A method and apparatus for deploying water control valves based on horizontal wells

Abstract

This application discloses a method and device for deploying water control valves based on horizontal wells, relating to the fields of reservoir development and intelligent control technology. The aim is to improve water control adaptability and dynamically balance water control efficiency with production capacity maintenance requirements. The technical solution is as follows: Based on the three-dimensional reservoir numerical model data of the target well block, the horizontal well trajectory of the target well is divided into multiple grid cells, and the permeability, water saturation, and porosity of each grid cell are extracted; based on the permeability, an anisotropic correction model is used to calculate the equivalent permeability of each grid cell; the water flooding probability of each grid cell is determined based on the equivalent permeability, water saturation, and porosity, and a continuous water flooding probability distribution map of the target well along the horizontal well trajectory is generated based on the water flooding probability; according to the continuous water flooding probability distribution map, an optimization objective function is used to optimize the deployment of the downhole inflow control device valves of the target well, obtaining the valve deployment result of the target well.

Description

Technical Field

[0001] This application relates to the field of reservoir development and intelligent control technology, and in particular to a method and device for deploying water control valves based on horizontal wells. Background Technology

[0002] Horizontal wells, as a core technology for improving oil recovery in complex reservoirs, are widely used in bottom-water reservoirs and fractured reservoirs. However, ineffective water production is a common problem during horizontal well development: due to reservoir heterogeneity (e.g., the permeability of fracture zones can be tens of times higher than that of the matrix zone) and the cone-protrusion effect at the oil-water interface, water intrusion channels easily form in high-permeability areas, leading to a rapid increase in well water cut and a decrease in single-well productivity. Existing water control technologies (such as mechanical water shut-off, chemical water shut-off, and inflow control devices with fixed pressure drop) generally suffer from poor adaptability, high cost, or inability to dynamically respond to reservoir changes, making it difficult to achieve a balance between water control efficiency and stable well production.

[0003] Currently, existing water control strategies largely rely on static design or human experience. This means that fixed water control schemes (such as the installation location and initial opening degree of downhole valves) are determined based on static data from the early stages of reservoir development or engineers' past experience, and these schemes are not adjusted according to reservoir changes after implementation. However, this approach ignores the dynamic evolution of the reservoir during development. The initially designed water control scheme gradually becomes out of sync with the actual reservoir conditions, resulting in poor adaptability and difficulty in dynamically balancing water control efficiency with production capacity maintenance requirements. This can easily lead to a rapid increase in well water cut or a sharp drop in single-well production. Summary of the Invention

[0004] In view of the above problems, this application provides a method and device for deploying water control valves based on horizontal wells, the main purpose of which is to improve water control adaptability and dynamically balance water control efficiency with production capacity maintenance requirements.

[0005] To solve the above-mentioned technical problems, this application proposes the following solution:

[0006] In a first aspect, this application provides a method for deploying water control valves based on horizontal wells, the method comprising:

[0007] Based on the three-dimensional reservoir numerical model data of the block where the target well is located, the horizontal well trajectory of the target well is divided into multiple grid cells, and the permeability, water saturation and porosity of each grid cell are extracted.

[0008] Based on the permeability, the equivalent permeability of each grid cell is calculated using a permeability anisotropy correction model, which is constructed based on the well inclination angle corresponding to the horizontal well trajectory of the target well.

[0009] The water flooding probability of each grid cell is determined based on the equivalent permeability, the water saturation, and the porosity, and a continuous water flooding probability distribution map of the target well along the horizontal well trajectory is generated based on the water flooding probability.

[0010] Based on the continuous flooding probability distribution map, the installation position and initial opening of the downhole inflow control device valves of the target well are optimized using an optimization objective function to obtain the valve deployment results of the target well. The optimization objective of the optimization objective function is to minimize ineffective water production. The constraints of the optimization objective function include valve quantity limit, wellbore pressure drop upper limit, and valve life requirement.

[0011] Secondly, this application provides a water control valve deployment device based on a horizontal well, the device comprising:

[0012] The first processing unit is used to divide the horizontal well trajectory of the target well into multiple grid cells based on the three-dimensional reservoir digital model data of the block where the target well is located, and to extract the permeability, water saturation and porosity of each grid cell.

[0013] The calculation unit is used to calculate the equivalent permeability of each grid cell based on the permeability obtained by the first processing unit using a permeability anisotropy correction model, wherein the permeability anisotropy correction model is constructed based on the well inclination angle corresponding to the horizontal well trajectory of the target well.

[0014] The second processing unit is used to determine the water flooding probability of each grid cell based on the equivalent permeability obtained by the calculation unit, the water saturation obtained by the first processing unit, and the porosity, and to generate a continuous water flooding probability distribution map of the target well along the horizontal well trajectory based on the water flooding probability.

[0015] The optimization unit is used to optimize the installation position and initial opening of the downhole inflow control device valves of the target well based on the continuous flooding probability distribution map obtained by the second processing unit and using an optimization objective function to obtain the valve deployment result of the target well. The optimization objective of the optimization objective function is to minimize ineffective water production. The constraints of the optimization objective function include valve quantity limit, wellbore pressure drop upper limit and valve life requirement.

[0016] To achieve the above objectives, according to a third aspect of this application, a storage medium is provided, the storage medium including a stored program, wherein, when the program is executed, the device where the storage medium is located is controlled to perform the water control valve deployment method based on the first aspect.

[0017] To achieve the above objectives, according to a fourth aspect of this application, a processor is provided for running a program, wherein the program executes the water control valve deployment method based on a horizontal well as described in the first aspect.

[0018] Using the above technical solution, this application provides a method and device for deploying water control valves based on horizontal wells. First, the horizontal well trajectory of the target well is divided into multiple grid cells based on the three-dimensional reservoir numerical model data of the block where the target well is located, and the permeability, water saturation, and porosity of each grid cell are extracted. Then, based on the permeability, the equivalent permeability of each grid cell is calculated using a permeability anisotropy correction model. The permeability anisotropy correction model is constructed based on the well inclination angle corresponding to the horizontal well trajectory of the target well. Then, the water flooding probability of each grid cell is determined based on the equivalent permeability, water saturation, and porosity, and a continuous water flooding probability distribution map of the target well along the horizontal well trajectory is generated based on the water flooding probability. Finally, based on the continuous water flooding probability distribution map, the installation position and initial opening of the downhole inflow control device valves of the target well are deployed and optimized using an optimization objective function to obtain the valve deployment result of the target well. The optimization objective of the optimization objective function is to minimize ineffective water production, and the constraints of the optimization objective function include valve quantity limits, wellbore pressure drop limits, and valve life requirements. The technical solution provided in this application, by dividing the horizontal well trajectory into multiple grid cells and extracting the permeability, water saturation, and porosity of each cell, can more accurately reflect the impact of reservoir heterogeneity on water flooding dynamics, avoid water control deviations caused by traditional homogenization assumptions, and provide high-resolution data support for subsequent valve deployment. It utilizes a permeability anisotropy correction model to calculate the equivalent permeability, eliminating the influence of well inclination angle on permeability anisotropy, further improving the accuracy of water flooding prediction. With the goal of minimizing ineffective water production, and considering valve quantity limitations, wellbore pressure drop limits, and lifespan requirements, it finds the optimal solution under complex constraints by optimizing the objective function. This allows for precise deployment of valve installation positions and initial openings, ensuring the economy, reliability, and sustainability of valve deployment, thereby reducing ineffective water production, extending well lifespan, and significantly improving oilfield development efficiency.

[0019] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0020] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0021] Figure 1 This paper presents a flowchart illustrating a water control valve deployment method based on a horizontal well, according to an embodiment of this application.

[0022] Figure 2 This paper illustrates a flowchart of another water control valve deployment method based on a horizontal well, provided in an embodiment of this application.

[0023] Figure 3 This illustration shows a block diagram of a water control valve deployment device based on a horizontal well, according to an embodiment of this application.

[0024] Figure 4 This paper illustrates a block diagram of another water control valve deployment device based on a horizontal well, as provided in an embodiment of this application. Detailed Implementation

[0025] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0026] Currently, existing water control strategies largely rely on static design or human experience. This means that fixed water control schemes (such as the installation location and initial opening degree of downhole valves) are determined based on static data from the early stages of reservoir development or engineers' past experience, and these schemes are not adjusted according to reservoir changes after implementation. However, this approach ignores the dynamic evolution of the reservoir during development (such as increased permeability anisotropy and a sudden increase in local water saturation due to long-term production). The initially designed water control scheme gradually becomes out of sync with the actual reservoir conditions, resulting in poor adaptability to water control and difficulty in dynamically balancing water control efficiency with production capacity maintenance requirements. This can easily lead to a rapid increase in well water cut or a sharp drop in single-well production.

[0027] Therefore, this application provides a method for deploying water control valves based on horizontal wells. This method can improve water control adaptability and dynamically balance water control efficiency with production capacity maintenance requirements. The specific execution steps are as follows: Figure 1 As shown, it includes:

[0028] 101. Based on the three-dimensional reservoir numerical model data of the block where the target well is located, the horizontal well trajectory of the target well is divided into multiple grid cells, and the permeability, water saturation and porosity of each grid cell are extracted.

[0029] In this step, three types of core data are acquired in advance for the block where the target well is located: seismic data, well logging data, and core experimental data. Seismic data, obtained through 3D seismic exploration, includes reservoir structure data (such as stratigraphic depth and fault distribution) to determine the macroscopic distribution of the reservoir. Well logging data, including logging curves of the target well and adjacent wells (such as resistivity, sonic transit time, and neutron porosity logging), is used to calibrate reservoir lithology and physical properties (permeability and porosity). Core experimental data consists of core samples obtained from the target well (at least three segments, each ≥1m in length). The original horizontal permeability (K_h) and original vertical permeability (K_v) are determined through laboratory core flow experiments, and the water saturation (S_w) is determined through centrifugation experiments, serving as a verification benchmark for the numerical model data.

[0030] The Petrel reservoir modeling software was used to integrate the three types of core data mentioned above. Specifically, data errors were eliminated (such as stratigraphic shift in seismic data and wellbore enlargement interference in well logging data). Missing well logging data were supplemented using the "adjacent well interpolation method" to ensure that the data covered the entire trajectory of the target well's horizontal section. Core experimental data were normalized to ensure that the units were consistent with the numerical model data (permeability unit: mD; porosity unit: decimal; water saturation unit: decimal).

[0031] Drilling-while-drilling (MWD) data is extracted from the target well's drilling report, including "well depth - wellhead coordinates - vertical depth - inclination angle - azimuth" at measurement points every 2 meters. This forms a spatial coordinate sequence for the horizontal well trajectory (e.g., at a well depth of 2000m, X=58200m, Y=32100m, vertical depth 1800m, inclination angle 85°, azimuth angle 120°). This sequence is then imported into a 3D reservoir digital model mesh in Petrel software. The coordinate sequence of the horizontal well trajectory is mapped onto the digital model mesh, and the digital model mesh cells traversed by the trajectory are determined. These cells are then "trajectory segmented," ensuring that each segmented mesh cell has a consistent length (e.g., 2-5m), ultimately forming N consecutive "horizontal well trajectory mesh cells." For example, if the target well's horizontal segment is 600m long, it is divided into 200 mesh cells, numbered 1-200.

[0032] Based on the permeability field data of the 3D digital model, the "fracture conductivity" of each model grid is calculated (formula: FCD=K_f×w, where K_f is the fracture permeability and w is the fracture width). A fracture zone determination threshold is set. If the fracture conductivity of a certain model grid is greater than 5D... If a grid is defined as a "fracture zone grid" (based on empirical values ​​from historical development data of the target block) and is located within 5m of the horizontal well trajectory, then the grid is considered a "matrix zone grid." All other grids are defined as "matrix zone grids." Using the original grid size from the digital model, the matrix zone digital model grid mapped from the trajectory is directly used as the "matrix zone trajectory grid cell" to ensure computational efficiency. The fracture zone grid employs a "locally refined grid," densifying the original grid into a denser grid, and then dividing it according to the horizontal well trajectory to obtain the "fracture zone trajectory grid cell." This densification allows for the capture of subtle flow paths in the fracture network (such as tiny fractures with a width of 0.1mm), avoiding the omission of water intrusion paths caused by traditional coarse grids.

[0033] The "distortion rate" (the ratio of the maximum side length to the minimum side length of the mesh) of the FLAC3D software was used to calculate the mesh. The distortion rate of the mesh in the crack zone was required to be <10%, and the distortion rate of the mesh in the matrix zone was required to be <20%, so as to ensure the calculation accuracy of the subsequent fluid flow simulation.

[0034] The original horizontal permeability (K_h) and original vertical permeability (K_v) of each trajectory grid cell are extracted from the "Permeability Field Attributes" of the 3D numerical model. If the grid cell contains both matrix and fractures, the "volume-weighted method" is used to calculate the overall permeability. The water saturation of each grid cell in the current development stage is extracted from the "Fluid Saturation Field" of the numerical model. If the numerical model is a dynamic simulation result, the average S_w value of the most recent time step (e.g., 1 month) is taken. The porosity of each grid cell is directly extracted from the "Porosity Field" of the numerical model. If there is a grid cell corresponding to the core data, it must be ensured that the error between the extracted φ value and the core experimental value is <5% (if the error exceeds the limit, the numerical model is corrected with the core data). The extracted parameters were processed using the Min-Max standardization formula: Standardized value = (Original value - Minimum value) / (Maximum value - Minimum value), where "Maximum value / Minimum value" is taken from the statistical range of parameters of similar reservoirs in the target block (e.g., K_h: 0.1-1000mD; S_w: 0.2-0.9; φ: 0.1-0.3). Extremely high permeability values ​​(e.g., K_h > 2000mD) in fracture zone grid cells were "truncated" (values ​​exceeding 2000mD were set to 2000mD) to avoid interference from outliers during subsequent model training.

[0035] 102. Based on permeability, the equivalent permeability of each grid cell is calculated using a permeability anisotropy correction model.

[0036] The permeability anisotropy correction model is constructed based on the inclination angle corresponding to the horizontal well trajectory of the target well.

[0037] In this step, based on the drilling survey data obtained in step 101, the average well inclination angle of each grid cell is calculated using the "linear interpolation method". The well inclination angle specifically refers to the angle between the wellbore axis and the horizontal plane, ranging from 0° (completely horizontal) to 90° (completely vertical). The well inclination angle is converted from "degrees" to "radians" (formula: radians = angle × π / 180) to ensure the accuracy of subsequent trigonometric function calculations.

[0038] Permeability anisotropy refers to the physical characteristic that the same rock exhibits different permeability in the horizontal and vertical directions. Horizontal permeability, parallel to the formation, is typically higher than vertical permeability. Based on the well inclination angle θ corresponding to the horizontal well trajectory of the target well, a permeability anisotropy correction model is constructed. Specifically, this is the equivalent permeability formula. The calculation logic is as follows: For each grid cell, the original horizontal permeability is multiplied by the square of the cosine of the well inclination angle to obtain the first weighted contribution value; the original vertical permeability is multiplied by the square of the sine of the well inclination angle to obtain the second weighted contribution value; and the first and second weighted contribution values ​​are then summed to obtain the equivalent permeability. The specific calculation formula is as follows:

[0039] ;

[0040] in, Equivalent permeability reflects the effective permeability in the actual flow direction; This refers to the original horizontal permeability in the permeability, which reflects the permeability along the horizontal direction of the reservoir. The original vertical permeability in the permeability refers to the permeability along the vertical direction of the reservoir, which is usually based on the anisotropy of sandstone reservoirs. The inclination angle corresponds to the horizontal well trajectory, and the inclination angle determines the weighting of horizontal / vertical permeability.

[0041] Select 3-5 grid cells with corresponding core data, and determine the actual effective permeability through a laboratory "inclined core flow experiment" (simulating well inclination conditions). Compare this result with the permeability calculated using the above formula. The comparison should be performed with an error of less than 10%. If the error exceeds 10%, adjustments should be made. The proportion of values, such as from 0.1 Adjusted to 0.08 Substitute all grid cells into the Eclipse reservoir simulator to simulate the target well's water production curve over the past year. Compare this with actual production data (such as water cut changes). If the average error between the simulated and actual water cut is less than 5%, the equivalent permeability calculation result is valid; otherwise, recalculate the well inclination angle or... Take the value until the error meets the standard.

[0042] 103. Determine the water flooding probability of each grid cell based on the equivalent permeability, water saturation, and porosity, and generate a continuous water flooding probability distribution map of the target well along the horizontal well trajectory based on the water flooding probability.

[0043] In this step, a Bayesian network model is used to calculate the water flooding probability of each grid cell. This model uses equivalent permeability, water saturation, and porosity as input variables. The structure of the Bayesian network model includes nodes (equivalent permeability, water saturation, and porosity) and a conditional probability table (CPT). The conditional probability table is determined based on historical oil well data using the maximum likelihood estimation method, reflecting the statistical relationship between each parameter and the water flooding probability.

[0044] For each grid cell, its equivalent permeability, water saturation, and porosity are input, and the water flooding probability P_w for that grid cell is calculated using a Bayesian network model. A threshold for the water flooding probability is set based on historical data (e.g., P_w > 0.6 is considered a high risk of water flooding). The Kriging interpolation algorithm is used to spatially interpolate the water flooding probability of the grid cells, generating a continuous water flooding probability distribution map along the horizontal well trajectory. The Kriging interpolation parameters (such as the variogram type and range parameters) are determined based on the geological characteristics of the block where the target well is located. The interpolation process considers the spatial correlation of the grid cells to ensure the continuity and smoothness of the distribution map. The generated continuous water flooding probability distribution map forms a continuous curve with the horizontal well trajectory as the horizontal axis and the water flooding probability as the vertical axis. The area below the curve is filled with gradient colors: probability 0-0.4 (blue) -> 0.4-0.6 (yellow) -> 0.6-0.8 (orange) -> 0.8-1.0 (red), which intuitively distinguishes the "low risk - medium risk - medium-high risk - high risk" areas. The crack zone range and high risk peak points are marked on the map to provide a clear "risk target area" for subsequent valve deployment.

[0045] After obtaining the continuous water flooding probability distribution map, its accuracy can be verified by comparing it with historical production data of the target well. For areas with abnormal fluctuations in the distribution map, the kriging interpolation parameters or the conditional probability table of the Bayesian network model are adjusted to smooth the distribution map and ensure that it conforms to geological laws.

[0046] 104. Based on the continuous flooding probability distribution map, the installation position and opening degree of the downhole inflow control device valve of the target well are optimized by using an optimization objective function to obtain the valve deployment result of the target well.

[0047] The optimization objective of the objective function is to minimize ineffective water production. The constraints of the objective function include valve quantity limits, wellbore pressure drop limits, and valve life requirements.

[0048] This step uses a multi-objective optimization function and a genetic algorithm to find the valve deployment scheme with the highest water control efficiency and lowest cost while meeting engineering constraints. The implementation is divided into four sub-steps:

[0049] In this step, the specific expression for optimizing the objective function is:

[0050] ;

[0051] in, To control water efficiency, For valve cost, and These are the weighting coefficients.

[0052] It should be noted that, To improve water control efficiency, the reduction ratio of ineffective water production in high-risk areas (P≥0.6) can be calculated by calculating the water production of high-risk grid cells before and after optimization. Valve cost, specifically the valve's total lifecycle cost, includes procurement cost, installation cost, and maintenance cost; and To determine the priority based on project requirements, in this embodiment, "water control takes precedence over cost," which can be taken as... =0.8, =0.2.

[0053] Among the constraints mentioned above, the valve quantity limit is set to a maximum of N_max (e.g., 15 valves), and the selection operation of the genetic algorithm ensures that the number of valves in each individual in the population does not exceed N_max; the wellbore pressure drop limit is set to a safe threshold of ΔP_max (e.g., 5MPa), and a penalty term is introduced into the fitness function. When the valve deployment scheme causes the wellbore pressure drop to exceed ΔP_max, the fitness value decreases by the square of the excess pressure drop; the valve life requirement is set to a valve opening adjustment range of ±10%, and the adjustment range of the valve opening is limited in the mutation operation to ensure that the valves are not frequently adjusted during long-term operation.

[0054] Based on the above objective function, a genetic algorithm is used for implementation, as follows: An initial population is generated, with each individual representing a valve deployment scheme (including valve position and opening degree); gene fragments of the best individual in each generation are retained to avoid premature convergence; tournament selection is performed based on fitness values ​​to retain high-fitness individuals; a single-point crossover operation is used to exchange partial genes (valve position and opening degree) between two parent individuals; random mutation is performed on some individuals to adjust the valve opening degree or position; the selection, crossover, and mutation operations are repeated until the maximum number of iterations is reached or the fitness value converges. Wellbore pressure drop simulation is performed on the optimized valve deployment scheme to verify whether it meets the upper limit constraint of wellbore pressure drop; reservoir numerical simulation is used to verify the water control effect and economy of the optimized scheme; after confirming that the scheme meets all constraints, the valve deployment results for the target well are generated, including a list of valve installation positions (grid cell number for each valve) and opening degree settings; the valve deployment results are transmitted to the downhole inflow control device to achieve automatic control.

[0055] Furthermore, to ensure the water control results, after the control operation is completed according to the valve deployment results, the production data of the horizontal well, including water production, oil production and wellbore pressure, can be monitored in real time. When the probability of water flooding suddenly increases to the risk probability threshold (e.g., P_w>0.8), the valve adjustment mechanism is automatically triggered to urgently close or adjust the associated valves in the high-risk area to the preset minimum opening degree (e.g., 20%) to control ineffective water production.

[0056] Based on the above Figure 1 As can be seen from the implementation method, the water control valve deployment method based on horizontal wells provided in this application divides the horizontal well trajectory into multiple grid cells and extracts the permeability, water saturation and porosity of each cell. This can more accurately reflect the impact of reservoir heterogeneity on water flooding dynamics, avoid water control deviation caused by traditional homogenization assumptions, and provide high-resolution data support for subsequent valve deployment. The equivalent permeability is calculated using a permeability anisotropy correction model to eliminate the influence of well inclination angle on permeability anisotropy, further improving the accuracy of water flooding prediction. With the goal of minimizing ineffective water production, combined with valve quantity restrictions, wellbore pressure drop upper limit and life requirements, the optimal solution is found under complex constraints by optimizing the objective function. This can accurately deploy the valve installation position and initial opening, ensuring the economy, reliability and sustainability of valve deployment, thereby reducing ineffective water production, extending well life and significantly improving oilfield development benefits.

[0057] Furthermore, the preferred embodiments of this application are based on the above... Figure 1 Based on this, a detailed explanation of the deployment process of water control valves based on horizontal wells is provided, and the specific steps are as follows: Figure 2 As shown, it includes:

[0058] 201. Based on the three-dimensional reservoir numerical model data of the block where the target well is located, the horizontal well trajectory of the target well is divided into multiple grid cells, and the permeability, water saturation and porosity of each grid cell are extracted.

[0059] This step combines the description of step 101 in the above method, and the same content will not be repeated here.

[0060] 202. Based on permeability, the equivalent permeability of each grid cell is calculated using a permeability anisotropy correction model.

[0061] This step combines the description of step 102 in the above method, and the same content will not be repeated here.

[0062] Furthermore, the permeability includes the original horizontal permeability and the original vertical permeability. Based on the permeability, the specific execution process of calculating the equivalent permeability of each grid cell using the permeability anisotropy correction model is as follows: For each grid cell, the original horizontal permeability is multiplied by the square of the cosine of the well inclination angle to obtain the first weighted contribution value, and the original vertical permeability is multiplied by the square of the sine of the well inclination angle to obtain the second weighted contribution value; the first weighted contribution value and the second weighted contribution value are summed to obtain the equivalent permeability.

[0063] The formula for calculating equivalent permeability is:

[0064] ;

[0065] in, For equivalent penetration rate, The original horizontal permeability in the permeability. This refers to the original vertical permeability in the permeability. This represents the inclination angle corresponding to the horizontal well trajectory.

[0066] By introducing the θ-well inclination angle to correct for permeability anisotropy, dynamic fusion of horizontal and vertical permeability is achieved, significantly improving the calculation accuracy of equivalent permeability. and The weighting of the data quantifies the contribution of permeability in different directions to fluid flow, more realistically reflects the impact of reservoir heterogeneity on water flooding dynamics, reduces the identification error of water flooded areas, provides reliable data support for the precise deployment of water control valves, and takes into account the flow differences between fracture zones and matrix zones, thereby improving the economy and sustainability of complex reservoir development.

[0067] 203. Determine the water flooding probability of each grid cell based on the equivalent permeability, water saturation, and porosity, and generate a continuous water flooding probability distribution map of the target well along the horizontal well trajectory based on the water flooding probability.

[0068] This step combines the description of step 103 in the above method, and the same content will not be repeated here.

[0069] Furthermore, the specific execution process for determining the water flooding probability of each grid cell based on the equivalent permeability, water saturation, and porosity, and generating a continuous water flooding probability distribution map of the target well along the horizontal well trajectory based on the water flooding probability, is as follows: The equivalent permeability, water saturation, and porosity are input as input variables into the Bayesian network model to calculate the water flooding probability of each grid cell; Based on the water flooding probability of each grid cell, the Kriging interpolation algorithm is used to generate a continuous water flooding probability distribution map of the target well along the horizontal well trajectory.

[0070] By using equivalent permeability (reflecting reservoir conductivity), water saturation (characterizing the degree of water intrusion), and porosity (affecting reservoir performance) as input variables, Bayesian networks can quantify the joint influence of these parameters on flooding probability, avoiding the one-sidedness of single-parameter prediction and improving the accuracy and interpretability of flooding prediction. The Kriging interpolation algorithm dynamically adjusts weights based on the spatial distance and variability function between computational units, avoiding the sensitivity of traditional interpolation methods to outliers, thereby generating a high-precision continuous flooding probability distribution map.

[0071] 204. Based on the continuous flooding probability distribution map, the installation position and opening degree of the downhole inflow control device valves of the target well are optimized using an optimization objective function to obtain the valve deployment results of the target well.

[0072] This step combines the description of step 104 in the above method, and the same content will not be repeated here.

[0073] Furthermore, based on the continuous flooding probability distribution map, the installation position and opening degree of the downhole inflow control device valves of the target well are optimized using an optimization objective function. The specific execution process for obtaining the valve deployment result of the target well is as follows: minimizing ineffective water production is taken as the optimization objective, and the valve quantity limit, wellbore pressure drop limit, and valve life requirement are taken as constraints to construct the optimization objective function corresponding to the target well; the installation position and opening degree of the downhole inflow control device valves are calculated using the optimization objective function to obtain the valve deployment result.

[0074] The objective function to be optimized is:

[0075] ;

[0076] in, To optimize the objective function to maximize the result, To control water efficiency, For valve cost, and These are the weighting coefficients.

[0077] By introducing water control efficiency, ineffective water production in high water-flooded areas is suppressed first, ensuring oil well productivity. Combined with the weighted combination of valve costs, a synergistic balance of multi-objective optimization is achieved, significantly improving the economic and technical feasibility of horizontal well water control strategies.

[0078] 205. Real-time monitoring of whether there are target grid cells where the probability of flooding suddenly increases to the risk probability threshold.

[0079] In this step, a distributed fiber optic sensing system is installed downhole in the target well, with a sensing node positioned every 50 meters along the horizontal well trajectory to monitor the temperature, pressure, and fluid characteristics within the wellbore in real time. A downhole data acquisition unit is also configured to collect monitoring data every 15 minutes and transmit the data to the surface control system via the downhole communication network. A real-time water flooding probability calculation module is deployed in the surface control system. This module dynamically calculates the current water flooding probability for each grid cell based on the continuous water flooding probability distribution map generated in step 203 and the real-time monitoring data.

[0080] The formula for calculating the probability of flooding is:

[0081] P_w(t) = P_w0 + k × (ΔT / Δt);

[0082] Where P_w0 is the initial flood probability (based on the continuous flood probability distribution map generated in step 203), k is the flood probability variation coefficient (determined based on historical data, with a typical value of 0.05-0.15), and ΔT / Δt is the real-time temperature change rate (unit: ℃ / min). A mapping relationship is established between the temperature change rate and the flood probability. When the temperature change rate exceeds a threshold (e.g., 0.3℃ / min), it indicates that the risk of flooding is increasing.

[0083] The risk probability threshold P_risk is determined based on historical oil well data and is generally set to 0.7-0.8 (P_w>0.75 is considered high risk). The risk threshold is automatically adjusted according to the current production status of the oil well (such as production rate and water cut). When the production rate exceeds 100 m³ / d, P_risk is set to 0.75, and when the production rate is below 50 m³ / d, P_risk is set to 0.85 to adapt to different production stages.

[0084] The criteria for determining a sudden increase are:

[0085] P_w(t)>P_risk and (P_w(t)-P_w(t-1))>ΔP_threshold;

[0086] Among them, ΔP_threshold is the threshold for a sudden increase in the probability of flooding, which is determined based on historical data, with a typical value of 0.15.

[0087] The monitoring system can perform real-time surge detection on each grid cell in 5-minute time windows. When the above surge conditions are met, the system marks the grid cell as a target grid cell with a "surge in flood probability". If a target grid cell exists, step 206 is executed. Otherwise, the surge detection process continues.

[0088] In addition, the accuracy of the water flooding probability calculation can be verified by comparing data with those from downhole flow meters and water cut analyzers. For grid cells with a false alarm rate exceeding 10%, the ΔP_threshold parameter is automatically adjusted to improve monitoring accuracy. A monitoring system performance evaluation mechanism is established to ensure that the monitoring accuracy is not less than 95%.

[0089] 206. Identify existing target grid cells as high-risk areas.

[0090] In this step, a high-risk area refers to the set of grid cells where the probability of flooding suddenly increases to the risk probability threshold (P_w>P_risk). The boundary of the area is determined by the spatial distribution of the grid cells. The flooding probability of the boundary grid cells satisfies P_w>P_risk, and the difference between the flooding probability of the boundary grid cells and that of the adjacent grid cells exceeds ΔP_boundary (typically 0.1).

[0091] High-risk areas are identified using a region growing algorithm. Starting from the first grid cell that meets the burst condition, the algorithm expands to adjacent grid cells until the flooding probability of all adjacent grid cells is lower than P_risk. The geometry of the high-risk area is determined by the spatial distribution of the grid cells, which is usually linear or blocky. The geometric parameters of the high-risk area, including area, length, and center point coordinates, are calculated using spatial analysis software (such as ArcGIS).

[0092] The system can recalculate high-risk areas every 15 minutes to ensure that the area boundaries are synchronized with changes in flood risk. When a high-risk area expands or shrinks, the system automatically updates the area boundaries. By comparing historical data, the system determines the typical expansion rate of high-risk areas (e.g., 0.5-1.5 grid cells / hour), providing a basis for subsequent risk prediction.

[0093] High-risk areas are highlighted on a continuous flood probability distribution map, with color coding indicating the degree of risk (probability 0-0.4 (blue) -> 0.4-0.6 (yellow) -> 0.6-0.8 (orange) -> 0.8-1.0 (red), intuitively distinguishing between "low-risk - medium-risk - medium-high-risk - high-risk" areas). A database linking high-risk areas with historical flood events is established to analyze the formation patterns of high-risk areas. High-risk areas are displayed in real time through a visual interface, providing decision support for operators.

[0094] In addition, the accuracy of high-risk areas can be verified through downhole flow monitoring data to ensure that the water production rate in high-risk areas is significantly higher than that in other areas. For high-risk areas that do not meet the verification criteria, the ΔP_threshold parameter in the sudden increase judgment criteria can be adjusted to establish a prediction model for high-risk areas and predict the future development trend of high-risk areas based on historical data.

[0095] 207. Based on the installation location of the downhole inflow control device valve, further determine whether there is another related downhole inflow control device valve in the high-risk area.

[0096] In this step, a valve installation location database is pre-established, containing information such as the ID, installation location (grid cell number), control range, and historical opening records for each valve. A precise correspondence is established between valve installation locations and grid cells, with each valve corresponding to one or more grid cells. The valve control range is defined as the set of grid cells that the valve can effectively control, typically consisting of the valve's own grid cell and two grid cells before and after it.

[0097] Spatial query technology is used to determine whether there are associated valves within a high-risk area. Specifically, for each grid cell within the high-risk area, the valve installation location database is queried to determine if any valve's control range includes that grid cell. Grid cells within the high-risk area must be within the valve's control range. Spatial indexing (such as R-tree) is used to accelerate the query process, ensuring a judgment speed of less than 100ms. A correlation matrix is ​​established to record the degree of correlation between high-risk areas and valves. For valves associated with high-risk areas, they are sorted according to their correlation with the high-risk area: Correlation = (Number of grid cells controlled by the valve in the high-risk area) / (Total number of grid cells in the high-risk area). The valve with the highest correlation is selected as the primary risk valve. Valves with a correlation below 0.3 are not considered for risk. For multiple valves with the same correlation, they are sorted according to their historical opening stability (standard deviation), with valves with higher opening stability being prioritized. If another associated downhole inflow control device valve exists, step 208 is executed.

[0098] In addition, historical valve control data can be used to verify the correlation, ensuring that the valves do indeed control flooding in high-risk areas. For valves with unclear correlations, simulation tests can be used to verify their control effects, establishing a reliability assessment mechanism for valve correlations to ensure that the accuracy of the correlations is no less than 90%.

[0099] It is important to emphasize that valve relationships are automatically recalculated after each update of high-risk areas. The relationship database is automatically updated whenever valve location or control range changes. Historical data analysis is used to determine the stability of valve relationships.

[0100] 208. Define the valve of another associated downhole inflow control device as a risk valve and control the risk valve.

[0101] Among them, the preset minimum opening is the minimum safe flow threshold to which the valve is adjusted in a risk situation.

[0102] In this step, the risk valve refers to a valve with a high degree of association with a high-risk area (association degree ≥ 0.5) and an increasing water flooding risk. The characteristic parameters of the risk valve include: association degree, current opening, historical opening change rate, valve type (such as electro-hydraulic drive valve, mechanical valve). Establish a priority ranking mechanism for risk valves, and prioritize the valves with high association degree and fast-growing water flooding risk.

[0103] The preset minimum opening (O_min) is the minimum safe flow threshold to which the valve is adjusted in a risk situation, ensuring that the oil well will not be completely shut down. The determination of O_min is based on historical data and reservoir engineering experience. The typical value is 20% - 30%, and its specific value is dynamically adjusted according to the production status of the oil well: when the liquid production volume > 100 m³ / d, O_min = 25%; when the liquid production volume is 50 - 100 m³ / d, O_min = 20%; when the liquid production volume < 50 m³ / d, O_min = 15%. Determine the optimal value of O_min through reservoir numerical simulation to ensure the basic production of the oil well while controlling ineffective water production.

[0104] When the water flooding risk increases sharply (P_w(t) - P_w(t - 1) > 0.3) and the water production rate exceeds 80%, execute an emergency shutdown and immediately adjust the valve opening to 0%. When the water flooding risk increases but does not reach the emergency level (0.15 < P_w(t) - P_w(t - 1) ≤ 0.3), adjust the valve opening to the preset minimum opening O_min. The adjustment of the valve opening is continuous and can be fine-tuned every 5 minutes to avoid mechanical wear caused by frequent valve switching.

[0105] The specific control process is as follows: when the risk valve is determined, the system generates a control instruction and sends it to the corresponding valve through the downhole communication network; after receiving the control instruction, the valve executes the opening adjustment operation and at the same time feeds back the execution result to the surface control system; during the control process, parameters such as wellbore pressure and flow rate are monitored in real time to ensure the safety of the adjustment process; if the wellbore pressure drop exceeds the safety threshold (ΔP_max = 5 MPa) after adjustment, the system automatically adjusts the valve opening back to the previous state.

[0106] To avoid frequent adjustment settings, the minimum time interval for valve opening adjustment can be set (such as 30 seconds). When the number of consecutive valve adjustments exceeds the threshold (such as 5 times / hour), the system automatically pauses the adjustment and issues a warning.

[0107] Based on the detailed implementation described in steps 205-208 above, by real-time monitoring of sudden changes in the probability of water flooding and linking the valves of the downhole inflow control device, dynamic response and precise water control in high-risk areas are achieved, significantly improving the safety and economy of oil well development.

[0108] Furthermore, as a response to the above Figure 1-2 The implementation of the method embodiment shown in this application provides a water control valve deployment device based on a horizontal well. This device is used to improve water control adaptability and dynamically balance water control efficiency with production capacity maintenance requirements. The embodiment of this device corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will not repeat the details of the aforementioned method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the aforementioned method embodiment. Specifically, as shown... Figure 3 As shown, the device includes:

[0109] The first processing unit 31 is used to divide the horizontal well trajectory of the target well into multiple grid cells based on the three-dimensional reservoir digital model data of the block where the target well is located, and to extract the permeability, water saturation and porosity of each grid cell.

[0110] The calculation unit 32 is used to calculate the equivalent permeability of each grid cell based on the permeability obtained by the first processing unit 31 using a permeability anisotropy correction model. The permeability anisotropy correction model is constructed based on the well inclination angle corresponding to the horizontal well trajectory of the target well.

[0111] The second processing unit 33 is used to determine the water flooding probability of each grid cell based on the equivalent permeability obtained by the calculation unit 32, the water saturation obtained by the first processing unit 31, and the porosity, and to generate a continuous water flooding probability distribution map of the target well along the horizontal well trajectory based on the water flooding probability.

[0112] The optimization unit 34 is used to optimize the installation position and initial opening of the downhole inflow control device valve of the target well based on the continuous flooding probability distribution map obtained by the second processing unit 33 and the optimization objective function, so as to obtain the valve deployment result of the target well. The optimization objective of the optimization objective function is to minimize ineffective water production. The constraints of the optimization objective function include valve quantity limit, wellbore pressure drop upper limit and valve life requirement.

[0113] Furthermore, such as Figure 4 As shown, the first processing unit 31 includes:

[0114] The identification module 311 is used to identify the fracture zone and matrix zone corresponding to the horizontal well trajectory in the three-dimensional reservoir numerical model data. The fracture zone is determined based on the joint analysis of the permeability field and fracture conductivity of the target well, and the matrix zone is the area outside the fracture zone.

[0115] The partitioning module 312 is used to partition the matrix area obtained by the identification module 311 using a first grid and the fracture zone using a second grid to obtain multiple grid cells corresponding to the horizontal well trajectory, wherein the grid density of the second grid is greater than that of the first grid.

[0116] Furthermore, such as Figure 4 As shown, the second processing unit 33 includes:

[0117] The first calculation module 331 is used to input the equivalent permeability, the water saturation and the porosity as input variables into the Bayesian network model to calculate the flooding probability of each grid cell.

[0118] The generation module 332 is used to generate a continuous flooding probability distribution map of the target well along the horizontal well trajectory based on the flooding probability of each grid cell obtained by the first calculation module 331 and using the Kriging interpolation algorithm.

[0119] Furthermore, such as Figure 4 As shown, the permeability includes the original horizontal permeability and the original vertical permeability; the permeability anisotropy correction model includes the square of the cosine of the well inclination angle and the square of the sine of the well inclination angle; based on the permeability, the calculation unit 32 includes:

[0120] The second calculation module 321 is used to multiply the original horizontal permeability by the square of the cosine of the well inclination angle to obtain a first weighted contribution value for each grid cell, and to multiply the original vertical permeability by the square of the sine of the well inclination angle to obtain a second weighted contribution value.

[0121] The third calculation module 322 is used to sum the first weighted contribution value and the second weighted contribution value obtained by the second calculation module 331 to obtain the equivalent penetration rate;

[0122] The formula for calculating the equivalent permeability is:

[0123] ;

[0124] in, For equivalent penetration rate, The original horizontal permeability in the permeability. The original vertical permeability in the permeability is mentioned. This represents the inclination angle corresponding to the horizontal well trajectory.

[0125] Furthermore, such as Figure 4 As shown, the optimization unit 34 includes:

[0126] Construction module 341 is used to construct the optimization objective function corresponding to the target well by taking the minimization of ineffective water production as the optimization objective and the valve quantity limit, wellbore pressure drop limit and valve life requirement as the constraints.

[0127] The fourth calculation module 342 is used to calculate the installation position and initial opening of the valve of the downhole inflow control device using the optimization objective function obtained by the construction module 341, so as to obtain the valve deployment result;

[0128] The optimization objective function is:

[0129] ;

[0130] in, To optimize the objective function to maximize the result, To control water efficiency, For valve cost, and These are the weighting coefficients.

[0131] Furthermore, such as Figure 4 As shown, the device further includes:

[0132] Monitoring unit 35 is used to monitor in real time whether there is a target grid cell that has suddenly increased the probability of flooding to the risk probability threshold.

[0133] The determination unit 36 ​​is used to determine the existing target grid cell as a high-risk area if the monitoring unit 35 detects whether there is a target grid cell whose flooding probability suddenly increases to the risk probability threshold.

[0134] The judgment unit 37 is used to further determine, based on the installation position of the downhole inflow control device valve, whether there is another associated downhole inflow control device valve in the high-risk area obtained by the determination unit 36;

[0135] Control unit 38 is configured to, if judgment unit 37 determines that there is another associated downhole inflow control device valve in the high-risk area, define the other associated downhole inflow control device valve as a risk valve and control the emergency closure of the risk valve, or

[0136] The risk valve is controlled to adjust to a preset minimum opening degree, which is the minimum safe flow threshold to which the valve is adjusted under risk conditions.

[0137] Furthermore, embodiments of this application also provide a storage medium for storing a computer program, wherein the computer program, when running, controls the device where the storage medium is located to execute the above-described... Figure 1-2 The method for deploying water control valves based on horizontal wells described in the article.

[0138] Furthermore, embodiments of this application also provide a processor for running a program, wherein the program executes the above-described... Figure 1-2 The method for deploying water control valves based on horizontal wells described in the article.

[0139] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0140] It is understood that the relevant features in the above methods and apparatus can be referenced interchangeably. Furthermore, the terms "first," "second," etc., in the above embodiments are used to distinguish between embodiments and do not represent the superiority or inferiority of any particular embodiment.

[0141] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0142] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0143] In addition, the memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0144] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0146] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0149] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0150] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0151] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0152] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for deploying a water control valve based on a horizontal well, characterized in that, The method includes: Based on the 3D reservoir digital model data of the target well block, the horizontal well trajectory of the target well is divided into multiple grid cells, and the permeability, water saturation and porosity of each grid cell are extracted. This includes: acquiring seismic data, well logging data and core experimental data of the target well block in advance; integrating the seismic data, well logging data and core experimental data through Petrel reservoir modeling software; importing the 3D reservoir digital model grid into Petrel reservoir modeling software; mapping the coordinate sequence of the horizontal well trajectory to the digital model grid; determining the digital model grid cells that the trajectory passes through; dividing the digital model grid cells that the trajectory passes through; and finally forming N continuous grid cells. Based on the permeability, an anisotropic permeability correction model is used to calculate the equivalent permeability of each grid cell. The anisotropic permeability correction model is constructed based on the inclination angle corresponding to the horizontal well trajectory of the target well, and includes: for each grid cell, multiplying the original horizontal permeability by the square of the cosine of the inclination angle to obtain a first weighted contribution value, multiplying the original vertical permeability by the square of the sine of the inclination angle to obtain a second weighted contribution value; and summing the first weighted contribution value and the second weighted contribution value to obtain the equivalent permeability. The process involves determining the water flooding probability of each grid cell based on the equivalent permeability, water saturation, and porosity, and generating a continuous water flooding probability distribution map of the target well along the horizontal well trajectory based on the water flooding probability. This includes: inputting the equivalent permeability, water saturation, and porosity as input variables into a Bayesian network model to calculate the water flooding probability of each grid cell; and generating the continuous water flooding probability distribution map of the target well along the horizontal well trajectory using a Kriging interpolation algorithm based on the water flooding probability of each grid cell. Based on the continuous flooding probability distribution map, the installation position and initial opening of the downhole inflow control device valves of the target well are optimized using an optimization objective function to obtain the valve deployment results of the target well. The optimization objective of the optimization objective function is to minimize ineffective water production. The constraints of the optimization objective function include valve quantity limit, wellbore pressure drop upper limit, and valve life requirement.

2. The method of claim 1, wherein, Based on the 3D reservoir numerical model data of the block where the target well is located, the horizontal well trajectory of the target well is divided into multiple grid cells, including: In the three-dimensional reservoir numerical model data, the fracture zone and matrix zone corresponding to the horizontal well trajectory are identified. The fracture zone is determined based on the joint analysis of the permeability field and fracture conductivity of the target well, and the matrix zone is the area outside the fracture zone. The matrix region is divided into a first grid, and the fracture zone is divided into a second grid to obtain multiple grid cells corresponding to the horizontal well trajectory. The grid density of the second grid is greater than that of the first grid.

3. The method of claim 1, wherein, The formula for calculating the equivalent permeability is: ； wherein, Ktis the equivalent permeability, Ktis the original horizontal permeability in the permeability, Ktis the original vertical permeability in the permeability, is the hole inclination angle corresponding to the horizontal well trajectory.

4. The method according to any one of claims 1-3, characterized in that, Based on the continuous flooding probability distribution map, the installation position and initial opening of the downhole inflow control device valves in the target well are optimized using an optimization objective function to obtain the valve deployment results for the target well, including: The optimization objective is to minimize ineffective water production, and the constraints are the valve quantity limit, wellbore pressure drop limit, and valve life requirement. The optimization objective function corresponding to the target well is then constructed. Using the aforementioned optimization objective function, the installation position and initial opening of the valve in the downhole inflow control device are calculated to obtain the valve deployment result; The optimization objective function is: ； in, To optimize the objective function to maximize the result, To control water efficiency, For valve cost, and These are the weighting coefficients.

5. The method according to claim 4, characterized in that, The method further includes: Real-time monitoring to detect whether there are target grid cells whose flooding probability suddenly increases to the risk probability threshold; If such a target grid cell exists, it will be identified as a high-risk area. Based on the installation location of the downhole inflow control device valve, it is further determined whether there is another associated downhole inflow control device valve in the high-risk area; If present, the associated other downhole inflow control valve is defined as a risk valve, and the emergency closure of the risk valve is controlled. The risk valve is controlled to adjust to a preset minimum opening degree, which is the minimum safe flow threshold to which the valve is adjusted under risk conditions.

6. A water control valve deployment device based on a horizontal well, characterized in that, The device includes: The first processing unit is used to divide the horizontal well trajectory of the target well into multiple grid cells based on the three-dimensional reservoir digital model data of the block where the target well is located, and to extract the permeability, water saturation and porosity of each grid cell. This includes: acquiring seismic data, well logging data and core experimental data of the block where the target well is located in advance; integrating the seismic data, well logging data and core experimental data through Petrel reservoir modeling software; importing the three-dimensional reservoir digital model grid into Petrel reservoir modeling software; mapping the coordinate sequence of the horizontal well trajectory to the digital model grid; determining the digital model grid cells that the trajectory passes through; dividing the digital model grid cells that the trajectory passes through; and finally forming N continuous grid cells. The calculation unit is used to calculate the equivalent permeability of each grid cell based on the permeability obtained by the first processing unit using a permeability anisotropy correction model. The permeability anisotropy correction model is constructed based on the well inclination angle corresponding to the horizontal well trajectory of the target well, and includes: for each grid cell, multiplying the original horizontal permeability by the square of the cosine of the well inclination angle to obtain a first weighted contribution value; multiplying the original vertical permeability by the square of the sine of the well inclination angle to obtain a second weighted contribution value; and summing the first weighted contribution value and the second weighted contribution value to obtain the equivalent permeability. The second processing unit is configured to determine the water flooding probability of each grid cell based on the equivalent permeability obtained by the calculation unit, the water saturation obtained by the first processing unit, and the porosity, and to generate a continuous water flooding probability distribution map of the target well along the horizontal well trajectory based on the water flooding probability. This includes: inputting the equivalent permeability, water saturation, and porosity as input variables into a Bayesian network model to calculate the water flooding probability of each grid cell; and generating the continuous water flooding probability distribution map of the target well along the horizontal well trajectory using a Kriging interpolation algorithm based on the water flooding probability of each grid cell. The optimization unit is used to optimize the installation position and initial opening of the downhole inflow control device valves of the target well based on the continuous flooding probability distribution map obtained by the second processing unit and using an optimization objective function to obtain the valve deployment result of the target well. The optimization objective of the optimization objective function is to minimize ineffective water production. The constraints of the optimization objective function include valve quantity limit, wellbore pressure drop upper limit and valve life requirement.

7. The apparatus according to claim 6, characterized in that, The first processing unit includes: The identification module is used to identify the fracture zone and matrix zone corresponding to the horizontal well trajectory in the three-dimensional reservoir digital model data. The fracture zone is determined based on the joint analysis of the permeability field and fracture conductivity of the target well, and the matrix zone is the area outside the fracture zone. The partitioning module is used to partition the matrix area obtained by the identification module using a first grid and the fracture zone using a second grid to obtain multiple grid cells corresponding to the horizontal well trajectory, wherein the grid density of the second grid is greater than that of the first grid.

8. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the storage medium to perform the water control valve deployment method based on any one of claims 1 to 5.

9. A processor, characterized in that, The processor is used to run a program, wherein the program executes the water control valve deployment method based on a horizontal well as described in any one of claims 1 to 5.

Images