A fracturing oil reservoir CO 2 Oil displacement flow simulation system and method

Abstract

The present invention discloses a system and method for simulating the flow of oil recovery from a fracturing oil reservoir, and the present invention relates to the technical field of numerical simulation of oil recovery flow from an oil reservoir. The system comprises the following steps: determining the position of artificial large fractures and micro-fracture regions generated by fracturing, establishing a finite element model of a fracturing oil reservoir, and performing meshing; establishing a comprehensive physical field coupling model, and calculating the crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient, and fracture strain data of different grids in the reservoir sub-region under different injection amounts based on the comprehensive physical field coupling model; establishing a neural network model, using historical fracturing oil reservoir flow data as input, and using the content data in the crude oil as a label to train the neural network model; inputting the flow data of oil recovery of different grids calculated by the comprehensive physical field coupling model into a prediction model to obtain a predicted value of the content in the crude oil; and drawing a curve chart of the changes in different data to characterize the simulation of the flow of oil recovery from a fracturing oil reservoir.

Description

Technical Field

[0001] The present invention relates to an oil reservoir The technical field of oil displacement flow numerical simulation is specifically a fracturing reservoir Oil recovery flow simulation system and method. Background Art

[0002] As global energy demand continues to grow, traditional oil resources are gradually depleting, and effective technical means are urgently needed to improve the recovery rate of existing oil reservoirs. Especially in aging oil fields, the recovery rate of crude oil usually faces huge challenges, and traditional mining methods can no longer meet economic and environmental requirements. In this regard, carbon dioxide ( ) Oil recovery technology has gradually become a popular and efficient oil recovery method due to its potential environmental friendliness and low cost. Injection can not only increase the reservoir pressure, but also effectively reduce the viscosity of crude oil, promote the flow of crude oil, and thus increase the recovery rate of crude oil. However, most current research still focuses on The physical mechanism of injection is lacking in the fractured reservoir. Systematic simulation and analysis of oil displacement flows.

[0003] In a fracturing reservoir, the presence of artificial fractures changes the flow path and flow characteristics of the fluid, so it is particularly important to accurately simulate these complex flow processes. Oil recovery flow simulation methods usually ignore the impact of reservoir microfractures, resulting in an inability to fully reflect the actual flow conditions. In addition, traditional simulation methods rely on empirical formulas and qualitative analysis, lacking the ability to monitor and adjust in real time. In order to overcome these technical difficulties, it is particularly important to establish an integrated finite element model and a comprehensive physical field coupling model. This can not only improve the understanding of flow conditions, but also provide a basis for optimization. The injection scheme provides a scientific basis.

[0004] Therefore, it is necessary to design a fracturing reservoir The oil displacement flow simulation solution is used to solve the above technical problems and realize the Dynamic prediction and optimization of oil displacement flow.

[0005] In the prior art, publication number CN114154430A discloses a method for fracturing an oil reservoir. The oil displacement flow simulation method includes the following steps: determining the location of artificial large fractures and micro-fracture areas generated by fracturing, and establishing a geometric model of the fracturing reservoir; establishing a mixed model to characterize fractures of different scales, performing grid division, and forming a grid system; establishing a component model to describe The oil displacement process takes into account the components and describes the phase changes and and the miscibility mechanism of crude oil; formulate a solution to solve the complex fractured reservoir component model to make the simulation process stable. However, this method needs to consider a variety of physical and chemical phenomena when establishing the component model, including phase changes and miscibility mechanisms. These complex interactions may make the model difficult to solve, especially under high pressure, low temperature or complex geological conditions, where nonlinearity, non-equilibrium and other problems may occur, making the simulation process unstable. At the same time, it does not take into account that the increase in pressure may cause changes in fracture stress, which may lead to poor simulation results. Therefore, this method is not only difficult to solve, consumes a lot of computing resources, but also reduces the accuracy and effectiveness of the system.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The object of the present invention is to provide a fracturing reservoir The invention discloses an oil displacement flow simulation system and method to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A fracturing oil reservoir Oil displacement flow simulation system, including:

[0010] The simulation model building module builds a finite element model of a fractured reservoir based on the location of artificial large fractures and micro-fracture areas caused by fracturing in the fractured reservoir to be analyzed, divides the finite element model of the fractured reservoir into equal areas, obtains several reservoir sub-areas, defines the grid density in the obtained reservoir sub-areas, and performs grid division;

[0011] Data monitoring module, used for experimental simulation based on the established finite element model of the fractured reservoir Injection process, record The injection amount is calculated based on the comprehensive physical field coupling model. Fractured reservoirs in different grids in the reservoir sub-area under different injection rates Oil flow data, the fractured reservoir Oil displacement flow data include crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data;

[0012] Neural network training module for collecting historical fracture reservoir data Oil displacement flow data and corresponding crude oil content data, and establish a neural network model based on the historical data collected to The oil displacement flow data is used as the input of the neural network model to The content data is used as a label to train the neural network model and obtain Content prediction model;

[0013] The actual content prediction module is used to calculate different The training is completed by inputting the crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data of different grids under injection volume. In the content prediction model, The content prediction model outputs the current crude oil content Predicted content value;

[0014] The simulation result characterization module is used to characterize the Content prediction and fractured reservoirs Oil displacement flow data, plotting different The curve diagram of data changes under injection rate is used to characterize the fractured reservoir Oil displacement flow simulation.

[0015] Furthermore, the finite element model of the fractured reservoir is divided into equal areas to obtain The number of grids is determined according to the number of artificial large fractures and micro fractures in each sub-region, and the grid density is defined in combination with the characteristic length of the sub-region. The formula for calculating the grid density is:

[0016] ;

[0017] In the formula, Indicates The grid density of each reservoir sub-region is Indicates The characteristic length of each reservoir sub-region, Indicates The number of grids determined by each reservoir sub-area, is the index of the reservoir sub-region, ;

[0018] The number of grids is determined according to the number of artificial large cracks and micro cracks in each sub-area, where the number of grids is The formula used for determination is:

[0019] ;

[0020] In the formula, and Respectively The number of artificial macrofractures and microfractures in each reservoir sub-area, is the grid quantity correction factor, where .

[0021] Furthermore, a comprehensive physical field coupling model is established, wherein the comprehensive physical field coupling model is established based on fluid dynamics equations, heat conduction equations and geostress equations.

[0022] Furthermore, the fluid dynamics equations based on the comprehensive physical field coupling model include the continuity equation and the momentum equation, wherein the specific expressions of the continuity equation and the momentum equation are respectively:

[0023] ;

[0024] ;

[0025] In the formula, represents the density of the fluid, that is, the density of the crude oil in the reservoir, represents the fluid velocity vector at time t, is the fluid velocity versus time The partial derivative of represents the pressure gradient, is the dynamic viscosity, The Laplace operator representing the fluid velocity, represents the body force, Indicates injected Contribution of volume to fluid momentum.

[0026] Furthermore, the specific expression of the heat conduction equation based on the comprehensive physical field coupling model is:

[0027] ;

[0028] In the formula, represents the specific heat capacity of crude oil, is the crude oil temperature at time t, represents the partial derivative of temperature with respect to time, is the temperature gradient, represents the thermal conductivity of crude oil, is the divergence of thermal conductivity and temperature gradient, express Heat source term resulting from additional heat release or absorption during the injection process.

[0029] Furthermore, the geostress equation includes an equilibrium equation and a strain-stress relationship equation, wherein the specific expressions of the equilibrium equation and the strain-stress relationship equation are respectively:

[0030] ;

[0031] ;

[0032] In the formula, represents the stress tensor, is the divergence of the stress tensor, represents the body force, represents the crack strain, is the Poisson's ratio of fractured rock formation, represent the maximum principal stress, the intermediate principal stress and the minimum principal stress respectively. is the elastic modulus of the fractured rock formation, Indicates that due to Additional pressure changes caused by injection.

[0033] Furthermore, the The content prediction model is established based on the long short-term memory network model LSTM model, the Tanh function is selected as the activation function, and the hyperparameters of the LSTM model are set. The hyperparameters of the LSTM model include: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing number and the number of hidden layer neurons;

[0034] The number of network layers is set to a 4-layer network structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32.

[0035] The present invention also provides a fracturing oil reservoir Oil displacement flow simulation method, the fracturing reservoir The oil displacement flow simulation method is used to control the above-mentioned fractured reservoir The oil displacement flow simulation system includes the following specific steps:

[0036] Based on the locations of artificial large fractures and micro-fracture areas caused by fracturing in the fracturing reservoir to be analyzed, a finite element model of the fracturing reservoir is established, the finite element model of the fracturing reservoir is divided into equal areas to obtain a number of reservoir sub-areas, and the grid density is defined in the obtained reservoir sub-areas to perform grid division;

[0037] Based on the established finite element model of the fractured reservoir, experimental simulation Injection process, record The injection amount is calculated based on the comprehensive physical field coupling model. Fractured reservoirs in different grids in the reservoir sub-area under different injection rates Oil flow data, the fractured reservoir Oil displacement flow data include crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data;

[0038] Acquisition of historical fractured reservoirs Oil displacement flow data and corresponding crude oil content data, and establish a neural network model based on the historical data collected to The oil displacement flow data is used as the input of the neural network model to The content data is used as a label to train the neural network model and obtain Content prediction model;

[0039] The different The training is completed by inputting the crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data of different grids under injection volume. In the content prediction model, The content prediction model outputs the current crude oil content Predicted content value;

[0040] Based on the obtained crude oil Content prediction and fractured reservoirs Oil displacement flow data, plotting different The curve diagram of data changes under injection rate is used to characterize the fractured reservoir Oil displacement flow simulation.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] First, the finite element model and the integrated physical field coupling model can accurately simulate the This method not only takes into account the impact of artificial fractures and microfractures, but also monitors multiple parameters in the reservoir, such as crude oil fluid velocity, fracture pressure, temperature and strain, in real time, providing a comprehensive understanding of the flow state, so that reservoir managers can better adjust Injection strategies can be developed to optimize recovery and extend the life of the oil field. Secondly, combining historical data with neural network models can achieve The establishment of this model not only improves the accuracy of prediction, but also allows dynamic adjustment based on real-time data, making it more flexible to respond to changing reservoir conditions in actual operations. This prediction model provides a scientific basis for reservoir management and enables more reasonable operation choices in a changing environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of the overall system structure of the present invention;

[0044] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0045] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0046] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0047] Example:

[0048] See also Figure 1 , the present invention provides a system structure:

[0049] A fracturing oil reservoir Oil displacement flow simulation system, including:

[0050] The simulation model building module builds a finite element model of a fractured reservoir based on the location of artificial large fractures and micro-fracture areas caused by fracturing in the fractured reservoir to be analyzed, divides the finite element model of the fractured reservoir into equal areas, obtains several reservoir sub-areas, defines the grid density in the obtained reservoir sub-areas, and performs grid division;

[0051] The finite element model of the fractured reservoir is divided into equal areas to obtain The number of grids is determined according to the number of artificial large fractures and micro fractures in each sub-region, and the grid density is defined in combination with the characteristic length of the sub-region. The formula for calculating the grid density is:

[0052] ;

[0053] In the formula, Indicates The grid density of each reservoir sub-region is Indicates The characteristic length of each reservoir sub-region, Indicates The number of grids determined by each reservoir sub-area, is the index of the reservoir sub-region, Among them, The characteristic length of the reservoir sub-region It represents the length of the fracture in the sub-area. The geometric characteristics of the reservoir can be obtained through geological exploration, seismic survey and drilling sampling techniques to determine the characteristic length.

[0054] The number of grids is determined according to the number of artificial large cracks and micro cracks in each sub-area, where the number of grids is The formula used for determination is:

[0055] ;

[0056] In the formula, and Respectively The number of artificial macrofractures and microfractures in each reservoir sub-area, is the grid quantity correction factor, where .

[0057] Data monitoring module, used for experimental simulation based on the established finite element model of the fractured reservoir Injection process, record The injection amount is calculated based on the comprehensive physical field coupling model. Fractured reservoirs in different grids in the reservoir sub-area under different injection rates Oil flow data, the fractured reservoir Oil displacement flow data include crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data;

[0058] A comprehensive physical field coupling model is established, wherein the comprehensive physical field coupling model is established based on fluid dynamics equations, heat conduction equations and geostress equations.

[0059] The fluid dynamics equations based on the comprehensive physical field coupling model include the continuity equation and the momentum equation, wherein the specific expressions of the continuity equation and the momentum equation are respectively:

[0060] ;

[0061] ;

[0062] In the formula, represents the density of the fluid, that is, the density of the crude oil in the reservoir, represents the fluid velocity vector at time t, is the fluid velocity versus time The partial derivative of represents the pressure gradient, is the dynamic viscosity, The Laplace operator representing the fluid velocity, represents the body force, Indicates injected The contribution of the mass to the fluid momentum can be accurately predicted using numerical simulations (such as CFD simulations) The effect of injection on fluid momentum can be characterized by both flow rate and fluid density.

[0063] The specific expression of the heat conduction equation based on the comprehensive physical field coupling model is:

[0064] ;

[0065] In the formula, represents the specific heat capacity of crude oil, is the crude oil temperature at time t, represents the partial derivative of temperature with respect to time, is the temperature gradient, represents the thermal conductivity of crude oil, is the divergence of thermal conductivity and temperature gradient, express Heat source term resulting from additional heat release or absorption during the injection process.

[0066] The geostress equation includes an equilibrium equation and a strain-stress relationship equation, wherein the specific expressions of the equilibrium equation and the strain-stress relationship equation are respectively:

[0067] ;

[0068] ;

[0069] In the formula, represents the stress tensor, is the divergence of the stress tensor, represents the body force, represents the strain of the crack, is the Poisson's ratio of fractured rock formation, represent the maximum principal stress, the intermediate principal stress and the minimum principal stress respectively. is the elastic modulus of the fractured rock formation, Indicates that due to Additional pressure changes caused by injection.

[0070] The stress tensor Describes the stress state of each point in the object. The specific parameters have the following meanings:

[0071] ;

[0072] Where the diagonal elements represent normal stress, Represents the normal stress in the x-axis direction. It represents the internal force per unit area in the x-axis direction, usually tensile stress (positive value) or compressive stress (negative value). is the normal stress in the y-axis direction, which has the same meaning as Same as, describing the internal force in the y-axis direction, Represents the normal stress in the z-axis direction, which has the same meaning as and Same, describing the internal force in the z-axis direction;

[0073] The off-diagonal elements represent shear stresses, It represents the shear stress applied in the x-axis direction, acting on the surface perpendicular to the y-axis direction. It represents the shear force per unit area in the x-axis direction; represents the shear stress applied in the y-axis direction, acting on the surface perpendicular to the x-axis direction. According to the symmetry of the stress tensor, ; is the shear stress applied in the x-axis direction, acting on the surface perpendicular to the z-axis direction, represents the shear stress applied in the z-axis direction, acting on the surface perpendicular to the x-axis direction. According to the symmetry of the stress tensor, ; is the shear stress applied in the y-axis direction, acting on the surface perpendicular to the z-axis direction, represents the shear stress applied in the z-axis direction, acting on the surface perpendicular to the y-axis direction. According to the symmetry of the stress tensor, ; The established coordinate system is a three-dimensional Cartesian coordinate system, which consists of three mutually perpendicular axes, usually marked as: the x-axis represents the horizontal direction, the y-axis represents the vertical direction, and the z-axis represents the depth direction.

[0074] Among them, the specific methods for solving the continuity equation and momentum equation include: discretization, using the finite difference method, finite element method or finite volume method to discretize the equations; setting initial and boundary conditions, defining the initial velocity and pressure of the flow field, and the conditions on the boundary (such as no slip, etc.); time step selection, selecting an appropriate time step to ensure stability; iterative solution, using time marching methods (such as explicit or implicit time stepping methods) to gradually calculate the flow field; using a simple algorithm (SIMPLE) or other coupling algorithms to solve the relationship between pressure and velocity.

[0075] The solution methods for the heat conduction equation and the geostress equation are similar. The solutions of each equation are interrelated and require an iterative method to reach the final equilibrium state and solution.

[0076] Neural network training module for collecting historical fracture reservoir data Oil displacement flow data and corresponding crude oil content data, and establish a neural network model based on the historical data collected to The oil displacement flow data is used as the input of the neural network model to The content data is used as a label to train the neural network model and obtain Content prediction model;

[0077] Said The content prediction model is established based on the long short-term memory network model LSTM model, and the Tanh function is selected as the activation function. The formula of the Tanh function is:

[0078] ;

[0079] In the formula, Represents the Tanh function, independent variable Represents the weighted sum of the neuron's input, that is, the result of weighted summation of the input received by the neuron from the previous layer;

[0080] At the same time, the hyperparameters of the LSTM model are set, and the hyperparameters of the LSTM model include: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing number, and the number of hidden layer neurons;

[0081] The number of network layers is set to a 4-layer network structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32.

[0082] The actual content prediction module is used to calculate different The training is completed by inputting the crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data of different grids under injection volume. In the content prediction model, The content prediction model outputs the current crude oil content Predicted content value;

[0083] Changes in content are usually time series data, involving historical inputs of multiple time steps. LSTM is designed specifically to process sequence data and can capture dynamic changes and long-term dependencies in time series. At the same time, STM can approximate complex nonlinear relationships, which is very useful for predicting fluids that contain multiple influencing factors (such as fluid velocity, pressure gradient, etc.). Content is crucial.

[0084] The simulation result characterization module is used to characterize the Content prediction and fractured reservoirs Oil displacement flow data, plotting different The curve diagram of data changes under injection rate is used to characterize the fractured reservoir Oil displacement flow simulation.

[0085] The data change curves include: crude oil fluid velocity curve, showing the change of crude oil fluid velocity over time, showing different The effect of injection volume on fluid velocity. Fracture pressure gradient curve, showing the change of pressure gradient in the fracture over time, evaluating the dynamic change of fracture pressure under different injection conditions. Fracture temperature gradient curve, showing the change of fracture temperature gradient over time, evaluating the effect of temperature change on The crack strain curve shows the change of crack strain over time and analyzes the effect of oil displacement. Effect of injection on fracture stability. The curve of content change over time shows different Injection rate, the crude oil in unit time Content changes.

[0086] The drawn curve graph can also be changed according to the specific parameters required.

[0087] See also Figure 2 The present invention also provides a fracturing reservoir Oil displacement flow simulation method, the fracturing reservoir The oil displacement flow simulation method is used to control the above-mentioned fractured reservoir The oil displacement flow simulation system includes the following specific steps:

[0088] Step 1: Based on the locations of artificial large fractures and micro-fracture areas generated by fracturing in the fracturing reservoir to be analyzed, a finite element model of the fracturing reservoir is established, and the finite element model of the fracturing reservoir is divided into equal areas to obtain a number of reservoir sub-areas, and the grid density is defined in the obtained reservoir sub-areas to perform grid division;

[0089] Step 2: Based on the established finite element model of the fractured reservoir, conduct experimental simulation Injection process, record The injection amount is calculated based on the comprehensive physical field coupling model. Fractured reservoirs in different grids in the reservoir sub-area under different injection rates Oil flow data, the fractured reservoir Oil displacement flow data include crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data;

[0090] Step 3: Acquire historical fractured reservoirs Oil displacement flow data and corresponding crude oil content data, and establish a neural network model based on the historical data collected to The oil displacement flow data is used as the input of the neural network model to The content data is used as a label to train the neural network model and obtain Content prediction model;

[0091] Step 4: Combine the different The training is completed by inputting the crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data of different grids under injection volume. In the content prediction model, The content prediction model outputs the current crude oil content Predicted content value;

[0092] Step 5: Based on the obtained crude oil Content prediction and fractured reservoirs Oil displacement flow data, plotting different The curve diagram of data changes under injection rate is used to characterize the fractured reservoir Oil displacement flow simulation.

[0093] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0094] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0095] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0096] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A fracturing reservoir The oil displacement flow simulation system is characterized by: Specifically include: The simulation model building module builds a finite element model of a fractured reservoir based on the location of artificial large fractures and micro-fracture areas caused by fracturing in the fractured reservoir to be analyzed, divides the finite element model of the fractured reservoir into equal areas, obtains several reservoir sub-areas, defines the grid density in the obtained reservoir sub-areas, and performs grid division; Data monitoring module, used for experimental simulation based on the established finite element model of the fractured reservoir Injection process, record The injection amount is calculated based on the comprehensive physical field coupling model. Fractured reservoirs in different grids in the reservoir sub-area under different injection rates Oil flow data, the fractured reservoir Oil displacement flow data include crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data; Establishing a comprehensive physical field coupling model, wherein the comprehensive physical field coupling model is established based on fluid dynamics equations, heat conduction equations and ground stress equations; The fluid dynamics equations based on the comprehensive physical field coupling model include the continuity equation and the momentum equation, wherein the specific expressions of the continuity equation and the momentum equation are respectively: In the formula, represents the density of the fluid, that is, the density of the crude oil in the reservoir, represents the fluid velocity vector at time t, is the fluid velocity versus time The partial derivative of represents the pressure gradient, is the dynamic viscosity, The Laplace operator representing the fluid velocity, represents the body force, Indicates injected Contribution of volume to fluid momentum; The specific expression of the heat conduction equation based on the comprehensive physical field coupling model is: In the formula, represents the specific heat capacity of crude oil, is the crude oil temperature at time t, represents the partial derivative of temperature with respect to time, is the temperature gradient, represents the thermal conductivity of crude oil, is the divergence of thermal conductivity and temperature gradient, express Heat source term resulting from additional heat release or absorption during the injection process; The geostress equation includes an equilibrium equation and a strain-stress relationship equation, wherein the specific expressions of the equilibrium equation and the strain-stress relationship equation are respectively: In the formula, represents the stress tensor, is the divergence of the stress tensor, represents the body force, represents the crack strain, is the Poisson's ratio of fractured rock formation, represent the maximum principal stress, the intermediate principal stress and the minimum principal stress respectively. is the elastic modulus of the fractured rock formation, Indicates that due to Additional pressure changes due to injection; Neural network training module for collecting historical fracture reservoir data Oil displacement flow data and corresponding crude oil content data, and establish a neural network model based on the historical data collected to The oil displacement flow data is used as the input of the neural network model to The content data is used as a label to train the neural network model and obtain Content prediction model; The actual content prediction module is used to calculate different The training is completed by inputting the crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data of different grids under injection volume. In the content prediction model, The content prediction model outputs the current crude oil content Predicted content value; The simulation result characterization module is used to characterize the Content prediction and fractured reservoirs Oil displacement flow data, plotting different The curve diagram of data changes under injection rate is used to characterize the fractured reservoir Oil displacement flow simulation.

2. A fracturing reservoir according to claim 1 The oil displacement flow simulation system is characterized by: The finite element model of the fractured reservoir is divided into equal areas to obtain The number of grids is determined according to the number of artificial large fractures and micro fractures in each sub-region, and the grid density is defined in combination with the characteristic length of the sub-region. The formula for calculating the grid density is: In the formula, Indicates The grid density of each reservoir sub-region is Indicates The characteristic length of each reservoir sub-region, Indicates The number of grids determined by each reservoir sub-area, is the index of the reservoir sub-region, ; The number of grids is determined according to the number of artificial large cracks and micro cracks in each sub-area, where the number of grids is The formula used for determination is: In the formula, and Respectively The number of artificial macrofractures and microfractures in each reservoir sub-area, is the grid quantity correction factor, where .

3. A fracturing oil reservoir according to claim 1 The oil displacement flow simulation system is characterized by: Said The content prediction model is established based on the long short-term memory network model LSTM model, the Tanh function is selected as the activation function, and the hyperparameters of the LSTM model are set. The hyperparameters of the LSTM model include: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing number and the number of hidden layer neurons; The number of network layers is set to a 4-layer network structure, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32.

4. A fracturing reservoir The oil displacement flow simulation method is characterized by: The fracturing oil reservoir Oil displacement flow simulation method for controlling the fractured oil reservoir according to any one of claims 1 to 3 The oil displacement flow simulation system includes the following specific steps: Based on the locations of artificial large fractures and micro-fracture areas caused by fracturing in the fracturing reservoir to be analyzed, a finite element model of the fracturing reservoir is established, the finite element model of the fracturing reservoir is divided into equal areas to obtain a number of reservoir sub-areas, and the grid density is defined in the obtained reservoir sub-areas to perform grid division; Based on the established finite element model of the fractured reservoir, experimental simulation Injection process, record The injection amount is calculated based on the comprehensive physical field coupling model. Fractured reservoirs in different grids in the reservoir sub-area under different injection rates Oil flow data, the fractured reservoir Oil displacement flow data include crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data; Acquisition of historical fractured reservoirs Oil displacement flow data and corresponding crude oil content data, and establish a neural network model based on the historical data collected to The oil displacement flow data is used as the input of the neural network model to The content data is used as a label to train the neural network model and obtain Content prediction model; The different The training is completed by inputting the crude oil fluid velocity, fracture pressure gradient, fracture temperature gradient and fracture strain data of different grids under injection volume. In the content prediction model, The content prediction model outputs the current crude oil content Predicted content value; Based on the crude oil Content prediction and fractured reservoirs Oil displacement flow data, plotting different The curve diagram of data changes under injection rate is used to characterize the fractured reservoir Oil displacement flow simulation.

Images