Shale oil flowback strategy real-time adjustment method and system based on numerical simulation

Abstract

The invention belongs to the technical field of petroleum and natural gas development, and particularly relates to a shale oil flowback strategy real-time adjustment method and system based on numerical simulation. In the prior art, the flow-back speed is too high, so that sand blockage or reservoir damage can be caused; according to the technical scheme, the method comprises the steps that a three-dimensional geological model is established based on original geological data; the method comprises the following steps: monitoring an on-site underground reservoir in real time, and acquiring flow data and pressure data of the on-site underground reservoir to obtain on-site reservoir data and on-site flowback parameters corresponding to the on-site reservoir data; training the three-dimensional geologic model by using the field reservoir data and the field flowback parameters; and utilizing the trained three-dimensional geologic model to predict a plurality of prediction reservoir data obtained by the on-site underground reservoir under different flowback parameters in real time, calculating an optimal solution of all the prediction reservoir data and obtaining real-time adjustment parameters, and performing real-time adjustment according to the real-time adjustment parameters.

Description

Technical Field

[0001] The present invention belongs to the technical field of oil and gas development, and in particular relates to a real-time adjustment method and system for shale oil flowback strategy based on numerical simulation. Background Art

[0002] In shale oil or shale gas extraction, hydraulic fracturing is a technology used to increase the permeability of reservoirs. It uses high pressure to pump a large amount of water and sand (sometimes other types of proppants) containing chemical additives into underground rock cracks to expand existing cracks and form new fracture networks, so that oil and gas trapped in the rock can flow more freely to the wellbore. After fracturing, part of the fracturing fluid will return to the surface along with the oil and gas in the reservoir. This process is called fluid backflow.

[0003] Fluid flowback is not only the process of recovering the previously injected fracturing fluid, but also an important stage to start collecting the actual produced oil and gas. The flowback fluid mainly includes the initially injected fracturing fluid, the native fluid released from the reservoir (such as crude oil, condensate, natural gas), and possible groundwater.

[0004] At present, there are some challenges during fluid return. For example, if the return speed is too fast, it may cause sand plugging or damage the reservoir. On the contrary, if the return speed is too slow, it will affect the initial production. Therefore, it is necessary to adjust the fluid return strategy in real time. Summary of the invention

[0005] In view of the technical problems in the above-mentioned prior art that a too fast backflow speed may cause sand blockage or damage the reservoir; conversely, if the backflow is too slow, it will affect the initial production, the present invention provides a real-time adjustment method and system for shale oil backflow strategy based on numerical simulation.

[0006] The technical solution adopted by the present invention is as follows: A real-time adjustment method for shale oil flowback strategy based on numerical simulation, comprising: S1: acquiring original geological data, and establishing a three-dimensional geological model based on the original geological data; S2: Real-time monitoring of the on-site underground reservoir, and obtaining flow data and pressure data of the on-site underground reservoir, to obtain on-site reservoir data and its corresponding on-site flowback parameters; S3: training the three-dimensional geological model using the field reservoir data and the field flowback parameters to obtain a trained three-dimensional geological model; S4: using the trained three-dimensional geological model to predict in real time multiple predicted reservoir data of the on-site underground reservoir under different flowback parameters, calculating the optimal solution of all predicted reservoir data and obtaining real-time adjustment parameters, and adjusting the flowback parameters of the on-site underground reservoir based on the real-time adjustment parameters.

[0007] Furthermore, the above S1 specifically includes: Acquire original geological data, including seismic exploration data, drilling logs, well logging data, core sample analysis data, and fluid sample test data; Based on the original geological data, a computer graphics method is used to perform a three-dimensional spatial representation of the underground reservoir to obtain an initial geological model; The initial geological model is subjected to uncertainty processing to obtain a three-dimensional geological model.

[0008] Furthermore, in the above S2, the on-site reservoir data is acquired using various sensors installed in the on-site underground reservoir.

[0009] Furthermore, the above S3 specifically includes: S3.1: Obtain historical data of the on-site underground reservoir and its corresponding historical flowback parameters, and preprocess the historical data to obtain preprocessed data; wherein the historical data is the on-site reservoir data in S2, and the historical flowback parameters are the on-site flowback parameters in S2; S3.2: Extracting features from the preprocessed data to obtain feature data; S3.3: Simulating the fluid flow behavior of the three-dimensional geological model based on the historical flowback parameters, and training the three-dimensional geological model using the characteristic data to obtain a trained three-dimensional geological model.

[0010] Furthermore, the above S4 specifically includes: S4.1: Use the trained three-dimensional geological model to predict the underground reservoir in the field and obtain multiple prediction results under different flowback parameters; S42: defining an optimization function, wherein the optimization objectives of the optimization function include maximizing output, minimizing costs, and minimizing environmental impact; S4.3: input all prediction results into the optimization function to obtain the Pareto optimal solution; S4.4: Based on the flowback parameters corresponding to the Pareto optimal solution, adjust the flowback parameters in the field flowback strategy.

[0011] In a second aspect, the present invention further provides a real-time adjustment system for shale oil flowback strategy based on numerical simulation, comprising: A model building module, used to obtain original geological data and build a three-dimensional geological model based on the original geological data; A real-time monitoring module is used to monitor the on-site underground reservoir in real time, obtain the flow data and pressure data of the on-site underground reservoir, and obtain the on-site reservoir data and its corresponding on-site flowback parameters; A model training module, used to train the three-dimensional geological model using the field reservoir data and the field flowback parameters to obtain a trained three-dimensional geological model; The model prediction module is used to use the trained three-dimensional geological model to predict in real time multiple predicted reservoir data obtained under different return parameters of the on-site underground reservoir, calculate the optimal solution of all predicted reservoir data and obtain real-time adjustment parameters, and adjust the return parameters of the on-site underground reservoir based on the real-time adjustment parameters.

[0012] Furthermore, the above-mentioned model building module is specifically used for: Acquire original geological data, including seismic exploration data, drilling logs, well logging data, core sample analysis data, and fluid sample test data; Based on the original geological data, a computer graphics method is used to perform a three-dimensional spatial representation of the underground reservoir to obtain an initial geological model; The initial geological model is subjected to uncertainty processing to obtain a three-dimensional geological model.

[0013] Furthermore, in the above-mentioned real-time monitoring module, various sensors installed in the on-site underground reservoir are used to obtain the on-site reservoir data.

[0014] Furthermore, the above model training module is specifically used for: Acquire the historical data of the on-site underground reservoir and its corresponding historical flowback parameters, and preprocess the historical data to obtain preprocessed data; wherein the historical data is the on-site reservoir data in the real-time monitoring module, and the historical flowback parameters are the on-site flowback parameters in the real-time monitoring module; Performing feature extraction on the preprocessed data to obtain feature data; The fluid flow behavior of the three-dimensional geological model is simulated based on the historical flowback parameters, and the three-dimensional geological model is trained using the characteristic data to obtain a trained three-dimensional geological model.

[0015] Furthermore, the above model prediction module is specifically used for: Use the trained 3D geological model to predict multiple prediction results of the underground reservoir under different flowback parameters; An optimization function is defined, wherein the optimization objectives of the optimization function include maximizing output, minimizing costs, and minimizing environmental impact; Input all prediction results into the optimization function to obtain the Pareto optimal solution; Based on the flowback parameters corresponding to the Pareto optimal solution, the flowback parameters in the on-site flowback strategy are adjusted.

[0016] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention optimizes and analyzes the prediction results under different flowback parameters to find the Pareto optimal solution, thereby rationally configuring the flowback parameters to avoid problems caused by too fast or too slow flowback speed. The real-time monitoring and feedback mechanism enables the system to quickly respond to changes in reservoir conditions, adjust the flowback parameters in time, and maintain the optimal operating state.

[0017] 2. The uncertainty processing step is introduced in the process of constructing the three-dimensional geological model of the present invention, so that the three-dimensional geological model can better reflect the complexity and variability in the actual situation, and enhance the robustness of the model.

[0018] 3. The present invention obtains on-site reservoir data through various sensors installed in the reservoir, thereby ensuring the freshness and accuracy of the data and supporting subsequent model training and prediction.

[0019] 4. The present invention extracts features from data, highlights the most valuable information for model training, and improves the learning efficiency and generalization performance of the model.

[0020] 5. The present invention generates multiple prediction results according to different flowback parameters, which increases the reference range for decision-making and helps to identify the best solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative work, among which: Figure 1 It is a flow chart of a real-time adjustment method of shale oil flowback strategy based on numerical simulation provided according to an embodiment of the present invention.

[0022] Figure 2 It is a structural schematic diagram of a real-time adjustment system for shale oil flowback strategy based on numerical simulation provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Figure 1 A flow chart of a method for real-time adjustment of shale oil flowback strategy based on numerical simulation according to an embodiment of the present invention is shown. Figure 1 As shown, a real-time adjustment method of shale oil flowback strategy based on numerical simulation according to an embodiment of the present invention includes: S1: acquiring original geological data, and establishing a three-dimensional geological model based on the original geological data; S2: Real-time monitoring of the on-site underground reservoir, and obtaining flow data and pressure data of the on-site underground reservoir, to obtain on-site reservoir data and its corresponding on-site flowback parameters; S3: training the three-dimensional geological model using the field reservoir data and the field flowback parameters to obtain a trained three-dimensional geological model; S4: using the trained three-dimensional geological model to predict in real time multiple predicted reservoir data of the on-site underground reservoir under different flowback parameters, calculating the optimal solution of all predicted reservoir data and obtaining real-time adjustment parameters, and adjusting the flowback parameters of the on-site underground reservoir based on the real-time adjustment parameters.

[0025] Optionally, S1 specifically includes: Acquire original geological data, including seismic exploration data, drilling logs, well logging data, core sample analysis data, and fluid sample test data; In this embodiment, the seismic exploration data is seismic waves, and the speed difference of seismic wave propagation is used to infer the distribution of underground rocks and fluids. Through reflection wave imaging technology and inversion algorithm, high-resolution underground structure images can be constructed; logging data is logging curves such as conductivity, density, and acoustic wave velocity obtained in the wellbore, which are used to determine the physical properties of rocks around the wellbore and are combined with seismic data to calibrate the geological model; core sample analysis data is laboratory testing of core samples taken directly from the well to obtain measured parameters such as porosity, permeability, and saturation. These data are very important for correcting and verifying numerical simulations.

[0026] Based on the original geological data, a computer graphics method is used to perform a three-dimensional spatial representation of the underground reservoir to obtain an initial geological model; In this embodiment, a method such as Kriging or Sequential Gaussian Simulation (SGS) is used to interpolate irregularly distributed data points to generate a continuous attribute field (such as porosity and permeability).

[0027] The initial geological model is subjected to uncertainty processing to obtain a three-dimensional geological model.

[0028] Optionally, in S2, the field reservoir data is acquired using various sensors installed in the field underground reservoir.

[0029] In this embodiment, various sensors installed in the wellbore, wellhead, ground facilities and pipelines collect data of physical quantities (such as pressure, temperature, flow, vibration, gas composition, etc.) in real time. The sensors include: Pressure sensor: measures pressure changes in the well and on the surface.

[0030] Temperature sensor: monitors the temperature distribution of the wellbore and formation.

[0031] Flow meter: measures the flow rate and total amount of oil, gas and water.

[0032] Vibration sensor: detects the operating status of equipment and prevents mechanical failure.

[0033] Gas detectors: Identify harmful gas leaks and ensure safety.

[0034] Fiber Optic Sensing: Use distributed fiber optic sensing technology (DTS, DAS) to monitor temperature and acoustic activity in long well sections.

[0035] The data collected by the sensors is then transmitted to the central control system or cloud platform using wired or wireless communication networks.

[0036] Optionally, S3 specifically includes: S3.1: Obtain historical data of the on-site underground reservoir and its corresponding historical flowback parameters, and preprocess the historical data to obtain preprocessed data; wherein the historical data is the on-site reservoir data in S2, and the historical flowback parameters are the on-site flowback parameters in S2; S3.2: Extracting features from the preprocessed data to obtain feature data; S3.3: Simulating the fluid flow behavior of the three-dimensional geological model based on the historical flowback parameters, and training the three-dimensional geological model using the characteristic data to obtain a trained three-dimensional geological model.

[0037] In this embodiment, a discretization technique such as a finite difference method (FDM), a finite element method (FEM) or a finite volume method (FVM) is used to solve partial differential equations to simulate the underground fluid flow and heat conduction process. The heat conduction formula is:

[0038] Where T is temperature, t is time, α is thermal diffusion coefficient, and Q is heat source term.

[0039] The fluid flow in porous media is simulated using Darcy's law, which is expressed as follows:

[0040] Among them, q represents flow rate, k represents permeability, A represents cross-sectional area, μ represents fluid viscosity, △P represents pressure difference, and L represents flow path length.

[0041] Optionally, S4 specifically includes: S4.1: Use the trained three-dimensional geological model to predict the underground reservoir in the field and obtain multiple prediction results under different flowback parameters; S42: defining an optimization function, wherein the optimization objectives of the optimization function include maximizing output, minimizing costs, and minimizing environmental impact; S4.3: input all prediction results into the optimization function to obtain the Pareto optimal solution; S4.4: Based on the flowback parameters corresponding to the Pareto optimal solution, adjust the flowback parameters in the field flowback strategy.

[0042] In this embodiment, based on the final return flow parameters, PLC (Programmable Logic Controller), DCS (Distributed Control System) and other automation equipment are used to perform specific control tasks. And remote monitoring and operation are carried out through the SCADA system (Supervisory Control and Data Acquisition System) to improve efficiency and safety.

[0043] Based on Figure 1 Based on the same principle as the method shown in , the embodiment of the present invention also provides a real-time adjustment system for shale oil flowback strategy based on numerical simulation, such as Figure 2 As shown in, including: A model building module, used to obtain original geological data and build a three-dimensional geological model based on the original geological data; A real-time monitoring module is used to monitor the on-site underground reservoir in real time, obtain the flow data and pressure data of the on-site underground reservoir, and obtain the on-site reservoir data and its corresponding on-site flowback parameters; A model training module, used to train the three-dimensional geological model using the field reservoir data and the field flowback parameters to obtain a trained three-dimensional geological model; The model prediction module is used to use the trained three-dimensional geological model to predict in real time multiple predicted reservoir data obtained under different return parameters of the on-site underground reservoir, calculate the optimal solution of all predicted reservoir data and obtain real-time adjustment parameters, and adjust the return parameters of the on-site underground reservoir based on the real-time adjustment parameters.

[0044] Optionally, the model building module is specifically used for: Acquire original geological data, including seismic exploration data, drilling logs, well logging data, core sample analysis data, and fluid sample test data; In this embodiment, the seismic exploration data is seismic waves, and the speed difference of seismic wave propagation is used to infer the distribution of underground rocks and fluids. Through reflection wave imaging technology and inversion algorithm, high-resolution underground structure images can be constructed; logging data is logging curves such as conductivity, density, and acoustic wave velocity obtained in the wellbore, which are used to determine the physical properties of rocks around the wellbore and are combined with seismic data to calibrate the geological model; core sample analysis data is laboratory testing of core samples taken directly from the well to obtain measured parameters such as porosity, permeability, and saturation. These data are very important for correcting and verifying numerical simulations.

[0045] Based on the original geological data, a computer graphics method is used to perform a three-dimensional spatial representation of the underground reservoir to obtain an initial geological model; In this embodiment, a method such as Kriging or Sequential Gaussian Simulation (SGS) is used to interpolate irregularly distributed data points to generate a continuous attribute field (such as porosity and permeability).

[0046] The initial geological model is subjected to uncertainty processing to obtain a three-dimensional geological model.

[0047] Optionally, in the real-time monitoring module, various sensors installed in the on-site underground reservoir are used to obtain the on-site reservoir data.

[0048] In this embodiment, a method such as Kriging or Sequential Gaussian Simulation (SGS) is used to interpolate irregularly distributed data points to generate a continuous attribute field (such as porosity and permeability).

[0049] The initial geological model is subjected to uncertainty processing to obtain a three-dimensional geological model.

[0050] Optionally, in S2, the field reservoir data is acquired using various sensors installed in the field underground reservoir.

[0051] In this embodiment, various sensors installed in the wellbore, wellhead, ground facilities and pipelines collect data of physical quantities (such as pressure, temperature, flow, vibration, gas composition, etc.) in real time. The sensors include: Pressure sensor: measures pressure changes in the well and on the surface.

[0052] Temperature sensor: monitors the temperature distribution of the wellbore and formation.

[0053] Flow meter: measures the flow rate and total amount of oil, gas and water.

[0054] Vibration sensor: detects the operating status of equipment and prevents mechanical failure.

[0055] Gas detectors: Identify harmful gas leaks and ensure safety.

[0056] Fiber Optic Sensing: Use distributed fiber optic sensing technology (DTS, DAS) to monitor temperature and acoustic activity in long well sections.

[0057] The data collected by the sensors is then transmitted to the central control system or cloud platform using wired or wireless communication networks.

[0058] Optionally, the model training module is specifically used to: Acquire the historical data of the on-site underground reservoir and its corresponding historical flowback parameters, and preprocess the historical data to obtain preprocessed data; wherein the historical data is the on-site reservoir data in the real-time monitoring module, and the historical flowback parameters are the on-site flowback parameters in the real-time monitoring module; Performing feature extraction on the preprocessed data to obtain feature data; The fluid flow behavior of the three-dimensional geological model is simulated based on the historical flowback parameters, and the three-dimensional geological model is trained using the characteristic data to obtain a trained three-dimensional geological model.

[0059] Optionally, the model prediction module is specifically used to: Use the trained 3D geological model to predict multiple prediction results of the underground reservoir under different flowback parameters; An optimization function is defined, wherein the optimization objectives of the optimization function include maximizing output, minimizing costs, and minimizing environmental impact; Input all prediction results into the optimization function to obtain the Pareto optimal solution; Based on the flowback parameters corresponding to the Pareto optimal solution, the flowback parameters in the on-site flowback strategy are adjusted.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions and improvements made by any technician familiar with the field within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A real-time adjustment method for shale oil flowback strategy based on numerical simulation, characterized in that: include: S1: acquiring original geological data, and establishing a three-dimensional geological model based on the original geological data; S2: Real-time monitoring of the on-site underground reservoir, and obtaining flow data and pressure data of the on-site underground reservoir, to obtain on-site reservoir data and its corresponding on-site flowback parameters; S3: training the three-dimensional geological model using the field reservoir data and the field flowback parameters to obtain a trained three-dimensional geological model; S4: using the trained three-dimensional geological model to predict in real time multiple predicted reservoir data of the on-site underground reservoir under different flowback parameters, calculating the optimal solution of all predicted reservoir data and obtaining real-time adjustment parameters, and adjusting the flowback parameters of the on-site underground reservoir based on the real-time adjustment parameters.

2. A method for real-time adjustment of shale oil flowback strategy based on numerical simulation according to claim 1, characterized in that: S1 specifically includes: Acquire original geological data, including seismic exploration data, drilling logs, well logging data, core sample analysis data, and fluid sample test data; Based on the original geological data, a computer graphics method is used to perform a three-dimensional spatial representation of the underground reservoir to obtain an initial geological model; The initial geological model is subjected to uncertainty processing to obtain a three-dimensional geological model.

3. The method for real-time adjustment of shale oil flowback strategy based on numerical simulation according to claim 1, characterized in that: In S2, various sensors installed in the on-site underground reservoir are used to obtain the on-site reservoir data.

4. The method for real-time adjustment of shale oil flowback strategy based on numerical simulation according to claim 1, characterized in that: S3 specifically includes: S3.1: Obtain historical data of the on-site underground reservoir and its corresponding historical flowback parameters, and preprocess the historical data to obtain preprocessed data; wherein the historical data is the on-site reservoir data in S2, and the historical flowback parameters are the on-site flowback parameters in S2; S3.2: Extracting features from the preprocessed data to obtain feature data; S3.3: Simulating the fluid flow behavior of the three-dimensional geological model based on the historical flowback parameters, and training the three-dimensional geological model using the characteristic data to obtain a trained three-dimensional geological model.

5. A method for real-time adjustment of shale oil flowback strategy based on numerical simulation according to claim 4, characterized in that: S4 specifically includes: S4.1: Use the trained three-dimensional geological model to predict the underground reservoir in the field and obtain multiple prediction results under different flowback parameters; S42: defining an optimization function, wherein the optimization objectives of the optimization function include maximizing output, minimizing costs, and minimizing environmental impact; S4.3: input all prediction results into the optimization function to obtain the Pareto optimal solution; S4.4: Based on the flowback parameters corresponding to the Pareto optimal solution, adjust the flowback parameters in the field flowback strategy.

6. A real-time adjustment system for shale oil flowback strategy based on numerical simulation, characterized in that: include: A model building module, used to obtain original geological data and build a three-dimensional geological model based on the original geological data; A real-time monitoring module is used to monitor the on-site underground reservoir in real time, obtain the flow data and pressure data of the on-site underground reservoir, and obtain the on-site reservoir data and its corresponding on-site flowback parameters; A model training module, used to train the three-dimensional geological model using the field reservoir data and the field flowback parameters to obtain a trained three-dimensional geological model; The model prediction module is used to use the trained three-dimensional geological model to predict in real time multiple predicted reservoir data obtained under different return parameters of the on-site underground reservoir, calculate the optimal solution of all predicted reservoir data and obtain real-time adjustment parameters, and adjust the return parameters of the on-site underground reservoir based on the real-time adjustment parameters.

7. A shale oil flowback strategy real-time adjustment system based on numerical simulation according to claim 6, characterized in that: The model building module is specifically used for: Acquire original geological data, including seismic exploration data, drilling logs, well logging data, core sample analysis data, and fluid sample test data; Based on the original geological data, a computer graphics method is used to represent the underground reservoir in three dimensions to obtain an initial geological model; The initial geological model is subjected to uncertainty processing to obtain a three-dimensional geological model.

8. A shale oil flowback strategy real-time adjustment system based on numerical simulation according to claim 6, characterized in that: In the real-time monitoring module, various sensors installed in the on-site underground reservoir are used to obtain the on-site reservoir data.

9. A shale oil flowback strategy real-time adjustment system based on numerical simulation according to claim 6, characterized in that: The model training module is specifically used for: Acquire the historical data of the on-site underground reservoir and its corresponding historical flowback parameters, and preprocess the historical data to obtain preprocessed data; wherein the historical data is the on-site reservoir data in the real-time monitoring module, and the historical flowback parameters are the on-site flowback parameters in the real-time monitoring module; Performing feature extraction on the preprocessed data to obtain feature data; The fluid flow behavior of the three-dimensional geological model is simulated based on the historical flowback parameters, and the three-dimensional geological model is trained using the characteristic data to obtain a trained three-dimensional geological model.

10. A shale oil flowback strategy real-time adjustment system based on numerical simulation according to claim 6, characterized in that: The model prediction module is specifically used for: Use the trained 3D geological model to predict multiple prediction results of the underground reservoir under different flowback parameters; An optimization function is defined, wherein the optimization objectives of the optimization function include maximizing output, minimizing costs, and minimizing environmental impact; Input all prediction results into the optimization function to obtain the Pareto optimal solution; Based on the flowback parameters corresponding to the Pareto optimal solution, the flowback parameters in the on-site flowback strategy are adjusted.

Images