A method, device, equipment, medium and product for determining a variable-resistance polymer staged profile control and flooding production scheme

Abstract

The embodiment of the application provides a method, device, equipment, medium and product for determining a variable-resistance polymer staged profile control and production scheme, and relates to the technical field of petroleum engineering development. The method constructs an optimization model with the maximum cumulative oil production and the minimum cumulative polymer consumption as the target, and automatically generates and evaluates multiple injection-production schemes based on the numerical simulation results and the preset constraint conditions, and finally selects the optimal solution. The numerical simulation model is used to generate development data in batches, which replaces the cumbersome parameter identification process in the traditional method and reduces the time consumption of early data processing. The manual trade-off between increasing oil production and controlling polymer consumption is converted into a double-target optimization problem, and the optimization solution combined with the constraint conditions can output multiple feasible schemes, which avoids the trade-off process of repeated trial and error. Finally, the optimal scheme is quickly screened through the evaluation rules, the process from data processing to scheme output is streamlined and automated, the scheme determination efficiency is improved, and the user demand is accurately matched.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil engineering development, and in particular to a method and device for determining a variable resistance polymer staged profile control injection-production scheme, equipment, medium and product. BACKGROUND

[0002] In the middle and later stages of oilfield development, the formation energy gradually decreases, and water injection is generally used to maintain pressure and drive crude oil to flow to the well. However, water injection can easily cause the production well to see water too early or even water channeling, so that a large amount of crude oil remains in the low-permeability layer and cannot be effectively produced. Under this background, injecting polymer into the injection well becomes an improvement measure, which increases the viscosity of the injected polymer and improves the efficiency of crude oil production. Therefore, how to determine the injection strategy of the polymer and develop an injection-production scheme that matches the specific reservoir conditions has become the key to ensuring the development benefit of the oilfield.

[0003] In the prior art, the injection-production scheme of the polymer in the injection well is determined by orthogonal design, gray correlation analysis and multivariate regression, etc. First, the related factors affecting the crude oil recovery rate are analyzed, and the key parameters that have a greater impact on the recovery rate are identified, such as the injection speed and injection concentration of the polymer, etc. Then, based on the analysis results of these key parameters, the corresponding parameter configuration in the injection-production scheme of the polymer in the injection well is determined, and thus the injection-production scheme of the polymer in the injection well is formed.

[0004] However, the prior art has the problem of low efficiency in determining the injection-production scheme of the polymer in the injection well. The reason is that the injection of the polymer is mainly aimed at improving the crude oil recovery rate, and a large amount of polymer is often needed to achieve this goal, which will lead to a sharp increase in material cost. When the scheme is developed, a trade-off needs to be made between the technical effect of increasing oil production and controlling the amount of polymer within a reasonable range. This trade-off process affects the efficiency of scheme determination. SUMMARY

[0005] The embodiments of the present application provide a method, device, equipment, medium and product for determining a variable resistance polymer staged profile control injection-production scheme, to solve the problem of low efficiency in determining the injection-production scheme of the polymer in the injection well in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a method for determining a variable resistance polymer staged profile control injection-production scheme, comprising:

[0007] obtaining a plurality of first data and a preset numerical simulation model; wherein the plurality of first data is used to represent the injection concentration and injection speed of the polymer of a target slug of a target injection well, and the target injection well refers to any one of a plurality of preset injection wells, and the target slug refers to any one of a plurality of slugs included in the target injection well;

[0008] input the plurality of first data into the numerical simulation model to obtain a plurality of first development data; wherein the plurality of first development data are used to represent oil production of a target oil production well when an input of the numerical simulation model is the plurality of first data, and the target oil production well is any one of a plurality of oil production wells having a displacement relationship with the target injection well;

[0009] According to the injection concentration and the injection speed, the polymer dosage of the target injection well is calculated.

[0010] According to the plurality of first development data and the polymer dosage, an injection-production optimization control model is constructed; wherein the injection-production optimization control model is an optimization model with the maximum cumulative oil production and the minimum cumulative polymer dosage as the target, the cumulative oil production is the sum of oil production of the plurality of oil production wells, and the cumulative polymer dosage is the sum of polymer dosage of the plurality of injection wells.

[0011] Based on a plurality of preset constraint conditions, the injection-production optimization control model is optimized and solved to obtain a plurality of injection-production schemes.

[0012] According to a preset evaluation rule, the plurality of injection-production schemes are evaluated to obtain an evaluation value of each injection-production scheme, and an injection-production scheme corresponding to a maximum value of the evaluation value is taken as a target injection-production scheme; wherein the target injection-production scheme includes a first concentration, a second concentration, a third concentration, a first speed, a second speed and a third speed, and the plurality of slugs include a first slug, a second slug and a third slug.

[0013] The polymer of the first concentration is injected into the first slug at the first speed, the polymer of the second concentration is injected into the second slug at the second speed, and the polymer of the third concentration is injected into the third slug at the third speed; wherein the first concentration is greater than the second concentration, and the second concentration is greater than the third concentration.

[0014] In a second aspect, the embodiments of the present application provide a device for determining a variable resistance polymer staged profile control injection-production scheme, comprising:

[0015] An acquisition module is configured to acquire a plurality of first data and a preset numerical simulation model; wherein the plurality of first data are used to represent an injection concentration and an injection speed of polymer of a target slug injected into a target injection well, the target injection well is any one of a plurality of preset injection wells, and the target slug is any one of a plurality of slugs included in the target injection well.

[0016] The computing module is configured to input the plurality of first data into the numerical simulation model to obtain a plurality of first development data, wherein the plurality of first development data are used to represent oil production of a target oil production well when the numerical simulation model is input with the plurality of first data, and the target oil production well is any one of a plurality of oil production wells having a displacement relationship with the target injection well.

[0017] The amount calculating module is configured to calculate a polymer amount of the target injection well according to the injection concentration and the injection speed.

[0018] The constructing module is configured to construct an injection-production optimization control model according to the plurality of first development data and the polymer amount, wherein the injection-production optimization control model is an optimization model with a target of maximizing cumulative oil production and minimizing cumulative polymer amount, the cumulative oil production is a sum of oil production of the plurality of oil production wells, and the cumulative polymer amount is a sum of polymer amounts of the plurality of injection wells.

[0019] The solving module is configured to perform optimization solving on the injection-production optimization control model based on a plurality of preset constraints to obtain a plurality of injection-production schemes.

[0020] The evaluation module is configured to evaluate the plurality of injection-production schemes according to a preset evaluation rule to obtain evaluation values of the injection-production schemes, and take an injection-production scheme corresponding to a maximum value of the evaluation values as a target injection-production scheme, wherein the target injection-production scheme includes a first concentration, a second concentration, a third concentration, a first speed, a second speed and a third speed, and the plurality of slugs include a first slug, a second slug and a third slug.

[0021] The staged injection module is configured to inject the polymer with the first concentration into the first slug at the first speed, inject the polymer with the second concentration into the second slug at the second speed, and inject the polymer with the third concentration into the third slug at the third speed, wherein the first concentration is greater than the second concentration, and the second concentration is greater than the third concentration.

[0022] In a third aspect, the present application provides an electronic device, comprising a processor and a memory connected with the processor in communication;

[0023] The memory stores computer execution instructions.

[0024] The processor, when executing the computer execution instructions stored in the memory, is configured to implement the method for determining a variable-resistance polymer staged profile control injection-production scheme according to any one of the first aspect.

[0025] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the method for determining a variable resistance polymer staged profile control injection-production scheme according to any one of the first aspect.

[0026] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the method for determining a variable resistance polymer staged profile control injection-production scheme according to any one of the first aspect.

[0027] The method for determining a variable resistance polymer staged profile control injection-production scheme, the device, the equipment, the medium and the product provided by the present application construct an optimization model with the maximum cumulative oil production and the minimum cumulative polymer consumption as the target, and automatically generate and evaluate multiple injection-production schemes based on the numerical simulation results and the preset constraint conditions, and finally select the optimal solution. The development data is generated in batches through the numerical simulation model, which replaces the cumbersome parameter identification process in the traditional method and reduces the time consumption of the early data processing. The artificial trade-off between increasing the oil production and controlling the polymer consumption is converted into a double-target optimization problem, and the optimization solution combined with the constraint conditions can automatically output multiple feasible injection-production schemes, which avoids the repeated trial-and-error trade-off process. Finally, the optimal scheme is quickly screened through the evaluation rules, the process from data processing to scheme output is streamlined and automated, and then the three-stage slug continuous injection of high-concentration pre-injection, medium-concentration transition and low-concentration subsequent injection is adopted, so that the polymer forms a strong-to-weak gradient displacement underground, which expands the swept volume and reduces the total polymer consumption, thereby reducing the cost and improving the oil recovery efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0029] Figure 1 The application scenario diagram of the method for determining a variable resistance polymer staged profile control injection-production scheme provided by the embodiments of the present application;

[0030] Figure 2 The flowchart of the method for determining a variable resistance polymer staged profile control injection-production scheme provided by the embodiments of the present application;

[0031] Figure 3 The x-direction permeability distribution diagram provided by the embodiments of the present application;

[0032] Figure 4 The porosity distribution diagram provided by the embodiments of the present application;

[0033] Figure 5A target function distribution diagram of polymer dosage and cumulative oil production provided by the embodiment of the present application is shown in the following figure:

[0034] Figure 6 A schematic diagram of average water saturation of the oil reservoir before optimization provided by the embodiment of the present application is shown in the following figure:

[0035] Figure 7 A schematic diagram of average water saturation of the oil reservoir after optimization provided by the embodiment of the present application is shown in the following figure:

[0036] Figure 8 A structural schematic diagram of the determination device of the variable resistance polymer grading profile control injection and production scheme provided by the embodiment of the present application is shown in the following figure:

[0037] Figure 9 A hardware structural schematic diagram of the electronic device provided by the embodiment of the present application is shown in the following figure.

[0038] The specific embodiments of the present application have been shown in the above figures, and will be described in more detail hereinafter. These figures and the written description are not intended to limit the scope of the present application in any way, but to illustrate the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0039] The exemplary embodiments will be described in detail herein with reference to the attached drawings. Unless otherwise specified, the same numbers in different drawings indicate the same or similar elements. The following exemplary embodiments are described in order to explain the present application to those skilled in the art. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the appended claims.

[0040] In the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using "first", "second", etc. Those skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. do not necessarily mean different. It should be noted that in the embodiments of the present application, "exemplary" or "for example" is used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific way. In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more.

[0041] It should be noted that the "at" in the embodiments of the present application can be at the moment when a certain condition occurs, or in a period of time after a certain condition occurs, and the embodiments of the present application do not make specific limitations. In addition, the method, device, equipment, medium and product provided by the embodiments of the present application are only examples, and the method, device, equipment, medium and product of the variable resistance polymer grading profile control injection and production scheme can also include more or less content.

[0042] In order to clearly describe the technical solutions of the embodiments of the present application, the following will briefly introduce some terms and technologies involved in the embodiments of the present application:

[0043] Injection and production well working system: In the process of reservoir development, the system operation specification and parameter control criterion formulated for injection wells and production wells. The injection medium selection and injection process control of injection wells need to be clarified, including dynamic adjustment of injection pressure and injection volume, to ensure that the injection fluid can enter the designated area of the reservoir as expected; the reasonable production method of the production well needs to be determined to control the production rhythm of the output fluid, and the production related parameters are adjusted in time according to the reservoir output dynamic.

[0044] Latin hypercube sampling: A method for generating initial samples in a multivariate research scenario, the core of which is to ensure that the value range of each variable to be studied is uniformly and comprehensively covered, while avoiding excessive concentration of samples or missing key intervals. It will first divide the possible value range of each variable into several non-overlapping intervals, then select a sample point from each interval, and ensure that the sample points corresponding to different variables do not repeatedly gather in the overall distribution through reasonable design, so that the final sample set can reflect the characteristics of different values of each variable itself, and also reflect the diversity of different variable value combinations.

[0045] The exemplary embodiments will be described in detail hereinafter with reference to the accompanying drawings. Wherever possible, the same reference numbers will be used in different drawings to refer to the same or like elements. The following description of the exemplary embodiments is not representative of all possible embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0046] The technical solutions of the present application will be described in detail in the following specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present application will be described with reference to the accompanying drawings.

[0047] In order to clearly understand the technical solutions of the present application, the prior art solutions are first introduced in detail. By injecting polymers into injection wells to increase the viscosity of the injected fluid, adjusting the injection profile, expanding the swept volume, and improving the efficiency of crude oil production. Therefore, how to determine the injection strategy of the polymer, and develop an injection-production scheme that matches the specific reservoir conditions, has become the key to ensuring the development efficiency of oilfields.

[0048] In the prior art, the factors affecting the recovery rate of crude oil are first analyzed, and the key parameters that have a greater impact on the recovery rate are identified. Based on the analysis results of these key parameters, the corresponding parameter configuration in the polymer injection-production scheme of the injection well is determined, and then the polymer injection-production scheme of the injection well is formed. However, the main goal of the prior art is to inject polymers to improve the recovery rate of crude oil, and a large amount of polymers often need to be injected to achieve this goal, which will lead to a sharp increase in material costs. When developing the scheme, a trade-off needs to be made between the technical effect of increasing oil production and controlling the amount of polymer used within a reasonable range. Therefore, the prior art has the problem of low efficiency in determining the polymer injection-production scheme of the injection well.

[0049] Therefore, in order to solve the problem of low efficiency in determining the polymer injection-production scheme of the injection well in the prior art, it is found in research that in order to solve this problem, a systematic optimization model can be constructed to convert the multi-objective trade-off process of improving the recovery rate and controlling the amount of polymer into mathematical solving and scheme evaluation: ① By means of numerical simulation or mathematical modeling tools, the technical goal of improving the recovery rate of crude oil and the cost goal of controlling the amount of polymer can be converted into a clear quantitative optimization direction, and then combined with the actual working conditions to set constraint conditions, and through model solving to quickly generate feasible schemes. ② Parameter optimization automation can be achieved by relying on data-driven and intelligent algorithms, that is, based on actual data such as injection well historical development data and polymer performance data, intelligent algorithms such as machine learning are used to identify key parameters that have a significant impact on the recovery rate and cost, and the configuration of the key parameters is optimized through algorithm iteration, forming an automatic link from parameter analysis to scheme generation, and shortening the scheme determination period. ③ A multi-well collaborative optimization framework can be established to simplify the scheme adjustment process, breaking the limitations of single-well independent analysis, and constructing an overall injection-production scheme optimization framework covering multiple injection wells, linking single-well parameter configuration with cumulative development effect and total polymer usage, and through the framework, the matching relationship between well parameters is coordinated, and the efficiency of scheme determination is improved.

[0050] Specifically: can rely on quantitative modeling and simulation tools, build injection-production program overall optimization system covering multiple injection wells: first through data integration and simulation analysis, the crude oil recovery rate improvement demand and polymer dosage cost control target is converted into the maximum cumulative oil production, cumulative polymer dosage minimization and other clear quantitative target, combined with the actual development conditions to set parameter constraints, with the help of model solution automatically generate multiple candidate programs, and finally through the pre-set standardized evaluation rules to complete the automatic screening of the optimal solution, to improve the efficiency of polymer injection-production program determination.

[0051] The method, device, equipment, medium and product for determining the variable-resistance polymer staged profile control injection-production program provided by the embodiments of the present application generate and evaluate multiple injection-production programs automatically based on the numerical simulation results and the preset constraint conditions, and finally select the optimal solution by constructing an optimization model with the maximum cumulative oil production and the minimum cumulative polymer dosage as the target. The development data are generated in batches through the numerical simulation model, which replaces the cumbersome parameter identification process in the traditional method and reduces the time-consuming of the early data processing. The manual trade-off between increasing the oil production and controlling the polymer dosage is converted into a double-target optimization problem, and the optimization solution combined with the constraint conditions can automatically output multiple feasible injection-production programs, which avoids the repeated trial-and-error trade-off process. Finally, the optimal program is quickly screened through the evaluation rules, the process from data processing to program output is streamlined and automated, and then the three-stage slug continuous injection of high-concentration pre-positioning, medium-concentration transition and low-concentration follow-up is adopted, so that the polymer forms a gradient displacement from strong to weak underground, expands the swept volume and reduces the total polymer dosage, reduces the cost and improves the recovery efficiency.

[0052] Based on the above creative findings, the technical scheme of the present application is proposed.

[0053] The application scenarios of the method for determining the variable-resistance polymer staged profile control injection-production program provided by the embodiments of the present application are introduced below. Figure 1 The application scenarios of the method for determining the variable-resistance polymer staged profile control injection-production program provided by the embodiments of the present application are introduced below. Figure 1As shown, the application scenario includes a mobile terminal 101 and a server 102. The mobile terminal 101 sends a plurality of first data to the server 102, the server 102 inputs the plurality of first data into a numerical simulation model to obtain a plurality of first development data, the server 102 calculates the polymer dosage of a target injection well according to the injection concentration and the injection speed, the server 102 constructs an injection-production optimization control model according to the plurality of first development data and the polymer dosage, the server 102 optimizes and solves the injection-production optimization control model based on a plurality of preset constraint conditions to obtain a plurality of injection-production schemes, the server 102 evaluates the plurality of injection-production schemes according to a preset evaluation rule to obtain evaluation values of the injection-production schemes, and takes an injection-production scheme corresponding to a maximum evaluation value as a target injection-production scheme, and the server 102 performs segmented injection of the polymer according to the target injection-production scheme.

[0054] The embodiments of the present application will be described below with reference to the accompanying drawings.

[0055] Figure 2 A flowchart of a method for determining a variable-resistance polymer staged profile control injection-production scheme provided by the embodiments of the present application is shown in FIG. 1. Figure 2 As shown, in the present embodiment, the execution subject of the embodiments of the present application is a server. The method for determining a variable-resistance polymer staged profile control injection-production scheme provided by the present embodiment includes the following steps:

[0056] S201, obtaining a plurality of first data and a preset numerical simulation model; wherein the plurality of first data is used to represent the injection concentration and the injection speed of the polymer of a target slug injected into a target injection well, and the target injection well refers to any one of a plurality of preset injection wells, and the target slug refers to any one of a plurality of slugs included in the target injection well.

[0057] Specifically, the plurality of first data can be obtained by collecting the historical development records of the same type of injection wells in the target area, extracting the actual parameters of different polymer injection concentrations and injection speeds therein as basic data, and combining indoor physical simulation experiments to test the effects of different concentration and speed combinations under simulated reservoir conditions to supplement and improve the data. As for the preset numerical simulation model, a mature oil reservoir numerical simulation framework in the industry can be referred to, and the actual geological data such as the geological structure, crude oil properties, and pore distribution of the reservoir where the target injection well is located are combined to calibrate and adjust the core parameters such as permeability, porosity, and fluid viscosity in the model, and the calculation accuracy of the model is verified through historical production data to ensure that it can accurately reflect the correlation between injection parameters and oil production, thereby obtaining the model. This step is used to provide reliable basic data for subsequent input of parameters into the model to calculate development data and construct an injection-production optimization control model.

[0058] The numerical simulation model can also be described as a polymer staged profile control numerical simulation model, which is obtained according to geological parameters of a target reservoir, fluid high-pressure physical properties, injection and production well operation systems and production history training, and can represent complex physical and chemical mechanisms. In the model, a gradient viscosity-reducing slug injection strategy is adopted, a high-concentration polymer solution slug is injected in the early stage to increase the viscosity of the water phase, reduce the water-oil mobility ratio, enhance the flow resistance of high-permeability layers and effectively control water channeling, and middle and low-concentration slugs are gradually injected in the later stage to improve the injection capacity of middle and low-permeability layers, expand swept volume and reduce interlayer mobility differences. The staged profile control complex physical and chemical phenomena mainly include the following three aspects:

[0059] (1) Polymer rheological effect in near-well and high-permeability layers: under high flow rate conditions, polymer molecular chains are subjected to shear to reduce viscosity, while in the displacement front, the molecular chains can be stretched to increase viscosity. The actual viscosity of the polymer is jointly determined by the two effects, which can be expressed as:

[0060]

[0061] wherein, is the corrected apparent viscosity, in centipoise, is the effective viscosity, in centipoise, is the shear parameter, dimensionless, is the shear sensitivity coefficient, dimensionless, is the stretching parameter, dimensionless, is the stretching sensitivity coefficient, dimensionless.

[0062] (2) Polymer adsorption retention and plugging effect on rock: the adsorption mass of the polymer on the rock surface can be expressed as:

[0063]

[0064] wherein, is the adsorption mass, in kilograms; is the adsorption concentration, in kilograms per cubic meter; is the rock density, in kilograms per cubic meter; is the rock volume, in cubic meters.

[0065] (3) Influence of polymer adsorption on oil and water phase relative permeability: polymer adsorption retention can cause the water phase relative permeability to decrease, and the correction formula is:

[0066]

[0067] wherein, is the permeability correction coefficient, dimensionless; is the residual resistance coefficient, dimensionless. is the adsorption concentration, and the unit is kilogram per cubic meter; is the maximum adsorption concentration, and the unit is kilogram per cubic meter.

[0068] S202, inputting the plurality of first data into a numerical simulation model to obtain a plurality of first development data; wherein the plurality of first development data is used to represent the oil production of the target production well when the input of the numerical simulation model is the plurality of first data, and the target production well is any one of the plurality of production wells having a displacement relationship with the target injection well.

[0069] Specifically, the sorted polymer injection concentration and injection speed can be input into the model in batches according to the parameter format and input order required by the numerical simulation model. The model will simulate the oil production process of the target production well under different parameter combinations according to the built-in core logic of reservoir fluid motion rules and polymer displacement mechanism, calculate and output the oil production corresponding to each group of parameters, and thus obtain the plurality of first development data. The role of this step is to establish the corresponding relationship between the injection parameters and the development effect data through model operation, to provide the required basic data for subsequent construction of injection-production optimization control model, and to realize the key connection from parameter input to optimization analysis.

[0070] Wherein, the displacement relationship refers to the pressure field and flow field formed after the polymer is injected into the target injection well, which can spread and drive the oil to flow to the target production well, thereby forming an effective displacement path and recovery response relationship between the target injection well and the target production well.

[0071] S203, calculating the polymer consumption of the target injection well according to the injection concentration and the injection speed.

[0072] Specifically, the polymer consumption can be obtained by associating and calculating the injection concentration, the injection speed, and the injection time length or the injection volume of the target slug. Specifically, the polymer consumption can be obtained by multiplying the injection concentration by the total injection amount determined by the injection speed and the injection time length, or by calculating the injection volume according to the injection speed, the injection time length, and the related parameters of the target slug corresponding to the well section, and then combining the concentration to calculate the consumption; this step is used to obtain the polymer consumption data of the target injection well under specific injection parameters, to provide basic data support for subsequent construction of the injection-production optimization control model which takes the minimum cumulative polymer consumption as one of the targets, and to provide a key basis for subsequent evaluation of the cost economy of different injection-production schemes.

[0073] S204, constructing an injection-production optimization control model according to the plurality of first development data and the polymer consumption; wherein the injection-production optimization control model is an optimization model which takes the maximum cumulative oil production and the minimum cumulative polymer consumption as the target, the cumulative oil production is the sum of the oil production of the plurality of production wells, and the cumulative polymer consumption is the sum of the polymer consumption of the plurality of injection wells.

[0074] Specifically, the multiple first development data and the polymer amount can be classified and sorted first, the polymer amount data corresponding to each injection well and the oil production data corresponding to each oil production well are distinguished, and then the single well data is summarized according to the demand of multi-well collaborative analysis, and the cumulative oil production and the cumulative polymer amount data of the multi-well are calculated; then, combined with the core demand of actual development, the maximum cumulative oil production and the minimum cumulative polymer amount are determined as the optimization target of the model, and the target is clearly defined by a mathematical expression, and the polymer injection concentration and the polymer injection speed are explicitly defined as the decision variables of the model, and through regression analysis, based on the summarized cumulative data and the corresponding decision variables, a mathematical correlation between the decision variables and the optimization target is established; finally, the optimization target expression, the decision variables and the correlation between the target are integrated to obtain the injection-production optimization control model. The role of this step is to convert the scattered development data into an analysis model with a clear optimization direction, to provide a structured calculation framework for solving the feasible injection-production scheme combined with the constraint conditions, and to change the traditional experience trade-off to precise mathematical calculation for scheme optimization.

[0075] Among them, the injection-production optimization control model can also be described as a polymer grading profile control intelligent injection-production optimization model, and the polymer grading profile control intelligent injection-production optimization model can be represented as:

[0076]

[0077]

[0078]

[0079]

[0080] Among them, is the cumulative oil production, unit: cubic meter; is the cumulative polymer injection amount, unit: cubic meter, is the polymer concentration of the w-th well and the s-th segment, unit: kg per cubic meter; is the injection volume corresponding to the segment, unit: cubic meter; is the i-th control variable, and are the lower limit and the upper limit, respectively; is the total number of control variables; C1 and C2 are the concentrations of the first and second stages of polymer flooding, respectively, C Se is the concentration of the last stage.

[0081] S205, based on the preset multiple constraint conditions, the injection-production optimization control model is optimized and solved to obtain multiple injection-production schemes.

[0082] Specifically, an initial population containing multiple potential injection-production schemes can be generated first, based on the actual adjustable range of the decision variables in the model, namely polymer injection concentration and polymer injection rate. Then, according to multiple preset constraints, the compliance of each parameter combination in the population is verified one by one. If the cumulative polymer usage corresponding to a certain parameter exceeds the reserve limit or the oil production does not meet the minimum requirement, the combination is removed. Subsequently, combined with the optimization objective of the model, the fitness value of each feasible parameter combination is calculated to quantify its degree of satisfaction with the optimization objective. Then, through crossover and mutation operations of a genetic algorithm, the feasible parameter combinations are iteratively evolved to generate a new parameter combination population, and the constraint verification and fitness calculation steps are repeated. After multiple iterations, when the iteration results tend to stabilize, multiple parameter combinations with good fitness performance and consistent satisfaction of the constraints are collected. These parameter combinations are the corresponding multiple injection-production schemes. This step is used to transform the injection-production optimization control model from a quantitative framework at the principle level into a set of feasible schemes that conform to actual production constraints. This avoids the generated schemes being unimplementable due to violations of objective conditions and ensures that the schemes always revolve around the optimization objective set by the model.

[0083] S206. Evaluate multiple injection and production schemes according to preset evaluation rules, obtain the evaluation value of each injection and production scheme, and take the injection and production scheme corresponding to the maximum evaluation value as the target injection and production scheme; wherein, the target injection and production scheme includes a first concentration, a second concentration, a third concentration, a first velocity, a second velocity, and a third velocity, and multiple slugs include a first slug, a second slug, and a third slug.

[0084] Specifically, the core dimensions of the evaluation rules can be clearly defined first. For example, the benefits and costs corresponding to the cumulative oil production and cumulative polymer usage can be assigned reasonable weights. Then, the comprehensive evaluation value of each injection and production scheme can be obtained through weighted calculation. Alternatively, quantitative standards for evaluation indicators can be set, and the oil production compliance and polymer usage control of each scheme can be scored and summed. This step is used to select the scheme with the best comprehensive performance from the multiple injection and production schemes obtained from the optimization solution. This ensures that the selected target injection and production scheme can not only meet the requirements of oil displacement effect, but also reasonably control polymer consumption. At the same time, the polymer injection concentration and rate parameters corresponding to different slugs in the scheme are clarified, providing a direct basis for subsequent actual injection operations.

[0085] For example, a dual-index evaluation system is constructed with cumulative oil production and polymer usage as optimization objectives. Cumulative oil production measures development effectiveness, while polymer usage reflects resource consumption. Together, they determine the overall performance of the proposed scheme. To ensure the objectivity and rationality of the results, a weighting method combining the analytic hierarchy process (AHP) and entropy weighting is used to obtain the combined weights of cumulative oil production and polymer usage. Based on the determined weights, the Top-Approximation-Ideal-Solution Ranking (TOPSIS) method is used to rank candidate schemes. First, the ideal solution (maximum cumulative oil production, minimum polymer usage) and the negative ideal solution (minimum cumulative oil production, maximum polymer usage) are determined. Then, the Euclidean distance between each scheme and the ideal and negative ideal solutions is calculated. Finally, the proximity of each scheme is obtained, and the schemes are ranked based on the proximity value. The larger the proximity value, the better the overall performance of the scheme. Through these optimization processes, a quantitative balance can be achieved between the two objectives of cumulative oil production and polymer usage, and the optimal polymer flooding scheme can be selected.

[0086] S207. A polymer of a first concentration is injected into a first stopper at a first speed, a polymer of a second concentration is injected into a second stopper at a second speed, and a polymer of a third concentration is injected into a third stopper at a third speed; wherein the first concentration is greater than the second concentration, and the second concentration is greater than the third concentration.

[0087] Specifically, by adjusting the polymer configuration module and flow control device of the injection system, the polymer solution of the corresponding concentration is first delivered to the injection port of the target sluice at a set rate. After the current sluice is injected, the concentration configuration and rate parameters of the next sluice are switched, and the injection operation of different sluices is completed in sequence. At the same time, the injection concentration and rate are confirmed in real time by the monitoring device to confirm whether the injection concentration and rate meet the requirements. This step is used to convert the staged injection parameters determined in the target injection and production plan into actual displacement operation. By using a polymer injection method with decreasing concentration, displacement resistance is efficiently established in the early stage of injection to improve the oil displacement effect. In the subsequent stage, the amount of polymer used is reduced to control costs, and finally the goal of variable resistance staged displacement is achieved.

[0088] The method for determining a variable-resistance polymer staged profile control injection-production scheme provided by the embodiment of the application comprises the following steps: constructing an optimization model with the maximum cumulative oil production and the minimum cumulative polymer consumption as the target, and automatically generating and evaluating multiple injection-production schemes based on the numerical simulation results and preset constraint conditions, and finally selecting the optimal solution. The development data are generated in batches through the numerical simulation model, which replaces the cumbersome parameter identification process in the traditional method and reduces the time consumption of the early data processing. The artificial trade-off between the increased oil production and the controlled polymer consumption is converted into a double-target optimization problem, and the optimization solution combined with the constraint conditions can automatically output multiple feasible injection-production schemes, which avoids the repeated trial-and-error trade-off process. Finally, the optimal scheme is quickly screened through the evaluation rules, the process from data processing to scheme output is streamlined and automated, and then the three-stage slug continuous injection of high-concentration pre-injection, medium-concentration transition and low-concentration subsequent injection is adopted, so that the polymer forms a gradient displacement from strong to weak underground, which not only expands the swept volume but also reduces the total polymer consumption, thereby reducing the cost and improving the oil recovery efficiency.

[0089] In a possible design, S205, based on the preset multiple constraint conditions, the injection-production optimization control model is optimized and solved to obtain multiple injection-production schemes, which comprise:

[0090] S2051, the multiple first data are sampled to obtain multiple second data; wherein the multiple second data are data obtained by sampling the multiple first data, and the multiple first data comprise the multiple second data.

[0091] Specifically, the actual value range of the polymer injection concentration and the injection speed in the multiple first data can be determined first, then the Latin hypercube sampling method is adopted to divide a plurality of intervals in the range in proportion, a combination of injection concentration and injection speed is randomly selected in each interval as a sample, and it is ensured that the selected samples are uniformly distributed in the entire parameter space, which covers extreme cases such as high concentration and high injection rate, low concentration and low injection rate, and also includes regular cases of medium concentration and injection rate. The sample data obtained in this way are the multiple second data. This step is used to select a part of data with representative and reasonable distribution from the multiple first data, which not only retains the key parameter information but also reduces the data processing amount when the proxy model is constructed subsequently, so that the proxy model can efficiently learn the rules between the parameters and the development effect, and provide a reliable sample basis for replacing the numerical simulation model for rapid calculation.

[0092] When sampling the first data, a Latin hypercube uniform sampling method is specifically used. The sampling method divides the value range of the polymer injection concentration, injection speed and other parameters into several mutually non-overlapping intervals, randomly selects a set of parameter combinations from each interval as sample points, and ensures that the sample points corresponding to different parameters are uniformly distributed in the overall parameter space, which not only avoids the problem of incomplete parameter coverage caused by excessive concentration of samples, but also effectively reduces the number of redundant samples. After obtaining the second data based on the sampling method, only a limited number of numerical simulations of polymer staged flooding is required to obtain the third development data corresponding to the second data, including the liquid production rate, oil production rate and water cut of each oil well and other staged flooding effect indicators. Subsequently, a radial basis function proxy model is constructed with these limited second data as input parameters and the corresponding third development data as output staged flooding effect indicators. The proxy model can accurately fit the mapping relationship between the polymer injection parameters and the staged flooding effect indicators. In the subsequent calculation of the target oil production, liquid production rate and other data, the proxy model can be directly called to complete the calculation without the need to repeatedly start the time-consuming real polymer flooding numerical simulation model. This process significantly reduces the number of calls to the real numerical simulation. The parameter space that originally requires hundreds or even thousands of numerical simulations to cover can be achieved through the combination of Latin hypercube sampling and proxy model with only a few tens of limited simulations, reducing the cost of occupying computer hardware resources such as reducing the calculation time and reducing memory consumption, and shortening the overall calculation period from several days to provide efficient computing support for subsequent data perturbation, screening and injection-production scheme optimization solution steps.

[0093] The polymer profile control numerical simulation model is time-consuming because it needs to accurately represent the complex physical and chemical mechanisms in the polymer staged profile control process, such as the polymer rheological effect in the near well and high permeability layer, the adsorption retention and plugging effect of the polymer on the rock surface, the influence of adsorption on the relative permeability of oil and water, and the like, and needs to be combined with the actual parameters of the target reservoir, such as geological structure, crude oil properties, and pore distribution, for fine calculation. Each simulation needs to iteratively solve the whole process dynamic process of reservoir fluid movement and polymer displacement, and the calculation amount is extremely large. The radial basis function surrogate model is based on the second data of the limited set obtained by Latin hypercube sampling, combined with the third development data of the corresponding numerical simulation output, and the mapping relationship between the injection parameters and the profile control effect is established by fitting, without the need to repeatedly calculate the complex physical and chemical process and the whole process reservoir dynamics, and the result can be quickly output only relying on the established mapping relationship, so the time consumption is short. Using the radial basis function surrogate model to replace the polymer profile control numerical simulation model can reduce the number of calls of the real numerical simulation, reduce the occupation cost of computer hardware resources, shorten the overall calculation period, and provide efficient calculation support for subsequent third data perturbation, fourth data screening, and injection-production optimization control model solving, avoid the low efficiency of scheme determination caused by frequent calling of time-consuming numerical simulation, and ensure the efficient promotion of injection-production scheme optimization from data processing to solving.

[0094] S2052, according to the plurality of second data, a surrogate model is constructed; wherein the surrogate model is used to replace the numerical simulation model to calculate the oil production of the target oil production well.

[0095] Specifically, the polymer injection concentration and injection speed in the plurality of second data can be input into the numerical simulation model, and the corresponding oil production can be calculated and output by the model, so as to obtain a plurality of third development data; the plurality of second data is input as a sample, and the plurality of third development data is output as a corresponding sample, from which training samples and test samples are divided, a neural network method is selected to construct a model, the polymer injection concentration and injection speed in the training samples are used as network input layer data, and the corresponding oil production is used as output layer target value, the model is trained to obtain a surrogate model, and the surrogate model is a polynomial used to represent the relationship between the parameters of the polymer injected into the target injection well and the oil production of the target oil production well. The role of this step is to construct a simplified model that can quickly calculate the oil production, and the calculation efficiency is higher than that of the numerical simulation model. The numerical simulation model can be replaced by the numerical simulation model in subsequent data screening and the like, so as to reduce the calculation time of the optimization process and improve the efficiency of the injection-production scheme determination.

[0096] The surrogate model can also be described as a radial basis function surrogate model, and the radial basis function surrogate model can be represented as:

[0097]

[0098] wherein, is the base function, is the weight, is the low order polynomial, N is the number of samples, is the objective function value predicted by the surrogate model, x is the input variable.

[0099] A batch of approximate objective function values are quickly predicted by the surrogate model, and the candidate solutions are screened by the surrogate model for real calculation. New sample points and real function values are added to the database for dynamic updating of the radial basis function surrogate model, achieving a balance between calculation efficiency and prediction accuracy.

[0100] In the iterative optimization process, a classifier-assisted pre-screening method based on ranking learning is used to generate candidate solutions and determine whether they enter real calculation by combining non-dominated level and crowding distance information. Then, non-dominated search based on hyper volume is performed to speed up convergence, and the hyper volume is defined as:

[0101]

[0102] wherein, S is the solution set, is the reference point, is used to measure the contribution of solution x. In actual optimization, candidate solutions with larger are preferentially selected to enter real function evaluation, and HV is the hyper volume, represents the value of the m objective functions, is the m components of the reference point.

[0103] To maintain the diversity of the solution set, representative individuals are selected from non-dominated solutions based on crowding distance, and the calculation formula is:

[0104]

[0105] wherein, and are the function values adjacent to the ith solution on the jth objective, and are the maximum and minimum values of the objective, respectively, and CD i is the crowding distance of the ith solution, which is used to measure the sparsity of the solution in the objective space in multi-objective optimization, and m is the number of reference points.

[0106] The non-dominated solutions are pre-screened by the surrogate model, and the solutions in sparse areas are preferentially selected for real function evaluation to achieve uniform supplement in the non-dominated front. The optimization process is executed in a loop until the maximum number of real function evaluations is reached. A non-dominated solution refers to a solution in multi-objective optimization that does not have another solution that is superior to it in all objectives. A non-dominated solution represents a compromise between different objectives, which may not be optimal in some objectives but cannot be completely replaced in the overall. The set of all non-dominated solutions is called the Pareto solution set, and the distribution of the Pareto solution set in the objective space forms the Pareto front, which intuitively shows the trade-off relationship between different optimization objectives and provides a basis for final scheme selection.

[0107] S2053, perturb the plurality of second data to obtain a plurality of third data; wherein the plurality of third data refers to data obtained by perturbing the plurality of second data.

[0108] Specifically, three different samples can be randomly selected from the plurality of second data, and the polymer injection concentrations of two samples are subtracted respectively, and the injection amounts are subtracted respectively, to obtain two groups of difference values; then the two groups of difference values are adjusted by a certain proportion, and the concentration and injection amount of the third sample are added respectively to form a new polymer injection concentration and injection speed combination; if the parameters of the new combination exceed the reasonable interval of the concentration and injection amount in actual production, the new combination is corrected to the interval boundary, and the new data obtained thereby is the plurality of third data. The role of this step is to perturb the existing samples by the difference mutation operator to generate more diversified parameter combinations and expand the search space of polymer parameters, thereby providing more abundant candidate data for subsequent screening of better polymer parameters.

[0109] S2054, based on the surrogate model and the preset screening target, screening the plurality of third data to obtain a plurality of fourth data; wherein the plurality of fourth data refers to polymer parameters capable of achieving maximum cumulative oil production and minimum cumulative polymer consumption, and the polymer parameters include injection concentration and injection speed.

[0110] Specifically, the preset screening target can be first determined to select a part of data with representative and reasonable distribution from a large amount of first data, so as to reduce the data amount while retaining the key parameter information. The polymer injection concentration and injection speed in the plurality of third data are input into the surrogate model, and the corresponding oil production of each group of data is quickly calculated by the surrogate model. Then, the calculation results are sorted according to the screening target. If the maximum cumulative oil production is taken as the target, the data is sorted from high to low according to the oil production, and a part of data at the top of the sorting is selected. If the minimum cumulative polymer consumption is taken as the target, the data is sorted from low to high according to the consumption, and a part of data at the top of the sorting is selected. At the same time, the data with parameters beyond the actual reasonable range is removed, and the remaining data is the plurality of fourth data. The role of this step is to select the polymer parameters closer to the optimization target from the large amount of third data generated by perturbation with the help of the fast calculation capability of the surrogate model, to reduce the data amount to be input into the numerical simulation model in the subsequent step to reduce the calculation burden, and to lay a foundation for generating high-quality injection and production schemes in the subsequent step.

[0111] S2055, input the plurality of fourth data into the numerical simulation model to obtain a plurality of second development data; wherein the plurality of second development data are used to represent the oil production of the target oil production well when the input of the numerical simulation model is the plurality of fourth data.

[0112] Specifically, the injection concentration and injection speed in the plurality of fourth data can be input into the model, and the model can simulate the development process of the target oil production well under each group of parameters according to the physical law of the reservoir and the principle of fluid displacement, calculate and output the corresponding oil production. These results are the plurality of second development data. The role of this step is to obtain the real development effect data corresponding to the fourth data through the accurate calculation of the numerical simulation model, to make up for the possible precision deviation of the surrogate model, and to provide reliable basic data for subsequent optimization and solution of the injection and production optimization control model based on the constraint conditions.

[0113] S2056, based on the plurality of constraint conditions and the plurality of second development data, the injection and production optimization control model is optimized and solved to obtain a plurality of injection and production schemes.

[0114] Specifically, the oil production in the plurality of second development data can be associated with the injection-production optimization control model, and the data can be taken as an actual reference basis for solving the model; then the simulated annealing algorithm is selected for optimization solving, a group of initial parameter combinations is generated according to the range of decision variables in the model; then it is checked whether each group of combinations meets all the constraint conditions, if the oil production of a combination does not meet the standard, the combination is excluded; for the combinations meeting the constraints, the adaptation degree of each combination to the optimization objective of the model is calculated in combination with the second development data; the parameter combinations are adjusted through algorithm iteration to gradually approach the optimization objective, and the combinations meeting the constraint conditions are always retained in the process; after multiple rounds of iteration, all parameter combinations meeting the constraints and having high adaptation degrees are collected, and these combinations are the plurality of injection-production schemes. The role of this step is to combine the injection-production optimization control model with the actual development constraints and the real development data, and to generate a feasible scheme set meeting the objective production conditions and reflecting the optimization objective through algorithm solving.

[0115] The technical effect of this scheme in this embodiment is that: the second data is obtained by sampling, the proxy model is constructed based on the second data, the problem of long calculation time of the numerical simulation model is effectively solved, and the numerical simulation model consuming time is not called every time to calculate the oil production of the target oil production well; then the third data is obtained by perturbing the second data, the fourth data meeting the maximum cumulative oil production and the minimum cumulative polymer consumption is screened out by means of the proxy model according to the screening target, only these limited fourth data are input into the numerical simulation model to obtain the second development data, and then the injection-production scheme is optimized and solved based on this, the number of times of calling the numerical simulation model and the real calculation amount are reduced, and the efficiency of optimization and solving of the injection-production optimization control model is improved.

[0116] In a possible design, S2052, the proxy model is constructed according to the plurality of second data, including:

[0117] S20521, inputting the plurality of second data into the numerical simulation model to obtain a plurality of third development data; wherein the plurality of third development data is used to represent the oil production of the target oil production well when the input of the numerical simulation model is the plurality of second data.

[0118] Specifically, the polymer injection concentration and injection speed in the plurality of second data can be input into the numerical simulation model first, the model will simulate the development process of the target oil production well under each group of parameters according to the built-in oil reservoir geological rules and fluid displacement principles, automatically calculate and output the corresponding oil production, and these output results are the plurality of third development data. The role of this step is to obtain complete corresponding data of “polymer parameters-development effect”, to provide accurate input and output samples for constructing the proxy model in combination with the second data, to ensure that the proxy model can establish the mapping relationship between the parameters and the development effect based on reliable simulation data, and to lay a foundation for subsequent rapid calculation.

[0119] S20522, constructing an agent model according to the plurality of second data and the plurality of third development data.

[0120] Specifically, the polymer injection concentration and injection speed in the plurality of second data can be taken as input variables, the oil production in the plurality of third development data can be taken as output variables, most of the data can be selected as training samples, and the remaining part can be taken as verification samples; then a polynomial function containing a first-order term, a second-order term and an interaction term of the variables is fitted by using the training samples to establish the correlation between the input and the output; and then the verification samples are substituted into the function, if the deviation of the prediction result from the third development data is within an acceptable range, the agent model is obtained, and if the deviation is too large, the function form is adjusted and fitted again. The role of this step is to construct a simplified model that can quickly calculate the oil production, replace the time-consuming numerical simulation model, and provide efficient calculation support for subsequent data perturbation and screening.

[0121] The technical effect of this scheme in this embodiment is that the second data is input into the numerical simulation model to obtain the corresponding oil production of the target oil production well, so as to form the input and output data pair required by the agent model. This kind of data pair is derived from the real numerical simulation result, which can ensure the accuracy of the corresponding relationship between the input and the output. Based on the accurate data pair, the agent model can accurately match the calculation logic and result characteristics of the numerical simulation model, effectively avoiding the calculation distortion problem of the agent model caused by the deviation of the training data. The agent model provides a basis for subsequent replacement of the numerical simulation model to quickly calculate the oil production of the target oil production well and accurately screen the target polymer parameters.

[0122] In one possible design, S2054, based on the agent model and the preset screening target, the plurality of third data is screened to obtain a plurality of fourth data, including:

[0123] S20541, inputting the plurality of third data into the agent model to obtain a plurality of fourth development data; wherein the plurality of fourth development data is used to represent the oil production of the target oil production well when the input of the agent model is the plurality of third data.

[0124] Specifically, the polymer injection concentration and injection speed in the plurality of third data can be input into the agent model, and the model can quickly calculate and output the corresponding oil production of each group of data according to the correlation between the parameters and the development effect established in the model. These results are the plurality of fourth development data. The role of this step is to quickly obtain the development effect data corresponding to the third data generated by perturbation by means of the efficient calculation capability of the agent model, to provide a quantitative basis for subsequent data screening based on the screening target, and to avoid the time-consuming calculation caused by directly using the numerical simulation model.

[0125] S20542, based on the plurality of fourth development data and the screening target, the plurality of third data is screened to obtain a plurality of fourth data.

[0126] Specifically, the oil production reflected by the plurality of fourth development data can be compared with the requirement for oil production in the screening target, and the polymer dosage associated with the third data can be combined with the requirement for dosage in the screening target. By setting the oil production threshold and the dosage control threshold, the third data that meets the requirements of oil production not lower than the threshold and dosage not more than the threshold can be reserved as the fourth data. Alternatively, the third data can be sorted according to the comprehensive adaptation degree of oil production and dosage, and the third data with better comprehensive performance can be selected. This step is used to screen the polymer parameters that meet the optimization direction from a large number of third data obtained by perturbation, reduce the data amount input into the numerical simulation model, improve the efficiency of the injection-production scheme optimization solution, and ensure that the screened data can provide effective support for constructing a better injection-production scheme.

[0127] The technical effect of the scheme in this embodiment is that the third data is input into the proxy model to obtain the corresponding target oil production of the oil production well, and the third data is screened to obtain the fourth data based on the screening target. This process takes advantage of the fast calculation speed of the proxy model, can efficiently process a large number of third data generated by perturbation, and quickly identify potential polymer parameters that meet the requirements of maximum cumulative oil production and minimum cumulative polymer dosage. At the same time, the fourth development data output by the proxy model is screened, which can ensure the fit degree of the screening result and the target, avoid invalid data entering the subsequent numerical simulation link, and reduce the calculation burden of the numerical simulation model.

[0128] In one possible design, S206, the plurality of injection-production schemes are evaluated according to the preset evaluation rule to obtain evaluation values of the injection-production schemes, including:

[0129] S2061, obtain user demand; wherein the user demand includes a first demand and a second demand, the first demand refers to maximum cumulative oil production and minimum cumulative polymer dosage, and the second demand refers to balanced cumulative oil production and cumulative polymer dosage.

[0130] Specifically, the core demand of the user in the current development stage can be understood through the user interaction interface, that is, whether the user pays more attention to improving the cumulative oil production, or pays more attention to reducing the cumulative polymer dosage, or hopes to balance the two. In this way, the first demand and the second demand of the user are determined. The role of this step is to provide a direction guide for subsequent calculation of the evaluation value of the injection-production scheme, to ensure that the evaluation process is closely related to the actual development target of the user, and to make the obtained evaluation value truly reflect the demand of the scheme for the user.

[0131] S2062, calculate the evaluation value of each injection-production scheme according to the user demand, the cumulative oil production and the cumulative polymer dosage.

[0132] Specifically, the weights of the cumulative oil production and the cumulative polymer consumption can be adjusted according to the user demand first. If the first demand of the user is to maximize the cumulative oil production, the weight of the cumulative oil production in the evaluation is increased. If the first demand of the user is to minimize the cumulative polymer consumption, the weight of the cumulative polymer consumption is increased. If the second demand is to balance the two, the weights of the two are kept at a similar level. Then, the cumulative oil production and the cumulative polymer consumption of all injection-production schemes are normalized. For example, the highest value of the cumulative oil production in all schemes is taken as a reference, and the oil production of each scheme is converted into a relative score. The lowest value of the cumulative polymer consumption is taken as a reference, and the consumption of each scheme is converted into a relative score. Then, the weight of each dimension is multiplied by the corresponding score, and the two products are added to obtain the evaluation value of each injection-production scheme. This step can accurately match the core demand of the user and avoid deviation of the scheme from the actual demand of the user due to single-dimensional evaluation. Through weight distribution and normalization processing, the evaluation values of different schemes have a unified and comparable standard, which provides an objective and reasonable quantitative basis for selecting the target injection-production scheme with the maximum evaluation value.

[0133] The technical effect of the scheme in this embodiment is that the evaluation value of each injection-production scheme is calculated by obtaining the user demand and combining the cumulative oil production and the cumulative polymer consumption. This process can accurately match the actual demand of the user, considering both the single target of maximizing the cumulative oil production and minimizing the cumulative polymer consumption, and taking into account the demand of balancing the two, thereby avoiding the problem of single evaluation standard or deviation from the actual demand. Based on the evaluation value calculation according to the user demand, the evaluation of each injection-production scheme is more targeted and practical, so that the finally selected target injection-production scheme truly matches the specific demand of the user, and the adaptation degree of the scheme to the actual application scene is improved.

[0134] In one possible design, S2062, the evaluation value of each injection-production scheme is calculated according to the user demand, the cumulative oil production and the cumulative polymer consumption, including:

[0135] S20621, in response to the first demand of the user demand, a first weight and a second weight are obtained; wherein the first weight is used to represent the importance of the cumulative oil production to the user, and the second weight is used to represent the importance of the cumulative polymer consumption to the user.

[0136] Specifically, the user's emphasis on the cumulative oil production and the cumulative polymer consumption can be understood through the user interaction interface. If the user prefers the cumulative oil production to be the largest, it is clear that the user's emphasis on the oil production is higher than that on the polymer consumption, so it is determined that the first weight is greater than the second weight. If the user prefers the cumulative polymer consumption to be the smallest, it is clear that the user's emphasis on the polymer consumption is higher than that on the oil production, so it is determined that the second weight is greater than the first weight, so as to obtain the first weight and the second weight. The role of this step is to convert the user's emphasis on the two indicators into quantifiable weight values, to provide a basis for subsequent calculation of the evaluation value combined with the oil production and the consumption, and to ensure that the evaluation value can accurately reflect the user's demand.

[0137] S20622, according to the first weight, the second weight, the cumulative oil production and the cumulative polymer consumption, calculating the evaluation value of each injection-production scheme.

[0138] Specifically, the cumulative oil production and the cumulative polymer consumption of all injection-production schemes can be normalized first to obtain the relative value of the oil production of each scheme, and the cumulative polymer consumption can be normalized according to its minimum value to obtain the relative value of the consumption of each scheme. Then, the first weight is multiplied by the relative value of the oil production of the corresponding scheme, and the second weight is multiplied by the relative value of the consumption of the corresponding scheme. The two products are added to obtain the evaluation value of the scheme. The role of this step is to integrate the user's emphasis on the oil production and the consumption into the evaluation value calculation through weight distribution and indicator normalization, so that the evaluation value can intuitively reflect the satisfaction degree of the scheme to the first demand, and provide a unified standard for comparison of different schemes.

[0139] S20623, in response to the user demand being the second demand, obtaining an ideal scheme and a negative ideal scheme; wherein the ideal scheme refers to a preset injection-production scheme with the maximum cumulative oil production and the minimum cumulative polymer consumption, and the negative ideal scheme refers to a preset injection-production scheme with the minimum cumulative oil production and the maximum cumulative polymer consumption.

[0140] Specifically, the cumulative oil production and the cumulative polymer consumption data corresponding to all injection-production schemes can be sorted first, and the maximum cumulative oil production and the minimum cumulative polymer consumption can be selected from these data to form the ideal scheme. At the same time, the minimum cumulative oil production and the maximum cumulative polymer consumption can be selected to form the negative ideal scheme. The role of this step is to provide a clear reference for subsequent calculation of the distance between each injection-production scheme and the ideal state and the worst state, so that the subsequent evaluation value calculation can accurately measure the performance of the scheme in balancing the cumulative oil production and the cumulative polymer consumption, and ensure that the evaluation process meets the user's second demand of pursuing balance between the two.

[0141] S20624, calculating the first Euclidean distance between each injection-production scheme and the ideal scheme, and the second Euclidean distance between each injection-production scheme and the negative ideal scheme.

[0142] Specifically, for each injection-production scheme, the difference between its normalized cumulative oil production and the normalized cumulative oil production of the ideal scheme, and the difference between its normalized cumulative polymer consumption and the normalized cumulative polymer consumption of the ideal scheme can be calculated, the two differences are squared respectively and then added, and then the square root of the added result is taken to obtain the first Euclidean distance of the scheme from the ideal scheme; in the same way, the difference between the normalized cumulative oil production and the normalized cumulative polymer consumption of the scheme and the corresponding indicators of the negative ideal scheme is calculated, and after squaring, summing and taking the square root, the second Euclidean distance from the negative ideal scheme is obtained. The role of this step is to quantify the gap between each injection-production scheme and the ideal state and the worst state, to provide objective data support for the subsequent calculation of the evaluation value combined with the two distances, so that the evaluation value can accurately reflect the performance of the scheme in the balance of cumulative oil production and cumulative polymer consumption, and truly meet the needs of users pursuing the balance of the two.

[0143] S20625、According to the first Euclidean distance of each injection-production scheme from the ideal scheme and the second Euclidean distance of each injection-production scheme from the negative ideal scheme, the evaluation value of each injection-production scheme is calculated.

[0144] Specifically, the second Euclidean distance of each injection-production scheme can be divided by the sum of the first Euclidean distance and the second Euclidean distance to obtain the evaluation value of the scheme, and the larger the value, the closer the scheme is to the ideal scheme and the farther the scheme is from the negative ideal scheme. The role of this step is to quantify the relative distance between the scheme and the ideal state and the worst state, and to convert the performance of the scheme in the balance of cumulative oil production and cumulative polymer consumption into a comparable evaluation value, to provide a clear basis for selecting an injection-production scheme that best meets the needs of users pursuing the balance of the two.

[0145] For example, a 27x27x6 inverted five-spot polymer staged profile control numerical simulation model is established based on a typical reservoir of a medium-low permeability reservoir to illustrate the determination process of the polymer injection-production scheme of the injection well. The basic parameters are shown in Table 1, Figure 2 and Figure 3 Table 1 is a polymer flooding numerical simulation basic parameter table provided by the embodiment of the present application, which lists the reservoir size, average porosity, permeability of each layer, viscosity and density of oil and water, injection-production rate and other key parameters, providing basic physical, chemical and engineering conditions for the numerical simulation of polymer staged profile control.

[0146] Table 1 Polymer flooding numerical simulation basic parameters

[0147]

[0148] Figure 3 The x-direction permeability distribution map provided by the embodiment of the present application shows the spatial distribution of the permeability of the reservoir in the x-direction through color differences, reflecting the heterogeneity of the reservoir permeability, and providing a basis for analyzing the flow characteristics of the fluid in the x-direction.Figure 4 The porosity distribution graph provided by the embodiment of the application represents the porosity distribution of different regions of the reservoir by color, reflects the spatial variation of the porosity of the reservoir, and provides intuitive support for studying the reservoir storage and percolation capacity. Figure 5 The target function distribution graph of the polymer dosage and cumulative oil production provided by the embodiment of the application presents the cumulative oil production distribution corresponding to different polymer dosages by scatter points, directly reflects the change relationship between the two, and provides a data basis for multi-objective optimization.

[0149] In combination with the engineering practice experience of polymer grading profile control and the capacity limit of injection equipment, negative values or excessively high injection concentrations and slug volumes are not allowed to appear in the process of reservoir development. The lower limit and upper limit constraints of the polymer injection concentration are set to 0 mg / L and 3000 mg / L respectively, and the lower limit and upper limit constraints of the slug volume of each well are set to 0 PV and 0.06 PV respectively.

[0150] The Pareto frontier target values are shown in Tables 2 and 3. Tables 2 and 3 list the cumulative oil production and polymer dosage of each candidate scheme on the Pareto frontier after multi-objective optimization, show the trade-off relationship between cumulative oil production (benefit) and polymer dosage (cost), and provide multiple non-dominated optimization candidate schemes.

[0151] Table 1 Pareto frontier target value table

[0152]

[0153] Table 2 Pareto frontier target value table

[0154]

[0155] Based on the above indexes, the subjective weights of each index are calculated by using the analytic hierarchy process method, and the objective weights of each index are calculated by using the entropy weight method. According to the principle of minimum relative entropy, the combined weights of each evaluation index are calculated, and the calculation results are shown in Table 4, which is the combined weight calculation result table. Table 4 gives the subjective weight, objective weight and combined weight of cumulative oil production and polymer dosage, which provides the index weight basis for the combination of subjective and objective scheme optimization.

[0156] Table 4 Combined weight calculation result table

[0157]

[0158] Based on the combined weight of each evaluation index, the TOPSIS method is used to optimize the candidate scheme. The calculation results show that the maximum relative closeness is 0.7218, as shown in Table 5. Compared with the actual scheme, the cumulative oil production of the optimized scheme is increased from 2.4825×105 m3 to 2.7085×105 m3, and the recovery rate is increased by 4.06%; the polymer consumption is reduced from 8.5527×105 m3 to 7.0656×105 m3.

[0159] Table 5 Benefit comparison table

[0160]

[0161] Figure 6 The average water saturation diagram of the reservoir before optimization provided for the embodiments of the present application, Figure 7 The average water saturation diagram of the reservoir after optimization provided for the embodiments of the present application. It can be found that before optimization, the displacement exists in the uneven distribution of the area, and the recovery rate is limited; after optimization, the injection fluid distribution is significantly improved, the unimpinged area is reduced, and the recovery rate is significantly improved. The results show that the method is easy to implement, has strong applicability, and can provide reliable basis for the polymer consumption control, economic benefit evaluation and development scheme optimization of the polymer staged profile control reservoir. Based on the dynamic production data and numerical simulation results of the target reservoir, the gradient viscosity reduction constraint and multi-objective collaborative optimization mechanism are innovatively introduced, which solves the technical problems of low optimization efficiency, high calculation cost and difficulty in considering recovery rate and polymer consumption in the traditional method. The method of the present application has strong engineering operability and popularization value, and can realize rapid and accurate optimization decision in different types of high water cut reservoirs.

[0162] The technical effect of the scheme in this embodiment is: specific evaluation value calculation methods are provided for the first and second needs of the user, making the evaluation process more targeted and scientific. When the user's demand is the first demand, the first and second weights are used to reflect the importance of cumulative oil production and cumulative polymer consumption to the user, so that the evaluation value calculation accurately reflects the user's preference; when the user's demand is the second demand, the ideal scheme and the negative ideal scheme are used, and the first and second Euclidean distances are calculated to determine the evaluation value, which objectively measures the closeness of each scheme to the ideal state. This detailed calculation method ensures the accuracy and rationality of the evaluation value, makes the evaluation of the injection-production scheme meet the actual demand, and improves the reliability of the evaluation result.

[0163] Figure 8 The structure schematic diagram of the variable resistance polymer staged profile control injection-production scheme determination device provided for the embodiments of the present application. As shown in Figure 8 The variable resistance polymer staged profile control injection-production scheme determination device comprises:

[0164] The acquisition module 801 is configured to acquire a plurality of first data and a preset numerical simulation model; the plurality of first data are used to represent an injection concentration and an injection speed of a polymer of a target slug injected into a target injection well, and the target injection well refers to any one of a plurality of preset injection wells, and the target slug refers to any one of a plurality of slugs included in the target injection well.

[0165] The calculation module 802 is configured to input the plurality of first data into the numerical simulation model to obtain a plurality of first development data; the plurality of first development data are used to represent an oil production of a target oil production well when the numerical simulation model is input with the plurality of first data, and the target oil production well refers to any one of a plurality of oil production wells having a displacement relationship with the target injection well.

[0166] The dosage calculation module 803 is configured to calculate a polymer dosage of the target injection well according to the injection concentration and the injection speed.

[0167] The construction module 804 is configured to construct an injection-production optimization control model according to the plurality of first development data and the polymer dosage; the injection-production optimization control model is an optimization model with a maximum cumulative oil production and a minimum cumulative polymer dosage as targets, the cumulative oil production is a sum of oil productions of the plurality of oil production wells, and the cumulative polymer dosage is a sum of polymer dosages of the plurality of injection wells.

[0168] The solving module 805 is configured to perform optimization solving on the injection-production optimization control model based on a plurality of preset constraint conditions to obtain a plurality of injection-production schemes.

[0169] The evaluation module 806 is configured to evaluate the plurality of injection-production schemes according to a preset evaluation rule to obtain evaluation values of the injection-production schemes, and take an injection-production scheme corresponding to a maximum evaluation value as a target injection-production scheme; the target injection-production scheme includes a first concentration, a second concentration, a third concentration, a first speed, a second speed, and a third speed, and the plurality of slugs include a first slug, a second slug, and a third slug.

[0170] The staged injection module 807 is configured to inject the polymer of the first concentration into the first slug at the first speed, inject the polymer of the second concentration into the second slug at the second speed, and inject the polymer of the third concentration into the third slug at the third speed; the first concentration is greater than the second concentration, and the second concentration is greater than the third concentration.

[0171] In a possible design, the solving module 805 includes:

[0172] The sampling unit is configured to sample the plurality of first data to obtain a plurality of second data; the plurality of second data is data obtained by sampling the plurality of first data, and the plurality of first data includes the plurality of second data.

[0173] The first construction unit is configured to construct a proxy model according to the plurality of second data, wherein the proxy model is configured to replace the numerical simulation model to calculate the oil production of the target oil well.

[0174] The disturbance unit is configured to disturb the plurality of second data to obtain a plurality of third data, wherein the plurality of third data is obtained by disturbing the plurality of second data.

[0175] The screening unit is configured to screen the plurality of third data based on the proxy model and a preset screening target to obtain a plurality of fourth data, wherein the plurality of fourth data is a polymer parameter capable of achieving maximum cumulative oil production and minimum cumulative polymer consumption, and the polymer parameter includes injection concentration and injection speed.

[0176] The first calculation unit is configured to input the plurality of fourth data into the numerical simulation model to obtain a plurality of second development data, wherein the plurality of second development data is used to represent the oil production of the target oil well when the input of the numerical simulation model is the plurality of fourth data.

[0177] The solving unit is configured to optimize and solve the injection-production optimization control model based on the plurality of constraint conditions and the plurality of second development data to obtain a plurality of injection-production schemes.

[0178] In a possible design, the first construction unit includes:

[0179] The first calculation component is configured to input the plurality of second data into the numerical simulation model to obtain a plurality of third development data, wherein the plurality of third development data is used to represent the oil production of the target oil well when the input of the numerical simulation model is the plurality of second data.

[0180] The first construction component is configured to construct the proxy model according to the plurality of second data and the plurality of third development data.

[0181] In a possible design, the screening unit includes:

[0182] The second calculation component is configured to input the plurality of third data into the proxy model to obtain a plurality of fourth development data, wherein the plurality of fourth development data is used to represent the oil production of the target oil well when the input of the proxy model is the plurality of third data.

[0183] The screening component is configured to screen the plurality of third data based on the plurality of fourth development data and the screening target to obtain the plurality of fourth data.

[0184] In a possible design, the evaluation module 806 includes:

[0185] The acquisition unit is configured to acquire a user demand, wherein the user demand comprises a first demand and a second demand, the first demand refers to a maximum cumulative oil production and a minimum cumulative polymer consumption, and the second demand refers to a balance between the cumulative oil production and the cumulative polymer consumption.

[0186] The second calculation unit is configured to calculate an evaluation value of each injection-production scheme according to the user demand, the cumulative oil production and the cumulative polymer consumption.

[0187] In a possible design, the second calculation unit comprises:

[0188] The first acquisition component is configured to acquire a first weight and a second weight in response to the user demand being the first demand, wherein the first weight is used to indicate an importance degree of the cumulative oil production to the user, and the second weight is used to indicate an importance degree of the cumulative polymer consumption to the user.

[0189] The third calculation component is configured to calculate an evaluation value of each injection-production scheme according to the first weight, the second weight, the cumulative oil production and the cumulative polymer consumption.

[0190] The second acquisition component is configured to acquire an ideal scheme and a negative ideal scheme in response to the user demand being the second demand, wherein the ideal scheme refers to a preset injection-production scheme with a maximum cumulative oil production and a minimum cumulative polymer consumption, and the negative ideal scheme refers to a preset injection-production scheme with a minimum cumulative oil production and a maximum cumulative polymer consumption.

[0191] The fourth calculation component is configured to calculate a first Euclidean distance between each injection-production scheme and the ideal scheme, and a second Euclidean distance between each injection-production scheme and the negative ideal scheme.

[0192] The fifth calculation component is configured to calculate an evaluation value of each injection-production scheme according to the first Euclidean distance between each injection-production scheme and the ideal scheme, and the second Euclidean distance between each injection-production scheme and the negative ideal scheme.

[0193] The determination apparatus for the variable-resistance polymer staged profile control injection-production scheme provided in this embodiment can perform Figure 2 The technical scheme of the determination method for the variable-resistance polymer staged profile control injection-production scheme shown in this embodiment is similar to that of the determination apparatus for the variable-resistance polymer staged profile control injection-production scheme shown in this embodiment, and thus the technical effects are similar, which will not be repeated here. Figure 2 The technical scheme of the determination method for the variable-resistance polymer staged profile control injection-production scheme shown in this embodiment is similar to that of the determination apparatus for the variable-resistance polymer staged profile control injection-production scheme shown in this embodiment, and thus the technical effects are similar, which will not be repeated here.

[0194] Figure 9 A hardware structure schematic diagram of an electronic device provided in this embodiment is shown in FIG. 9. Figure 9 As shown in FIG. 9, the electronic device 90 comprises at least one processor 901 and a memory 902. The electronic device 90 further comprises a communication component 903. The processor 901, the memory 902 and the communication component 903 are connected through a bus 904.

[0195] In the implementation process, the at least one processor 901 executes the computer-executed instructions stored in the memory 902, so that the at least one processor 901 is used to implement the determination method of the variable-resistance polymer grading profile control and production scheme in the above-mentioned embodiment.

[0196] The specific implementation process of the processor 901 can refer to the method embodiments described above, which have similar implementation principles and technical effects, and will not be described here in detail.

[0197] In the above-mentioned embodiments, it should be understood that the processor 901 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as hardware processor execution or executed by a combination of hardware and software modules in the processor.

[0198] The memory 902 can include a high-speed RAM memory, and can also include a non-volatile storage NVM, for example, at least one disk memory.

[0199] The bus 904 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus 904 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus 904 in the drawings of the present application does not limit to only one bus or one type of bus.

[0200] The functions implemented by the electronic device and the host device are described above, and the scheme provided by the embodiments of the present application is introduced. It can be understood that the electronic device or the host device includes hardware structures and / or software modules corresponding to the functions in order to implement the above functions. The units and algorithm steps of the examples described in combination with the embodiments disclosed in the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of the embodiments of the present application.

[0201] The embodiments of the present application also provide a computer readable storage medium, and the computer readable storage medium stores computer execution instructions. When the computer execution instructions are executed by a processor, a method for determining a variable resistance polymer hierarchical profile control injection and production scheme is implemented. In the specific implementation of the method for determining a variable resistance polymer hierarchical profile control injection and production scheme, each module can be implemented as a processor.

[0202] The readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0203] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the electronic device or the host device.

[0204] The embodiments of the present application also provide a computer program product, which includes a computer program. When the computer program is executed by a processor, a method for determining a variable resistance polymer hierarchical profile control injection and production scheme is implemented.

[0205] The computer program is stored in a readable storage medium, and the at least one processor can read the computer program from the readable storage medium, and execute the computer program to perform the scheme provided by any of the above embodiments.

[0206] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by relevant hardware instructed by programs. The foregoing programs can be stored in a computer readable storage medium. When the programs are executed, the steps of the above-mentioned method embodiments are executed; and the foregoing storage medium includes various media capable of storing program codes, such as ROM, RAM, magnetic disks, or optical disks.

[0207] So far, the technical scheme of the present application has been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical scheme of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical scheme recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical scheme deviate from the scope of the technical scheme of the embodiments of the present application.

Claims

1. A method for determining a variable resistance polymer staged injection-production scheme, characterized in that, include: Acquire multiple first data and a preset numerical simulation model; wherein, the multiple first data are used to represent the injection concentration and injection rate of the polymer injected into the target slug of the target injection well, the target injection well refers to any one of the preset multiple injection wells, and the target slug is any one of the multiple slugs included in the target injection well; The plurality of first data are input into the numerical simulation model to obtain a plurality of first development data; wherein, the plurality of first development data are used to represent the oil production of the target oil well when the input of the numerical simulation model is the plurality of first data, and the target oil well is any one of a plurality of oil wells that have a displacement relationship with the target injection well; The amount of polymer used in the target injection well is calculated based on the injection concentration and the injection rate. Based on the multiple first development data and the polymer usage, an injection-production optimization control model is constructed; wherein, the injection-production optimization control model is an optimization model with the objectives of maximizing cumulative oil production and minimizing cumulative polymer usage, wherein the cumulative oil production is the sum of the oil production of the multiple oil-producing wells, and the cumulative polymer usage is the sum of the polymer usage of the multiple injection wells; The plurality of first data are sampled to obtain a plurality of second data; The plurality of second data are input into the numerical simulation model to obtain a plurality of third development data; wherein, the plurality of third development data are used to represent the oil production of the target oil well when the input of the numerical simulation model is the plurality of second data; Based on the plurality of second data and the plurality of third development data, a proxy model is constructed; the proxy model is used to replace the numerical simulation model to calculate the oil production of the target oil well; The plurality of second data are perturbed to obtain a plurality of third data; based on the proxy model and the preset filtering target, the plurality of third data are filtered to obtain a plurality of fourth data; The plurality of fourth data are input into the numerical simulation model to obtain a plurality of second development data; Based on multiple preset constraints and the multiple second development data, the injection and extraction optimization control model is optimized and solved to obtain multiple injection and extraction schemes; Obtain user needs; wherein, the user needs include a first need and a second need, the first need refers to the maximum cumulative oil production and the minimum cumulative polymer usage, and the second need refers to the balance between the cumulative oil production and the cumulative polymer usage; Based on the user demand, the cumulative oil production, and the cumulative polymer usage, calculate the evaluation value of each injection and production scheme; The injection and production scheme corresponding to the maximum value of the evaluation value is taken as the target injection and production scheme; wherein, the target injection and production scheme includes a first concentration, a second concentration, a third concentration, a first velocity, a second velocity, and a third velocity, and the plurality of slugs includes a first slug, a second slug, and a third slug; The polymer of the first concentration is injected into the first stopper at the first speed, the polymer of the second concentration is injected into the second stopper at the second speed, and the polymer of the third concentration is injected into the third stopper at the third speed; wherein the first concentration is greater than the second concentration, and the second concentration is greater than the third concentration.

2. The method for determining the variable resistance polymer staged injection and production scheme according to claim 1, characterized in that, The method further includes: The plurality of second data are data obtained by sampling the plurality of first data, and the plurality of first data include the plurality of second data; The plurality of third data refers to the data obtained by perturbing the plurality of second data; The plurality of fourth data refers to polymer parameters that enable the maximum cumulative oil production and the minimum cumulative polymer usage, wherein the polymer parameters include the injection concentration and the injection rate; The plurality of second development data are used to represent the oil production of the target oil well when the input of the numerical simulation model is the plurality of fourth data.

3. The method for determining the variable resistance polymer staged injection and production scheme according to claim 2, characterized in that, Based on the proxy model and preset filtering targets, the plurality of third data are filtered to obtain a plurality of fourth data, including: The plurality of third data are input into the proxy model to obtain a plurality of fourth development data; wherein, the plurality of fourth development data are used to represent the oil production of the target oil well when the input of the proxy model is the plurality of third data; Based on the plurality of fourth development data and the filtering target, the plurality of third data are filtered to obtain the plurality of fourth data.

4. The method for determining the variable resistance polymer staged injection and production scheme according to claim 1, characterized in that, The step of calculating the evaluation value of each injection-production scheme based on the user demand, the cumulative oil production, and the cumulative polymer usage includes: In response to the user demand, which is the first demand, a first weight and a second weight are obtained; wherein, the first weight is used to represent the importance of the cumulative oil production to the user, and the second weight is used to represent the importance of the cumulative polymer usage to the user; The evaluation value of each injection and production scheme is calculated based on the first weight, the second weight, the cumulative oil production, and the cumulative polymer usage. In response to the user demand being the second demand, an ideal solution and a negative ideal solution are obtained; wherein, the ideal solution refers to the injection and production solution with the maximum cumulative oil production and the minimum cumulative polymer consumption, and the negative ideal solution refers to the injection and production solution with the minimum cumulative oil production and the maximum cumulative polymer consumption. Calculate the first Euclidean distance between each injection and extraction scheme and the ideal scheme, and the second Euclidean distance between each injection and extraction scheme and the negative ideal scheme; The evaluation value of each injection and extraction scheme is calculated based on the first Euclidean distance between each injection and extraction scheme and the ideal scheme, and the second Euclidean distance between each injection and extraction scheme and the negative ideal scheme.

5. A device for determining a variable resistance polymer staged injection and production scheme, characterized in that, include: The acquisition module is used to acquire multiple first data and a preset numerical simulation model; wherein, the multiple first data are used to represent the injection concentration and injection rate of the polymer injected into the target slug of the target injection well, the target injection well refers to any one of the preset multiple injection wells, and the target slug is any one of the multiple slugs included in the target injection well; The calculation module is used to input the plurality of first data into the numerical simulation model to obtain a plurality of first development data; wherein, the plurality of first development data is used to represent the oil production of the target oil well when the input of the numerical simulation model is the plurality of first data, and the target oil well is any one of a plurality of oil wells that have a displacement relationship with the target injection well; The dosage calculation module is used to calculate the polymer dosage of the target injection well based on the injection concentration and the injection rate. A construction module is used to construct an injection-production optimization control model based on the plurality of first development data and the polymer usage; wherein, the injection-production optimization control model is an optimization model with the objectives of maximizing cumulative oil production and minimizing cumulative polymer usage, wherein the cumulative oil production is the sum of the oil production of the plurality of oil-producing wells, and the cumulative polymer usage is the sum of the polymer usage of the plurality of injection wells; The solution module is used to sample the plurality of first data to obtain a plurality of second data; The plurality of second data are input into the numerical simulation model to obtain a plurality of third development data; wherein, the plurality of third development data are used to represent the oil production of the target oil well when the input of the numerical simulation model is the plurality of second data; Based on the plurality of second data and the plurality of third development data, a proxy model is constructed; the proxy model is used to replace the numerical simulation model to calculate the oil production of the target oil well; The plurality of second data are perturbed to obtain a plurality of third data; based on the proxy model and the preset filtering target, the plurality of third data are filtered to obtain a plurality of fourth data; The plurality of fourth data are input into the numerical simulation model to obtain a plurality of second development data; Based on multiple preset constraints and the multiple second development data, the injection and extraction optimization control model is optimized and solved to obtain multiple injection and extraction schemes; An evaluation module is used to obtain user needs; wherein, the user needs include a first need and a second need, the first need refers to the maximum cumulative oil production and the minimum cumulative polymer usage, and the second need refers to the balance between the cumulative oil production and the cumulative polymer usage; Based on the user demand, the cumulative oil production, and the cumulative polymer usage, an evaluation value for each injection and production scheme is calculated; the injection and production scheme corresponding to the maximum evaluation value is taken as the target injection and production scheme; wherein, the target injection and production scheme includes a first concentration, a second concentration, a third concentration, a first velocity, a second velocity, and a third velocity, and the multiple slugs include a first slug, a second slug, and a third slug; A graded injection module is used to inject a polymer of the first concentration into a first stopper at a first speed, inject a polymer of the second concentration into a second stopper at a second speed, and inject a polymer of the third concentration into a third stopper at the third speed; wherein the first concentration is greater than the second concentration, and the second concentration is greater than the third concentration.

6. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; When the processor executes the computer execution instructions stored in the memory, it is used to implement the method for determining the variable resistance polymer staged injection and production scheme as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for determining a variable resistance polymer staged injection and production scheme as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, The system includes a computer program, which, when executed by a processor, is used to implement the method for determining a variable resistance polymer staged injection and production scheme as described in any one of claims 1 to 4.

Images