image data set through the SC-CO2 hydrate phase state data testing system;

[0053] Step S102, dividing the physical dataset and the image dataset into a training dataset and a test dataset;

[0054] Step S103: constructing a SC-CO2 hydrate phase state data prediction generation model, and training and optimizing the SC-CO2 hydrate phase state data prediction generation model using a training data set and a test data set to obtain an optimal generalization model;

[0055] Step S104: acquiring data to be analyzed under different environmental conditions, predicting the data to be analyzed using the optimal generalization model to obtain prediction results, and generating an SC-CO2 hydrate phase diagram based on the prediction results.

[0056] The following describes the phase evolution of SC-CO2 hydrate at an SC-CO2:water ratio of 8:2. This method first establishes an SC-CO2 hydrate phase data testing system based on multi-source monitoring technology. This system acquires physical data sets, such as temperature and pressure, as well as image data. These data sets are then divided into training and test data sets. An adaptive single-layer-double-layer SC-CO2 hydrate phase state short-term memory network (ASD-SC-CO2PS-LSTM), or SC-CO2 hydrate phase state data prediction and generation model, is then constructed. The training and test data are used as inputs to the SC-CO2 hydrate phase state data prediction and generation model, which is then trained and optimized to obtain an optimal generalization model. This optimal generalization model can directly extract critical data for SC-CO2 hydrate phase evolution. Using this optimal generalization model for prediction of the data under analysis improves both the accuracy and efficiency of the prediction results. On this basis, the SC-CO2 hydrate phase diagram is generated according to the prediction results.

[0057] Figure 2 FIG. 1 is a schematic diagram of a SC-CO2 hydrate phase data testing system in an embodiment of the present invention. Figure 2 As shown, in some embodiments, the SC-CO2 hydrate phase data testing system includes a SC-CO2 control generation system, a topology control imaging system and a nuclear magnetic resonance control imaging system; the SC-CO2 hydrate phase data testing system is connected to the data control processing module 16.

[0058] Specifically, the SC-CO2 control generation system includes a gas cylinder 1, the gas outlet end of the gas cylinder 1 is connected to a high-pressure plunger pump 3, the output end of the high-pressure plunger pump 3 is connected to a CNC constant temperature water tank 5, a corrosion-resistant container 4 is provided on the outside of the CNC constant temperature water tank 5, the output end of the CNC constant temperature water tank 5 is connected to a deionized water bottle 8 through a corrosion-resistant conduit 6, a quick-closing valve 7 is provided on the corrosion-resistant conduit 6, and the output end of the deionized water bottle 8 is connected to the topology control imaging module.

[0059] Furthermore, the corrosion-resistant container 4 and the corrosion-resistant conduit 6 are made of super martensitic stainless steel HP2-13Cr to prevent the corrosion container from leaking during the SC-CO2 injection process, resulting in the pressure being unable to reach the level required to generate SC-CO2 hydrate.

[0060] Figure 3 is a schematic diagram of a topology controlled imaging system according to an embodiment of the present invention. Figure 3 As shown, the topological control imaging system includes a base 18, on which a mounting rail 20 is fixed by fastening bolts 19, and on which a plurality of corresponding X-ray probes 27 and block detection plates 26 are arranged. The X-ray probes 27 and the block detection plates 26 are connected to the data control processing module 16 via data wires 10.

[0061] The mounting track 20 consists of two semicircular, multi-layered grooves. The X-ray probe 27 and segmented detection plates 26 are controlled by the data control processing module 16 within each groove, allowing for the appropriate positioning of the SC-CO2 phase evolution image. Furthermore, the segmented detection plates 26 are curved, and each segmented detection plate 26 has its own switch to ensure SC-CO2 phase evolution imaging at varying resolutions.

[0062] The nuclear magnetic resonance controlled imaging system includes a magnetic pole system cabin 9, on which a magnet 11 is provided; the nuclear magnetic resonance controlled imaging system also includes a wavelet signal amplifier 12, an image conversion generator 14 and a nuclear magnetic radio frequency source generator 15, and the nuclear magnetic radio frequency source generator 15, the magnet 11, the wavelet signal amplifier 12, the image conversion generator 14 and the data control processing module 16 are connected in sequence to form a closed loop.

[0063] The nuclear magnetic resonance controlled imaging system also includes a loading chamber 22 and a porous medium 29, which is arranged inside the loading chamber 22; the loading chamber 22 includes an outer chamber plate 21 and an inner chamber plate 28, both of which are transparent; a number of temperature sensors 24 and a heating component 25 are arranged between the outer chamber plate 21 and the inner chamber plate 28; the nuclear magnetic resonance controlled imaging system also includes a pressure controller 17, which is connected to the temperature sensor 24, the heating component 25 and the data control processing module 16.

[0064] Furthermore, the outer chamber plate 21 is made of aluminum oxynitride material, which has an average transmittance of about 80%, a bending strength of 300MPa-400MPa, and a high temperature resistance of up to 2200°C, to ensure smooth imaging during the experiment and not damage the nuclear magnetic resonance imaging system equipment. The inner chamber plate 28 is made of graphene transparent glass material, which has an average transmittance of about 80%, a strength dozens of times greater than that of steel, and a thermal conductivity of up to 5300W / (mK), to ensure smooth imaging and rapid temperature control during the experiment. The loading chamber 22 adopts an inner hollow ring structure design, and the temperature sensor 24 and the multi-layer arc-shaped heating component 25 are located between the outer chamber plate 21 and the inner chamber plate 28 to accurately control and quickly control temperature and pressure changes.

[0065] Through the above system, the deficiency of being unable to directly observe the phase evolution of SC-CO2 hydrate has been overcome, and a visualization experiment of the phase evolution of SC-CO2 hydrate has been realized, thereby reducing the economic cost of the SC-CO2 hydrate phase evolution observation experiment, and the SC-CO2 hydrate phase diagram can be obtained with a small amount of experimental data.

[0066] In some embodiments, step S103, training and optimizing the SC-CO2 hydrate phase data prediction generation model using a training data set and a test data set to obtain an optimal generalization model, includes: training and fine-tuning the SC-CO2 hydrate phase data prediction generation model using the training data set; inputting the test data set into the SC-CO2 hydrate phase data prediction generation model to obtain a predicted value; determining a relative error of the SC-CO2 hydrate phase data prediction generation model based on the predicted value and the true value, and determining the optimal generalization model based on the relative error.

[0067] In this embodiment, the division of the training data set and the test data set can be performed according to a preset ratio. For example, 30% of the obtained physical data set and image data set is used as the training data set to train the SC-CO2 hydrate phase state data prediction generation model. The remaining 70% of the physical data set and image data set is used as the test data set to optimize the SC-CO2 hydrate phase state data prediction generation model. When the relative error between its predicted value and the true value obtained by the experiment reaches 0.95, the currently optimized phase diagram generation model is established as the best generalization model, such as Figure 4 As shown, Figure 4 : is a calculation flow chart of the SC-CO2 hydrate phase data prediction generation model in an embodiment of the present invention, and the analytical expression of the relative error is as follows:

[0068]

[0069] in, V prediction represents the predicted value,V ture If the relative error is less than 0.95, the physical and image datasets are re-acquired and the SC-CO2 hydrate phase data prediction model is trained and optimized until the optimal generalization model is obtained.

[0070] Based on the above embodiment, step S104, obtaining data to be analyzed under different environmental conditions, predicting the data to be analyzed by using the optimal generalization model to obtain prediction results, and generating an SC-CO2 hydrate phase diagram based on the prediction results, includes: inputting the data to be analyzed into the optimal generalization model, predicting the data to be analyzed by using the optimal generalization model to obtain critical temperature and critical pressure data of the phase evolution of SC-CO2 hydrate; and generating the SC-CO2 hydrate phase diagram based on the critical temperature and critical pressure data.

[0071] For example, the optimal generalized model is used to predict the critical temperature and adjacent pressure data of the phase evolution of SC-CO2 hydrate, and the SC-CO2 hydrate phase diagram is constructed, such as Figure 5-6 As shown, Figure 5 : is a schematic diagram comparing the experimental predicted value and the true value in an embodiment of the present invention, Figure 6 Schematic diagram of the SC-CO2 hydrate phase diagram constructed in an embodiment of the present invention.

[0072] In the above embodiment, the expression of the constructed SC-CO2 hydrate phase data prediction generation model is as follows:

[0073]

[0074] in, Indicates the selection gate, represents the forget gate, represents the input gate, Indicates candidate status, represents the sigmoid function, represents the weight of image input data, represents the physical input data weight, represents element-wise multiplication, represents element addition, W ASD represents the selection gate weight matrix, W forget represents the forget gate weight matrix, W input represents the input gate weight matrix, W CS represents the candidate state of the weight matrix, b ASD represents the selection gate bias vector, b forgetrepresents the forget gate bias vector, b input represents the input gate bias vector, b CS represents the candidate state of the bias vector, H t-1 represents the hidden state at time t-1, X t Represents the current input at time t, tanh represents the hyperbolic tangent function, and its value ranges from -1 to 1.

[0075] The unit update, hidden state update and output calculation process of the SC-CO2 hydrate phase data prediction generation model can be expressed as:

[0076]

[0077] in, Indicates the unit status, represents the output gate, b output Represents the output gate bias vector.

[0078] In addition, when constructing the SC-CO2 hydrate phase diagram through the SC-CO2 hydrate phase state data prediction generation model, software such as Excel, Origin and MATLAB can be used to draw the SC-CO2 hydrate phase diagram.

[0079] The present invention also provides a supercritical carbon dioxide hydrate phase diagram generating device. The supercritical carbon dioxide hydrate phase diagram generating device provided by the present invention is described below. The supercritical carbon dioxide hydrate phase diagram generating device described below and the supercritical carbon dioxide hydrate phase diagram generating method described above can be referenced to each other. Figure 7 This is a structural block diagram of the supercritical carbon dioxide hydrate phase diagram generating device provided by the present invention, such as Figure 7 As shown, the device includes:

[0080] An acquisition module 701 is used to establish an SC-CO2 hydrate phase state data testing system based on a multi-source monitoring technology, and to acquire a physical data set and an image data set through the SC-CO2 hydrate phase state data testing system;

[0081] A division module 702 is used to divide the physical data set and the image data set into a training data set and a test data set;

[0082] The optimization module 703 is used to construct a SC-CO2 hydrate phase state data prediction generation model, and train and optimize the SC-CO2 hydrate phase state data prediction generation model using a training data set and a test data set to obtain an optimal generalization model;

[0083] The generation module 704 is used to obtain the data to be analyzed under different environmental conditions, predict the data to be analyzed using the optimal generalization model to obtain prediction results, and generate the SC-CO2 hydrate phase diagram based on the prediction results.

[0084] When using this device, the acquisition module 701 first establishes an SC-CO2 hydrate phase state data testing system based on multi-source monitoring technology. This system acquires physical data sets such as temperature and pressure, as well as an image data set. The partitioning module 702 then divides the acquired physical and image data sets into a training data set and a test data set. The optimization module 703 then constructs an adaptive single-layer-double-layer SC-CO2 hydrate phase state short-term memory network (ASD-SC-CO2PS-LSTM), i.e., a SC-CO2 hydrate phase state data prediction and generation model. The training and test data are used as inputs to the SC-CO2 hydrate phase state data prediction and generation model, which is trained and optimized to obtain an optimal generalization model. The optimal generalization model trained by the generation module 704 can directly extract critical data for SC-CO2 hydrate phase state evolution. Using this optimal generalization model to predict the data to be analyzed can improve the accuracy and efficiency of the prediction results. Based on this, an SC-CO2 hydrate phase diagram is generated based on the prediction results.

[0085] Figure 8 An example of a physical structure diagram of an electronic device is shown below. Figure 8 As shown, the electronic device may include: a processor 801, a communication interface 802, a memory 803, and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other via the communication bus 804. The processor 801 may call the logic instructions in the memory 803 to execute the supercritical carbon dioxide hydrate phase diagram generation method, which includes:

[0086] Establish an SC-CO2 hydrate phase data testing system based on multi-source monitoring technology, and obtain physical and image data sets through the SC-CO2 hydrate phase data testing system;

[0087] Divide the physical dataset and image dataset into training dataset and test dataset;

[0088] A prediction model for SC-CO2 hydrate phase data was constructed and trained and optimized using training and test datasets to obtain the optimal generalization model.

[0089] The data to be analyzed under different environmental conditions are obtained, and the data to be analyzed are predicted using the optimal generalization model to obtain the prediction results, and the SC-CO2 hydrate phase diagram is generated based on the prediction results.

[0090] Furthermore, the logic instructions in the aforementioned memory 803 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0091] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the supercritical carbon dioxide hydrate phase diagram generation method provided by the above methods, which includes:

[0092] Establish an SC-CO2 hydrate phase data testing system based on multi-source monitoring technology, and obtain physical and image data sets through the SC-CO2 hydrate phase data testing system;

[0093] Divide the physical dataset and image dataset into training dataset and test dataset;

[0094] A prediction model for SC-CO2 hydrate phase data was constructed and trained and optimized using training and test datasets to obtain the optimal generalization model.

[0095] The data to be analyzed under different environmental conditions are obtained, and the data to be analyzed are predicted using the optimal generalization model to obtain the prediction results, and the SC-CO2 hydrate phase diagram is generated based on the prediction results.

[0096] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the method for generating a supercritical carbon dioxide hydrate phase diagram provided by the above methods, the method comprising:

[0097] Establish an SC-CO2 hydrate phase data testing system based on multi-source monitoring technology, and obtain physical and image data sets through the SC-CO2 hydrate phase data testing system;

[0098] Divide the physical dataset and image dataset into training dataset and test dataset;

[0099] A prediction model for SC-CO2 hydrate phase data was constructed and trained and optimized using training and test datasets to obtain the optimal generalization model.

[0100] The data to be analyzed under different environmental conditions are obtained, and the data to be analyzed are predicted using the optimal generalization model to obtain the prediction results, and the SC-CO2 hydrate phase diagram is generated based on the prediction results.

[0101] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0102] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods of each embodiment or certain portions of the embodiments.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for generating a supercritical carbon dioxide hydrate phase diagram, characterized in that: include: Establishing an SC-CO2 hydrate phase state data testing system based on multi-source monitoring technology, and acquiring physical data sets and image data sets through the SC-CO2 hydrate phase state data testing system; Dividing the physical dataset and the image dataset into a training dataset and a test dataset; Constructing a SC-CO2 hydrate phase state data prediction generation model, and training and optimizing the SC-CO2 hydrate phase state data prediction generation model using the training data set and the test data set to obtain an optimal generalization model; Acquiring data to be analyzed under different environmental conditions, predicting the data to be analyzed using the optimal generalization model to obtain prediction results, and generating an SC-CO2 hydrate phase diagram based on the prediction results; The SC-CO2 hydrate phase state data testing system comprises an SC-CO2 control generation system, a topology control imaging system and a nuclear magnetic resonance control imaging system; the SC-CO2 hydrate phase state data testing system is connected to a data control processing module (16).

2. The method for generating a supercritical carbon dioxide hydrate phase diagram according to claim 1, wherein: The SC-CO2 control generation system comprises a gas cylinder (1), the gas outlet end of the gas cylinder (1) is connected to a high-pressure plunger pump (3), the output end of the high-pressure plunger pump (3) is connected to a numerically controlled constant-temperature water tank (5), a corrosion-resistant container (4) is provided on the outside of the numerically controlled constant-temperature water tank (5), the output end of the numerically controlled constant-temperature water tank (5) is connected to a deionized water bottle (8) via a corrosion-resistant conduit (6), a quick-closing valve (7) is provided on the corrosion-resistant conduit (6), and the output end of the deionized water bottle (8) is connected to a topological control imaging module.

3. The method for generating a supercritical carbon dioxide hydrate phase diagram according to claim 1, wherein: The topological control imaging system includes a support platform (18), a mounting rail (20) is fixedly provided on the support platform (18) by fastening bolts (19), a plurality of mutually corresponding X-ray probes (27) and block detection plates (26) are provided on the mounting rail (20), and the X-ray probes (27) and the block detection plates (26) are connected to the data control processing module (16) via data wires (10).

4. The method for generating a supercritical carbon dioxide hydrate phase diagram according to claim 3, wherein: The mounting track (20) is composed of two semicircular multi-layer grooves, and the X-ray probe (27) and the segmented detection plate (26) are freely movable in each layer of the grooves under the control of the data control processing module (16).

5. The method for generating a supercritical carbon dioxide hydrate phase diagram according to claim 1, wherein: The nuclear magnetic resonance controlled imaging system comprises a magnetic pole system cabin (9), and a magnet (11) is provided on the magnetic pole system cabin (9); the nuclear magnetic resonance controlled imaging system also comprises a wavelet signal amplifier (12), an image conversion generator (14) and a nuclear magnetic radio frequency source generator (15), and the nuclear magnetic radio frequency source generator (15), the magnet (11), the wavelet signal amplifier (12), the image conversion generator (14) and the data control processing module (16) are sequentially connected to form a closed loop; The nuclear magnetic resonance controlled imaging system further comprises a loading chamber (22) and a porous medium (29), wherein the porous medium (29) is arranged inside the loading chamber (22); the loading chamber (22) comprises an outer chamber plate (21) and an inner chamber plate (28), wherein both the outer chamber plate (21) and the inner chamber plate (28) are transparent; a plurality of temperature sensors (24) and a heating assembly (25) are arranged between the outer chamber plate (21) and the inner chamber plate (28); the nuclear magnetic resonance controlled imaging system further comprises a pressure controller (17), wherein the pressure controller (17) is connected to the temperature sensor (24), the heating assembly (25) and the data control processing module (16).

6. The method for generating a supercritical carbon dioxide hydrate phase diagram according to claim 1, wherein: The SC-CO2 hydrate phase state data prediction generation model is trained and optimized using the training data set and the test data set to obtain an optimal generalization model, including: Training and fine-tuning the SC-CO2 hydrate phase data prediction generation model using the training data set; Inputting the test data set into the SC-CO2 hydrate phase state data prediction generation model to obtain a predicted value; The relative error of the SC-CO2 hydrate phase state data prediction generation model is determined according to the predicted value and the true value, and the optimal generalization model is determined according to the relative error.

7. The method for generating a supercritical carbon dioxide hydrate phase diagram according to claim 1, wherein: Acquiring data to be analyzed under different environmental conditions, predicting the data to be analyzed using the optimal generalization model to obtain prediction results, and generating an SC-CO2 hydrate phase diagram based on the prediction results, including: Inputting the data to be analyzed into the optimal generalization model, predicting the data to be analyzed using the optimal generalization model, and obtaining critical temperature and critical pressure data of the phase evolution of SC-CO2 hydrate; The SC-CO2 hydrate phase diagram is generated according to the critical temperature and the critical pressure data.

8. A supercritical carbon dioxide hydrate phase diagram generating device, characterized in that: include: an acquisition module, configured to establish an SC-CO2 hydrate phase state data testing system based on a multi-source monitoring technology, and to acquire a physical data set and an image data set through the SC-CO2 hydrate phase state data testing system; A division module, configured to divide the physical dataset and the image dataset into a training dataset and a test dataset; an optimization module for constructing a SC-CO2 hydrate phase state data prediction generation model, and training and optimizing the SC-CO2 hydrate phase state data prediction generation model using the training data set and the test data set to obtain an optimal generalization model; A generation module is used to obtain data to be analyzed under different environmental conditions, predict the data to be analyzed using the optimal generalization model to obtain prediction results, and generate an SC-CO2 hydrate phase diagram based on the prediction results; The SC-CO2 hydrate phase state data testing system comprises an SC-CO2 control generation system, a topology control imaging system and a nuclear magnetic resonance control imaging system; the SC-CO2 hydrate phase state data testing system is connected to a data control processing module (16).

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the supercritical carbon dioxide hydrate phase diagram generating method according to any one of claims 1 to 7 is implemented.

Images