Method and apparatus for determining the effective CO2 storage in oil reservoirs
By constructing an effective burial map and using machine learning models, combined with component numerical simulation and phase simulation software, the problem of speed and accuracy in determining CO2 burial in reservoirs in existing technologies has been solved, achieving rapid and accurate burial assessment.
Patent Information
- Application Number
- CN202410308081.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-18
- Publication Date
- 2026-02-24
- Estimated Expiration
- 2044-03-18
AI Technical Summary
Existing technologies make it difficult to quickly and accurately determine the effective CO2 reserves in reservoirs, especially due to errors and computational complexity caused by over-reliance on empirical values or cumbersome numerical simulation methods.
By acquiring basic data of reservoir blocks, multiple effective storage maps are constructed. Machine learning models are used to predict the effective storage coefficient. Combined with component numerical simulation models and phase simulation software, the effective storage amount of CO2 is quickly and accurately determined.
It enables rapid and accurate determination of the effective CO2 reserves in oil reservoirs, reduces calculation errors, and improves assessment efficiency.
Smart Images
Figure CN118364703B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of petroleum development technology, and specifically to a method, apparatus and storage medium for determining the effective CO2 reserves in an oil reservoir. Background Technology
[0002] Currently, the effective CO2 storage capacity in an oil reservoir can be directly determined by analogy or numerical simulation. Alternatively, the effective CO2 storage coefficient can be determined by empirical and numerical simulation methods, and then the effective CO2 storage capacity in the reservoir can be determined based on the effective CO2 storage coefficient.
[0003] In existing technologies, determining the effective CO2 storage coefficient in reservoirs using empirical methods relies excessively on empirical values, resulting in significant errors in the determined effective storage coefficient and consequently inaccurate determinations of the effective storage volume. Similarly, determining the effective CO2 storage coefficient through numerical simulation is overly cumbersome, making it difficult to reliably and quickly assess the effective CO2 storage coefficient, which also leads to inaccurate determinations of the effective storage volume.
[0004] If the effective CO2 storage capacity is determined by analogy, i.e., based on empirical data on CO2 storage, the effectiveness varies significantly across different reservoir types. Currently, pilot CO2 storage experiments are conducted on a relatively limited range of reservoir types, making it difficult to accurately determine the effective CO2 storage capacity using analogy methods due to the limited availability of relevant parameters. Similarly, determining the effective CO2 storage capacity through numerical simulation, i.e., by calculating the difference between injected CO2 and CO2 produced, is also problematic because numerical simulations rely on numerous reservoir parameters, resulting in complex and computationally intensive calculations that hinder rapid determination of the effective CO2 storage capacity. Summary of the Invention
[0005] The purpose of this application is to provide a method, apparatus and storage medium for determining the effective CO2 storage in an oil reservoir, so as to solve the problem that it is difficult to quickly and accurately determine the effective CO2 storage in an oil reservoir in the prior art.
[0006] To achieve the above objectives, the first aspect of this application provides a method for determining the effective CO2 storage capacity in an oil reservoir, comprising:
[0007] Obtain basic reservoir data, current burial pressure, current reservoir temperature, and current reservoir permeability for the reservoir block to be evaluated;
[0008] The theoretical CO2 reserves in the reservoir block to be evaluated are determined based on the reservoir basic data.
[0009] Construct multiple effective burial plots for the reservoir block to be evaluated. Each effective burial plot includes a predicted effective burial coefficient corresponding to the preset reservoir permeability and preset reservoir temperature under the preset burial pressure.
[0010] The current effective CO2 burial coefficient in the reservoir block to be evaluated is determined based on multiple effective burial charts, current burial pressure, current reservoir temperature, and current reservoir permeability.
[0011] The current effective CO2 reserves in the reservoir block to be evaluated are determined based on the theoretical reserves and the current effective reserves coefficient.
[0012] In this embodiment of the application, determining the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on multiple effective burial maps, current burial pressure, current reservoir temperature, and current reservoir permeability includes: selecting effective burial maps under the current burial pressure from multiple effective burial maps as maps to be searched; traversing the maps to be searched to obtain a preset reservoir temperature that matches the current reservoir temperature and a preset reservoir permeability that matches the current reservoir permeability; and determining the predicted effective burial coefficient corresponding to the matched preset reservoir temperature and preset reservoir permeability as the current effective burial coefficient.
[0013] In this embodiment of the application, constructing multiple effective burial plots for the reservoir block to be evaluated includes: constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the effective burial coefficient prediction model to obtain the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; and constructing multiple effective burial plots based on the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure.
[0014] In this embodiment, constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure includes: constructing a component numerical simulation model of the reservoir block to be evaluated; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the component numerical simulation model to obtain the simulated effective burial amount of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; determining the simulated effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure based on the theoretical burial amount and the simulated effective burial amount; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into different machine learning models so that different machine learning models output simulated effective burial coefficients corresponding to different preset permeability, preset reservoir temperature, and preset burial pressure, thereby training different machine learning models; and selecting the machine learning model that meets the preset conditions from the trained machine learning models as the effective burial coefficient prediction model after the different machine learning models have been trained.
[0015] In this embodiment of the application, constructing a component numerical simulation model of the reservoir block to be evaluated includes: acquiring geological modeling data of the reservoir block to be evaluated, and constructing a geological model of the reservoir block to be evaluated based on the geological modeling data; acquiring fluid data of reservoir fluids in the reservoir block to be evaluated, the solubility coefficient of CO2 in oil and water in the reservoir block to be evaluated, and the diffusion coefficient in the reservoir core; acquiring historical production data of the reservoir block to be evaluated; and constructing a component numerical simulation model based on the geological model and according to the fluid data, solubility coefficient, diffusion coefficient, and historical production data of the reservoir.
[0016] In the embodiments of this application, the machine learning models include linear regression models, support vector machines, tree ensembles, Gaussian process regression models, neural networks, and regression trees.
[0017] In this embodiment of the application, the current effective buried amount is determined by formula (1):
[0018] Formula (1)
[0019] in, This refers to the current effective CO2 reserves in the reservoir block to be evaluated. It refers to the current effective CO2 burial coefficient in the reservoir block to be evaluated. This refers to the theoretical CO2 reserves in the reservoir block to be evaluated.
[0020] In this embodiment of the application, the theoretical burial quantity is determined by formula (2):
[0021]
[0022] Formula (2)
[0023] in, This refers to the theoretical CO2 reserves in the reservoir block to be evaluated. This refers to the density of CO2 in the reservoir block to be evaluated under reservoir conditions, expressed in kg / m³. 3 , The recovery rate of crude oil in the reservoir block to be evaluated before CO2 injection breakthrough is expressed in f. The oil recovery rate is the crude oil recovery rate after injecting a predetermined volume of CO2 into the reservoir block to be evaluated, expressed in units of f. A represents the reservoir area of the reservoir block to be evaluated, expressed in units of... h represents the reservoir thickness of the block to be evaluated, in meters (m). The reservoir porosity of the oil-bearing block to be evaluated is expressed in f. The bound water saturation of the reservoir block to be evaluated is expressed in f. This refers to the injected water volume of the reservoir block to be evaluated, in units of... , The water production of the reservoir block to be evaluated is expressed in units of... , The solubility coefficient of CO2 in water in the reservoir block to be evaluated is expressed in f. The value represents the solubility coefficient of CO2 in the oil in the reservoir block to be evaluated, expressed in units of f.
[0024] A second aspect of this application provides an apparatus for determining the effective CO2 storage capacity in an oil reservoir, comprising:
[0025] The memory is configured to store instructions; and
[0026] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned method for determining the effective CO2 reserves in an oil reservoir.
[0027] A third aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned method for determining the effective CO2 content in an oil reservoir.
[0028] The above technical solution obtains the reservoir basic data, current burial pressure, current reservoir temperature, and current reservoir permeability of the reservoir block to be evaluated; determines the theoretical CO2 burial amount in the reservoir block to be evaluated based on the reservoir basic data; constructs multiple effective burial maps for the reservoir block to be evaluated, each effective burial map including a predicted effective burial coefficient corresponding to a preset burial pressure, preset reservoir permeability, and preset reservoir temperature; determines the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on multiple effective burial maps, current burial pressure, current reservoir temperature, and current reservoir permeability; and determines the current effective burial amount of CO2 in the reservoir block to be evaluated based on the theoretical burial amount and the current effective burial coefficient. This method can quickly and more accurately determine the effective burial amount of CO2 in the reservoir.
[0029] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description
[0030] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:
[0031] Figure 1 The schematic diagram illustrates a process flow diagram of a method for determining the effective CO2 storage capacity in an oil reservoir according to an embodiment of this application;
[0032] Figure 2 The schematic diagram illustrates a process flow diagram of a method for determining the effective CO2 storage capacity in an oil reservoir according to another embodiment of this application;
[0033] Figure 3 The illustration shows a schematic diagram of the training and optimization process of the agent model according to an embodiment of this application;
[0034] Figure 4a The diagram illustrates an effective burial factor chart of a reservoir at a burial pressure of 14 MPa according to an embodiment of this application.
[0035] Figure 4b The illustration shows a schematic diagram of the effective burial coefficient of a reservoir under a burial pressure of 15 MPa according to an embodiment of this application.
[0036] Figure 4c The diagram illustrates an effective burial factor chart of a reservoir at a burial pressure of 16 MPa according to an embodiment of this application.
[0037] Figure 4dThe diagram illustrates an effective burial factor chart of a reservoir at a burial pressure of 17 MPa according to an embodiment of this application.
[0038] Figure 5 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation
[0039] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0040] It should be noted that if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.
[0041] Figure 1 The illustration schematically shows a flow chart of a method for determining the effective CO2 storage capacity in an oil reservoir according to an embodiment of this application. Figure 1 As shown in one embodiment of this application, a method for determining the effective CO2 storage capacity in an oil reservoir is provided, comprising the following steps:
[0042] Step 101: Obtain the reservoir basic data, current burial pressure, current reservoir temperature, and current reservoir permeability of the reservoir block to be evaluated.
[0043] When determining the effective CO2 storage capacity in a reservoir block to be evaluated, the processor can acquire the reservoir basic data, current storage pressure, current reservoir temperature, and current reservoir permeability of the reservoir block to be evaluated. The reservoir block to be evaluated refers to the reservoir block for which CO2 storage potential is to be assessed. The reservoir basic data includes the CO2 density under reservoir conditions in the reservoir block to be evaluated, the oil recovery rate before CO2 injection breakthrough in the reservoir block to be evaluated, the oil recovery rate after CO2 injection in the reservoir block to be evaluated, the reservoir area, reservoir thickness, reservoir porosity, bound water saturation, injected water volume, produced water volume, CO2 solubility coefficient in water, and CO2 solubility coefficient in oil in the reservoir block to be evaluated.
[0044] Step 102: Determine the theoretical CO2 reserves in the reservoir block to be evaluated based on the reservoir basic data.
[0045] The processor can determine the theoretical CO2 reserves in the reservoir block to be evaluated based on reservoir baseline data. In this embodiment, the theoretical reserves are determined by formula (2):
[0046]
[0047] Formula (2)
[0048] in, This refers to the theoretical CO2 reserves in the reservoir block to be evaluated. This refers to the density of CO2 in the reservoir block to be evaluated under reservoir conditions, expressed in kg / m³. 3 , The recovery rate of crude oil in the reservoir block to be evaluated before CO2 injection breakthrough is expressed in f. The recovery rate of crude oil after injecting a preset volume of CO2 into the reservoir block to be evaluated is expressed in units of f. The preset volume can be customized according to requirements. A represents the reservoir area of the reservoir block to be evaluated, expressed in units of... h represents the reservoir thickness of the block to be evaluated, in meters (m). The reservoir porosity of the oil-bearing block to be evaluated is expressed in f. The bound water saturation of the reservoir block to be evaluated is expressed in f. This refers to the injected water volume of the reservoir block to be evaluated, in units of... , The water production of the reservoir block to be evaluated is expressed in units of... , The solubility coefficient of CO2 in water in the reservoir block to be evaluated is expressed in f. The value represents the solubility coefficient of CO2 in the oil in the reservoir block to be evaluated, expressed in units of f.
[0049] Step 103: Construct multiple effective burial plots for the reservoir block to be evaluated. Each effective burial plot includes a predicted effective burial coefficient corresponding to the preset reservoir permeability and preset reservoir temperature under the preset burial pressure.
[0050] The processor can construct multiple effective burial maps for the reservoir block to be evaluated. Each effective burial map includes a predicted effective burial coefficient corresponding to a preset burial pressure, preset reservoir permeability, and preset reservoir temperature. That is, any two effective burial maps correspond to different preset burial pressures, and each can include the predicted effective burial coefficient corresponding to the preset reservoir permeability and preset reservoir temperature at the corresponding preset burial pressure. Here, the preset burial pressure refers to the preset upper limit pressure of burial.
[0051] In this embodiment of the application, constructing multiple effective burial plots for the reservoir block to be evaluated includes: constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the effective burial coefficient prediction model to obtain the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; and constructing multiple effective burial plots based on the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure.
[0052] When constructing multiple effective burial plots for the reservoir block to be evaluated, the processor can obtain different preset permeability, preset reservoir temperature and preset burial pressure, and can construct an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature and preset burial pressure.
[0053] In this embodiment, constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure includes: constructing a component numerical simulation model of the reservoir block to be evaluated; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the component numerical simulation model to obtain the simulated effective burial amount of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; determining the simulated effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure based on the theoretical burial amount and the simulated effective burial amount; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into different machine learning models so that different machine learning models output simulated effective burial coefficients corresponding to different preset permeability, preset reservoir temperature, and preset burial pressure, thereby training different machine learning models; and selecting the machine learning model that meets the preset conditions from the trained machine learning models as the effective burial coefficient prediction model after the different machine learning models have been trained.
[0054] The processor can construct a component numerical simulation model of the reservoir block to be evaluated. In this embodiment, constructing the component numerical simulation model of the reservoir block to be evaluated includes: acquiring geological modeling data of the reservoir block to be evaluated, and constructing a geological model of the reservoir block to be evaluated based on the geological modeling data; acquiring historical fluid data of the reservoir fluids of the reservoir block to be evaluated, the solubility coefficient of CO2 in oil and water of the reservoir block to be evaluated, and the diffusion coefficient in the reservoir core; acquiring historical production data of the reservoir block to be evaluated; and constructing a component numerical simulation model based on the geological model and the fluid data, solubility coefficient, diffusion coefficient, and historical production data of the reservoir.
[0055] The processor can acquire geological modeling data for the reservoir block to be evaluated. This geological modeling data may include well location coordinates, core elevation, well trajectory data, stratigraphic data, structural interpretation data, and logging data for the reservoir block. The processor can construct a geological model of the reservoir block to be evaluated based on this geological modeling data. Specifically, geological modeling can be performed using geological modeling software and the geological modeling data of the reservoir block to be evaluated to obtain a geological model of the reservoir block to be evaluated. This geological model accurately reflects the reservoir structure and properties.
[0056] The processor can acquire fluid data of reservoir fluids in the reservoir block to be evaluated, the solubility coefficient of CO2 in oil and water, and the diffusion coefficient in the reservoir core. The fluid data refers to reservoir fluid PVT data or fluid laboratory experimental data, which may include CO2 injection expansion experiment data, isocomposition expansion experiment data, and flash evaporation experiment data. The processor can also acquire historical production data of the reservoir block to be evaluated. This historical production data may include reservoir pressure variation data, reservoir relative permeability curve data, oilfield well history data, and oil, gas, and water production data.
[0057] The processor can construct a component numerical simulation model based on a geological model and using fluid data, solubility coefficients, diffusion coefficients, and historical reservoir production data. Specifically, phase simulation software can be used to fit the fluid data to obtain the state equation parameters for the actual reservoir fluid properties. Then, reservoir numerical simulation software is used to construct a component numerical simulation model based on the geological model, combining the state equation parameters, solubility coefficients, diffusion coefficients, and historical reservoir production data. This component numerical simulation model can be used to simulate CO2 flooding and storage in the reservoir block to be evaluated. Through this model, the variation patterns of different components in the reservoir block under evaluation during the reservoir production process can be determined.
[0058] After constructing a component numerical simulation model of the reservoir block to be evaluated, the processor can input different preset permeability, preset reservoir temperature, and preset burial pressure into the component numerical simulation model. The component numerical simulation model can determine the mole fraction of CO2 components in different phases of the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure. These different phases may include oil, gas, and water. Then, based on the mole fraction of CO2 components in different phases, the content of CO2 components in different phases can be determined, and subsequently, based on the content of CO2 components in different phases, the simulated effective burial amount of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure can be determined.
[0059] The processor determines the simulated effective CO2 storage coefficient for the reservoir block under evaluation under different preset permeability, preset reservoir temperature, and preset storage pressure based on the theoretical and simulated effective CO2 storage amounts. Specifically, the ratio between the simulated effective storage amount and the theoretical storage amount can be determined as the simulated effective storage coefficient. Then, the processor can use the simulated effective CO2 storage coefficients for the reservoir block under evaluation under different preset permeability, preset reservoir temperature, and preset storage pressure as a training set.
[0060] The processor can input different preset permeability, preset reservoir temperature, and preset burial pressure into different machine learning models, so that different machine learning models can output different simulated effective burial coefficients corresponding to preset permeability, preset reservoir temperature, and preset burial pressure, in order to train different machine learning models.
[0061] In this embodiment, the machine learning model includes linear regression models, support vector machines, tree ensembles, Gaussian process regression models, neural networks, and regression trees. Specifically, the linear regression model includes linear models, interaction-effect linear models, robust linear models, and stepwise linear models. Support vector machines include linear SVMs, quadratic SVMs, cubic SVMs, fine-grained Gaussian SVMs, medium-grained Gaussian SVMs, and coarse-grained Gaussian SVMs. Tree ensembles include boosting trees and bagging trees. Gaussian process regression models include quadratic rational GPRs, quadratic exponential GPRs, Matern5 / 2 GPRs, and exponential GPRs. Neural networks include narrow neural networks, medium-grained neural networks, wide neural networks, two-layer neural networks, and three-layer neural networks. Regression trees include fine-grained trees, medium-grained trees, and coarse-grained trees.
[0062] For different machine learning models, training is considered complete when the number of iterations reaches a preset number and / or the prediction error reaches a preset value. When different machine learning models have completed training, the model that meets preset conditions is selected as the effective embedding coefficient prediction model. These preset conditions include a prediction accuracy within a preset range. That is, a machine learning model with prediction accuracy within a preset range can be selected as the effective embedding coefficient prediction model. The preset range can be set according to actual needs. If there are multiple trained machine learning models with prediction accuracy within the preset range, any one of them can be selected as the effective embedding coefficient prediction model, or the model with the highest prediction accuracy can be selected.
[0063] When constructing an effective burial coefficient prediction model for the reservoir block to be evaluated, the processor can input different preset permeability, preset reservoir temperature, and preset burial pressure into the effective burial coefficient prediction model. This allows the effective burial coefficient prediction model to output the predicted effective burial coefficient of CO2 in the reservoir block under different preset permeability, preset reservoir temperature, and preset burial pressure. The preset permeability, preset reservoir temperature, and preset burial pressure used here can be the same as those used to train the machine learning model, or they can be different, depending on the requirements. Subsequently, the processor can construct multiple effective burial maps based on the predicted effective burial coefficients of CO2 in the reservoir block under different preset permeability, preset reservoir temperature, and preset burial pressure. Each effective burial map includes the predicted effective burial coefficient corresponding to the preset reservoir permeability and preset reservoir temperature at the preset burial pressure.
[0064] Step 104: Determine the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on multiple effective burial charts, current burial pressure, current reservoir temperature, and current reservoir permeability.
[0065] The processor can determine the current effective CO2 burial coefficient in the reservoir block to be evaluated based on multiple effective burial maps, current burial pressure, current reservoir temperature, and current reservoir permeability.
[0066] In this embodiment of the application, determining the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on multiple effective burial maps, current burial pressure, current reservoir temperature, and current reservoir permeability includes: selecting effective burial maps under the current burial pressure from multiple effective burial maps as maps to be searched; traversing the maps to be searched to obtain a preset reservoir temperature that matches the current reservoir temperature and a preset reservoir permeability that matches the current reservoir permeability; and determining the predicted effective burial coefficient corresponding to the matched preset reservoir temperature and preset reservoir permeability as the current effective burial coefficient.
[0067] The processor can select the effective reservoir map under the current reservoir pressure from multiple effective reservoir maps as the search map. The search map includes the predicted effective reservoir coefficients corresponding to the preset reservoir permeability and preset reservoir temperature under the current reservoir pressure. Then, the processor can iterate through the search map to obtain the preset reservoir temperature matching the current reservoir temperature and the preset reservoir permeability matching the current reservoir permeability. Next, the processor can determine the predicted effective reservoir coefficients corresponding to the matched preset reservoir temperature and preset reservoir permeability as the current effective reservoir coefficients.
[0068] Step 105: Determine the current effective CO2 reserves in the reservoir block to be evaluated based on the theoretical reserves and the current effective reserves coefficient.
[0069] Given the theoretical CO2 reserves and current effective reserves coefficient of the reservoir block to be evaluated, the processor can determine the current effective CO2 reserves in the reservoir block based on these two parameters. Specifically, the processor can determine the current effective CO2 reserves in the reservoir block to be evaluated as the product of the theoretical CO2 reserves and the current effective reserves coefficient.
[0070] Specifically, in this embodiment of the application, the current effective buried amount is determined by formula (1):
[0071] Formula (1)
[0072] in, This refers to the current effective CO2 reserves in the reservoir block to be evaluated. It refers to the current effective CO2 burial coefficient in the reservoir block to be evaluated. This refers to the theoretical CO2 reserves in the reservoir block to be evaluated.
[0073] like Figure 2 As shown, a flowchart illustrating another method for determining the effective CO2 reserves in an oil reservoir is provided.
[0074] When determining the effective CO2 storage capacity in an oil reservoir, geological modeling data for different types of reservoirs can be collected first to create a geological model that accurately reflects the geological characteristics of typical reservoir types. Phase simulation software is then used to simulate reservoir fluid PVT experiments, yielding a state equation that reflects the actual properties of the reservoir fluids. Simultaneously, the results of CO2 solubility tests in oil and water and CO2 diffusion coefficient measurements in porous media cores are used for the numerical simulation phase calculation. Based on the fitting of historical reservoir production data, numerical simulations of CO2 displacement under different reservoir permeability, formation temperature, and upper limit pressure are conducted to obtain the effective CO2 storage capacity under these conditions. After obtaining the numerical simulation results, the corresponding simulated effective storage coefficient can be determined based on the effective CO2 storage capacity and theoretical storage capacity under different reservoir permeability, formation temperature, and upper limit pressure.
[0075] Given the simulated effective burial coefficients under different reservoir conditions and burial operating conditions, a model dataset can be constructed based on different reservoir permeability, formation temperature, upper burial pressure, and corresponding simulated effective burial coefficients. This model dataset includes multiple training samples. Each training sample includes reservoir temperature, burial pressure, permeability, and the simulated effective burial coefficient. After establishing the model dataset, given operating parameters (reservoir temperature, burial pressure, and permeability in each training sample) can be input into multiple individual surrogate models to obtain the predicted effective burial coefficients under those parameters, thus training multiple individual surrogate models. Subsequently, model optimization can be performed to improve model accuracy. Specifically, the surrogate model that meets the computational accuracy requirements can be selected from the multiple trained individual surrogate models as the final model.
[0076] like Figure 3 The diagram illustrates the training and optimization process of a surrogate model. When training the surrogate model, a model dataset can be constructed based on different reservoir permeability, formation temperature, upper limit pressure of burial, and the corresponding simulated effective burial coefficient. Multiple surrogate models can then be trained using this dataset, where M1 to M6 represent the multiple surrogate models. During the training of each surrogate model, model optimization can be performed, for example, by continuously optimizing the weight parameters of each surrogate model until the training completion conditions for each surrogate model are met. After each surrogate model has been trained, an ensemble algorithm can be used to select one surrogate model from the trained models as the final effective burial coefficient prediction model through a voting decision.
[0077] Next, the given operating parameters, or new operating parameters, can be input into the final model to predict the effective reservoir coefficient under the corresponding operating parameters, thereby establishing an effective reservoir coefficient chart. When multiple sets of predicted effective reservoir coefficients are determined, effective reservoir coefficient charts can be established based on these multiple sets of predicted effective reservoir coefficients. One reservoir pressure corresponds to one effective reservoir coefficient chart. Each effective reservoir coefficient chart includes the predicted effective reservoir coefficient corresponding to the reservoir temperature and reservoir permeability at the corresponding reservoir pressure.
[0078] Figure 4(a) shows the effective burial coefficient of a reservoir at a burial pressure of 14 MPa; Figure 4(b) shows the effective burial coefficient of a reservoir at a burial pressure of 15 MPa; Figure 4(c) shows the effective burial coefficient of a reservoir at a burial pressure of 16 MPa; and Figure 4(d) shows the effective burial coefficient of a reservoir at a burial pressure of 17 MPa.
[0079] After establishing an effective storage coefficient chart, the effective storage capacity of the corresponding reservoir block can be determined based on this chart. Specifically, for the reservoir block to be evaluated, the permeability, reservoir temperature, and storage pressure of the reservoir block can be obtained, and the theoretical storage capacity of the reservoir block to be evaluated can be determined. Based on the storage pressure, the predicted effective storage coefficient corresponding to the permeability and reservoir temperature in the corresponding effective storage coefficient chart can be found. Then, the effective storage capacity of the reservoir block to be evaluated can be determined based on the determined predicted effective storage coefficient and the theoretical storage capacity. For example, consider a reservoir of the above type with a permeability of 900 mD, a reservoir temperature of 70℃, a pore volume calculated using the volumetric method of 2,311,201 m³, bound water saturation of 0.3, a recovery rate of 0.01% before CO2 breakthrough, a recovery rate of 9.59% after CO2 breakthrough, an upper limit pressure of 17 MPa, a measured CO2 solubility coefficient of 0.3685 m³ / m³ in oil, and a CO2 solubility coefficient of 0.1455 m³ / m³ in water. The calculated theoretical CO2 reserves are 241,079 tons. (Refer to the map...) Figure 4d The effective CO2 storage coefficient is 0.1946 at a permeability of 900 mD and a reservoir temperature of 70℃. Therefore, the effective CO2 storage in this type of reservoir is calculated to be 46,900 tons.
[0080] In one embodiment, another method for determining the effective CO2 storage capacity in an oil reservoir is provided, comprising the following steps:
[0081] Step 1: Collect geological modeling data for typical reservoir blocks. This data includes well location coordinates, core elevation, well trajectory data, stratigraphic data, structural interpretation data, and logging data. Mature geological modeling software is used to perform geological modeling, resulting in a geological model that reflects the actual reservoir structure and properties. This geological model can be used to establish component numerical simulation models.
[0082] Step Two: Collect PVT experimental data, CO2 solubility measurement data in oil-water analysis, and CO2 diffusion coefficient measurement data in reservoir cores for typical reservoir blocks. The PVT experimental data includes CO2 injection expansion data, isocomposition expansion data, and flash evaporation data. The PVT experimental data are fitted using phase simulation software to obtain a state equation reflecting the actual reservoir fluid properties. This equation, combined with the experimentally measured solubility and diffusion coefficients, is input into the phase calculation section of the component model for numerical simulation phase calculations.
[0083] Step 3: Collect historical production data for typical reservoir blocks, including reservoir pressure variation curves, reservoir relative permeability curves, capillary pressure curves, well history data, and oil, gas, and water production data. Establish a component numerical simulation model using reservoir numerical simulation software, and perform production history fitting based on the work done in the first two steps to accurately simulate the current oil and water distribution and production dynamics of the reservoir, laying the foundation for accurate simulation of CO2-driven oil recovery.
[0084] Step 4: Using the established component numerical simulation model, CO2 flooding and storage simulations are carried out under different reservoir permeability, different reservoir temperature, and different upper limit pressure of storage. The effective storage amount of CO2 is calculated by the difference between CO2 injection and production.
[0085] Step 5: Collect data on the target block, namely the reservoir area, reservoir thickness, porosity, bound water saturation, water injection data, crude oil recovery rate data, and experimental data on CO2 dissolution in oil and water. Use phase calculation software to calculate the density of CO2 under reservoir temperature and burial pressure conditions, and substitute the above data into the following formula to obtain the theoretical burial amount of CO2.
[0086]
[0087] in, This refers to the theoretical CO2 reserves in a typical type of oil reservoir block. This refers to the density of CO2 in a typical type of reservoir block under reservoir conditions, expressed in kg / m³. 3 , The recovery rate of crude oil before CO2 injection breakthrough in a typical type of reservoir block is expressed in f. The oil recovery rate (f) is the crude oil recovery rate after injecting a predetermined volume of CO2 into a typical type of reservoir block, where A is the reservoir area of the typical type of reservoir block, in units of... h represents the reservoir thickness of a typical reservoir block, in meters. The reservoir porosity is expressed in f for a typical type of reservoir block. The bound water saturation of a typical type of reservoir block is expressed in f. This refers to the injected water volume in a typical type of reservoir block, in units of... , The water production is for a typical type of reservoir block, in units of... , The solubility coefficient of CO2 in water in a typical type of oil reservoir block is given by f. This represents the CO2 solubility coefficient in oil in a typical type of reservoir block, expressed in units of f.
[0088] Step Six: Substitute the effective storage volume obtained in Step Four and the theoretical storage volume obtained in Step Five into the following formula to calculate the effective storage coefficient. This yields the effective storage coefficients for the research type of reservoir under different permeabilities, reservoir temperatures, and upper storage pressures. A dataset can then be constructed based on different permeabilities, reservoir temperatures, upper storage pressures, and corresponding effective storage coefficients. This dataset can then be used as training data for machine learning models.
[0089] = /
[0090] in, This refers to the effective CO2 storage capacity in the oil reservoir of the research type. This refers to the effective CO2 burial coefficient in the studied type of reservoir. It refers to the theoretical CO2 reserves in the research type of reservoir.
[0091] Step 7: Input the dataset of multi-factor variables and effective burial coefficient obtained in Step 6 into multiple machine learning models, and train these models using a regression learning algorithm to obtain multiple trained machine learning models. Then, optimize and filter the accuracy of these trained models to obtain a surrogate model for calculating the CO2 effective burial coefficient that meets the required accuracy. By inputting new reservoir temperature, permeability, and burial pressure parameters, the surrogate model is used to achieve accurate and rapid calculation of the effective burial coefficient, and an effective burial coefficient calculation chart is generated.
[0092] Step 8: After changing the reservoir temperature, permeability and burial pressure for the same type of reservoir, use the process in Step 5 to calculate the theoretical CO2 burial amount of the reservoir to be evaluated, and refer to the effective burial coefficient calculation chart drawn in Step 7 to realize the rapid calculation of the effective CO2 burial amount.
[0093] The above technical solution obtains the reservoir basic data, current burial pressure, current reservoir temperature, and current reservoir permeability of the reservoir block to be evaluated; determines the theoretical CO2 burial amount in the reservoir block to be evaluated based on the reservoir basic data; constructs multiple effective burial maps for the reservoir block to be evaluated, each effective burial map including a predicted effective burial coefficient corresponding to a preset burial pressure, preset reservoir permeability, and preset reservoir temperature; determines the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on multiple effective burial maps, current burial pressure, current reservoir temperature, and current reservoir permeability; and determines the current effective burial amount of CO2 in the reservoir block to be evaluated based on the theoretical burial amount and the current effective burial coefficient, enabling rapid and accurate determination of the effective CO2 burial amount in the reservoir.
[0094] Figure 1 and 2This is a flowchart illustrating a method for determining the effective CO2 storage capacity in an oil reservoir, as illustrated in one embodiment. It should be understood that, although... Figure 1 and 2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 and 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
[0095] In one embodiment, an apparatus for determining the effective CO2 storage capacity in an oil reservoir is provided, comprising:
[0096] The memory is configured to store instructions; and
[0097] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned method for determining the effective CO2 reserves in an oil reservoir.
[0098] In one embodiment, a storage medium is provided having a program stored thereon that, when executed by a processor, implements the method described above for determining the effective CO2 reserves in an oil reservoir.
[0099] In one embodiment, a processor is provided for running a program, wherein the program executes the method described above for determining the effective CO2 reserves in an oil reservoir.
[0100] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores data such as multiple effective CO2 burial plots. The network interface A02 communicates with external terminals via a network connection. When executed by the processor A01, the computer program B02 implements a method for determining the effective CO2 burial quantity in an oil reservoir.
[0101] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0102] This application provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring basic reservoir data, current burial pressure, current reservoir temperature, and current reservoir permeability of the reservoir block to be evaluated; determining the theoretical CO2 burial quantity in the reservoir block to be evaluated based on the basic reservoir data; constructing multiple effective burial maps of the reservoir block to be evaluated, each effective burial map including a predicted effective burial coefficient corresponding to a preset burial pressure, preset reservoir permeability, and preset reservoir temperature; determining the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on the multiple effective burial maps, current burial pressure, current reservoir temperature, and current reservoir permeability; and determining the current effective burial quantity of CO2 in the reservoir block to be evaluated based on the theoretical burial quantity and the current effective burial coefficient.
[0103] In this embodiment of the application, determining the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on multiple effective burial maps, current burial pressure, current reservoir temperature, and current reservoir permeability includes: selecting effective burial maps under the current burial pressure from multiple effective burial maps as maps to be searched; traversing the maps to be searched to obtain a preset reservoir temperature that matches the current reservoir temperature and a preset reservoir permeability that matches the current reservoir permeability; and determining the predicted effective burial coefficient corresponding to the matched preset reservoir temperature and preset reservoir permeability as the current effective burial coefficient.
[0104] In this embodiment of the application, constructing multiple effective burial plots for the reservoir block to be evaluated includes: constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the effective burial coefficient prediction model to obtain the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; and constructing multiple effective burial plots based on the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure.
[0105] In this embodiment, constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure includes: constructing a component numerical simulation model of the reservoir block to be evaluated; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the component numerical simulation model to obtain the simulated effective burial amount of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; determining the simulated effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure based on the theoretical burial amount and the simulated effective burial amount; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into different machine learning models so that different machine learning models output simulated effective burial coefficients corresponding to different preset permeability, preset reservoir temperature, and preset burial pressure, thereby training different machine learning models; and selecting the machine learning model that meets the preset conditions from the trained machine learning models as the effective burial coefficient prediction model after the different machine learning models have been trained.
[0106] In this embodiment of the application, constructing a component numerical simulation model of the reservoir block to be evaluated includes: acquiring geological modeling data of the reservoir block to be evaluated, and constructing a geological model of the reservoir block to be evaluated based on the geological modeling data; acquiring fluid data of reservoir fluids in the reservoir block to be evaluated, the solubility coefficient of CO2 in oil and water in the reservoir block to be evaluated, and the diffusion coefficient in the reservoir core; acquiring historical production data of the reservoir block to be evaluated; and constructing a component numerical simulation model based on the geological model and according to the fluid data, solubility coefficient, diffusion coefficient, and historical production data of the reservoir.
[0107] In the embodiments of this application, the machine learning models include linear regression models, support vector machines, tree ensembles, Gaussian process regression models, neural networks, and regression trees.
[0108] In this embodiment of the application, the current effective buried amount is determined by formula (1):
[0109] Formula (1)
[0110] in, This refers to the current effective CO2 reserves in the reservoir block to be evaluated. It refers to the current effective CO2 burial coefficient in the reservoir block to be evaluated. This refers to the theoretical CO2 reserves in the reservoir block to be evaluated.
[0111] In this embodiment of the application, the theoretical burial quantity is determined by formula (2):
[0112]
[0113] Formula (2)
[0114] in, This refers to the theoretical CO2 reserves in the reservoir block to be evaluated. This refers to the density of CO2 in the reservoir block to be evaluated under reservoir conditions, expressed in kg / m³. 3 , The recovery rate of crude oil in the reservoir block to be evaluated before CO2 injection breakthrough is expressed in f. The oil recovery rate is the crude oil recovery rate after injecting a predetermined volume of CO2 into the reservoir block to be evaluated, expressed in units of f. A represents the reservoir area of the reservoir block to be evaluated, expressed in units of... h represents the reservoir thickness of the block to be evaluated, in meters (m). The reservoir porosity of the oil-bearing block to be evaluated is expressed in f. The bound water saturation of the reservoir block to be evaluated is expressed in f. This refers to the injected water volume of the reservoir block to be evaluated, in units of... , The water production of the reservoir block to be evaluated is expressed in units of... , The solubility coefficient of CO2 in water in the reservoir block to be evaluated is expressed in f. The value represents the solubility coefficient of CO2 in the oil in the reservoir block to be evaluated, expressed in units of f.
[0115] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes a method for determining the effective CO2 reserves in an oil reservoir.
[0116] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0117] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0118] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0119] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0120] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0121] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0122] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0123] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. 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 apparatus that includes that element.
[0124] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for determining the effective CO2 storage capacity in an oil reservoir, characterized in that, The method includes: Obtain basic reservoir data, current burial pressure, current reservoir temperature, and current reservoir permeability for the reservoir block to be evaluated; The theoretical CO2 reserves in the reservoir block to be evaluated are determined based on the reservoir basic data. Construct multiple effective burial plots for the reservoir block to be evaluated. Each effective burial plot includes a predicted effective burial coefficient corresponding to a preset reservoir permeability and a preset reservoir temperature under a preset burial pressure. The current effective CO2 burial coefficient in the reservoir block to be evaluated is determined based on the multiple effective burial charts, the current burial pressure, the current reservoir temperature, and the current reservoir permeability. The current effective CO2 content in the reservoir block to be evaluated is determined based on the theoretical storage capacity and the current effective storage coefficient. The step of determining the current effective burial coefficient of CO2 in the reservoir block to be evaluated based on the multiple effective burial maps, the current burial pressure, the current reservoir temperature, and the current reservoir permeability includes: selecting the effective burial map under the current burial pressure from the multiple effective burial maps as the map to be searched; traversing the map to be searched to obtain a preset reservoir temperature that matches the current reservoir temperature and a preset reservoir permeability that matches the current reservoir permeability; and determining the predicted effective burial coefficient corresponding to the matched preset reservoir temperature and preset reservoir permeability as the current effective burial coefficient. The construction of multiple effective burial maps for the reservoir block to be evaluated, each effective burial map including a predicted effective burial coefficient corresponding to a preset reservoir permeability and a preset reservoir temperature under a preset burial pressure, includes: constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the effective burial coefficient prediction model to obtain the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; and constructing the multiple effective burial maps based on the predicted effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure. The step of constructing an effective burial coefficient prediction model for the reservoir block to be evaluated based on different preset permeability, preset reservoir temperature, and preset burial pressure includes: constructing a component numerical simulation model for the reservoir block to be evaluated; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into the component numerical simulation model to obtain the simulated effective burial amount of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure; determining the simulated effective burial coefficient of CO2 in the reservoir block to be evaluated under different preset permeability, preset reservoir temperature, and preset burial pressure according to the theoretical burial amount and the simulated effective burial amount; inputting different preset permeability, preset reservoir temperature, and preset burial pressure into different machine learning models so that different machine learning models output simulated effective burial coefficients corresponding to different preset permeability, preset reservoir temperature, and preset burial pressure, thereby training different machine learning models; and selecting the machine learning model that meets the preset conditions from the trained machine learning models as the effective burial coefficient prediction model after the different machine learning models have been trained.
2. The method for determining the effective CO2 storage capacity in an oil reservoir according to claim 1, characterized in that, The construction of the component numerical simulation model for the reservoir block to be evaluated includes: Obtain geological modeling data of the reservoir block to be evaluated, and construct a geological model of the reservoir block to be evaluated based on the geological modeling data; The fluid data of the reservoir fluid in the reservoir block to be evaluated, the solubility coefficient of CO2 in oil and water in the reservoir block to be evaluated, and the diffusion coefficient in the reservoir core are obtained. Obtain historical production data of the reservoir block to be evaluated; Based on the geological model, and according to the fluid data, the solubility coefficient, the diffusion coefficient, and the reservoir historical production data, the component numerical simulation model is constructed.
3. The method for determining the effective CO2 storage capacity in an oil reservoir according to claim 1, characterized in that, The machine learning models include linear regression models, support vector machines, tree ensembles, Gaussian process regression models, neural networks, and regression trees.
4. The method for determining the effective CO2 storage capacity in an oil reservoir according to claim 1, characterized in that, The current effective buried quantity is determined by formula (1): Formula (1) in, This refers to the current effective CO2 reserves in the reservoir block to be evaluated. This refers to the current effective CO2 burial coefficient in the reservoir block to be evaluated. This refers to the theoretical CO2 reserves in the reservoir block to be evaluated.
5. The method for determining the effective CO2 storage capacity in an oil reservoir according to claim 1, characterized in that, The theoretical burial volume is determined by formula (2): Formula (2) in, This refers to the theoretical CO2 reserves in the reservoir block to be evaluated. This refers to the density of CO2 in the reservoir block to be evaluated under reservoir conditions, expressed in kg / m³. 3 , The recovery rate of crude oil in the reservoir block to be evaluated before CO2 injection breakthrough is expressed in f. The oil recovery rate is the crude oil recovery rate after injecting a predetermined volume of CO2 into the reservoir block to be evaluated, expressed in units of f. A represents the reservoir area of the reservoir block to be evaluated, expressed in units of... h represents the reservoir thickness of the block to be evaluated, in meters (m). The reservoir porosity of the oil-bearing block to be evaluated is expressed in f. The bound water saturation of the reservoir block to be evaluated is expressed in f. This refers to the injected water volume of the reservoir block to be evaluated, in units of... , The water production of the reservoir block to be evaluated is expressed in units of... , The solubility coefficient of CO2 in water in the reservoir block to be evaluated is expressed in f. The value represents the solubility coefficient of CO2 in the oil in the reservoir block to be evaluated, expressed in units of f.
6. An apparatus for determining the effective CO2 storage capacity in an oil reservoir, characterized in that, The device includes: The memory is configured to store instructions; and The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for determining the effective CO2 reserves in an oil reservoir according to any one of claims 1 to 5.
7. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform a method for determining the effective CO2 reserves in an oil reservoir according to any one of claims 1 to 5.