Coupling flow simulation and comprehensive pressure drop characterization method, device and equipment of inflow control valve and medium

Abstract

The invention discloses a coupling flow simulation and comprehensive pressure drop characterization method, device and equipment of an inflow control valve and a medium, and relates to the technical field of computers. Establishing a multi-phase flow motion differential equation set of the separate mining shaft, and quantifying a coupling criterion; an initial coupling flow simulation model is obtained according to the separated mining shaft multiple coupling grid, the separated mining shaft multiphase flow motion differential equation set and the coupling criterion; training the initial coupling flow simulation model according to a drifting model key coefficient inversion method to obtain a target coupling flow simulation model; simulating pressure drop conditions under different production parameters based on the target coupling flow simulation model to obtain a pressure drop sample, and constructing an inflow control valve comprehensive pressure drop proxy model based on the pressure drop sample by utilizing a machine learning algorithm; simulation is achieved based on the target coupling flow simulation model, and pressure drop representation is achieved based on the inflow control valve comprehensive pressure drop proxy model. The accuracy of simulation and pressure drop characterization can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a coupled flow simulation and comprehensive pressure drop characterization method, device, equipment and medium for an inflow control valve. Background Art

[0002] Due to the complexity of the well completion section, inflow control device (ICD), and multiphase flow in the wellbore, the characteristic parameters of the production wellbore are constantly changing and uncertain. It is impossible to accurately describe the transient flow process in the wellbore and accurately characterize the influence of fluid and process parameters on oil and gas wellbore flow and the interaction mechanism.

[0003] Current research on multiphase flow in complex oil and gas wellbores considers the completion section, control tools, pump, and wellbore sections separately. For example, one study used CFD technology to simulate the flow characteristics of the rectangular groove gap seal structure in a pumping plunger pump, revealing the flow resistance mechanism and the rational design of the seal structure parameters. Another study applied the drift model (DFM) and Euler particle model to the aforementioned CFD erosion model to predict the erosion rate within the electric pump. Other studies investigated pump stage performance, flow patterns within the impeller of a rotary electric submersible pump, and pressure surge under varying gas-liquid flow rates, suction pressures, and rotational speeds. Some researchers have also proposed a transient multiphase flow model based on DFM to analyze the changing trends of liquid holdup, pressure, and temperature upstream and downstream of the wellhead valve, as well as at the bottom of the well and within the separator.

[0004] Furthermore, coupled modeling of the flow within complex wellbores, including completions, ICDs, pumps, and wellbore sections, building a unified grid system, and numerically solving transient flows has become a current and future research paradigm. Some studies have developed isothermal, multicomponent wellbore models based on the drift model (DFM) to investigate the coupling process between the wellbore and the reservoir. Other studies have considered the phase changes of fluids during non-isothermal gas lift, developing component multiphase flow models based on the DFM to analyze the phase changes within the wellbore and simulate the distribution of the wellbore pressure field during gas lift. Other researchers have also developed component multiphase flow models based on the DFM and coupled them with the reservoir to simulate the transient process of wellbore liquid loading during gas well production, while also using the model to predict gas well productivity. Furthermore, some studies have developed a dynamic coupled reservoir-wellbore-lifting equipment model to simulate the dynamic coupling between the reservoir, wellbore, and lifting equipment, enabling simulation and sensitivity analysis of four common lifting methods: beam pumping, surface-driven progressive cavity pumping, electric submersible pumping, and gas lift. Other researchers have used a commercial dynamic multiphase flow simulator (OLGA) to study the interaction between reservoir inflow, wellbore flow, and operating parameters in electric pump wells.

[0005] However, with the development of unconventional oil and gas reservoirs and the need for fine stratified exploitation of high-water-content reservoirs, production tubing strings are becoming increasingly complex. Complex flow control tools such as downhole inflow control valves, Y-tubes, tees, and reducers interfere with wellbore flow, causing the physical properties, flow patterns, and even phase state of multiphase fluids to become more complex. This makes it impossible to simulate multiphase flow in production wellbores and accurately characterize the process and laws of wellbore pressure drop changes.

[0006] In summary, how to improve the accuracy of multiphase flow simulation and pressure drop characterization in production wellbore is an urgent problem to be solved. Summary of the Invention

[0007] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for coupled flow simulation and comprehensive pressure drop characterization of an inflow control valve, which can improve the accuracy of multiphase flow simulation and pressure drop characterization in a separate production wellbore. The specific scheme is as follows:

[0008] In a first aspect, the present application discloses a coupled flow simulation and integrated pressure drop characterization method for an inflow control valve, comprising:

[0009] Constructing a multi-coupling grid for a production wellbore; the multi-coupling grid for a production wellbore is a grid for realizing coupled flow of multiphase fluids through a plurality of downhole inflow control valves;

[0010] Establishing a differential equation group of multiphase flow motion in the production wellbore, and quantifying a coupling criterion based on the coupling flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore;

[0011] Obtaining an initial coupled flow simulation model according to the multiple coupled grids of the production wellbore, the differential equations of multiphase flow motion in the production wellbore, and the coupling criterion;

[0012] Training the initial coupled flow simulation model according to a drift model key coefficient inversion method and using the real-time observation data of the wellbore to obtain a target coupled flow simulation model;

[0013] Based on the target coupled flow simulation model, the pressure drop conditions under different production parameters are simulated to obtain pressure drop samples. A machine learning algorithm is used to train a model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model.

[0014] Optionally, the step of constructing a multi-coupling grid for separate production wellbores includes:

[0015] Based on a general grid construction method, a multi-coupled grid for a production wellbore is constructed hierarchically; the multi-coupled grid for the production wellbore includes networks corresponding to the downhole inflow control valve area, the pump barrel area, and the wellbore area; the multi-coupled grid for the production wellbore is a hierarchical unstructured grid and a three-dimensional radial grid.

[0016] Optionally, the differential equations for multiphase flow motion in the production wellbore include a gas phase continuity equation and a liquid phase continuity equation corresponding to the downhole inflow control valve and a gas-liquid mixed phase momentum equation corresponding to the wellbore.

[0017] Optionally, the quantitative coupling criterion based on the coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore includes:

[0018] Adjust the flow pressure by adjusting the opening of the downhole inflow control valve;

[0019] Based on the adjusted inflow parameters and in accordance with the principle of conservation of energy and the target state equation, a coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore is determined, and a coupling criterion is quantified based on the coupled flow mechanism; the adjusted inflow parameters include flow pressure and opening; and the target state equation is an IPR state equation or an SKR state equation.

[0020] Optionally, the step of training the initial coupled flow simulation model according to the drift model key coefficient inversion method and using the real-time observation data of the wellbore to obtain the target coupled flow simulation model includes:

[0021] The drift model key coefficients are inverted according to the drift model key coefficient inversion method and the ensemble Kalman filter and the real-time observation data of the wellbore are used to train the initial coupled flow simulation model until the data accuracy of the model output meets the preset accuracy to obtain the target coupled flow simulation model.

[0022] Optionally, the using a machine learning algorithm and training a model based on the pressure drop samples to construct an inflow control valve integrated pressure drop proxy model includes:

[0023] A machine learning algorithm is used to train a model based on the pressure drop samples until a temporary proxy model that meets predetermined requirements is obtained, and the temporary proxy model is used as the comprehensive pressure drop proxy model of the inflow control valve; wherein the predetermined requirements are that the root mean square error between the model prediction value and the true value is the maximum value among all temporary proxy models, and the R-squared is the minimum value among all temporary proxy models.

[0024] In a second aspect, the present application discloses a coupled flow simulation and integrated pressure drop characterization device for an inflow control valve, comprising:

[0025] A grid construction module is used to construct a multi-coupling grid for a production wellbore; the multi-coupling grid for a production wellbore is a grid for realizing coupled flow of multiphase fluids through a number of downhole inflow control valves;

[0026] An equation group establishment module is used to establish a differential equation group for multiphase flow motion in the production wellbore and quantify a coupling criterion based on the coupling flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore;

[0027] A first model building module is used to obtain an initial coupled flow simulation model based on the multiple coupled grids of the production wellbore, the differential equations of multiphase flow motion in the production wellbore, and the coupling criterion;

[0028] A model training module is used to train the initial coupled flow simulation model according to a drift model key coefficient inversion method and using the real-time observation data of the wellbore to obtain a target coupled flow simulation model;

[0029] The second model construction module is used to simulate the pressure drop conditions under different production parameters based on the target coupled flow simulation model to obtain pressure drop samples, and use a machine learning algorithm and train a model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model.

[0030] Optionally, the grid construction module is specifically used to hierarchically construct a multi-coupled grid of a production wellbore based on a general grid construction method; the multi-coupled grid of the production wellbore includes networks corresponding to the downhole inflow control valve area, the pump barrel area and the wellbore area; the multi-coupled grid of the production wellbore is a hierarchical unstructured grid and a three-dimensional radial grid.

[0031] In a third aspect, the present application discloses an electronic device, comprising:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve disclosed above.

[0034] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve disclosed above.

[0035] It can be seen that the present application constructs a multi-coupling grid for a production wellbore; the multi-coupling grid for a production wellbore is a grid for realizing the coupled flow of multiphase fluids through a number of downhole inflow control valves; a group of differential equations for the motion of multiphase flow in the production wellbore is established, and a coupling criterion is quantified based on the coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore; an initial coupled flow simulation model is obtained according to the multi-coupling grid for the production wellbore, the group of differential equations for the motion of multiphase flow in the production wellbore and the coupling criterion; the initial coupled flow simulation model is trained according to the drift model key coefficient inversion method and the real-time observation data of the wellbore to obtain a target coupled flow simulation model; the pressure drop conditions under different production parameters are simulated based on the target coupled flow simulation model to obtain pressure drop samples, and a machine learning algorithm is used to train the model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model. It can be seen that the present application quantifies the coupling criteria to improve the accuracy of the model; the present application uses the drift model key coefficient inversion method to train the model to further improve the accuracy of the model; in addition, the inflow control valve comprehensive pressure drop proxy model in the present application is constructed on the basis of the target coupled flow simulation model. On the basis of improving the accuracy of the target coupled flow simulation model, it is believed that the accuracy of the inflow control valve comprehensive pressure drop proxy model is also improved; in summary, the present application can improve the accuracy of multiphase flow simulation and pressure drop characterization in the production wellbore. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0037] Figure 1 This is a flow chart of a coupled flow simulation and comprehensive pressure drop characterization method for an inflow control valve disclosed in this application;

[0038] Figure 2 This is a schematic diagram of the flow of a separate production wellbore disclosed in this application;

[0039] Figure 3 This is a schematic diagram of a local mixed flow simulation of an ICD oil pipe section disclosed in this application;

[0040] Figure 4 This is a schematic diagram of the transformation, formation and development process of a local flow pattern in an oil pipe after mixed flow disclosed in this application;

[0041] Figure 5A schematic diagram of a wellbore multi-coupled grid disclosed in this application;

[0042] Figure 6 This is a schematic diagram of an inflow node of an inflow control device disclosed in this application;

[0043] Figure 7 A schematic diagram of an inversion process disclosed in this application;

[0044] Figure 8 A schematic diagram of a process for establishing a comprehensive pressure drop proxy model disclosed in this application;

[0045] Figure 9 This is a schematic structural diagram of a coupled flow simulation and comprehensive pressure drop characterization device for an inflow control valve disclosed in this application;

[0046] Figure 10 This is a structural diagram of an electronic device disclosed in the application. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making creative efforts are within the scope of protection of the present invention.

[0048] With the development of unconventional oil and gas reservoirs and the need for fine-separated production of high-water-cut reservoirs, production tubing strings are becoming increasingly complex. Complex flow control tools such as downhole inflow control valves (ICDs), Y-tubes, tees, and reducers interfere with wellbore flow, causing more complex changes in the physical properties, flow patterns, and even phase states of multiphase fluids. This makes it impossible to simulate multiphase flow in production wellbores and accurately characterize the process and laws of wellbore pressure drop changes.

[0049] To this end, the embodiment of the present application proposes a coupled flow simulation and comprehensive pressure drop characterization scheme for an inflow control valve, which can improve the accuracy of multiphase flow simulation and pressure drop characterization in a production wellbore.

[0050] The present application discloses a coupled flow simulation and integrated pressure drop characterization method for an inflow control valve. Figure 1 As shown, the method includes:

[0051] Step S11: constructing a multi-coupling grid of a production wellbore; the multi-coupling grid of the production wellbore is a grid that realizes the coupled flow of multiphase fluids through a number of downhole inflow control valves.

[0052] The working principle of the electric pump lift well is as follows: the oil and gas multiphase fluid in the formation flows into the oil pipe through the downhole flow control valve ICD, is pressurized by the electric submersible centrifugal pump, and is discharged to the wellhead nozzle to reduce the pressure and enter the production pipeline. The flow in the production wellbore is as follows: Figure 2 As shown, Figure 2 This is a schematic diagram of the flow of a production wellbore, which includes ICD, separator, data cable, power cable, Y connector, and submersible electric pump. It should be pointed out that under complex wellbore conditions, coupling the inflow dynamics, wellbore dynamics, fluid characteristics and process is the key to improving wellbore flow prediction. In order to simulate the lifting process of the formation fluid from the electric pump production well through the ICD from the oil pipe to the submersible pump and then to the wellhead fluid, a transient model and numerical simulation method considering the coupled flow of multiphase fluids with ICD disturbance are proposed to simulate the dynamic changes of temperature, pressure, flow rate, flow pattern, liquid holdup and pressure drop of multiphase fluids flowing into the ICD and merging into the wellbore with time under different production parameters. For details, see Figure 3 and Figure 4 As shown in the figure, combined with the actual ICD structure and the combination of completion strings, considering the influence of complex wellbore and multiphase fluid, the local flow pattern transformation, formation and development process of multiphase fluids with different components, physical properties, flow rates and ICD structures in the production section of the oil pipe are studied. Specifically, Figure 3 This is a schematic diagram of a local mixed flow simulation of an ICD oil pipe section. The figure shows the implementation of the local mixed flow simulation, which includes the upper joint, test subject, switch valve, high-temperature motor, connecting pipe, circuit compartment, and lower joint. Figure 4 This is a schematic diagram of the transformation, formation, and development of local flow patterns in the tubing after mixing. The figure partially shows the downhole inflow control valve, tubing, and packer. Q1, Q2, and Q3 represent ICD inflows. The figure includes three parts. The middle part has local turbulence. After mixing, the fluid flow rate / flow pattern undergoes a relatively large disturbance, the flow rate increases, and the flow patterns in the upper and lower parts are fully developed.

[0053] In this embodiment, the construction of the multi-coupled grid of the production wellbore includes: hierarchically constructing the multi-coupled grid of the production wellbore based on a general grid construction method; the multi-coupled grid of the production wellbore includes networks corresponding to the downhole inflow control valve area, the pump barrel area and the wellbore area; the multi-coupled grid of the production wellbore is a hierarchical unstructured grid and a three-dimensional radial grid.

[0054] It should be pointed out that the current multi-coupled grid modeling of the production distributor inflow control valve ICD-pump barrel-wellbore has a large coupling span and cannot effectively deal with the contradiction between the large-scale pipe flow in the wellbore, the mesoscale flow in the downhole pump barrel, and the small-scale flow in the production distributor inflow valve. This application is based on a general grid construction method and constructs grids hierarchically to form a multi-scale grid system of hierarchical unstructured grids, three-dimensional radial grids, ICD and pump barrel area-three-dimensional wellbore grids; the wellbore multi-coupled grids are as follows: Figure 5 As shown, Figure 5 This is a schematic diagram of a multi-coupled wellbore mesh. The mesh is a local partial mesh. The local wellbore section includes the tubing, annulus, packer, and wellbore wall. The cross-section shows the direction of radial flow and axial flow in the tubing. The mesh includes ICD, tubing nodes, annulus nodes, and boundary nodes.

[0055] Step S12: establishing a differential equation group of multiphase flow motion in the production wellbore, and quantifying a coupling criterion based on the coupling flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore.

[0056] It should be noted that in order to simulate multiphase flow in wellbores numerically, the classical set of fluid dynamics conservation equations (mass and momentum of each phase and energy balance) is combined into a coupled nonlinear system of partial differential equations. The calculations of these models are based on the identified flow patterns, and their transition criteria can be explicitly applied based on the intermediate results of the simulation, or they can be solved implicitly together with the momentum equations used. The complex wellbore flow dynamics simulator in this study is based on a mechanistic model that includes a set of momentum equations for each continuous liquid (water and oil) and gas phase; the governing equations for the VOF model regarding the multiphase flow simulation calculation are as follows:

[0057] Volume fraction equation:

[0058] ;

[0059] in, is the density of the qth phase, in kg / m 3 ;for The velocity of the qth phase, in m / s; is the mass transfer from the qth phase to the pth phase; Mass transfer from phase p to phase q; is the source term, which defaults to zero and can also be set to a constant or user-defined mass source term.

[0060] Momentum equation:

[0061] ;

[0062] in, is the speed, m / s; is the velocity transposed matrix; is the acceleration due to gravity, m / s 2 ; is the body force, N; is the pressure difference, Pa.

[0063] Energy equation:

[0064] ;

[0065] in, is the density in kg / m 3 ; is energy, unit is J; is the speed in m / s; is pressure, unit is Pa; T is temperature, unit is ℃; is the effective thermal conductivity, in units of ; is the source phase of the energy equation, including thermal radiation and some other heat sources.

[0066] The differential equations for multiphase flow in the separate production wellbore include the gas and liquid continuity equations corresponding to the downhole inflow control valve, and the gas-liquid mixed phase momentum equation corresponding to the wellbore. Specifically, the differential equations for multiphase flow in the separate production oil and gas lift wellbore are established, taking into account the excitation effects of the ICD production controller and wellbore coordinated parameters. Furthermore, the gas and liquid continuity equations, as well as the gas-liquid mixed phase momentum equation in the wellbore, are established, taking into account the coupled flow characteristics between the downhole inflow control device (ICD) and the wellbore.

[0067] Gas phase continuity equation:

[0068] ;

[0069] Liquid continuity equation:

[0070] ;

[0071] The gas-liquid mixed phase momentum equation corresponding to the wellbore:

[0072] ;

[0073] in, is the gas phase density, in kg / m 3 ; is the liquid density, in kg / m 3 ; is the gas phase coefficient, dimensionless; is the liquid phase volume coefficient, dimensionless; is the gas phase velocity, in m / s; is the liquid phase flow rate, in m / s; t is the time, in s; x is the spatial length, in m; p is the pressure, in Pa; is the gravity component, the unit is Pa / m; is the flow resistance component, and its unit is Pa / m.

[0074] In this embodiment, the quantitative coupling criterion based on the coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore includes: adjusting the flow pressure by adjusting the opening of the downhole inflow control valve; determining the coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore based on the adjusted inflow parameters and according to the principle of conservation of energy and the target state equation, and quantifying the coupling criterion based on the coupled flow mechanism; the adjusted inflow parameters include flow pressure and opening; the target state equation is an IPR state equation or an SKR state equation.

[0075] It should be pointed out that the study of the multi-ICD inflow boundary and wellbore coupled flow mechanism and the quantitative coupling criteria are required; for details, see Figure 6 As shown in the figure, it is a schematic diagram of an inflow node of an inflow control device; by adjusting the ICD opening and adjusting the flow pressure, the liquid production of each reservoir in the completion section can be finely controlled. Figure 6 As shown in the figure, by adjusting the ICD opening to adjust the flow pressure, the liquid production of each reservoir in the completion section can be finely controlled. The mouth pressure is known to be , ICD opening is When the produced fluid ICD flows into the tubing, according to the principle of energy conservation, the following relationship is satisfied: 1. The pressure before the nozzle is (flow pressure) With pressure behind the mouth The pressure difference is 2. Pressure difference , output liquid volume 、ICD opening Satisfy the pressure loss constraint; the output fluid is , satisfying the formation inflow dynamics, i.e. IPR; formation temperature ,pressure According to the state equation, the liquid-gas and liquid compressibility factors are: 、 According to the above coupling relationship between formation and ICD, the connection equation between ICD nodes is determined, where the compressibility factor of gas and liquid phases is related to the flow pressure. and formation temperature The connection equations are shown as follows:

[0076] .

[0077] Step S13: obtaining an initial coupled flow simulation model according to the multiple coupled grids of the production wellbore, the differential equations of multiphase flow motion in the production wellbore, and the coupling criterion.

[0078] Step S14: training the initial coupled flow simulation model according to the drift model key coefficient inversion method and using the real-time observation data of the wellbore to obtain a target coupled flow simulation model.

[0079] In this embodiment, the target coupled flow simulation model is obtained by training the initial coupled flow simulation model according to the drift model key coefficient inversion method and using the real-time observation data of the wellbore, including: inverting the drift model key coefficients according to the drift model key coefficient inversion method and the ensemble Kalman filter and training the initial coupled flow simulation model using the real-time observation data of the wellbore until the target coupled flow simulation model is obtained when the data accuracy of the model output meets the preset accuracy.

[0080] It should be noted that see Figure 7 As shown in the figure, it is a schematic diagram of the inversion process; in the figure, based on the intelligent monitoring system of electric pump production wells, the measured data and the simulation model are integrated, the key coefficients of the drift model are inverted using the ensemble Kalman filter (ENKF), and a real-time data and simulation model feedback mechanism is established to improve the model simulation accuracy.

[0081] Step S15: Based on the target coupled flow simulation model, the pressure drop conditions under different production parameters are simulated to obtain pressure drop samples, and a machine learning algorithm is used to train a model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model.

[0082] In this embodiment, the method of using a machine learning algorithm and training a model based on the pressure drop samples to construct an inflow control valve integrated pressure drop proxy model includes: using a machine learning algorithm and training a model based on the pressure drop samples until a temporary proxy model that meets predetermined requirements is obtained, and using the temporary proxy model as the inflow control valve integrated pressure drop proxy model; wherein the predetermined requirements are that the root mean square error (RMSE) between the model prediction value and the true value is the maximum value among all temporary proxy models, and the R-squared (R 2 ) is the minimum value among all temporary agent models.

[0083] It should be pointed out that this application proposes a comprehensive pressure drop prediction model for diverted mixed flow in production wellbore based on deep learning of CFD simulation samples. The diverted mixed flow simulation model established above is used to simulate the dynamic changes of temperature, pressure, flow rate, flow pattern, liquid holdup, and pressure drop of multiphase fluid flowing into ICD and entering the oil pipe under different production parameters. The CNN algorithm is used to establish an agent model for calculating the comprehensive pressure drop of diverted mixed flow. The agent model establishment process is as follows: Figure 8As shown in FIG, a schematic diagram of a process for establishing a comprehensive pressure drop proxy model is shown; first, a virtual sample of a separated ICD turning mixed flow is established through ICD flow modeling and multi-phase simulation software, and an actual test sample of ICD flow pressure drop is obtained through ICD permanent cable test data. A sample library of a separated ICD turning mixed flow comprehensive pressure drop is obtained based on the virtual sample of the separated ICD turning mixed flow and the actual test sample of ICD flow pressure drop, the main control privacy affecting the comprehensive pressure drop is determined, and a machine learning algorithm training model is optimized, and finally an ICD flow comprehensive pressure drop proxy model that meets the predetermined requirements is obtained; it should be pointed out that the main control factors affecting the comprehensive pressure drop can be analyzed by evaluating the importance of parameter features through Pearson correlation analysis, and the main control factors affecting the comprehensive pressure drop can also be analyzed through LightGBM (Light Gradient Boosting Machine, extremely fast lightweight gradient boosting machine), XGBoost (extreme Gradient Boosting, gradient boosting algorithm), LR (logistic regression, logistic regression), RF (random forest), BP neural network (Back Propagation Neural Network, based on error back propagation algorithm), CNN (Convolutional Neural Network, convolutional neural network), LSTM (Long Short-Term Memory, a special type of recurrent neural network) to train the model to obtain the ICD flow comprehensive pressure drop proxy model.

[0084] In summary, due to the complexity of the multiphase flow in the completion section, inflow control device, and wellbore of the production well, the characteristic parameters of the production wellbore are constantly changing and uncertain, making it impossible to accurately describe the process of transient flow in the wellbore, and unable to accurately characterize the influence of fluid and process parameters on the flow of oil and gas wellbore and the interaction mechanism. Therefore, a method for implementing transient simulation of multiphase flow diversion mixing in production wellbore and a method for characterizing comprehensive pressure loss are proposed. By using the drift model (DFM), the flow distribution coefficient and drift velocity in the DFM are corrected, and a multiphase inflow transient simulation model of ICD in multiple layers of downhole sections is established. A comprehensive pressure loss prediction model for diversion mixing flow in production wellbore based on deep learning of CFD simulation samples is proposed, forming a method for characterizing local energy loss at ICD and oil pipes, which can improve the accuracy of multiphase flow simulation and pressure drop characterization in production wellbore.

[0085] It can be seen that the present application constructs a multi-coupling grid for a production wellbore; the multi-coupling grid for a production wellbore is a grid for realizing the coupled flow of multiphase fluids through a number of downhole inflow control valves; a group of differential equations for the motion of multiphase flow in the production wellbore is established, and a coupling criterion is quantified based on the coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore; an initial coupled flow simulation model is obtained according to the multi-coupling grid for the production wellbore, the group of differential equations for the motion of multiphase flow in the production wellbore and the coupling criterion; the initial coupled flow simulation model is trained according to the drift model key coefficient inversion method and the real-time observation data of the wellbore to obtain a target coupled flow simulation model; the pressure drop conditions under different production parameters are simulated based on the target coupled flow simulation model to obtain pressure drop samples, and a machine learning algorithm is used to train the model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model. It can be seen that the present application quantifies the coupling criteria to improve the accuracy of the model; the present application uses the drift model key coefficient inversion method to train the model to further improve the accuracy of the model; in addition, the inflow control valve comprehensive pressure drop proxy model in the present application is constructed on the basis of the target coupled flow simulation model. On the basis of improving the accuracy of the target coupled flow simulation model, it is believed that the accuracy of the inflow control valve comprehensive pressure drop proxy model is also improved; in summary, the present application can improve the accuracy of multiphase flow simulation and pressure drop characterization in the production wellbore.

[0086] Correspondingly, the embodiment of the present application also discloses a coupled flow simulation and comprehensive pressure drop characterization device for an inflow control valve, see Figure 9 As shown, the device includes:

[0087] A grid construction module 11 is used to construct a multi-coupling grid for production wellbore; the multi-coupling grid for production wellbore is a grid for realizing multiphase fluid coupling flow through a number of downhole inflow control valves;

[0088] An equation group establishment module 12 is used to establish a differential equation group of multiphase flow motion in the production wellbore and quantify a coupling criterion based on the coupling flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore;

[0089] A first model building module 13 is configured to obtain an initial coupled flow simulation model based on the multiple coupled grids of the production wellbore, the differential equations of multiphase flow motion in the production wellbore, and the coupling criterion;

[0090] A model training module 14 is configured to train the initial coupled flow simulation model according to a drift model key coefficient inversion method and utilize the real-time observation data of the wellbore to obtain a target coupled flow simulation model;

[0091] The second model construction module 15 is used to simulate the pressure drop conditions under different production parameters based on the target coupled flow simulation model to obtain pressure drop samples, and use a machine learning algorithm and train a model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model.

[0092] Among them, the more specific working processes of the above modules can refer to the corresponding contents disclosed in the above embodiments, which will not be repeated here.

[0093] It can be seen that the present application constructs a multi-coupling grid for a production wellbore; the multi-coupling grid for a production wellbore is a grid for realizing the coupled flow of multiphase fluids through a number of downhole inflow control valves; a group of differential equations for the motion of multiphase flow in the production wellbore is established, and a coupling criterion is quantified based on the coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore; an initial coupled flow simulation model is obtained according to the multi-coupling grid for the production wellbore, the group of differential equations for the motion of multiphase flow in the production wellbore and the coupling criterion; the initial coupled flow simulation model is trained according to the drift model key coefficient inversion method and the real-time observation data of the wellbore to obtain a target coupled flow simulation model; the pressure drop conditions under different production parameters are simulated based on the target coupled flow simulation model to obtain pressure drop samples, and a machine learning algorithm is used to train the model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model. It can be seen that the present application quantifies the coupling criteria to improve the accuracy of the model; the present application uses the drift model key coefficient inversion method to train the model to further improve the accuracy of the model; in addition, the inflow control valve comprehensive pressure drop proxy model in the present application is constructed on the basis of the target coupled flow simulation model. On the basis of improving the accuracy of the target coupled flow simulation model, it is believed that the accuracy of the inflow control valve comprehensive pressure drop proxy model is also improved; in summary, the present application can improve the accuracy of multiphase flow simulation and pressure drop characterization in the production wellbore.

[0094] Furthermore, an embodiment of the present application also provides an electronic device. Figure 10 The structure diagram of the electronic device 20 is shown according to an exemplary embodiment. The content in the diagram should not be considered as any limitation to the scope of application of the present application.

[0095] Figure 10A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps of the coupled flow simulation and integrated pressure drop characterization method for an inflow control valve disclosed in any of the aforementioned embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0096] In this embodiment, the power supply 26 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and the external device. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this application and is not specifically limited here; the input and output interface 24 is used to obtain external input data or output data to the outside world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0097] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, a magnetic disk, or an optical disk, etc. The resources stored thereon can include a computer program 221, which can be stored in a temporary or permanent manner. In addition to including a computer program capable of performing the coupled flow simulation and integrated pressure drop characterization method for an inflow control valve performed by the electronic device 20 as disclosed in any of the aforementioned embodiments, the computer program 221 can further include computer programs capable of performing other specific tasks.

[0098] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve disclosed above.

[0099] The specific steps of the method can be referred to the corresponding contents disclosed in the above embodiments, and will not be repeated here.

[0100] The various embodiments in this application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part.

[0101] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0102] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0103] Finally, it should be noted that, in this document, relational terms such as first and first are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0104] The above is a detailed introduction to the coupled flow simulation and comprehensive pressure drop characterization method, device, equipment, and storage medium of a flow control valve provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A coupled flow simulation and comprehensive pressure drop characterization method for an inflow control valve, characterized in that: include: Constructing a multi-coupling grid for a production wellbore; the multi-coupling grid for a production wellbore is a grid for realizing coupled flow of multiphase fluids through a plurality of downhole inflow control valves; Establishing a differential equation group of multiphase flow motion in the production wellbore, and quantifying a coupling criterion based on the coupling flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore; Obtaining an initial coupled flow simulation model according to the multiple coupled grids of the production wellbore, the differential equations of multiphase flow motion in the production wellbore, and the coupling criterion; Training the initial coupled flow simulation model according to a drift model key coefficient inversion method and using the real-time observation data of the wellbore to obtain a target coupled flow simulation model; Based on the target coupled flow simulation model, the pressure drop conditions under different production parameters are simulated to obtain pressure drop samples. A machine learning algorithm is used to train a model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model.

2. The coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve according to claim 1, characterized in that: The construction of the multiple coupled grids of the production wellbore comprises: Based on a general grid construction method, a multi-coupled grid for a production wellbore is constructed hierarchically; the multi-coupled grid for the production wellbore includes networks corresponding to the downhole inflow control valve area, the pump barrel area, and the wellbore area; the multi-coupled grid for the production wellbore is a hierarchical unstructured grid and a three-dimensional radial grid.

3. The coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve according to claim 1, characterized in that: The differential equations for multiphase flow motion in the production wellbore include a gas phase continuity equation and a liquid phase continuity equation corresponding to the downhole inflow control valve and a gas-liquid mixed phase momentum equation corresponding to the wellbore.

4. The coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve according to claim 1, characterized in that: The quantitative coupling criterion based on the coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore includes: Adjust the flow pressure by adjusting the opening of the downhole inflow control valve; Based on the adjusted inflow parameters and in accordance with the principle of conservation of energy and the target state equation, a coupled flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore is determined, and a coupling criterion is quantified based on the coupled flow mechanism; the adjusted inflow parameters include flow pressure and opening; and the target state equation is an IPR state equation or an SKR state equation.

5. The coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve according to claim 1, characterized in that: The method of inverting the key coefficients of the drift model and using the real-time observation data of the wellbore to train the initial coupled flow simulation model to obtain the target coupled flow simulation model includes: The drift model key coefficients are inverted according to the drift model key coefficient inversion method and the ensemble Kalman filter and the real-time observation data of the wellbore are used to train the initial coupled flow simulation model until the data accuracy of the model output meets the preset accuracy to obtain the target coupled flow simulation model.

6. The coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve according to claim 1, characterized in that: The method of using a machine learning algorithm and training a model based on the pressure drop samples to construct an inflow control valve integrated pressure drop proxy model includes: A machine learning algorithm is used to train a model based on the pressure drop samples until a temporary proxy model that meets predetermined requirements is obtained, and the temporary proxy model is used as the comprehensive pressure drop proxy model of the inflow control valve; wherein the predetermined requirements are that the root mean square error between the model prediction value and the true value is the maximum value among all temporary proxy models, and the R-squared is the minimum value among all temporary proxy models.

7. A coupled flow simulation and comprehensive pressure drop characterization device for an inflow control valve, characterized in that: include: A grid construction module is used to construct a multi-coupling grid for a production wellbore; the multi-coupling grid for a production wellbore is a grid for realizing coupled flow of multiphase fluids through a number of downhole inflow control valves; An equation group establishment module is used to establish a differential equation group for multiphase flow motion in the production wellbore and quantify a coupling criterion based on the coupling flow mechanism between the inflow boundary of the downhole inflow control valve and the wellbore; A first model building module is used to obtain an initial coupled flow simulation model based on the multiple coupled grids of the production wellbore, the differential equations of multiphase flow motion in the production wellbore, and the coupling criterion; A model training module is used to train the initial coupled flow simulation model according to a drift model key coefficient inversion method and using the real-time observation data of the wellbore to obtain a target coupled flow simulation model; The second model construction module is used to simulate the pressure drop conditions under different production parameters based on the target coupled flow simulation model to obtain pressure drop samples, and use a machine learning algorithm and train a model based on the pressure drop samples to construct an inflow control valve comprehensive pressure drop proxy model, so as to realize simulation based on the target coupled flow simulation model and realize pressure drop characterization based on the inflow control valve comprehensive pressure drop proxy model.

8. The coupled flow simulation and comprehensive pressure drop characterization device for an inflow control valve according to claim 7, characterized in that: The grid construction module is specifically used to hierarchically construct a multi-coupled grid for a production wellbore based on a general grid construction method; the multi-coupled grid for the production wellbore includes networks corresponding to the downhole inflow control valve area, the pump barrel area, and the wellbore area; the multi-coupled grid for the production wellbore is a hierarchical unstructured grid and a three-dimensional radial grid.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that Used to store a computer program; wherein, when the computer program is executed by a processor, the coupled flow simulation and comprehensive pressure drop characterization method of the inflow control valve according to any one of claims 1 to 6 is implemented.

Images