Method, device and equipment for regulating and controlling fracturing pump injection parameters

Abstract

The invention discloses a fracturing pump injection parameter regulation and control method, device and equipment. The method comprises the following steps: acquiring geological parameters of a target reservoir; based on the geological parameters, target fracturing pump injection parameters of the target reservoir are determined; determining a pump injection program corresponding to an oil-gas well of the target reservoir based on the target fracturing pump injection parameter, and performing fracturing pump injection based on the pump injection program; real-time fracturing fluid parameters in the fracturing pump injection process are collected, and well bottom sand bank form information of the target well is determined based on the real-time fracturing fluid parameters; and the target fracturing pump injection parameters are adjusted based on the well bottom sand bank form information, and fracturing pump injection is carried out based on the adjusted target fracturing pump injection parameters. By means of the method, the target fracturing pump injection parameters and the pump injection program conforming to the target reservoir can be automatically determined, the well bottom sand bank form information can be determined on the basis of the real-time fracturing fluid parameters, then real-time regulation and control and optimization of the fracturing pump injection parameters can be achieved, and the real-time performance, the intelligence and the accuracy of regulation and control of the fracturing site pump injection parameters are improved.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas development, and in particular to a method, device and equipment for controlling fracturing pumping parameters. Background Art

[0002] Hydraulic fracturing is an effective means of extracting crude oil. However, due to various factors, such as formation complexity and fluid properties, downhole conditions such as sand plugging often occur during fracturing operations. The current solution is for field operators to independently adjust parameters such as emulsion concentration, displacement, and sand concentration based on their experience. Limited by the experience of field personnel, two issues arise: first, the sand concentration during sand addition can sometimes be too high, causing sand plugging; second, the sand concentration can be too low, resulting in waste of fracturing fluid. The occurrence of downhole conditions and increased fracturing fluid usage significantly increase fracturing costs. Therefore, precise control of operation parameters such as sand and emulsion concentrations is of great practical significance for reducing costs and increasing efficiency.

[0003] Currently, some technical solutions use artificial intelligence models to learn from historical construction data to predict pressure fluctuations, providing early warning of fracturing anomalies or automatically adjusting injection rates based on field data and preset parameters. However, these methods are unable to accurately and quickly determine current pressure conditions, provide reliable construction recommendations, or achieve real-time, intelligent, and precise control and optimization of pumping parameters at the fracturing site.

[0004] Currently, no effective solution has been found to the above-mentioned problem of being unable to achieve real-time, intelligent and precise regulation and optimization of fracturing field pumping parameters. Summary of the Invention

[0005] The purpose of the embodiments of this specification is to provide a method, device and equipment for controlling fracturing pumping parameters to solve the problem of being unable to achieve real-time, intelligent and precise control and optimization of fracturing field pumping parameters.

[0006] To solve the above technical problems, the first aspect of this specification provides a method for controlling fracturing pumping parameters, comprising:

[0007] Obtain geological parameters of target reservoir;

[0008] Determining target fracturing pumping parameters for the target reservoir based on the geological parameters;

[0009] Determining a pumping program corresponding to an oil and gas well in the target reservoir based on the target fracturing pumping parameters, and performing fracturing pumping based on the pumping program;

[0010] Collecting real-time fracturing fluid parameters during the fracturing pumping process, and determining the bottom sand bank morphology information of the target well based on the real-time fracturing fluid parameters;

[0011] The target fracturing pumping parameters are adjusted based on the bottom hole sand bank morphology information, so as to perform fracturing pumping based on the adjusted target fracturing pumping parameters.

[0012] In some embodiments of this specification, determining target fracturing pumping parameters of the target reservoir based on the geological parameters includes:

[0013] Determine, based on the geological parameters, a historical reservoir whose similarity to the target reservoir meets a preset threshold, and obtain historical geological data and historical fracturing data of the historical reservoir;

[0014] The historical geological data and the historical fracturing data are input into a machine learning model for training, and the geological parameters are input into the trained machine learning model to obtain the target fracturing pumping parameters.

[0015] In some embodiments of this specification, determining a pumping program corresponding to an oil and gas well in the target reservoir based on the target fracturing pumping parameters includes:

[0016] Acquire sand carrying test data, wherein the sand carrying test data is obtained by simulating the settlement of fracturing fluid under different fracturing pumping parameters;

[0017] Determine a mapping relationship between a sedimentation threshold value and a fracturing pumping parameter under a critical sand carrying condition based on the sand carrying test data;

[0018] Based on the mapping relationship and the target fracturing pumping parameters, the pumping program is determined, and the pumping program includes a variation relationship between the target fracturing pumping parameters and the target fracturing pumping parameters.

[0019] In some embodiments of this specification, determining the bottomhole sand bank morphology information of the target well based on the real-time fracturing fluid parameters includes:

[0020] Obtaining wellbore parameters and fracture parameters of the target well;

[0021] The wellbore parameters, the fracture parameters, the target fracturing pumping parameters and the real-time fracturing fluid parameters are input into a pre-trained neural network model, and the bottom well sand bank morphology information is output.

[0022] In some embodiments of this specification, the neural network model is a physical information neural network model, which is trained in the following manner:

[0023] Obtain historical oil and gas well data, historical fracture data, historical fracturing data, historical fracturing fluid data, and historical sand bank morphology data of historical reservoirs;

[0024] Constructing an initial neural network model with wellbore parameters, fracture parameters, fracturing pumping parameters, and fracturing fluid parameters of the oil and gas well as model inputs and predicted well bottom sand bank morphology information as output, as well as a loss function of the initial neural network model;

[0025] Constructing physical constraint equations in the fracturing pumping process, wherein the physical constraint equations at least include a fluid mass conservation equation, a particle settling kinetics equation, and a fracture propagation model;

[0026] The physical constraint equation is used as the condition of the loss function, the historical oil and gas well data, the historical crack data, the historical fracturing data, and the historical fracturing fluid data are used as training input data, and the historical sand bank morphology data is used as training output to train the initial neural network model to obtain the physical information neural network model.

[0027] In some embodiments of the present specification, adjusting the target fracturing pumping parameters based on the bottom hole sand bank morphology information, and performing fracturing pumping based on the adjusted target fracturing pumping parameters, includes:

[0028] Analyze the morphological information of the well bottom sand bank to determine the current well bottom construction condition;

[0029] Adjusting the target fracturing pumping parameters based on the bottom hole construction conditions;

[0030] The control parameters of each fracturing pumping device are determined based on the adjusted target fracturing pumping parameters, and each fracturing pumping device is controlled based on the control parameters.

[0031] In some embodiments of the present specification, the real-time fracturing fluid parameters include at least the viscosity and sand ratio of the fracturing fluid.

[0032] A second aspect of this specification provides a fracturing pumping parameter control device, comprising:

[0033] An acquisition module, used to obtain geological parameters of the target reservoir;

[0034] A first determination module is configured to determine target fracturing pumping parameters of the target reservoir based on the geological parameters;

[0035] A pumping module, configured to determine a pumping program corresponding to the oil and gas well of the target reservoir based on the target fracturing pumping parameters, and perform fracturing pumping based on the pumping program;

[0036] A second determination module is used to collect real-time fracturing fluid parameters during the fracturing pumping process, and determine the bottom sand bank morphology information of the target well based on the real-time fracturing fluid parameters;

[0037] A control module is used to adjust the target fracturing pumping parameters based on the bottom hole sand bank morphology information, so as to perform fracturing pumping based on the adjusted target fracturing pumping parameters.

[0038] The third aspect of this specification provides an electronic device, comprising: a memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the steps of the method described in the first aspect by executing the computer instructions.

[0039] A fourth aspect of this specification provides a computer-readable storage medium, which stores computer program instructions. When the computer program instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0040] The fracturing pumping parameter control method, device and equipment provided in the embodiments of this specification obtain the geological parameters of the target reservoir; determine the target fracturing pumping parameters of the target reservoir based on the geological parameters; determine the pumping program corresponding to the oil and gas wells in the target reservoir based on the target fracturing pumping parameters, and perform fracturing pumping based on the pumping program; collect real-time fracturing fluid parameters during the fracturing pumping process, and determine the bottom hole sand bank morphology information of the target well based on the real-time fracturing fluid parameters; adjust the target fracturing pumping parameters based on the bottom hole sand bank morphology information, and perform fracturing pumping based on the adjusted target fracturing pumping parameters. Through the above method, the target fracturing pumping parameters and pumping program that meet the target reservoir can be automatically determined based on the geological parameters of the target reservoir. In addition, during the pressure pumping process, real-time fracturing fluid parameters can be collected, and the bottom hole sand bank morphology information of the target well can be determined based on the real-time fracturing fluid parameters. The bottom hole working conditions can be determined based on the bottom hole sand bank morphology information and the target fracturing pumping parameters can be adjusted to achieve real-time regulation and optimization of the fracturing pumping parameters, thereby improving the real-time, intelligence and accuracy of the fracturing field pumping parameter regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the implementation methods or the description of the prior art. Obviously, the drawings described below are only some implementation methods recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0042] Figure 1 Shown is a schematic diagram of a method for controlling fracturing pumping parameters provided in an embodiment of this specification;

[0043] Figure 2 FIG2 is a schematic diagram of a data transmission module provided in an embodiment of this specification;

[0044] Figure 3 Shown is a schematic diagram of sand carrying experimental data provided in the embodiments of this specification;

[0045] Figure 4 Shown is a schematic diagram of the pumping procedure provided in the embodiment of this specification;

[0046] Figure 5 The figure shows a schematic diagram of the sand bank at the bottom of a well provided in an embodiment of this specification;

[0047] Figure 6 Shown is a schematic diagram of a fracturing pumping parameter control device provided in an embodiment of this specification;

[0048] Figure 7 Shown is a schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the technical solutions in this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0050] As mentioned above, when controlling pressure parameters at the construction site, manual judgment of construction parameters such as viscosity and sand concentration is still required. When human judgment is wrong, the dry powder dosage is incorrectly adjusted, resulting in unreasonable viscosity settings, which can cause sand blockage or excess fluid, and cannot achieve real-time, intelligent, and precise regulation and optimization of fracturing site pumping parameters.

[0051] The embodiments of this specification provide a method for controlling fracturing pumping parameters, which can determine the target fracturing pumping parameters and pumping program of the target reservoir based on indoor experiments and machine learning, combined with the geological parameters of the target reservoir. When pressure pumping is performed based on the pumping program, real-time fracturing fluid parameters can be collected, and the bottom hole sand bank morphology information of the target well can be determined based on the real-time fracturing fluid parameters. The bottom hole working conditions can be determined based on the bottom hole sand bank morphology information and the target fracturing pumping parameters can be adjusted to achieve real-time control and optimization of the fracturing pumping parameters, thereby improving the real-time, intelligence and accuracy of the fracturing field pumping parameter control.

[0052] It is understood that the execution subject of each step of the method provided in the embodiments of the present application may be an electronic device, which refers to an electronic device with data calculation, processing and storage capabilities. The electronic device may be a terminal such as a personal computer (PC), a tablet computer, a smart phone, a wearable device, an intelligent robot, etc.; it may also be a server. Among them, the server may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0053] The following first introduces the method for controlling the parameters of the fracturing pumping provided in the embodiment of the present application with reference to the accompanying drawings.

[0054] Figure 1 Shown is a schematic diagram of the method for controlling the parameters of the fracturing pumping provided in the embodiment of this specification. Although this specification provides the method operation steps or device structure as shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial merger based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure is applied to an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiment or drawings (for example, in a parallel processor or multi-threaded processing environment, or even in a distributed processing, server cluster implementation environment). As Figure 1 As shown, the method may include:

[0055] S101: Obtain geological parameters of the target reservoir.

[0056] It can be understood that geological parameters are used to characterize the geological characteristics of the target reservoir. When reservoirs with different geological characteristics are subjected to fracturing and pumping, the applicable fracturing and pumping parameters are different. Based on the geological parameters of the target reservoir, a reservoir with similar geological characteristics to the target reservoir can be selected from historical reservoirs, and the target fracturing and pumping parameters of the target reservoir can be determined based on the historical fracturing data of the corresponding reservoir. Exemplarily, geological parameters may include reservoir depth, thickness, permeability, porosity, natural fracture density, rock mechanics parameters, and geostress field distribution. Furthermore, geological parameters can be obtained by logging the target reservoir, performing core experiments, seismic inversion, etc., or the geological parameters used in the fracturing process of adjacent oil and gas wells can be used as the geological parameters obtained in the above steps.

[0057] S102: Determine target fracturing pumping parameters of the target reservoir based on the geological parameters.

[0058] It can be understood that the target fracturing pumping parameters may include sand ratio, number of clusters, sand addition amount per cluster, liquid addition amount per cluster, etc.

[0059] It is understood that when determining target fracturing and pumping parameters for a target reservoir based on geological parameters, historical reservoirs similar to the target reservoir can be identified in conjunction with the geological parameters, and the target fracturing and pumping parameters can be determined based on historical fracturing data of the historical reservoirs. Specifically, the target fracturing and pumping parameters can be determined based on the determined historical fracturing data using data matching or machine learning methods.

[0060] In some embodiments of this specification, the target fracturing pumping parameters can be determined by data matching. Specifically, based on the geological parameters, determining the target fracturing pumping parameters of the target reservoir can include: calculating the similarity between the geological parameters and the historical geological parameters of the historical reservoirs in the database, and screening out the historical reservoirs corresponding to the historical geological parameters whose similarity meets a preset threshold (e.g., 90%, 95%, etc.), then obtaining the historical pumping data corresponding to the historical reservoirs from the database, and processing the historical pumping data to obtain the target fracturing pumping parameters. The processing of the historical pumping data can be, for example, taking an average value, a weighted average, etc., which is not limited by this specification.

[0061] In some embodiments of this specification, target fracturing and pumping parameters can be determined using machine learning methods. Specifically, determining the target fracturing and pumping parameters for the target reservoir based on the geological parameters may include: determining, based on the geological parameters, a historical reservoir whose similarity to the target reservoir meets a preset threshold, and obtaining historical geological data and historical fracturing data for the historical reservoir; inputting the historical geological data and historical fracturing data into a machine learning model for training, and inputting the geological parameters into the trained machine learning model to obtain the target fracturing and pumping parameters. Exemplary machine learning models may include, for example, random forest models, regression models, and the like.

[0062] In the embodiments of this specification, a machine learning model that matches the data features of historical fracturing data can be constructed based on the prediction scenario of the current fracturing pumping parameters, and the parameters corresponding to the acquired historical geological data can be used as input features, and the parameters corresponding to the historical fracturing data can be used as output features. The historical geological data corresponding to the input features can be used as training input, and the historical fracturing data corresponding to the output features can be used as the expected output of the training. Machine learning can then be performed based on the training input and the expected output, and the geological parameters of the target reservoir can be input into the trained machine learning model to obtain target fracturing pumping parameters suitable for the target reservoir.

[0063] In some embodiments of this specification, target pumping parameters may be determined not only in conjunction with geological parameters but also based on the geological parameters and the target fracture height and width of the target well to be obtained by the current fracturing of the target reservoir. Specifically, historical reservoir data may be obtained by matching the fracture height, fracture width, and geological parameters, and the target fracturing pumping parameters may be determined based on the historical pumping data of the target reservoir. The process for determining target fracturing pumping parameters based on historical pumping data can be described in the previous embodiments and will not be further elaborated here.

[0064] S103: Determine a pumping program corresponding to the oil and gas well of the target reservoir based on the target fracturing pumping parameters, and perform fracturing pumping based on the pumping program.

[0065] It can be understood that a pumping program is a set of detailed operating instructions and parameter settings used to guide the injection of fracturing fluid and proppant during hydraulic fracturing, in order to safely and efficiently form and maintain formation fractures and avoid abnormal operating conditions such as sand plugging. Specifically, parameters such as displacement, sand ratio, and viscosity during the fracturing pumping process can be specified based on the target fracturing pumping parameters. The fracturing pumping process can also be divided into stages, including the injection sequence of the pre-fluid, sand-carrying fluid, and displacement fluid. At the same time, the pressure during the fracturing pumping process can be controlled to determine the upper limit of the wellhead pressure to prevent overpressure of the equipment or formation.

[0066] In some embodiments of the present specification, determining the pumping program corresponding to the oil and gas wells in the target reservoir based on the target fracturing pumping parameters may include: obtaining sand-carrying experimental data, the sand-carrying experimental data being data obtained by simulating the sedimentation of fracturing fluid in the fracture under different fracturing pumping parameters; determining the mapping relationship between the sedimentation threshold under critical sand-carrying conditions and the fracturing pumping parameters based on the sand-carrying experimental data; and determining the pumping program based on the mapping relationship and the target fracturing pumping parameters, the pumping program including the relationship between the target fracturing pumping parameters and the sedimentation threshold under critical sand-carrying conditions.

[0067] Specifically, the sand-carrying experimental data may include proppant settlement under different displacements and sand ratios under set experimental fracture width, fracture height, number of clusters, viscosity, etc., and a mapping relationship can be determined based on the data to automatically generate a pumping program based on the mapping relationship and the target fracturing pumping parameters.

[0068] In the embodiments of this description, by combining experimental data with machine learning, the automatic generation of pumping programs can be achieved, the accuracy of fracturing pumping can be improved, the fracture morphology can be optimized, the proppant placement efficiency can be improved, and the risk of sand plugging can be reduced.

[0069] S104: collecting real-time fracturing fluid parameters during the fracturing pumping process, and determining bottomhole sand bank morphology information of the target well based on the real-time fracturing fluid parameters.

[0070] In some embodiments of the present specification, the real-time fracturing fluid parameters may include at least the viscosity and sand ratio of the fracturing fluid.

[0071] Specifically, viscosity can be measured in real time at the fracturing fluid outlet using a viscometer. This data can then be uploaded and used to predict the bottomhole sand bank morphology. Furthermore, the viscometer's real-time viscosity can include both kinematic and dynamic viscosities. Dynamic viscosity characterizes the fracturing fluid's ability to resist deformation, while kinematic viscosity characterizes its flow characteristics under gravity or inertia. By monitoring both dynamic and kinematic viscosities, more accurate information on the bottomhole sand bank morphology can be obtained.

[0072] Specifically, the sand ratio can be determined by real-time monitoring of the fracturing fluid at the fracturing fluid outlet using a densitometer. This data can then be uploaded for use in predicting the bottomhole sand bank morphology. Furthermore, the densitometer can measure the fracturing fluid density in real time, and the proppant mass in the fracturing fluid can be calculated based on the density, which can then be uploaded.

[0073] It can be understood that the above-mentioned real-time fracturing fluid parameters are an example in the embodiments of this specification. In other embodiments, the real-time fracturing fluid parameters may also include more or fewer parameters. For example, in addition to the above-mentioned viscosity and sand ratio, they may also include pressure, displacement, etc. The specific settings can be made in combination with the application scenario and application requirements, and corresponding sensors can be set at the outlet end for real-time collection of corresponding parameters.

[0074] In some embodiments of this specification, after real-time fracturing fluid parameters are collected, fracturing equipment can be controlled and adjusted based on the real-time fracturing fluid parameters. For example, when the viscosity is lower than or higher than a set viscosity, the metering pump of the distributor can be controlled to adjust the amount of dry powder added in real time; when the sand ratio is lower than or higher than a set sand ratio, the mass of sand entering the mixing tank can be controlled in real time.

[0075] In some embodiments of this specification, bottomhole sand bank morphology information can be represented by a bottomhole sand bank morphology image. The bottomhole sand bank morphology image can be predicted based on real-time fracturing fluid parameters. The image can then be analyzed to determine the current bottomhole operating conditions, allowing subsequent target fracturing and pumping parameters to be adjusted and optimized based on the current bottomhole operating conditions. It is understood that in other embodiments, bottomhole sand bank morphology information can be represented in other forms besides images, and this specification does not limit this.

[0076] In some embodiments of this specification, determining the bottomhole sand bank morphology information of a target well based on the real-time fracturing fluid parameters may include: obtaining wellbore parameters and fracture parameters of the target well; inputting the wellbore parameters, the fracture parameters, the target fracturing pumping parameters, and the real-time fracturing fluid parameters into a pre-trained neural network model, and outputting the bottomhole sand bank morphology information. Specifically, the wellbore parameters may include well depth and well diameter, and the fracture parameters may include fracture width and fracture height.

[0077] In some embodiments of the present specification, the neural network model is a physical information neural network model, which can be trained in the following manner: obtaining historical oil and gas well data, historical crack data, historical fracturing data, historical fracturing fluid data and historical sand bank morphology data of historical reservoirs; constructing an initial neural network model with the wellbore parameters, crack parameters, fracturing pumping parameters and fracturing fluid parameters of the oil and gas wells as model inputs, and the predicted bottom hole sand bank morphology information as output, as well as a loss function of the initial neural network model; constructing physical constraint equations in the fracturing pumping process, the physical constraint equations at least including the fluid mass conservation equation, the particle sedimentation kinetics equation, and the crack extension model; using the physical constraint equations as the conditions of the loss function, and training the initial neural network model with the historical oil and gas well data, the historical crack data, the historical fracturing data, and the historical fracturing fluid data as training input data, and the historical sand bank morphology data as training output to obtain the physical information neural network model.

[0078] In the embodiments of this specification, based on the physical information neural network model, by introducing physical constraint equation constraints into the neural network model, the model can not only fit experimental or field data, but also make the prediction results follow known physical laws. In addition, through the physical constraint equation constraints, in scenarios where data is scarce, the physical constraint equations can provide additional regularization for model predictions, reducing dependence on a large amount of labeled data. In addition, multi-physical field coupling can be achieved by simultaneously processing multiple interacting physical processes, including fluid flow, particle sedimentation, etc., thereby achieving rapid, accurate and reliable prediction of the sand bank morphology at the bottom of the well, reducing the risk of sand plugging, and saving fracturing fluid usage.

[0079] In some embodiments of the present specification, the physical information neural network model may include an input layer, a hidden layer, and an output layer. The input layer is used to receive physical parameters such as displacement, sand ratio, fracturing fluid viscosity, fracture height, fracture width, number of clusters, etc. The hidden layer can perform multi-layer nonlinear changes on the parameters received by the input layer, learn the complex mapping relationship between input and output, and the output layer can be used to predict the target variable. The output features of the output layer may include sand bank height distribution, proppant concentration profile, etc. The loss function constructed during the training process may include data-driven loss, such as the loss that measures the difference between the predicted value and the actual observed value, and may also include physical-driven loss, such as the residual of the physical constraint equation, and corresponding weight coefficients may be set for the data-driven loss and the physical-driven loss to balance data fitting and physical consistency.

[0080] S105: adjusting the target fracturing pumping parameters based on the bottom hole sand bank morphology information, and performing fracturing pumping based on the adjusted target fracturing pumping parameters.

[0081] It can be understood that the real-time operating conditions of the target well's bottom-hole fracturing pumping can be analyzed based on the bottom-hole sand bank morphology information. This information can then be used to adjust the target fracturing pumping parameters and conduct subsequent fracturing pumping based on the adjustment results. The real-time operating conditions analyzed can include, for example, whether the current bottom-hole sand bank morphology meets the expected sand filling requirements, whether the current displacement and sand ratio pose a risk of sand plugging, and the expected sand bank height and time when sand plugging occurs.

[0082] In some embodiments of the present specification, adjusting the target fracturing pumping parameters based on the bottom hole sand bank morphology information, and performing fracturing pumping based on the adjusted target fracturing pumping parameters, may include: analyzing the bottom hole sand bank morphology information to determine the current bottom hole construction conditions; adjusting the target fracturing pumping parameters based on the bottom hole construction conditions; determining the control parameters of each fracturing pumping device based on the adjusted target fracturing pumping parameters, and controlling each fracturing pumping device based on the control parameters. The fracturing pumping equipment may include a sand mixing vehicle, a liquid mixing vehicle, a density meter, a viscometer, an electric pump fracturing skid assembly, a dry powder mixing device, and the like. Furthermore, the control of the density meter and the viscometer may include controlling the frequency of data acquisition and uploading, and the control of the dry powder mixing device may include controlling the amount of dry powder added to the dry powder mixing device.

[0083] The present invention also provides a fracturing pumping control system that uses machine learning to autonomously determine the required fracturing fluid viscosity and sand concentration. Viscometers and densitometers monitor the actual viscosity and sand concentration in real time, issuing instructions and making decisions to adjust the fracturing fluid viscosity and sand concentration in real time. The system can include a central control system, an autonomous learning module, an early warning module, and a data transmission module.

[0084] The autonomous learning module can retrieve fracturing parameters from a database of similar blocks and determine whether the sand-to-liquid ratio and number of stages are reasonable based on the input data. If the autonomous learning module determines that the input data is unreasonable based on historical data, it will provide recommended construction data, including sand-to-liquid ratio, sand addition per cluster, liquid addition per cluster, and number of clusters. Based on the recommended construction data, the central control system can then automatically provide a pumping program.

[0085] Among them, the early warning module can obtain the mapping relationship between the sedimentation threshold and the fracturing pumping parameters under the critical sand-carrying conditions based on the indoor sand-carrying test data as the indoor sand-carrying test law, and then obtain the proppant sedimentation threshold. When the displacement, sand ratio and emulsion concentration are lower than the sand-carrying threshold, the central control system can autonomously give pumping program recommendations based on the sedimentation threshold.

[0086] After manually confirming the pumping program, enter the program and control each system to carry out construction according to the latest pumping program.

[0087] The autonomous learning module can also use PINN (Physics-Informed Neural Networks) for machine learning to predict the state of sand banks at the bottom of the well. PINN adds physical model constraints, which can greatly improve the accuracy of neural network predictions and significantly reduce the time required to obtain sand bank movement.

[0088] Furthermore, the autonomous learning module predicts the sand bank shape at the bottom of the well, and can determine the wellbore construction status. Based on the predictions, parameters such as sand ratio and displacement can be adjusted in real time to ensure that the sand addition strength meets the specified requirements. Furthermore, the early warning module can also issue a sand blockage warning based on the predicted sand bank shape at the bottom of the well, prompting users to reduce the sand ratio or increase the viscosity when the sand bank height rises rapidly.

[0089] refer to Figure 2 As shown, the data transmission module in the embodiment of this specification may include a sand blender, a liquid mixing vehicle, a densitometer, a viscometer, an electric pump fracturing skid group, and a control console.

[0090] Among them, the viscometer can monitor the kinematic viscosity and dynamic viscosity of the outlet end in real time, and input the data into the central control system in real time. When the viscosity is lower or higher than the set viscosity, the metering pump of the distributor is controlled to adjust the amount of dry powder added in real time.

[0091] The densitometer can monitor the sand ratio at the liquid outlet in real time. By measuring the density in real time, the density meter can calculate the mass of the proppant in the liquid and transmit the data to the central control system in real time. When the sand ratio is lower or higher than the set sand ratio, the mass of the sand entering the mixing tank is controlled in real time.

[0092] Furthermore, in order to ensure that the dry powder is more easily dissolved when using dry powder fracturing, the data transmission module can also include a dry powder mixing device. Specifically, the dry powder mixing device can include a distributor, a vibrating screen, a mixing tank, a sand tank and a dry powder tank; the distributor is 2m 3 There is a tank with a metering pump under the tank, which is connected to the control room and controls the amount of dry powder added through the central control system; the dry powder enters the vibrating screen so that it can enter the mixing tank evenly; the mixing tank is used to mix the fracturing fluid and make the proppant evenly distributed in the fracturing fluid; there is a booster pump at the inlet end to allow the dry powder to enter the mixing tank quickly and evenly.

[0093] The specific application process of the fracturing pump injection control system provided in the above embodiment will be further described below with reference to specific examples.

[0094] In the examples of this specification, fracturing fluid A was selected for indoor testing. Assuming the fracture width was 6 mm, the fracture height was 30 m, the number of clusters was 3, and the viscosity was 10 mPa·s, the experimental results can be shown as follows: Figure 3 As shown. Figure 3 It can be seen that under the condition of 10% sand ratio, the displacement is higher than 9m 3 / min, in order to avoid sand blockage; under the condition of 20% sand ratio, the displacement is higher than 13m 3 / min, in order to avoid sand blockage; under the condition of 30% sand ratio, the displacement is higher than 18m 3 / min, can avoid sand blockage.

[0095] Based on the historical data of the historical reservoir close to the target reservoir, the pump master program can be generated and combined with Figure 3 Based on the indoor experimental results, it is determined whether sand blockage occurs and the pumping program is adjusted. The final pumping program can be as follows Figure 4 shown.

[0096] During the pumping process, the viscosity and sand ratio of the fracturing fluid at the outlet can be collected in real time, and the sand bank prediction model obtained by PINN neural network training can be used to predict the shape of the sand bank at the bottom of the well. The predicted sand carrying results can be shown as follows: Figure 5 As shown, the prediction results can indicate that the sand carrying effect is good.

[0097] Based on the above-mentioned fracturing pumping parameter control method, one or more embodiments of this specification also provide a fracturing pumping parameter control device. The device may include a device (including a distributed system), software (application), module, plug-in, server, client, etc. that uses the method described in the embodiment of this specification and is combined with the necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived. Figure 6 The figure shows a schematic diagram of a fracturing pumping parameter control device provided in an embodiment of the present application. Figure 6 As shown, the fracturing pumping parameter control device 600 may include:

[0098] The acquisition module 601 is used to acquire geological parameters of the target reservoir.

[0099] The first determination module 602 is configured to determine target fracturing pumping parameters of the target reservoir based on the geological parameters.

[0100] The pumping module 603 is configured to determine a pumping program corresponding to the oil and gas wells in the target reservoir based on the target fracturing pumping parameters, and perform fracturing pumping based on the pumping program.

[0101] The second determination module 604 is configured to collect real-time fracturing fluid parameters during the fracturing pumping process, and determine the bottom hole sand bank morphology information of the target well based on the real-time fracturing fluid parameters.

[0102] The control module 605 is configured to adjust the target fracturing pumping parameters based on the bottom hole sand bank morphology information, so as to perform fracturing pumping based on the adjusted target fracturing pumping parameters.

[0103] In some embodiments of the present specification, the first determination module 602 can be specifically used to: determine a historical reservoir whose similarity with the target reservoir meets a preset threshold based on the geological parameters, and obtain historical geological data and historical fracturing data of the historical reservoir; input the historical geological data and the historical fracturing data into a machine learning model for training, and input the geological parameters into the trained machine learning model to obtain the target fracturing pumping parameters.

[0104] In some embodiments of the present specification, when the pumping module 603 determines the pumping program corresponding to the oil and gas wells of the target reservoir based on the target fracturing pumping parameters, it can be specifically used to: obtain sand-carrying experimental data, which is data obtained by simulating the sedimentation of fracturing fluid under different fracturing pumping parameters in the fracture; determine the mapping relationship between the sedimentation threshold under critical sand-carrying conditions and the fracturing pumping parameters based on the sand-carrying experimental data; determine the pumping program based on the mapping relationship and the target fracturing pumping parameters, and the pumping program includes the relationship between the target fracturing pumping parameters and the sedimentation threshold under critical sand-carrying conditions.

[0105] In some embodiments of the present specification, when the second determination module 604 determines the bottom hole sand bank morphology information of the target well based on the real-time fracturing fluid parameters, it can be specifically used to: obtain the wellbore parameters and fracture parameters of the target well; input the wellbore parameters, the fracture parameters, the target fracturing pumping parameters and the real-time fracturing fluid parameters into a pre-trained neural network model, and output the bottom hole sand bank morphology information.

[0106] In some embodiments of the present specification, the neural network model is a physical information neural network model, which is trained in the following manner: obtaining historical oil and gas well data, historical crack data, historical fracturing data, historical fracturing fluid data and historical sand bank morphology data of historical reservoirs; constructing an initial neural network model with the wellbore parameters, crack parameters, fracturing pumping parameters and fracturing fluid parameters of the oil and gas wells as model inputs, and the predicted bottom hole sand bank morphology information as output, as well as a loss function of the initial neural network model; constructing physical constraint equations in the fracturing pumping process, the physical constraint equations at least including the fluid mass conservation equation, the particle sedimentation kinetics equation, and the crack extension model; using the physical constraint equations as the conditions of the loss function, and training the initial neural network model with the historical oil and gas well data, the historical crack data, the historical fracturing data, and the historical fracturing fluid data as training input data, and the historical sand bank morphology data as training output to obtain the physical information neural network model.

[0107] In some embodiments of the present specification, the control module 605 can be specifically used to: analyze the bottom hole sand bank morphology information to determine the current bottom hole construction conditions; adjust the target fracturing pumping parameters based on the bottom hole construction conditions; determine the control parameters of each fracturing pumping equipment based on the adjusted target fracturing pumping parameters, and control each fracturing pumping equipment based on the control parameters.

[0108] In some embodiments of the present specification, the real-time fracturing fluid parameters include at least the viscosity and sand ratio of the fracturing fluid.

[0109] The description and functions of the above modules can be understood by referring to the content of the fracturing pump injection parameter control method part, which will not be repeated here.

[0110] The present application also provides an electronic device, such as Figure 7 As shown, the electronic device may include a processor 701 and a memory 702, wherein the processor 701 and the memory 702 may be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0111] The processor 701 may be a central processing unit (CPU). The processor 701 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0112] The memory 702 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the fracturing pumping parameter control method in the embodiment of the present invention (for example, Figure 6 The processor 701 executes the non-transient software programs, instructions, and modules stored in the memory 702, thereby executing various functional applications and data processing of the processor, that is, implementing the fracturing pumping parameter control method in the above method embodiment.

[0113] The memory 702 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created by the processor 701, etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 702 may optionally include a memory remotely located relative to the processor 701, and these remote memories may be connected to the processor 701 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0114] The one or more modules are stored in the memory 702 and, when executed by the processor 701, perform the following fracturing pumping parameter control method:

[0115] Acquire geological parameters of a target reservoir; determine target fracturing and pumping parameters of the target reservoir based on the geological parameters; determine a pumping program corresponding to an oil and gas well in the target reservoir based on the target fracturing and pumping parameters, and perform fracturing and pumping based on the pumping program; collect real-time fracturing fluid parameters during the fracturing and pumping process, and determine bottomhole sand bank morphology information of the target well based on the real-time fracturing fluid parameters; adjust the target fracturing and pumping parameters based on the bottomhole sand bank morphology information, and perform fracturing and pumping based on the adjusted target fracturing and pumping parameters.

[0116] The specific details of the above electronic device can be understood by referring to the corresponding descriptions and effects in the above method embodiments, and will not be repeated here.

[0117] This specification also provides a computer storage medium, wherein the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the above-mentioned fracturing pumping parameter control method are implemented.

[0118] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The storage medium can also include a combination of the above-mentioned types of memory.

[0119] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0120] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0121] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0122] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute certain parts of the methods of each embodiment of the present application.

[0123] The present application can be used in a wide variety of general-purpose or specialized computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments that include any of the above.

[0124] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0125] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Those skilled in the art will readily appreciate that various modifications and variations to the embodiments of this specification are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this specification shall be within the scope of protection of this specification.

Claims

1. A method for controlling fracturing pumping parameters, characterized in that: include: Obtain geological parameters of target reservoir; Determining target fracturing pumping parameters for the target reservoir based on the geological parameters; Determining a pumping program corresponding to an oil and gas well in the target reservoir based on the target fracturing pumping parameters, and performing fracturing pumping based on the pumping program; Collecting real-time fracturing fluid parameters during the fracturing pumping process, and determining the bottom sand bank morphology information of the target well based on the real-time fracturing fluid parameters; The target fracturing pumping parameters are adjusted based on the bottom hole sand bank morphology information, so as to perform fracturing pumping based on the adjusted target fracturing pumping parameters.

2. The method for controlling fracturing pumping parameters according to claim 1, characterized in that: Determining target fracturing pumping parameters of the target reservoir based on the geological parameters includes: Determine, based on the geological parameters, a historical reservoir whose similarity to the target reservoir meets a preset threshold, and obtain historical geological data and historical fracturing data of the historical reservoir; The historical geological data and the historical fracturing data are input into a machine learning model for training, and the geological parameters are input into the trained machine learning model to obtain the target fracturing pumping parameters.

3. The method for controlling fracturing pumping parameters according to claim 1, wherein: Determining a pumping program corresponding to an oil and gas well in the target reservoir based on the target fracturing pumping parameters includes: Acquire sand carrying test data, wherein the sand carrying test data is obtained by simulating the settlement of fracturing fluid under different fracturing pumping parameters; Determine a mapping relationship between a sedimentation threshold value and a fracturing pumping parameter under a critical sand carrying condition based on the sand carrying test data; Based on the mapping relationship and the target fracturing pumping parameters, the pumping program is determined, and the pumping program includes a variation relationship between the target fracturing pumping parameters and the target fracturing pumping parameters.

4. The method for controlling fracturing pumping parameters according to claim 1, wherein: Determining the bottom sand bank morphology information of the target well based on the real-time fracturing fluid parameters includes: Obtaining wellbore parameters and fracture parameters of the target well; The wellbore parameters, the fracture parameters, the target fracturing pumping parameters and the real-time fracturing fluid parameters are input into a pre-trained neural network model, and the bottom well sand bank morphology information is output.

5. The method for controlling fracturing pumping parameters according to claim 4, characterized in that: The neural network model is a physical information neural network model, which is trained in the following way: Obtain historical oil and gas well data, historical fracture data, historical fracturing data, historical fracturing fluid data, and historical sand bank morphology data of historical reservoirs; Constructing an initial neural network model with wellbore parameters, fracture parameters, fracturing pumping parameters, and fracturing fluid parameters of the oil and gas well as model inputs and predicted well bottom sand bank morphology information as output, as well as a loss function of the initial neural network model; Constructing physical constraint equations in the fracturing pumping process, wherein the physical constraint equations at least include a fluid mass conservation equation, a particle settling kinetics equation, and a fracture propagation model; The physical constraint equation is used as the condition of the loss function, the historical oil and gas well data, the historical crack data, the historical fracturing data, and the historical fracturing fluid data are used as training input data, and the historical sand bank morphology data is used as training output to train the initial neural network model to obtain the physical information neural network model.

6. The method for controlling fracturing pumping parameters according to claim 1, wherein: Adjusting the target fracturing pumping parameters based on the bottom well sand bank morphology information, and performing fracturing pumping based on the adjusted target fracturing pumping parameters, including: Analyze the morphological information of the well bottom sand bank to determine the current well bottom construction condition; Adjusting the target fracturing pumping parameters based on the bottom hole construction conditions; The control parameters of each fracturing pumping device are determined based on the adjusted target fracturing pumping parameters, and each fracturing pumping device is controlled based on the control parameters.

7. The method for controlling fracturing pumping parameters according to claim 1, characterized in that: The real-time fracturing fluid parameters include at least the viscosity and sand ratio of the fracturing fluid.

8. A fracturing pumping parameter control device, characterized in that: include: An acquisition module, used to obtain geological parameters of the target reservoir; A first determination module is configured to determine target fracturing pumping parameters of the target reservoir based on the geological parameters; A pumping module, configured to determine a pumping program corresponding to the oil and gas well of the target reservoir based on the target fracturing pumping parameters, and perform fracturing pumping based on the pumping program; A second determination module is used to collect real-time fracturing fluid parameters during the fracturing pumping process, and determine the bottom sand bank morphology information of the target well based on the real-time fracturing fluid parameters; A control module is used to adjust the target fracturing pumping parameters based on the bottom hole sand bank morphology information, so as to perform fracturing pumping based on the adjusted target fracturing pumping parameters.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the steps of the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images