A Method and System for Intelligent Co-optimization of Fracturing Parameters and Well Location in Shale Oil 3D Development

Abstract

This application discloses a method and system for intelligent collaborative optimization of fracturing parameters and well locations in shale oil three-dimensional development, relating to the field of oil and gas field development technology. The method includes: constructing a multi-objective optimization model for horizontal well fracturing process parameters in a target shale oil block; establishing a proxy model for horizontal well fracturing process parameter optimization based on the objective function in the optimization model and a horizontal well fracturing sample set; using the proxy model and the optimization model, employing a multi-objective optimization algorithm to obtain the optimal fracturing process parameters of a benchmark horizontal well; and for the three-dimensional development well group in the target shale oil block, constructing a multi-objective optimization model for collaborative optimization of horizontal well fracturing parameters and well locations, and using the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as initial values, employing a multi-objective optimization algorithm through numerical simulation to obtain the optimal fracturing process parameters and well locations for the three-dimensional development well group in the target shale oil block. This application can quickly and accurately determine the optimal horizontal well fracturing process parameters and horizontal well locations.

Description

Technical Field

[0001] This application relates to the field of oil and gas field development technology, and in particular to a method and system for intelligent collaborative optimization of fracturing parameters and well locations in shale oil three-dimensional development. Background Technology

[0002] Horizontal wells combined with volumetric fracturing are a crucial method for achieving large-scale, efficient development of shale oil reservoirs. The rational selection of fracturing process parameters and horizontal well locations is essential for shale oil development. Several methods for optimizing fracturing process parameters and well locations already exist.

[0003] Specifically, for example, see Chinese Patent Publication No. CN114329729A, which proposes an optimization design and well placement method for a three-dimensional development well network. This method transforms the practical problem of well spacing optimization into a conditionally constrained nonlinear multivariate collaborative optimization minimization problem by constructing objective functions for average well spacing, average internal rate of return per well, and average recovery rate per well, thereby obtaining the minimum average well spacing of the development unit. However, this method only optimizes the well spacing of the target development unit and does not consider the optimization of fracturing process parameters; moreover, the well spacing between different wells is the same, failing to consider reservoir heterogeneity.

[0004] See Chinese Patent Publication No. CN115467649A, which proposes a method, system, and three-dimensional well network for optimizing well network deployment in small-well-spacing three-dimensional development. This method constructs a well network and well location optimization model for three-dimensional development using development parameters, and solves for the optimal solution of the well network and well location optimization model to obtain the optimal development parameters, thereby optimizing the well network for small-well-spacing three-dimensional development. However, in this method, optimization variables such as the horizontal section length and the number of perforation clusters per section are average values ​​of all wells within the block, without considering the differences in reservoir characteristics between different wells and different sections.

[0005] There are also methods that use the net present value of the entire area as the target for single-objective optimization, which cannot take into account both economic benefits and production improvement. At the same time, hierarchical optimization cannot guarantee the overall optimal coordination between fracture parameters and well location.

[0006] Therefore, current methods for horizontal well fracturing and well location optimization in shale oil development still cannot fully consider the differences in reservoir characteristics across different wells and sections. Furthermore, fracturing optimization and well location optimization are isolated, making it difficult to achieve overall synergistic optimization and resulting in low computational efficiency. There is an urgent need for a rapid and accurate method to achieve intelligent synergistic optimization of fracturing parameters and well locations in shale oil development, in order to increase production, reduce costs, and achieve large-scale, cost-effective development of shale oil reservoirs. Summary of the Invention

[0007] The purpose of this application is to provide a method and system for intelligent collaborative optimization of fracturing parameters and well locations in shale oil three-dimensional development, which can quickly and accurately determine the optimal horizontal well fracturing process parameters and horizontal well locations.

[0008] To achieve the above objectives, this application provides the following solution.

[0009] Firstly, this application provides a method for intelligent collaborative optimization of fracturing parameters and well locations in shale oil three-dimensional development, comprising: constructing a horizontal well fracturing sample set based on a reservoir geological model and a stress field model of the target shale oil block; both the reservoir geological model and the stress field model of the target shale oil block consider the heterogeneity of reservoir characteristics; constructing a multi-objective optimization model for horizontal well fracturing process parameters of the target shale oil block; establishing a proxy model for optimizing horizontal well fracturing process parameters based on the objective function in the horizontal well fracturing sample set and the multi-objective optimization model for horizontal well fracturing process parameters; and optimizing the horizontal well fracturing process parameters based on the proxy model. Based on the theoretical model and the multi-objective optimization model for horizontal well fracturing process parameters, a multi-objective optimization algorithm is used to obtain the optimal fracturing process parameters for the benchmark horizontal well in the target shale oil block. For the three-dimensional development well group in the target shale oil block, a multi-objective optimization model for the coordinated optimization of horizontal well fracturing parameters and well location is constructed. Based on the multi-objective optimization model for the coordinated optimization of horizontal well fracturing parameters and well location, using the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as the initial values, a multi-objective optimization algorithm is used to obtain the optimal fracturing process parameters and well location for volumetric fracturing of horizontal wells in the three-dimensional development well group of the target shale oil block through numerical simulation.

[0010] Secondly, a shale oil three-dimensional development fracturing parameter and well location intelligent collaborative optimization system includes: a fracturing sample set construction module, a fracturing process parameter optimization model construction module, a fracturing proxy model establishment module, a fracturing parameter optimization module, a fracturing parameter and well location collaborative optimization model construction module, and a fracturing and well location collaborative optimization model solving module.

[0011] The system includes the following modules: a fracturing sample set construction module for constructing a horizontal well fracturing sample set based on the reservoir geological model and stress field model of the target shale oil block; a fracturing process parameter optimization model construction module for constructing a multi-objective optimization model for the horizontal well fracturing process parameters of the target shale oil block; a fracturing surrogate model establishment module for establishing a horizontal well fracturing process parameter optimization surrogate model based on the objective function in the horizontal well fracturing sample set and the multi-objective optimization model; and a fracturing parameter optimization module for using multi-objective optimization techniques based on the horizontal well fracturing process parameter optimization surrogate model and the horizontal well fracturing process parameter multi-objective optimization model. The system employs a multi-objective optimization model to obtain the optimal fracturing process parameters for benchmark horizontal wells in the target shale oil block. A fracturing parameter and well location co-optimization model construction module is used to construct a multi-objective optimization model for the co-optimization of horizontal well fracturing parameters and well locations for the three-dimensional development well group in the target shale oil block. A fracturing and well location co-optimization model solving module is used to obtain the optimal fracturing process parameters and well locations for volumetric fracturing of horizontal wells in the three-dimensional development well group of the target shale oil block through numerical simulation, based on the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as initial values, using a multi-objective optimization algorithm.

[0012] According to the specific embodiments provided in this application, this application has the following technical effects.

[0013] This application provides a method and system for intelligent collaborative optimization of fracturing parameters and well locations in shale oil three-dimensional development. It constructs a multi-objective optimization model for the collaborative optimization of horizontal well fracturing parameters and well locations, making fracturing and well location design more scientific and rational. Addressing the high-dimensional complexity of variables arising from multiple wells and fracturing sections, a hierarchical decoupling strategy is adopted. First, the fracturing process parameters of a benchmark horizontal well are optimized, and these optimized parameters are used as the initial values ​​for the subsequent collaborative optimization of fracturing parameters and well locations in the three-dimensional development well group. This effectively reduces the optimization space and enhances the global optimization capability. Furthermore, the hierarchical decoupling strategy accelerates the selection of initial values ​​for fracturing parameters and well locations through a proxy model for horizontal well fracturing process parameter optimization. During collaborative optimization, numerical simulation is directly used, fully considering the heterogeneity of reservoir characteristics in each well and each fracturing section, while ensuring the accuracy and efficiency of fracturing process parameter and well location optimization. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1This is a flowchart illustrating an intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development, provided as an embodiment of this application.

[0016] Figure 2 Pareto optimal solution set diagram for multi-objective optimization of fracturing of benchmark horizontal wells in a target shale oil block provided in another embodiment of this application.

[0017] Figure 3 The image shows the fracture morphology diagram corresponding to the optimal fracturing process parameters for multi-objective optimization of fracturing of a benchmark horizontal well in a target shale oil block, provided in another embodiment of this application.

[0018] Figure 4 A graph showing the change of the Hypervolume index during the optimization process, provided for another embodiment of this application.

[0019] Figure 5 A diagram showing the results of co-optimization of fracturing process parameters and well location for three-dimensional development of horizontal wells in a target shale oil block, provided as another embodiment of this application.

[0020] Figure 6 A comparison chart of three production performance evaluation indicators before and after considering reservoir heterogeneity in the volumetric fracturing of horizontal wells for the three-dimensional development of a target shale oil block, provided for another embodiment of this application.

[0021] Figure 7 A comparison chart of three mining performance indicators obtained by different optimization methods provided in another embodiment of this application.

[0022] Figure 8 This is a schematic diagram of the functional modules of an intelligent collaborative optimization system for fracturing parameters and well locations in shale oil three-dimensional development, provided as an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] In one exemplary embodiment, such as Figure 1 As shown, a method for intelligent collaborative optimization of fracturing parameters and well locations in three-dimensional shale oil development is provided, including the following steps 101 to 106.

[0026] Step 101: Based on the reservoir geological model and stress field model of the target shale oil block, construct a horizontal well fracturing sample set; both the reservoir geological model and stress field model of the target shale oil block consider the heterogeneity of reservoir characteristics;

[0027] Step 102: Construct a multi-objective optimization model for horizontal well fracturing process parameters in the target shale oil block;

[0028] Step 103: Based on the horizontal well fracturing sample set and the objective function in the multi-objective optimization model of horizontal well fracturing process parameters, establish a proxy model for optimizing horizontal well fracturing process parameters;

[0029] Step 104: Based on the horizontal well fracturing process parameter optimization proxy model and the horizontal well fracturing process parameter multi-objective optimization model, the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block are obtained by using a multi-objective optimization algorithm;

[0030] Step 105: For the three-dimensional development well group of the target shale oil block, construct a multi-objective optimization model for the coordinated optimization of horizontal well fracturing parameters and well location;

[0031] Step 106: Based on the multi-objective optimization model for co-optimization of horizontal well fracturing parameters and well location, using the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as the initial values, the multi-objective optimization algorithm is used to obtain the optimal fracturing process parameters and well location for volumetric fracturing of horizontal wells in the three-dimensional development well group of the target shale oil block through numerical simulation.

[0032] In another exemplary embodiment of this application, step 101 described above may be replaced by steps 201 to 204.

[0033] Step 201: Construct the reservoir geological model and stress field model of the target shale oil block, and based on the reservoir geological model and stress field model of the target shale oil block, obtain the basic simulation model of multi-stage fracturing horizontal wells of the target shale oil block on the basis of historical fitting.

[0034] Through four steps—geological modeling, geomechanical modeling, fracture simulation, and production capacity simulation—an integrated workflow from well completion fracturing to production capacity prediction is achieved, forming a basic simulation model of multi-stage fracturing horizontal wells in the target shale oil block. First, based on seismic data of the target shale oil block, stratigraphic calibration and structural interpretation are performed. Constraints and corrections are then applied using measured stratigraphic information from well logging data within the target shale oil block to obtain the bedding planes and fault structures of the target reservoir, establishing a structural model of the target shale oil block. Using sedimentary facies plane maps of the target shale oil block and the sandstone and mudstone distribution obtained from well logging interpretation, a sedimentary facies model is established. Using facies-controlled modeling methods, permeability, porosity, oil saturation, and net-to-gross ratio attribute models of the target shale oil block are established, yielding a geological model of the target shale oil reservoir. One-dimensional geomechanical modeling is then performed using density and P-wave / S-wave transit time well logging curves. Based on the dynamic and static rock mechanics parameter relationships measured in laboratory rock mechanics experiments, one-dimensional rock mechanics curves for static Young's modulus, static Poisson's ratio, compressive strength, tensile strength, internal friction angle, and brittleness index are interpreted, with seismic data inversion impedance data volume as a constraint. Three-dimensional rock mechanical properties are generated through interpolation, followed by three-dimensional geomechanical modeling. Pore pressure, maximum horizontal principal stress, minimum horizontal principal stress, and overlying strata pressure attribute fields are established to obtain the stress field model of the target shale oil block. Based on the established reservoir geological model and stress field model, a natural fracture model is established using the ant-body tracing method. Fracture propagation simulation is conducted based on the pumping procedures during actual fracturing operations in existing wells. By fitting the construction pressure curve during fracturing, the hydraulic fracturing fracture morphology is obtained. At this point, the numerical simulation model includes both hydraulic and natural fractures. Based on this numerical simulation model, production capacity simulation is performed. By adjusting the attribute parameters of the reservoir geological model and stress field model of the target shale oil block, the pressure, oil production, and water production during the production process of existing wells in the oilfield are fitted to obtain the basic simulation model of multi-stage fracturing horizontal wells in the target shale oil block.

[0035] Step 202: Based on the basic model of multi-stage fracturing horizontal wells in the target shale oil block, considering the geological parameters and fracturing process parameters affecting the production of shale oil horizontal wells, generate multiple scheme combinations consisting of single-well simulation models and fracturing process parameters. Ideally, the number of generated scheme combinations is generally no less than 200.

[0036] For example, geological parameters affecting the production of shale oil horizontal wells include, but are not limited to, porosity, permeability, oil saturation, Young's modulus, Poisson's ratio, brittleness index, maximum / minimum horizontal principal stress, overlying strata pressure, and fracturing pressure; fracturing process parameters affecting the production of shale oil horizontal wells include, but are not limited to, horizontal well section length, horizontal section azimuth, number of fracturing sections, spacing between fracturing sections, number of perforation clusters in each fracturing section, amount of proppant added in each fracturing section, amount of fluid added in each fracturing section, and proportion of quartz sand in each fracturing section.

[0037] Step 203: Perform integrated geological and engineering simulation based on the single-well simulation model and fracturing process parameters of each scheme combination to obtain the production dynamics corresponding to each scheme combination; the production dynamics include, but are not limited to, daily water production, daily oil production, daily gas production and oil saturation field at each time step.

[0038] Integrated geological engineering simulation is the numerical simulation mentioned above.

[0039] Step 204: Construct a horizontal well fracturing sample set with geological parameters and fracturing process parameters as inputs, and the production dynamics corresponding to each scheme combination as the output. This includes the following steps:

[0040] Step 204-1: Based on the single-well simulation model for each scheme combination, obtain descriptive statistics of geological parameters along the horizontal well. These descriptive statistics include, but are not limited to, the mean, variance, coefficient of variation, maximum value, minimum value, and probability distribution of each geological parameter.

[0041] Step 204-2: Combine the fracturing process parameters in each scheme combination with the descriptive statistics of the geological parameters along the horizontal well obtained from the corresponding single-well simulation model to form a parameter combination.

[0042] Specifically, a parameter combination is formed by descriptive statistics of geological parameters along the horizontal well, the length of the horizontal well section, the azimuth of the horizontal section, the number of fractured sections, the spacing between fractured sections, the number of perforation clusters in each fractured section, the amount of sand added in each fractured section, the amount of liquid added in each fractured section, and the proportion of quartz sand in each fractured section.

[0043] Step 204-3: Using the parameter combination as input and the production dynamics corresponding to the scheme combination as output, construct a horizontal well fracturing sample set.

[0044] In one example, step 202 above can be replaced by steps 301 to 307.

[0045] Step 301: Determine the range of values ​​for fracturing process parameters in the target shale oil block. Specifically, based on the current fracturing technology level, obtain the range of values ​​for fracturing process parameters in the target shale oil block. Fracturing process parameters whose value ranges need to be specified include, but are not limited to, horizontal well section length, horizontal section azimuth angle, number of fracturing sections, spacing between fracturing sections, number of perforation clusters, proppant injection intensity, fluid injection intensity, and quartz sand ratio.

[0046] Step 302: Based on the required number of parameter combinations, within the range of values ​​for fracturing process parameters in the target shale oil block, the Latin hypercube sampling method is used to sample the fracturing process parameters to obtain the parameter combinations. Specifically, the following process parameters are sampled: horizontal well section length, horizontal section azimuth, number of fracturing sections, fracturing section spacing, number of perforation clusters in each fracturing section, proppant loading rate in each fracturing section, fluid loading rate in each fracturing section, and quartz sand ratio in each fracturing section. Wherein: proppant loading rate in each fracturing section = sampled proppant loading intensity × fracturing section length; fluid loading rate in each fracturing section = sampled fluid loading intensity × fracturing section length. The fracturing section length is calculated as follows: from the sampled fracturing section spacing, the starting point of each fracturing section is determined along the horizontal wellbore; the distance between the starting points of two adjacent fracturing sections is the fracturing section length.

[0047] Step 303: Set the value of sample number i to 1.

[0048] Step 304: For the i-th sample in the fracturing process parameter combination, extract a single-well simulation model from the basic simulation model of the multi-stage fracturing horizontal well in the target shale oil block. The basic shape of the single-well simulation model is a cuboid, where the length of the cuboid = length of the horizontal well section + safety distance × 2, the width of the cuboid = fracture half-length × 2 + safety distance × 2, and the height is the thickness of the target shale oil block within the rectangular area with known length and width. The safety distance is generally taken as 150m-500m, and the fracture half-length can be obtained from the monitoring data of the already fracturing wells in the target shale oil block or the simulation results of fracturing propagation.

[0049] Step 305: Combine the i-th sample in the fracturing process parameter combination with the corresponding single-well simulation model extracted from the multi-stage fracturing horizontal well basic simulation model of the target shale oil block to form a scheme combination.

[0050] Step 306: Increment the value of i by 1, return to the step of extracting a single-well simulation model from the multi-stage fracturing horizontal well basic simulation model of the target shale oil block for the i-th sample in the fracturing process parameter combination, and stop the operation when the value of i is greater than the number of samples in the fracturing process parameter combination, so as to obtain multiple initial scheme combinations composed of fracturing process parameters and single-well simulation models.

[0051] Step 307: Eliminate schemes with mismatched parameters from the initial scheme combination. Schemes with mismatched parameters include, but are not limited to, situations where the horizontal well section length cannot accommodate the preset number of fractures (i.e., the horizontal well section length is less than the fracture section spacing × the preset number of fracture sections), where the physical space cannot accommodate the designed number of fractures, and situations where the fracturing fluid injection volume and proppant volume are mismatched. For example, if the ratio of proppant volume to fluid volume in the fracture section exceeds the empirical threshold for the target shale oil block, it may lead to sand plugging risk or cause ineffective proppant (sand grain) settlement. Eliminating the corresponding schemes with mismatched parameters yields the scheme combination consisting of fracturing process parameters and a single-well simulation model.

[0052] For example, steps 301-306 generate 300 sets of schemes, and step 307 finally yields 291 sets of schemes.

[0053] In another exemplary embodiment of this application, the objective function in the multi-objective optimization model of the horizontal well fracturing process parameters in step 102 above is:

[0054] ;

[0055] ;

[0056] ;

[0057] ;

[0058] In the formula, The overall goal is to optimize the fracturing process parameters for horizontal wells. The net present value of a single well. This represents the final recoverable reserves of a single well. This is an indicator of the utilization level of a single well. Represents the maximum value function. For each well, the variable to be optimized is... To simulate the maximum production time, The discount rate is... Given the current crude oil price, For the first The crude oil production of this horizontal well in that year, For the first Annual operating cost of the horizontal well For fixed costs, The drilling and completion cost of this horizontal well. The cost of fracturing this horizontal well; The time since the oil well was abandoned; This represents the total number of grid cells in the single-well simulation model. For the first The initial oil saturation of each grid, for Time of the first Oil saturation of each grid cell For the first The vertical distance between each grid and its nearest pressure crack This refers to the spacing between fracturing sections.

[0059] ;

[0060] ;

[0061] ;

[0062] In the formula, The operating cost per cubic meter of oil, The cost per meter of drilling and completion. The cost of fracturing sand per cubic meter, The cost per cubic meter of fracturing fluid, The cost of fracturing operations for each fracturing segment. The length of the horizontal well section. For reservoir depth, The total amount of sand added to the well. This represents the total amount of fluid added to the well. The number of fracturing stages. The variables to be optimized for a single well are:

[0063] ;

[0064] ;

[0065] ;

[0066] In the formula, These are the well-level parameters for a single well. The azimuth angle is the horizontal segment. This refers to the spacing between fracturing sections. These are the fracturing parameters for the first stage of fracturing in a single well. These are the fracturing parameters for the second fracturing stage. For single well number Fracturing parameters for the fracturing stage. For single well number Fracturing parameters for the fracturing stage. This represents the maximum number of fracturing stages in a single well within the target shale oil block. , 、 、 They are the first single wells The number of perforation clusters, sand addition, liquid addition, and quartz sand ratio in the fracturing section.

[0067] The constraints in the multi-objective optimization model for horizontal well fracturing process parameters are:

[0068] ;

[0069] In the formula, for The first in One optimization variable, for The Middle The lower bound of each optimization variable. for The Middle The upper limit of each optimization variable, It is an integer. for The first in One optimization variable, for The Middle The lower bound of each optimization variable. for The Middle The upper limit of each optimization variable.

[0070] In another exemplary embodiment of this application, step 103 described above may be replaced by steps 401 to 402.

[0071] Step 401: Based on the horizontal well fracturing sample set, and combined with the objective function in the multi-objective optimization model of horizontal well fracturing process parameters, obtain the objective function values ​​of different samples in the horizontal well fracturing sample set.

[0072] For example, step 101 constructs a horizontal well fracturing sample set. Each sample in the set contains model parameters such as geology and fracturing technology, as well as dynamic production parameters such as daily oil production and oil saturation field. Economic parameters such as operating cost per cubic meter of oil and drilling / completion cost per meter can be determined based on the actual conditions of the oilfield. Therefore, the net present value of a single well can be calculated based on the dynamic production data of each sample and the actual parameters of the oilfield. By fitting the daily oil production during the simulation period using a modern production decline model, the production dynamics of the well from the start of production to its abandonment can be predicted, and the final recoverable reserves of a single well can be calculated. Specifically, the modern production decline model includes, but is not limited to, Arps, PLE, SEPD, and Duong models. The utilization index of a single well can be calculated using the oil saturation field of the model under the maximum production time T obtained through integrated geological and engineering simulation.

[0073] Step 402: Using the geological parameters and fracturing process parameters of the samples in the horizontal well fracturing sample set as input, and the objective function value of the samples as output, construct a surrogate model for optimizing the horizontal well fracturing process parameters using machine learning methods. The aforementioned machine learning methods include, but are not limited to, XGBoost (eXtreme Gradient Boosting), Gaussian Process Regression (GPR), and Support Vector Regression (SVR).

[0074] For example, XGBoost is used to construct a surrogate model for optimizing horizontal well fracturing process parameters. This embodiment combines ten-fold cross-validation with a Bayesian optimization algorithm to achieve automatic adjustment of hyperparameters in the surrogate model. This embodiment uses three commonly used evaluation metrics to assess the performance of the surrogate model, including the coefficient of determination (R²). 2 The three metrics are: root mean square error (RMSE) and mean squared error (MAE). The formulas for calculating these metrics are as follows.

[0075] .

[0076] .

[0077] .

[0078] In the formula, Indicates the first z The true value of the objective function corresponding to each sample; Indicates the first z The predicted value of the objective function corresponding to each sample; This represents the average value of the objective function. This indicates the number of samples in the sample set.

[0079] The multi-objective optimization algorithm described in step 104 includes, but is not limited to, the Fast Non-Dominated Sorting Genetic Algorithm (NSGA-II), the Improved Strength Pareto Evolutionary Algorithm (PSGA-II), the Elite Slime Fungus Optimization Algorithm (ESMA-II), multi-objective particle swarm optimization (MPS), and decomposition-based multi-objective evolutionary algorithms. In another exemplary embodiment of this application, step 104 employs the Fast Non-Dominated Sorting Genetic Algorithm (NSGA-II) to optimize fracturing process parameters. The multi-objective optimization model is as described in step 102, and the objective function value is predicted using the surrogate model constructed in step 103. The hyperparameters of the optimization algorithm are shown in Table 1. The Pareto optimal solution set obtained in this embodiment is as follows: Figure 2 As shown. The fracturing fracture morphology corresponding to the optimal fracturing process parameters after optimization of the initial scheme in this embodiment is as follows. Figure 3 As shown.

[0080] Table 1 NSGA-II Algorithm Parameter Settings

[0081]

[0082] In another exemplary embodiment of this application, the objective function for the co-optimization of fracturing process parameters and well location in the multi-objective optimization model for the horizontal well fracturing parameters and well location in step 105 above is:

[0083] ;

[0084] ;

[0085] ;

[0086] ;

[0087] In the formula, The overall goal is to coordinate the optimization of horizontal well fracturing parameters and well location. The total economic net present value within the target shale oil block. This represents the total final recoverable reserves of all wells within the target shale oil block. This is an indicator of the overall utilization level within the target shale oil block. These are variables for the coordinated optimization of horizontal well fracturing parameters and well location; For the hash symbol, This represents the total number of horizontal wells. For the first Koujingdi annual crude oil production For the first Horizontal well Annual operating costs For the first The fixed costs of a horizontal well. For the first Drilling and completion costs of a horizontal well For the first The cost of fracturing a horizontal well. For the first The abandonment time of a horizontal well; For the first The total number of grids within the control area of ​​a horizontal well; For the first Horizontal well The initial oil saturation of each grid, for Time of the first Horizontal well Oil saturation of each grid cell For the first Horizontal well The vertical distance between each grid and its nearest pressure crack For the first The spacing between fracturing sections in a horizontal well. The variables for co-optimization of horizontal well fracturing parameters and well location are:

[0088] ;

[0089] ;

[0090] ;

[0091] ;

[0092] In the formula, For well group-level parameters of the first horizontal well in the target shale oil block, These are the well group-level parameters for the second horizontal well in the target shale oil block. These are the well group-level parameters for the third horizontal well in the target shale oil block. For the target shale oil block Well group-level parameters of a horizontal well. For the target shale oil block Well group-level parameters of a horizontal well. For the target shale oil block Well class parameters for a horizontal well. For the target shale oil block The fracturing parameters of the first fracturing stage in a horizontal well. For the target shale oil block Fracturing parameters for the second fracturing stage of a horizontal well. For the target shale oil block Horizontal well Fracturing parameters for the fracturing stage. For the target shale oil block Horizontal well Fracturing parameters for the fracturing stage; For the target shale oil block The number of fracturing stages in a horizontal well. For the first Length of the horizontal section of a horizontal well i For the first The azimuth angle of the horizontal section of a horizontal well. For the first Spacing between fracturing sections in a horizontal well. , 、 、 The first Horizontal well The number of perforation clusters, sand addition, liquid addition, and quartz sand ratio in the fracturing section.

[0093] The constraints of the multi-objective optimization model for co-optimizing horizontal well fracturing parameters and well location are as follows:

[0094] ;

[0095] In the formula, for The first in One optimization variable, for The Middle The lower bound of each optimization variable. for The Middle The upper limit of each optimization variable, for The Middle One optimization variable, for The Middle The lower bound of each optimization variable. for The Middle The upper limit of each optimization variable; For the first horizontal well The coordinates of the target point in the X direction. For the first horizontal well The coordinates of the target point in the X direction. For the first horizontal well The target's coordinates in the Y direction. For the first horizontal well The target's coordinates in the Y direction. For the first horizontal well The coordinates of the target point in the Z direction. For the first horizontal well The coordinates of the target point in the Z direction. The scope of the target well area; The minimum distance between two adjacent wells. For the first horizontal well The coordinates of the target point in the X direction. For the first horizontal well The target's coordinates in the Y direction. For the first horizontal well The target point's coordinates in the Z direction. During the optimization process, the well spacing between adjacent wells is constrained to be greater than... This can reduce the adverse effects of inter-well interference on oil well production. Specifically, the minimum distance between two adjacent wells can be obtained based on the actual conditions of the target shale oil block through integrated geological and engineering simulation or analysis of production dynamic data.

[0096] In another exemplary embodiment of this application, step 106 described above may be replaced by steps 501 to 504.

[0097] Step 501: Set the hyperparameters of the multi-objective optimization algorithm. Hyperparameters include, but are not limited to, population size, number of evolutionary iterations, crossover distribution index, mutation distribution index, and crossover probability.

[0098] Step 502: Based on the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block, a combination of constrained perturbation and random sampling is used to generate individuals with a number equal to the population size, thus obtaining the initial population.

[0099] Step 503: Based on the multi-objective optimization model for the coordinated optimization of horizontal well fracturing parameters and well location, using the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as initial values, and combined with the initialization population, a multi-objective optimization algorithm is used to iteratively optimize the optimal fracturing process parameters and well location for volumetric fracturing of horizontal wells in the three-dimensional development of the target shale oil block. The objective function value in the multi-objective optimization model is obtained through integrated geological and engineering numerical simulation calculations using the reservoir geological model and stress field model of the target shale oil block.

[0100] Step 504: When the termination optimization criteria are met, output the optimal fracturing process parameters and well location. The termination optimization criteria include, but are not limited to, the maximum number of iterations and fitness value convergence.

[0101] Step 106, when co-optimizing the optimal fracturing process parameters and well locations, adopted development indicators (crude oil production, oil saturation, economic net present value, final recoverable reserves, utilization index, etc.) calculated by reservoir numerical simulation. The numerical simulation was carried out based on the reservoir geological model and stress field model of the target shale oil block. The reservoir geological model and stress field model of the target shale oil block have already considered the heterogeneity of reservoir characteristics during the establishment process. Therefore, the development indicators calculated by reservoir numerical simulation have already taken into account the impact of heterogeneity.

[0102] Step 502 can be replaced by steps 601-603:

[0103] Step 601: Using the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as a benchmark, add a certain disturbance as the fracturing process parameters in the initialization population.

[0104] Preferably, the disturbance does not exceed 20%, that is, for each variable in the fracturing process parameters, the disturbance is within -20% ≤ δ Randomly select disturbance factors within the range of ≤20%. δ The optimal fracturing process parameters for benchmark horizontal wells Multiply by (1+ δ Then, it is determined whether the value satisfies the constraints of the mathematical model for the coordinated optimization of horizontal well fracturing parameters and well location. If it does, it is used as the value of the corresponding fracturing process parameter in the initialization population; if it does not, the perturbation factor is reselected until the constraints are met.

[0105] A better approach is to adjust the disturbance factor for different wells and different fracturing sections. δ All should be selected randomly.

[0106] Step 602: Based on the constraints of the mathematical model for the co-optimization of horizontal well fracturing parameters and well location, determine the value range of other parameters in the initialization population besides the fracturing process parameters.

[0107] The Latin hypercube sampling method is used to sample within the range of parameter values ​​to generate an initial sample set of parameters other than fracturing process parameters.

[0108] Add Gaussian white noise to each sample parameter in the initial sample set; preferably, control the noise intensity to 10%-20% of the parameter standard deviation; determine whether each sample parameter meets the constraints of the mathematical model for the co-optimization of horizontal well fracturing parameters and well location. If it does, use it as the value of other parameters in the initial population except for fracturing process parameters; if it does not meet, resample and add noise until the constraints are met.

[0109] Step 603: Combine the values ​​of the fracturing process parameters in the initial population with the values ​​of other parameters besides the fracturing process parameters to form individuals in the initial population;

[0110] Step 604: Repeat steps 601-603 until the number of samples in the initial population is equal to the set population size, thus obtaining the initial population.

[0111] In another exemplary embodiment of this application, step 106 employs a fast non-dominated sorting genetic algorithm with an optimal initialization strategy to perform coordinated optimization of fracturing process parameters and well location for volumetric fracturing of horizontal wells in the target shale oil block. For example, the Hypervolume index is used to represent the optimization effect of the fast non-dominated sorting genetic algorithm at different iteration numbers. Figure 4 The graph shows the changes in the Hypervolume index during the optimization process. As the number of iterations increases, the Hypervolume value gradually increases, indicating that the optimization algorithm has found a series of solutions with high yield and economic benefits in the search space. When the iteration reaches 50 times, the Hypervolume value begins to stabilize and reaches a relatively stable value. Through synergistic optimization of fracturing process parameters and well locations, a triple improvement in expected yield, economic benefits, and utilization can be achieved under different heterogeneous conditions and well location characteristics, thereby maximizing the exploitation effect of the well group.

[0112] The fracture morphology and optimal well location results corresponding to the optimal fracturing process parameters of the target well group obtained in this embodiment are as follows: Figure 5 As shown. Compared to the optimization results that do not consider reservoir heterogeneity, this embodiment optimizes the reservoir while fully considering its heterogeneity, as follows: Figure 6 As shown, the optimization results of this embodiment show that the final recoverable reserves increased by 24.97%, NPV increased by 29.85%, and the recovery rate increased by 27.51%. Compared with the existing method of optimizing fracturing process parameters and well locations by constructing a surrogate model and then combining it with an optimization algorithm, this embodiment directly calls the numerical simulation coupled optimization algorithm to perform collaborative optimization of fracturing process parameters and well locations based on the optimization results of the benchmark horizontal well obtained by the surrogate model. In the optimization results, the accuracy of the final recoverable reserves increased by 12.65%, the accuracy of NPV increased by 12.53%, and the accuracy of the recovery rate increased by 12.58%. Figure 7 Compared with existing methods that directly utilize numerical simulation coupled with optimization algorithms, the optimization results of this embodiment are very close to those of the former, but the computation time is only 11.5% of the former, which can significantly improve optimization efficiency and save a lot of time costs.

[0113] The main advantages of this application are as follows.

[0114] 1. By using a multi-objective function to optimize fracturing process parameters and well locations, we can consider both the net present value and the final recoverable reserves and utilization level. Compared with existing methods, this approach makes the decision-making more scientific.

[0115] 2. Co-optimization problems involve numerous variables, especially those involving the optimization of fracturing process parameters for multiple wells. Each well also includes multiple fracturing stages, further increasing the number of optimization variables. Traditional methods are prone to getting trapped in local optima. The optimization strategy of this application is decoupling, dividing the problem into two levels. First, the fracturing process parameters of a benchmark horizontal well are optimized. Then, the optimization results are used as the initial values ​​for the co-optimization problem of fracturing process parameters and well locations, narrowing the search range and improving the optimization solution efficiency.

[0116] 3. The optimization process requires predicting oil well production dynamics through numerical simulation. This process, when calculated using specialized software, is extremely time-consuming. Therefore, existing methods often address this issue by constructing surrogate models. While surrogate models are fast, they struggle to accurately account for reservoir heterogeneity, often resulting in significant errors compared to actual simulation results. To address this problem, this application uses a surrogate model in the optimization of benchmark horizontal wells to accelerate the process and narrow the optimization range with shorter computation time. Then, collaborative optimization is performed. To ensure accuracy, the surrogate model is no longer used in collaborative optimization; instead, numerical simulations are directly invoked, and optimization is performed while fully considering reservoir heterogeneity. This shortens the optimization time and ensures the accuracy of the results.

[0117] Based on the same inventive concept, this application also provides a shale oil 3D development fracturing parameter and well location intelligent collaborative optimization system for implementing the above-mentioned method for intelligent collaborative optimization of shale oil 3D development fracturing parameters and well locations. The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the shale oil 3D development fracturing parameter and well location intelligent collaborative optimization system provided below can be found in the limitations of the shale oil 3D development fracturing parameter and well location intelligent collaborative optimization method described above, and will not be repeated here.

[0118] In one exemplary embodiment, such as Figure 8 As shown, a shale oil three-dimensional development fracturing parameter and well location intelligent collaborative optimization system is provided, including: fracturing sample set construction module, fracturing process parameter optimization model construction module, fracturing proxy model establishment module, fracturing parameter optimization module, fracturing parameter and well location collaborative optimization model construction module, and fracturing and well location collaborative optimization model solving module.

[0119] The system includes the following modules: a fracturing sample set construction module for constructing a horizontal well fracturing sample set based on the reservoir geological model and stress field model of the target shale oil block; a fracturing process parameter optimization model construction module for constructing a multi-objective optimization model for the horizontal well fracturing process parameters of the target shale oil block; a fracturing surrogate model establishment module for establishing a horizontal well fracturing process parameter optimization surrogate model based on the objective function in the horizontal well fracturing sample set and the multi-objective optimization model; and a fracturing parameter optimization module for using multi-objective optimization techniques based on the horizontal well fracturing process parameter optimization surrogate model and the horizontal well fracturing process parameter multi-objective optimization model. The system employs a multi-objective optimization model to obtain the optimal fracturing process parameters for benchmark horizontal wells in the target shale oil block. A fracturing parameter and well location co-optimization model construction module is used to construct a multi-objective optimization model for the co-optimization of horizontal well fracturing parameters and well locations for the three-dimensional development well group in the target shale oil block. A fracturing and well location co-optimization model solving module is used to obtain the optimal fracturing process parameters and well locations for volumetric fracturing of horizontal wells in the three-dimensional development well group of the target shale oil block through numerical simulation, based on the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as initial values, using a multi-objective optimization algorithm.

[0120] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for intelligent collaborative optimization of fracturing parameters and well location in shale oil three-dimensional development, characterized in that, include: Based on the reservoir geological model and stress field model of the target shale oil block, a horizontal well fracturing sample set was constructed; Both the reservoir geological model and stress field model of the target shale oil block take into account the heterogeneity of reservoir characteristics; Construct a multi-objective optimization model for horizontal well fracturing process parameters in target shale oil blocks; Based on the horizontal well fracturing sample set and the objective function in the multi-objective optimization model of horizontal well fracturing process parameters, a proxy model for the optimization of horizontal well fracturing process parameters is established. Based on the horizontal well fracturing process parameter optimization proxy model and the horizontal well fracturing process parameter multi-objective optimization model, the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block are obtained by using a multi-objective optimization algorithm. For the three-dimensional development well group of the target shale oil block, a multi-objective optimization model is constructed to coordinate the optimization of horizontal well fracturing parameters and well location; Based on the multi-objective optimization model that coordinates horizontal well fracturing parameters and well location optimization, the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block are used as the initial values. The multi-objective optimization algorithm is used to obtain the optimal fracturing process parameters and well locations for volumetric fracturing of horizontal wells in the three-dimensional development well group of the target shale oil block through numerical simulation.

2. The intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development according to claim 1, characterized in that, Based on the reservoir geological model and stress field model of the target shale oil block, a horizontal well fracturing sample set was constructed, specifically including: Construct reservoir geological models and stress field models for the target shale oil block, and based on historical fitting, obtain a basic simulation model of multi-stage fracturing horizontal wells for the target shale oil block. Based on the basic simulation model of multi-stage fracturing horizontal wells in the target shale oil block, multiple scheme combinations consisting of single-well simulation models and fracturing process parameters are generated. Based on the single-well simulation model and fracturing process parameters of each scheme combination, an integrated geological engineering simulation is performed to obtain the production dynamics corresponding to each scheme combination; the production dynamics include daily water production, daily oil production, daily gas production, and the oil saturation field at each time step; A horizontal well fracturing sample set is constructed, with combinations of geological parameters and fracturing process parameters as inputs and the production dynamics corresponding to each combination as the output.

3. The intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development according to claim 2, characterized in that, Based on the basic simulation model of multi-stage fracturing horizontal wells in the target shale oil block, multiple scheme combinations consisting of single-well simulation models and fracturing process parameters are generated, specifically including: Determine the range of values ​​for fracturing process parameters in the target shale oil block; Based on the number of required parameter combinations, within the range of values ​​for fracturing process parameters in the target shale oil block, the Latin hypercube sampling method is used to sample the fracturing process parameters to obtain the fracturing process parameter combinations. Initialize the value of i to 1; For the i-th sample in the combination of fracturing process parameters, a single-well simulation model is extracted from the basic simulation model of multi-stage fracturing horizontal wells in the target shale oil block. The i-th sample in the combination of fracturing process parameters and the corresponding single-well simulation model extracted from the basic simulation model of multi-stage fracturing horizontal wells in the target shale oil block constitute a scheme combination; Increment the value of i by 1, return to the step of extracting a single-well simulation model from the basic simulation model of multi-stage fracturing horizontal wells in the target shale oil block for the i-th sample in the combination of fracturing process parameters, and stop the operation when the value of i is greater than the number of samples in the combination of fracturing process parameters, and obtain multiple initial scheme combinations consisting of single-well simulation models and fracturing process parameters. By eliminating scheme combinations with mismatched parameters from the initial scheme combination, multiple scheme combinations are obtained, consisting of single-well simulation models and fracturing process parameters.

4. The intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development according to claim 1, characterized in that, The objective function in the multi-objective optimization model for horizontal well fracturing process parameters is: ； ； ； ； In the formula, The overall goal is to optimize the fracturing process parameters for horizontal wells. The net present value of a single well. This represents the final recoverable reserves of a single well. This is an indicator of the utilization level of a single well. Represents the maximum value function. For each well, the variable to be optimized is... To simulate the maximum production time, The discount rate is... Given the current crude oil price, For the first Annual crude oil production from horizontal wells For the first Annual operating cost of horizontal wells For fixed costs, For the drilling and completion costs of horizontal wells, The cost of fracturing the well; The time since the oil well was abandoned; This represents the total number of grid cells in the single-well simulation model. For the first The initial oil saturation of each grid, for Time of the first Oil saturation of each grid cell For the first The vertical distance of each grid cell from the nearest crack. This refers to the spacing between fracturing sections; ； ； ； In the formula, The operating cost per cubic meter of oil, The cost per meter of drilling and completion. The cost of fracturing sand per cubic meter, The cost per cubic meter of fracturing fluid, The cost of fracturing operations for each fracturing segment. The length of the horizontal well section. For reservoir depth, The total amount of sand added to the well. This represents the total amount of fluid added to the well. This refers to the number of fracturing stages; The variables to be optimized for a single well are: ； ； ； In the formula, These are the well-level parameters for a single well. These are the segment-level parameters for the first fracturing stage of a single well. These are the segment-level parameters for the second fracturing stage of a single well. For single well number Segment-level parameters of the fracturing segment. For single well number Fracturing parameters for the fracturing stage. This represents the maximum number of fracturing stages in a single well within the target shale oil block. The azimuth angle is the horizontal segment. This refers to the spacing between fracturing sections. , 、 、 They are the first single wells Number of perforation clusters, amount of sand added, amount of liquid added, and proportion of quartz sand in the fracturing stage; The constraints in the multi-objective optimization model for horizontal well fracturing process parameters are as follows: ； In the formula, for The first in One optimization variable, for The Middle The lower bound of each optimization variable. for The Middle The upper limit of each optimization variable, It is an integer. for The first in One optimization variable, for The Middle The lower bound of each optimization variable. for The Middle The upper limit of each optimization variable.

5. The intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development according to claim 1, characterized in that, Based on the horizontal well fracturing sample set and the objective function in the multi-objective optimization model of horizontal well fracturing process parameters, a surrogate model for optimizing horizontal well fracturing process parameters is established, specifically including: Based on the horizontal well fracturing sample set, and combined with the objective function in the multi-objective optimization model of horizontal well fracturing process parameters, the objective function values ​​of different samples in the horizontal well fracturing sample set are obtained; Using the geological parameters and fracturing process parameters of the samples in the horizontal well fracturing sample set as inputs and the objective function value of the samples as outputs, a machine learning method is used to construct a proxy model for optimizing the horizontal well fracturing process parameters.

6. The intelligent collaborative optimization method for fracturing parameters and well location in shale oil three-dimensional development according to claim 1, characterized in that, The objective function for the co-optimization of fracturing process parameters and well location in the multi-objective optimization model for horizontal well fracturing parameters and well location is: ； ； ； ； In the formula, The overall goal is to coordinate the optimization of horizontal well fracturing parameters and well location. The total economic net present value within the target shale oil block. This represents the total final recoverable reserves of all wells within the target shale oil block. This is an indicator of the overall utilization level within the target shale oil block. Represents the maximum value function. These are variables for the coordinated optimization of horizontal well fracturing parameters and well location; For maximum production time, This represents the total number of horizontal wells. The discount rate is... Given the current crude oil price, For the first Koujingdi annual crude oil production For the first Horizontal well No. Annual operating costs For the first The fixed costs of a horizontal well. For the first Drilling and completion costs of a horizontal well For the first The cost of fracturing a horizontal well; For the first The abandonment time of a horizontal well; For the first The total number of grids within the control area of ​​a horizontal well. For the first Horizontal well No. The initial oil saturation of each grid, for Time of the first Horizontal well No. Oil saturation of each grid cell For the first Horizontal well The vertical distance of each grid cell from the nearest crack. For the first Spacing between fracturing sections in a horizontal well; The optimization variables for the horizontal well fracturing parameters and well location co-optimization are: ； ； ； ； In the formula, For well group-level parameters of the first horizontal well in the target shale oil block, These are the well group-level parameters for the second horizontal well in the target shale oil block. These are the well group-level parameters for the third horizontal well in the target shale oil block. For the target shale oil block Well group-level parameters of a horizontal well. For the target shale oil block Well group-level parameters of a horizontal well. For the target shale oil block Well class parameters for a horizontal well. For the target shale oil block The fracturing parameters of the first fracturing stage in a horizontal well. For the target shale oil block Fracturing parameters for the second fracturing stage of a horizontal well. For the target shale oil block Horizontal well Fracturing parameters for the fracturing stage. For the target shale oil block Horizontal well Fracturing parameters for the fracturing stage; For the target shale oil block The number of fracturing stages in a horizontal well. This represents the maximum number of fracturing stages in a single well within the target shale oil block. For the first Length of the horizontal section of a horizontal well For the first The azimuth angle of the horizontal section of a horizontal well. For the first Spacing between fracturing sections in a horizontal well. , 、 、 The first Horizontal well Number of perforation clusters, amount of sand added, amount of liquid added, and proportion of quartz sand in the fracturing stage; The constraints of the multi-objective optimization model for co-optimizing horizontal well fracturing parameters and well location are as follows: ； In the formula, for The first in One optimization variable, for The Middle The lower bound of each optimization variable. for The Middle The upper limit of each optimization variable, It is an integer. for The Middle One optimization variable, for The Middle The lower bound of each optimization variable. for U i,J The Middle The upper limit of each optimization variable; For the first horizontal well The coordinates of the target point in the X direction. For the first horizontal well The coordinates of the target point in the X direction. For the first horizontal well The target's coordinates in the Y direction. For the first horizontal well The target's coordinates in the Y direction. For the first horizontal well The coordinates of the target point in the Z direction. For the first horizontal well The coordinates of the target point in the Z direction. The scope of the target well area; The minimum distance between two adjacent wells. For the first horizontal well The coordinates of the target point in the X direction. For the first horizontal well The target's coordinates in the Y direction. For the first horizontal well The target point's coordinates in the Z direction.

7. The intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development according to claim 1, characterized in that, The multi-objective optimization algorithms include: fast non-dominated sorting genetic algorithm, elite slime mold optimization algorithm, and multi-objective particle swarm optimization algorithm.

8. The intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development according to claim 1, characterized in that, Based on the multi-objective optimization model for the coordinated optimization of horizontal well fracturing parameters and well locations, using the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as initial values, the multi-objective optimization algorithm is used to obtain the optimal fracturing process parameters and well locations for volumetric fracturing of horizontal wells in the three-dimensional development well group of the target shale oil block through numerical simulation. Specifically, this includes: Set the hyperparameters of the multi-objective optimization algorithm; the hyperparameters include population size, number of evolutionary iterations, crossover distribution index, mutation distribution index, and crossover probability; Based on the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block, a method combining constrained perturbation and random sampling is used to generate individuals with a number equal to the population size, thus obtaining the initial population; Based on the multi-objective optimization model for co-optimization of horizontal well fracturing parameters and well location, the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block are used as the initial values. Combined with the initialization population, the multi-objective optimization algorithm is used to iteratively optimize the optimal fracturing process parameters and well location for volumetric fracturing of horizontal wells in the three-dimensional development of the target shale oil block. When the termination optimization criteria are met, the optimal fracturing process parameters and well location are output; the termination optimization criteria include the maximum number of iterations and the convergence of the fitness value.

9. The intelligent collaborative optimization method for fracturing parameters and well locations in shale oil three-dimensional development according to claim 8, characterized in that, Based on the optimal fracturing process parameters of benchmark horizontal wells in the target shale oil block, a method combining constrained perturbation and random sampling is used to generate individuals of equal size to the population, resulting in an initial population, which specifically includes: The optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block are used as the benchmark, and after adding perturbation, they are used as the fracturing process parameters in the initial population. Based on the constraints of the multi-objective optimization model for co-optimization of horizontal well fracturing parameters and well location, the values ​​of parameters other than fracturing process parameters in the initialization population are determined. The values ​​of fracturing process parameters in the initial population are combined with the values ​​of parameters other than fracturing process parameters to form individuals in the initial population; The initial population is obtained when the number of individuals in the initial population equals the set population size.

10. A shale oil three-dimensional development fracturing parameter and well location intelligent collaborative optimization system, characterized in that, include: The fracturing sample set construction module is used to construct a horizontal well fracturing sample set based on the reservoir geological model and stress field model of the target shale oil block; The fracturing process parameter optimization model construction module is used to construct a multi-objective optimization model for horizontal well fracturing process parameters in target shale oil blocks. The fracturing proxy model establishment module is used to establish a horizontal well fracturing process parameter optimization proxy model based on the horizontal well fracturing sample set and the objective function in the horizontal well fracturing process parameter multi-objective optimization model. The fracturing parameter optimization module is used to obtain the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block based on the horizontal well fracturing process parameter optimization proxy model and the horizontal well fracturing process parameter multi-objective optimization model, using a multi-objective optimization algorithm. The module for constructing a collaborative optimization model for fracturing parameters and well locations is used to build a multi-objective optimization model for the collaborative optimization of horizontal well fracturing parameters and well locations for three-dimensional development well groups in target shale oil blocks. The fracturing and well location co-optimization model solution module is used to obtain the optimal fracturing process parameters and well locations for volumetric fracturing of horizontal wells in the target shale oil block through numerical simulation based on the multi-objective optimization model of horizontal well fracturing parameters and well location co-optimization of horizontal wells in the three-dimensional development well group of the target shale oil block, using the optimal fracturing process parameters of the benchmark horizontal well in the target shale oil block as the initial values ​​and the multi-objective optimization algorithm.

Images