A method for predicting the shut-in time of a self-flowing well and a method for optimizing the size of a choke

Abstract

The application discloses a self-flowing well stop spraying time prediction method and a choke size optimization method. The prediction of the stop spraying time fully considers the time-varying influence of reservoirs, wellbores, wellheads and fluid physical property parameters, and the choke size of the oil well obtained on the basis is the optimal choke size (the longest self-flowing oil production period is obtained on the basis of the maximum cumulative oil production) for achieving the optimization target according to the actual production dynamics of the well. The application overcomes the shortcomings in the traditional method that the wellbore and reservoir parameters are considered as static parameters and thus long-term prediction of the self-flowing well dynamic analysis cannot be performed, and overcomes the shortcomings that the adjustment of the choke size of the oil well during the self-flowing period depends on the experience of people and the artificial workload is large.

Description

Technical Field

[0001] This invention relates to the field of oil extraction technology, specifically to a method for predicting the shutdown time of a flowing well and a method for optimizing the size of the nozzle. Background Technology

[0002] Predicting the shutdown time of flowing wells and optimizing well production regimes based on production needs is crucial. Optimized single-well production regimes can extend the flowing production period or maximize cumulative oil production during the flowing production period. In the early stages of oilfield development, abundant formation energy allows wells to flow. However, as production increases, formation pressure decreases and water cut rises, eventually causing the well to stop flowing. At this point, appropriate artificial lift methods are needed. Scientific prediction of well flowout time provides support for adjusting lift modes and ensuring normal operation. Furthermore, accurate prediction of well shutdown time under actual production conditions such as oilfield production and export restrictions, and optimization of well operating regimes to prevent premature shutdown, are of great significance in the initial design of oilfield development plans and in reservoir dynamic analysis after production commences.

[0003] Currently, the main methods for predicting the shutdown time of flowing wells, both domestically and internationally, are: minimum bottom hole flowing pressure method, minimum wellhead oil pressure method, and minimum formation pressure prediction method.

[0004] For the minimum formation pressure method, uncertainties exist in formation pressure prediction, reservoir energy changes, and pipeline flow model selection. Yang Junzheng (2019)'s "Research on Prediction Method of Stoppage Time of Flowing Wells in Halfaya Oilfield" is based on multiphase pipeline flow and nodal analysis technology, and simultaneously considers water cut and formation pressure changes to predict the stoppage time of flowing wells. This method considers the formation pressure of the oil well as having a linear relationship with time, and only considers the change of water cut in the formation pressure prediction of stoppage, without considering the changes in oil well production and fluid properties.

[0005] For the minimum bottomhole flowing pressure method, uncertainties exist in aspects such as the selection of pipe flow formulas and models. The lack of reservoir data and the inaccuracy of numerical simulation results directly affect the prediction results. Huang Bingguang (1997), in "Practical Reservoir Engineering and Dynamic Analysis Methods," considered water cut, fluid density, crude oil volume coefficient, reservoir depth, degassing point depth, friction coefficient, and crude oil saturation pressure to establish an empirical formula for calculating the shut-off flowing pressure of vertical wells suitable for Chinese reservoirs. He then combined this with the prediction of bottomhole flowing pressure to calculate the shut-off time. This method uses empirical formulas to calculate the shut-off flowing pressure of vertical wells, which significantly limits its application. Furthermore, since the bottomhole flowing pressure prediction is based on production trends at a specific time, there is considerable uncertainty in predictions for longer periods. Liu Xiangping's "Establishing a Bottom-Flow Pressure Prediction Model for Flowing Wells Using Neural Networks" and Gong Jingjing's "Application of BP Neural Network in Bottom-Flow Pressure Prediction of Flowing Wells" utilize the highly nonlinear mapping capability of neural networks to predict bottom-flow pressure by training the relationship between characteristic parameters such as nozzle, depth, oil production, gas production, water production, oil pressure, casing pressure, and crude oil density and the measured values ​​of bottom-flow pressure. However, this method depends on the quality and quantity of training samples and makes it difficult to establish the relationship between bottom-flow pressure prediction and stop-flow time prediction.

[0006] The minimum wellhead pressure method is only applicable to specific nozzle sizes. Wang Qinghua's "Prediction of Well Stoppage Time in the Ahdeb Oilfield, Iraq" considers an exponential decrease in wellhead oil pressure over time with a constant nozzle size, and derives the well stoppage time by fitting the wellhead pressure decrease trend. However, since wellhead pressure is affected by production allocation, the method considering an exponential decrease is not typical.

[0007] Therefore, none of the above methods can predict the stop-flow time of a flowing well in the long term based on the dynamic analysis of the flowing well, and they cannot overcome the disadvantages of relying on human experience and the large amount of manual work required for adjusting the size of the nozzle during the oil well's flow period. Summary of the Invention

[0008] The purpose of this invention is to provide a method for predicting the shutdown time of a flowing well and an optimization method for nozzle size. This method fully considers the influence of formation pressure, water cut, gas-oil ratio, fluid properties, tubing friction, and production index. Based on the time-varying inflow dynamic curve and time-varying pressure loss along the flow path, it predicts the shutdown time of the well under the current nozzle. Combining the longest self-flowing period and the single-well cumulative oil production target, it automatically obtains the optimized nozzle size for well production. This method overcomes the shortcomings of traditional methods that consider wellbore and reservoir parameters as static parameters and cannot make long-term predictions for the dynamic analysis of flowing wells. It also overcomes the shortcomings of nozzle size adjustment during the self-flowing period of oil wells relying on human experience and having a large amount of manual work.

[0009] To achieve the above-mentioned technical objectives, the present invention is implemented through the following technical solution:

[0010] A method for predicting the shutdown time of a flowing well includes the following steps:

[0011] (1) Fit the oil well pressure test data at different times to obtain the uncertain parameters of wellbore and fluid properties at different test times. , This represents the total number of tests.

[0012] (2) Based on the fitted values ​​of uncertain parameters at different test times obtained in step (1), analyze the relationship between cumulative oil production and uncertain parameters, and establish a prediction model for uncertain parameters of the target well;

[0013] (3) Based on the principle of material balance, establish a regression model between formation pressure and cumulative fluid production for the calculation and prediction of formation pressure in oil wells;

[0014] (4) Combine the target well uncertainty parameter prediction model and the actual production data of the oil well to accurately calculate the bottom pressure of the oil well at different times. Then, combine the real-time prediction of the formation pressure of the oil well to calculate the historical production capacity index of the oil well and establish the oil well production capacity index prediction model.

[0015] (5) By combining historical data on water cut of oil wells, a regression equation is established to obtain a water cut prediction model for oil wells;

[0016] (6) Combining the prediction models obtained in steps (2), (3), (4) and (5), establish a dynamic model of oil well inflow under different cumulative production to calculate the bottom pressure of oil wells under different cumulative oil production. Then, combine the uncertain parameters of wellbore and fluid properties to establish a prediction model of oil well head pressure under different cumulative production to calculate the oil well head pressure under different oil production under the corresponding cumulative oil production. Combine the nozzle flow model to solve the prediction model of the stop-blowing time to obtain the oil well stop-blowing time.

[0017] Furthermore, the oil well pressure test data at different times mentioned in step (1) above includes pressure profiles. Temperature profile and fluid density profile Step (1) further includes a wellbore profile calculation model. Calculation model based on wellbore profile Establish deterministic parameters The uncertain parameters of wellbore and fluid properties at different test times were optimized using the following Bayesian optimization formula. Optimization and adjustments will be made:

[0018]

[0019] in: , , These are the weights of the fitting loss function for the pressure profile, temperature profile, and fluid density profile, respectively. , , , represent the given parameters in the i-th test. and ,according to The pressure profile, temperature profile, and fluid density profile obtained from the model calculation.

[0020] Furthermore, the above optimized uncertain parameters and the Cumulative oil production during this test By performing fitting, the prediction model for the uncertain parameters of the target well is obtained as follows: ,in The cumulative oil production obtained through the regression equation With uncertainty parameters The function.

[0021] Furthermore, the regression model between formation pressure and cumulative fluid production in step (3) is as follows:

[0022]

[0023] in Equations were fitted using actual oil well production data. get; Mean formation pressure, in psi; Initial formation pressure, in psi; The well control radius is in meters (m). Porosity is a dimensionless quantity. The thickness of the perforation is in meters (m). The overall compression factor is expressed in units of... , This is the bottom hole flowing pressure, measured in psi.

[0024] Furthermore, based on the prediction model of uncertain parameters With determined real-time production parameters Calculation model based on wellbore profile Obtain historical data of bottom hole flowing pressure in oil wells Then, by combining the regression model between formation pressure and cumulative fluid production with actual oil production data, the real-time production index of oil wells is calculated. To obtain the capacity index prediction model ,in This is a capacity index, in units of... ; Through The series of data obtained by regression and The function.

[0025] Furthermore, the oil well water cut prediction model in step (5) is as follows: ,in and These are the slope and intercept, respectively, and in production, they are both fitting parameters for early-stage oil well data.

[0026] Furthermore, in step (6), the inflow dynamic model of oil wells under different cumulative production is the Petrobras three-phase flow inflow dynamic model. The corresponding oil well inflow dynamic curve is plotted by calculating the bottom hole pressure of oil wells under different cumulative oil production. ,in Bottom hole flowing pressure, in psi; For oil production, per unit ;

[0027] The wellhead pressure prediction model combines the well water cut prediction model, the uncertain parameter prediction model, and the wellbore profile calculation model. Calculate the wellhead pressure of oil wells at different production rates under the corresponding cumulative oil production. And plot the wellhead pressure curve of the oil well. ;

[0028] The nozzle flow model is as follows: Taking the logarithm of both sides yields... , To produce a gas-oil ratio, For the size of the nozzle, Moisture content, , , and Oil wellhead pressure Oil-to-gas production ratio Oil nozzle size Oil production and moisture content Parameters obtained by fitting historical production data, plus moisture content Both the gas-oil ratio (GOR) and the production oil ratio are functions of the cumulative oil recovery; therefore, the nozzle flow model formula can be written as: ;

[0029] The prediction model for the stop-spray time is as follows: Get the current nozzle size Stop spraying time ,in, The unit is psi, representing the minimum wellhead pressure required for external transmission.

[0030] After combining the predicted well shut-off time and single-well cumulative oil production target based on the above technical solutions, an optimization model for the nozzle size of the well shut-off is established to obtain the optimized nozzle size.

[0031] Furthermore, the optimization model for the nozzle size of the oil well to stop flow is as follows: Used to obtain the maximum cumulative oil production Output optimized oil well nozzle size.

[0032] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0033] This invention provides a method for predicting the shutdown time of a flowing well. This method fully considers the influence of formation pressure, water cut, gas-oil ratio, fluid properties, tubing friction, and production index. Based on the time-varying inflow dynamic curve and time-varying pressure loss along the flow path, it predicts the shutdown time of the well currently connected to the nozzle. This overcomes the shortcomings of traditional methods that treat wellbore and reservoir parameters as static parameters, making long-term prediction of the dynamics of flowing wells impossible. Furthermore, by combining the longest flowing period and the single-well cumulative oil production target, an optimization model for the nozzle size during well shutdown is established to obtain the optimized nozzle size for the flowing period. This overcomes the shortcomings of relying on human experience and the large amount of manual labor required for adjusting the nozzle size during the flowing period. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0035] Figure 1 shows the framework of the Bayesian algorithm for fitting the target well pressure profile provided in an embodiment of the present invention.

[0036] Figure 2 is a schematic diagram of the target well pressure profile fitting before and after the embodiment of the present invention.

[0037] Figure 3 shows the target well uncertainty parameter prediction model provided in an embodiment of the present invention;

[0038] Figure 4 shows the target well formation pressure prediction model provided in an embodiment of the present invention;

[0039] Figure 5 shows the real-time bottom hole pressure calculation of the target well provided in an embodiment of the present invention;

[0040] Figure 6 shows the target well productivity index prediction model provided in an embodiment of the present invention;

[0041] Figure 7 shows the target well water cut prediction model provided in an embodiment of the present invention;

[0042] Figure 8 shows the dynamic model of oil well inflow under different cumulative production of the target well provided in the embodiment of the present invention;

[0043] Figure 9 shows the dynamic inflow of different cumulative production and wellhead pressure curves of oil wells provided in the embodiments of the present invention;

[0044] Figure 10 shows the target well nozzle flow model provided in an embodiment of the present invention;

[0045] Figure 11 is a schematic diagram of the target well nozzle size optimization process provided in an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0047] Example

[0048] A method for predicting the shutdown time of a flowing well and a method for optimizing the nozzle size, comprising the following steps:

[0049] (1) Fit the oil well pressure test data at different times to obtain the uncertain parameters of wellbore and fluid properties at different test times. , This represents the total number of tests.

[0050] (2) Based on the fitted values ​​of uncertain parameters at different test times obtained in step (1), analyze the relationship between cumulative oil production and uncertain parameters, and establish a prediction model for uncertain parameters of the target well;

[0051] (3) Based on the principle of material balance, establish a regression model between formation pressure and cumulative fluid production for the calculation and prediction of formation pressure in oil wells;

[0052] (4) Combine the target well uncertainty parameter prediction model and the actual production data of the oil well to accurately calculate the bottom pressure of the oil well at different times. Then, combine the real-time prediction of the formation pressure of the oil well to calculate the historical production capacity index of the oil well and establish the oil well production capacity index prediction model.

[0053] (5) By combining historical data on water cut of oil wells, a regression equation is established to obtain a water cut prediction model for oil wells;

[0054] (6) Combining the prediction models obtained in steps (2), (3), (4) and (5), establish a dynamic model of oil well inflow under different cumulative production to calculate the bottom pressure of oil wells under different cumulative oil production. Then, combine the uncertain parameters of wellbore and fluid properties to establish a prediction model of oil well head pressure under different cumulative production to calculate the oil well head pressure under different oil production under the corresponding cumulative oil production. Combine the nozzle flow model to solve the prediction model of the stop-blowing time to obtain the oil well stop-blowing time.

[0055] For the uncertain parameters of wellbore and fluid properties at different test times in step (1) , To determine the total number of tests, it is necessary to first identify the set of uncertainties affecting pressure, temperature, and fluid density along the wellbore as it flows from the reservoir to the wellhead. The main uncertain parameters selected in this invention include: wellbore friction. Crude oil density Crude oil viscosity Natural gas density Formation water density Crude oil saturation pressure Heat transfer coefficient Crude oil specific heat Specific heat of formation water Specific heat of natural gas ,Right now .

[0056] Then combine the wellbore profile calculation model In this embodiment, the Beggs-Brill model is selected to calculate the wellbore profile and establish a deterministic parameter set. Deterministic parameters include: well depth Inner diameter of oil pipe Inner diameter of the casing Wellhead pressure (Reservoir pressure), wellhead temperature (Reservoir temperature), daily oil production Daily water production Daily gas production and geothermal gradient ,Right now .

[0057] In obtaining the set of uncertain parameters Afterwards, as Figure 1 The Bayesian optimization algorithm shown optimizes and adjusts the above-mentioned oil well number 1. Uncertain parameters during secondary flow pressure testing Then, pressure profiles obtained from oil well pressure tests at different times were analyzed. Temperature profile and fluid density profile Perform fitting, such as Figure 2 As shown, the fitting formula is as follows:

[0058] ,in: , , These are the weights of the fitting loss function for the pressure profile, temperature profile, and fluid density profile, respectively. , , , represent the given parameters in the i-th test. and The pressure profile, temperature profile, and fluid density profile were calculated based on the Beggs-Brill model.

[0059] By fitting and optimizing the above formula, we can obtain the [then]... Uncertain parameters during secondary flow pressure testing .

[0060] In step (2), the uncertain parameters obtained from the multiple flowing pressure tests of the oil well are fitted and optimized. ( (Total number of flow pressure profile tests) and the first Cumulative oil production during this test Constitute a series of point sets Then the point set Ordinary Least Squares (OLS) is used for fitting regression to obtain a prediction model for uncertain parameters. ,in That is, the cumulative oil production obtained through regression. With uncertainty parameters The function, in this implementation, is obtained as described above. Figure 3 The model shown is a prediction model for uncertain parameters such as crude oil viscosity, friction coefficient, gasoline ratio, and saturation pressure as a function of cumulative oil production.

[0061] After determining the prediction model for the uncertain parameters, step (3) then uses the principle of material balance to obtain the regression model between formation pressure and cumulative fluid production. The result is as follows Figure 4 As shown, where Equations were fitted using actual oil well production data. get; Mean formation pressure, in psi; Initial formation pressure, in psi; The well control radius is in meters (m). Porosity is a dimensionless quantity. The thickness of the perforation is in meters (m). The overall compression factor is expressed in units of... , This is the bottom hole flowing pressure, measured in psi.

[0062] The uncertainty parameter prediction model obtained from steps (1) and (2) above With known and determined real-time production parameters Historical bottomhole flowing pressure data of oil wells were obtained using the Beggs-Brill model, a wellbore profile calculation model. The result is as follows Figure 5 As shown, the real-time production index of the oil well is further calculated by combining the regression model between formation pressure and cumulative fluid production obtained in step (3) with the actual oil production data. To obtain the capacity index prediction model ,like Figure 6 As shown; where This is a capacity index, in units of... ; Through The series of data obtained by regression and The function.

[0063] Based on historical data of water cut and cumulative oil production during the oil well's self-flowing period, regression analysis was performed using the Ordinary Least Squares (OLS) method on these known historical data to obtain a prediction model for water cut during the oil well's self-flowing period. This allows for the prediction of water cut values ​​at different oil production levels in oil wells. The results obtained in this embodiment are as follows: Figure 7 As shown, mathematically , These are the slope and intercept, respectively, and in production, they are both fitting parameters for early-stage oil well data.

[0064] In the above calculations, the obtained uncertain parameter prediction models, the regression model between formation pressure and cumulative production, the production index prediction model, and the well water cut prediction model are combined. The Petrobras three-phase flow inflow dynamic model is also introduced for long-term prediction of the dynamic analysis of flowing wells. The bottom hole pressure of the well is calculated under different cumulative oil production rates, and the corresponding well inflow dynamic curves are plotted. The result is as follows Figure 8 As shown, where Bottom hole flowing pressure, in psi; For oil production, per unit .

[0065] To make the results more accurate, after obtaining the bottom hole pressure of oil wells under different cumulative oil production rates, the results were further combined with oil well water cut prediction models, uncertain parameter prediction models, and wellbore profile calculation models. Calculate the wellhead pressure of oil wells at different production rates under the corresponding cumulative oil production. Calculate the pressure in psi and plot the wellhead pressure curve. The result is as follows Figure 9 As shown; and further, a nozzle flow model is introduced. The optimization was performed, and the result is as follows: Figure 10 As shown, taking the logarithm of both sides simplifies to obtain... , To produce gas-oil ratio, The nozzle size is in meters (m), and the oil production rate is... Unit STB For moisture content, and , , and The above parameters refer to the wellhead pressure of the oil well. Compared to producing gas and oil Oil nozzle size Oil production Moisture content Historical production data were obtained by fitting the data using the least squares method. Additionally, moisture content was also considered. Both the gas-oil ratio (GOR) and the production oil ratio are functions of the cumulative oil recovery; therefore, the nozzle flow model formula can be written as: .

[0066] The results obtained from the above steps are then substituted into the jet cessation time prediction model. Get the current nozzle size The spray stop time T, where, The unit is psi, representing the minimum wellhead pressure required for external transmission.

[0067] Before obtaining a more accurate nozzle size for the oil well, it is necessary to further consider the nozzle size optimization model for when the oil well stops flowing. To achieve the maximum cumulative oil production In this embodiment, to efficiently obtain the nozzle size, an optimized nozzle size for the self-spraying period is automatically output through a stored computer pseudocode program, and the result is as follows: Figure 11 As shown, the pseudocode program is as follows:

[0068] Set p wh,min ,δ

[0069] NP i =0

[0070] d i =d0

[0071] While(True)

[0072] {(q o,i,p wh,i )|p wh (q o ,NP i )= (q o ,NP i ,d i )}

[0073] While(p wh,i >p wh,min )

[0074] {(q o,i ,p wh,i )|p wh (q o ,NP i )= (q o ,NP i ,d i )}

[0075] NP i =NP i +q o,i

[0076] If (max{q o}p wh (q o ,NP i )<=p wh,min Then Break

[0077] d i = d i -δ

[0078] in, Adjust the nozzle size to the minimum. Let i be the daily oil production during the i-th test. Let be the wellhead pressure during the i-th test. Note that... Figure 11 The pressure curve at the wellhead and the size of the nozzle The intersection point (point A) of the flow model curves is equal to the minimum required wellhead pressure. At that time, continue to use the grease fitting. The injection will stop, so the nozzle size needs to be adjusted. The adjustment amount each time is... At this time, the wellhead pressure corresponds to the point The wellbore pressure loss is the corresponding ordinate The difference is adjusted by continuously reducing the size of the nozzle to extend the self-flowing oil production period of the oil well. When the cumulative production of the oil well reaches... At that time, the maximum value of the wellhead pressure curve is equal to the minimum required wellhead pressure. At point B, the oil well completely lost its self-flowing capability.

[0079] The electronic device carrying the computer pseudocode program can be a desktop computer, laptop, handheld computer, or cloud server, etc. The electronic device may include, but is not limited to, a processor. Those skilled in the art will understand that the schematic diagram is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, etc.

[0080] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0081] The memory can be used to store the computer program or module. The processor implements various functions of the electronic device by running or executing the computer program or module stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0082] If the integrated units of the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments, or it can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0083] The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0084] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting the shutdown time of a flowing well, characterized in that, Includes the following steps: (1) Fit the oil well pressure test data at different times to obtain the uncertain parameters of wellbore and fluid properties at different test times. , The total number of tests, wherein the oil well pressure test data at different times includes pressure profiles. Temperature profile and fluid density profile It also includes a wellbore profile calculation model. The The model is based on the Beggs-Brill model, calculated using wellbore profiles. Determine deterministic parameters The uncertain parameters of wellbore and fluid properties at different test times were optimized using the following Bayesian optimization formula. Optimization and adjustments will be made: ； in: , , These are the weights of the fitting loss function for the pressure profile, temperature profile, and fluid density profile, respectively. , , , represent the given parameters in the i-th test. and ,according to The pressure profile, temperature profile, and fluid density profile obtained from the model calculations; (2) Based on the fitted values ​​of uncertain parameters at different test times obtained in step (1), analyze the relationship between cumulative oil production and uncertain parameters, and establish a prediction model for uncertain parameters of the target well; (3) Based on the principle of material balance, establish a regression model between formation pressure and cumulative fluid production for the calculation and prediction of formation pressure in oil wells; (4) Combine the target well uncertainty parameter prediction model and the actual production data of the oil well to accurately calculate the bottom pressure of the oil well at different times. Then, combine the real-time prediction of the formation pressure of the oil well to calculate the historical production capacity index of the oil well and establish the oil well production capacity index prediction model. (5) By combining historical data on water cut of oil wells, a regression equation is established to obtain a water cut prediction model for oil wells; (6) Combining the prediction models obtained in steps (2), (3), (4) and (5), establish a dynamic model of oil well inflow under different cumulative production to calculate the bottom pressure of oil wells under different cumulative oil production. Then, combine the uncertain parameters of wellbore and fluid properties to establish a prediction model of oil well head pressure under different cumulative production to calculate the oil well head pressure under different oil production under the corresponding cumulative oil production. Combine the nozzle flow model to solve the prediction model of the stop-blowing time to obtain the oil well stop-blowing time.

2. The method for predicting the shutdown time of a flowing well according to claim 1, characterized in that, By analyzing uncertain parameters and the Cumulative oil production during this test By performing a fitting operation, where i = 1, 2, ..., k, the prediction model for the uncertain parameters of the target well is obtained as follows: ,in Cumulative oil production obtained through regression equation With uncertainty parameters The function.

3. The method for predicting the shutdown time of a flowing well according to claim 2, characterized in that, The regression model between formation pressure and cumulative fluid production is as follows: ； in Equations were fitted using actual oil well production data. The result is obtained; where q is the oil well production, and n is the intercept parameter of the fitted equation. Mean formation pressure, in psi; Initial formation pressure, in psi; The well control radius is in meters (m). Porosity is a dimensionless quantity. The thickness of the perforation is in meters (m). The overall compression factor is expressed in units of... , This is the bottom hole flowing pressure, measured in psi.

4. The method for predicting the shutdown time of a flowing well according to claim 3, characterized in that, Prediction model based on uncertain parameters With determined real-time production parameters Calculation model based on wellbore profile Obtain historical data of bottom hole flowing pressure in oil wells Then, by combining the regression model between formation pressure and cumulative fluid production with actual oil production data, the real-time production index of oil wells is calculated. To obtain the capacity index prediction model ,in This is a capacity index, in units of... ; Through The series of data obtained by regression and The function, where, .

5. The method for predicting the shutdown time of a flowing well according to claim 4, characterized in that, The oil well water cut prediction model in step (5) is as follows: ,in and These are the slope and intercept, respectively, and in production, they are both fitting parameters for early-stage oil well data.

6. The method for predicting the shutdown time of a flowing well according to claim 5, characterized in that, The inflow dynamic model for oil wells under different cumulative production is the Petrobras three-phase flow inflow dynamic model. The corresponding oil well inflow dynamic curves are plotted by calculating the bottom hole pressure under different cumulative oil production. ,in Bottom hole flowing pressure, in psi; Oil production, in STB; The wellhead pressure prediction model combines the well water cut prediction model, the uncertain parameter prediction model, and the wellbore profile calculation model. Calculate the wellhead pressure of oil wells at different production rates under the corresponding cumulative oil production. And plot the wellhead pressure curve of the oil well. ; The nozzle flow model is as follows: Taking the logarithm of both sides yields... , To produce a gas-oil ratio, For the size of the nozzle, Moisture content, , , and Oil wellhead pressure Oil-to-gas production ratio Oil nozzle size Oil production and moisture content Parameters obtained by fitting historical production data, plus moisture content Both the gas-oil ratio (GOR) and the production oil ratio are functions of the cumulative oil recovery; therefore, the nozzle flow model formula can be written as: ; The prediction model for the stop-spray time is as follows: Get the current nozzle size Stop spraying time ,in, The unit is psi, representing the minimum wellhead pressure required for external transmission.

7. A method for optimizing nozzle size, characterized in that, Based on the well shutdown time predicted by the method for predicting the shutdown time of a flowing well as described in claim 6, and the target cumulative oil production for a single well, an optimization model for the nozzle size of the well shutdown nozzle is established. The optimization model for the nozzle size of the well shutdown nozzle is as follows: Used to obtain the maximum cumulative oil production Output optimized nozzle size.

8. An electronic device, characterized in that, include: processor; Memory is used to store processor-executable instructions; The processor is configured to execute the method for predicting the stop-flow time of a flowing well as described in any one of claims 1-6 or the method for optimizing the nozzle size as described in claim 7.

9. A computer-readable storage medium, characterized in that, It includes a stored computer program, which, when executed, performs the method for predicting the stop-flow time of a flowing well as described in any one of claims 1-6 or the method for optimizing the nozzle size as described in claim 7.

Images