Proppant injection strategy optimization method and system under multilayer fracture distribution

Abstract

The invention discloses a proppant injection strategy optimization method and system under multilayer fracture distribution. The method comprises the following steps: acquiring a static attribute set of a multi-layer crack, and inputting a pre-trained multi-scale coupling model to calculate a dynamic response potential set; based on the potential set, solving the problems of flow conductivity balance and effective filling volume maximization through a multi-objective optimization algorithm, and generating an initial injection parameter combination matched with potential of each layer; in the injection process, model parameters are subjected to inversion and online calibration through real-time monitoring data; and re-optimizing based on the calibrated model, generating an updated injection parameter combination, and adjusting field equipment in real time, including switching interlayer fluid or adjusting a propping agent particle size time sequence. According to the method, closed-loop intelligent optimization from design and perception to dynamic adjustment and optimization is realized, and the distribution uniformity and fracturing effect of the propping agent in the multi-layer crack are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of petroleum engineering, in particular to a proppant injection strategy optimization method and system under multi-layer fracture distribution. BACKGROUND

[0002] In the fracturing operation of oil and gas exploitation, the condition of multi-layer fracture distribution is increasingly common. However, there are many problems to be solved in the current proppant injection strategy for multi-layer fractures.

[0003] Traditional proppant injection strategies often adopt a single mode without fully considering the significant differences in geometry, permeability and rock characteristics of each layer of fractures. The geometry of multi-layer fractures is extremely complex, the length of different layers of fractures can vary from tens of meters to hundreds of meters, the width varies in millimeters or even microns, the height difference is also large, and the bending degree and branching of each layer of fractures are different. For example, in some deep oil and gas reservoirs, the upper layer of fractures may be relatively short and straight, while the lower layer of fractures may be longer and in a complex network structure.

[0004] At the same time, the permeability of each layer of fractures is greatly different due to different reservoir characteristics, and the low permeability layer may only have 1 mD, while the high permeability layer can reach more than 100 mD. The rock characteristics are also complex, and the high hardness of the rock layer will hinder the embedding of the proppant, and the large brittleness of the rock layer will produce a large number of micro-fractures during fracturing, changing the pressure conduction path and the filling space of the proppant.

[0005] Under such complex multi-layer fracture distribution conditions, the traditional injection strategy is prone to cause uneven distribution of proppant. In the low permeability fracture layer, the proppant is difficult to enter smoothly, causing insufficient support, while in the high permeability fracture layer, the proppant may be excessively aggregated due to too fast flow rate, not only wasting resources, but also reducing the conductivity of the fracture. This series of problems causes some fractures to close prematurely, making it difficult to improve the production of oil and gas wells, and the cost of exploitation is high, which seriously restricts the efficient development of the oil and gas exploitation industry. Therefore, it is urgent to develop a proppant injection strategy optimization method that can adapt to multi-layer fracture distribution.

[0006] In view of this, the present application is proposed. SUMMARY

[0007] To solve the above technical problems, the present application proposes a proppant injection strategy optimization method and system under multi-layer fracture distribution, aiming to improve the rationality of proppant distribution and the fracturing effect in hydraulic fracturing operation, thereby improving the productivity of oil and gas wells.

[0008] Specifically, the following technical solutions are adopted: A proppant injection strategy optimization method under multi-layer fracture distribution, comprising: Step S1, obtaining a static attribute set and a dynamic response potential set of multi-layer fractures of a target well; the static attribute set at least includes permeability, porosity, average width, length, tortuosity and branch density of each layer fracture; the dynamic response potential set is obtained by inputting the static attribute set into a pre-trained multi-scale fracture expansion-proppant migration coupling model, and is used to represent the expansion trend and proppant carrying capacity of the fracture under different injection conditions; the multi-scale fracture expansion-proppant migration coupling model at least includes a macroscopic fracture expansion sub-model, a proppant migration and settlement sub-model and a fracture conductivity prediction sub-model which are coupled with each other, wherein the macroscopic fracture expansion sub-model is used to simulate the dynamic geometric change of the fracture in the stress field, and the output at least includes the time-varying fracture length, height and dynamic width distribution; the proppant migration and settlement sub-model takes the fracture dynamic geometry output by the macroscopic fracture expansion sub-model as an input field, simulates the transport, settlement and sand dam formation process of proppants with different particle sizes therein; and the fracture conductivity prediction sub-model calculates the equivalent permeability and conductivity of the fracture according to the final proppant placement concentration and distribution output by the proppant migration and settlement sub-model; Step S2, based on the dynamic response potential set, applying an optimization algorithm to solve a function with multi-objectives of equalizing the conductivity of each layer fracture and maximizing the effective filling volume of proppants, and outputting an initial injection parameter combination for different fracture layers of the target well; the initial injection parameter combination includes injection flow rate, injection pressure and median proppant particle size which are matched with the dynamic response potential of each layer fracture; Step S3, in the injection process, real-time monitoring data of each layer fracture of the target well is obtained through a downhole monitoring network, the real-time monitoring data includes inlet pressure, proppant concentration distribution and microseismic event data; and the real-time monitoring data is input into the multi-scale fracture expansion-proppant migration coupling model to inverse and online calibrate the fracture geometric parameters and proppant settlement coefficients of the model; Step S4, using the calibrated multi-scale fracture expansion-proppant migration coupling model to re-execute the optimization solving process of step S2, generate an updated injection parameter combination, and adjust the field injection equipment in real time; the adjustment includes switching the injection fluid characteristics between different layer positions, or realizing the time sequence change of the proppant particle size in the same injection fluid, so as to adapt to the dynamic evolution of the fracture.

[0009] As an optional embodiment of the present application, in a proppant injection strategy optimization method under multi-layer fracture distribution of the present application, the macroscopic fracture expansion sub-model, the proppant migration and settlement sub-model and the fracture conductivity prediction sub-model are coupled with each other, including: The macroscopic fracture propagation sub-model transmits the updated fracture dynamic width distribution w(x, y, t) to the proppant migration and settling sub-model at each calculation time step as its migration space field; The proppant migration and settling sub-model calculates the proppant local concentration c(x, y, t) and the formed sand dam height, which are fed back to the macroscopic fracture propagation sub-model for correcting the local fracture effective mechanical width and flow resistance. The fracture conductivity prediction sub-model starts after the completion of the construction simulation, and its input is completely dependent on the final output of the proppant migration and settling sub-model.

[0010] As an optional embodiment of the present application, in the macroscopic fracture propagation sub-model of the proppant injection strategy optimization method under multi-layer fracture distribution, the dynamic width calculation of the fracture considers the influence of the proppant concentration, and adopts the following modified formula: w_eff(x, t) = w_h(x, t) - β × c(x, t); Where w_eff(x, t) is the effective hydraulic width at position x at time t, w_h(x, t) is the theoretical hydraulic width calculated by rock mechanics and fluid pressure, c(x, t) is the proppant volume concentration at the same position and time, and β is the embedding / plugging correction coefficient related to the proppant particle size and rock hardness.

[0011] As an optional embodiment of the present application, in the proppant injection strategy optimization method under multi-layer fracture distribution, the proppant migration and settling sub-model is realized by solving the following coupled equation groups: Continuity equation: ; Momentum equation: ; Proppant settling velocity: v_s = f(d_p, ρ_p, ρ_f, μ, c); Where, is the partial differential symbol, t is the time, is the vector differential operator, w is the fracture width, c is the proppant concentration, v is the average flow rate of the sand-carrying fluid, μ is the viscosity of the fracturing fluid, p is the pressure in the fracture, v_s is the proppant settling velocity, and d_p, ρ_p, ρ_f, μ and c are functions of the proppant particle size d_p, the proppant and fracturing fluid densities ρ_p, ρ_f, the viscosity μ and the local concentration c.

[0012] As an optional embodiment of the present application, in the proppant injection strategy optimization method under multi-layer fracture distribution, the function with the multi-objective of equalizing the fracture conductivity of each layer and maximizing the effective proppant filling volume in step S2 is: Maximize: F = α × F_volume + (1-α) × F_balance; wherein, F_volume = ( ∑ V_i ) / V_total, represents the normalized value of total effective proppant packing volume, V_i is the predicted proppant effective packing volume of the i-th fracture layer, which is calculated according to the injection parameter combination by the multi-scale fracture propagation-proppant migration coupling model, ∑ V_i represents the summation of i from 1 to n, and V_total is the sum of the volumes of all fracture layers; F_balance = 1 / (1 + σ(C_i) / μ(C_i)), represents the conductivity balance index, C_i is the predicted dimensionless conductivity of the i-th fracture layer, σ(C_i) and μ(C_i) are the standard deviation and mean value of the conductivity of each layer, respectively, and the closer the value of the conductivity balance index is to 1, the more balanced it is; α is a preset weight coefficient, the value range is 0.3 to 0.7, and is used to adjust the relative importance of the two optimization objectives.

[0013] As an optional embodiment of the application, in the multi-layer fracture distribution-based proppant injection strategy optimization method of the application, in step S2, an optimization algorithm is applied to solve a multi-objective function with the equalization of the conductivity of each fracture layer and the maximization of the effective proppant packing volume, including: Step S201, encoding the initial injection parameter combination for different fracture layers into a solution vector, the solution vector at least including the injection flow rate, injection pressure and median proppant particle size of each layer; a population containing multiple solution vectors is initialized in a random generation or heuristic generation based on historical construction cases; Step S202, for each solution vector in the population, inputting the solution vector into the multi-scale fracture propagation-proppant migration coupling model to calculate the predicted proppant effective packing volume V_i and the predicted dimensionless conductivity C_i of each layer; then, the fitness value of the solution vector is calculated according to the multi-objective function F; Step S203, based on the fitness value of the solution vector, an advantage individual is selected by using the tournament selection method, and a simulated binary crossover and a polynomial mutation operation are performed on the advantage individual to generate a new offspring population; Step S204, repeating step S202 and step S203 until the fitness value of the optimal solution vector in the population meets the preset value within a continuous preset number of generations, or the maximum number of iterations is reached, decoding and outputting the optimal solution vector at this time as the initial injection parameter combination.

[0014] As an optional embodiment of the present application, in the method for optimizing the proppant injection strategy under the multi-layer fracture distribution, in step S3, the real-time monitoring data is input into the multi-scale fracture propagation-proppant migration coupling model, and the inversion and online calibration of the fracture geometric parameters and the proppant settling coefficient of the model include: In step S301, a state vector X is defined, which at least includes a subset of fracture geometric parameters and a proppant settling coefficient λ to be calibrated in the multi-scale fracture propagation-proppant migration coupling model, and the subset of fracture geometric parameters includes the fracture half-length of each layer and the dynamic width distribution coefficient; an observation vector Y is defined, and the elements of the observation vector Y correspond to the obtained real-time monitoring data; In step S302, a set including N model instances is initialized, where N is an integer greater than 1; each model instance is a copy of the multi-scale fracture propagation-proppant migration coupling model, but a random disturbance value based on a preset probability distribution of prior knowledge is given to each component of the state vector X of each model instance, thereby generating N different initial state vectors X_1, X_2,..., X_N; in the current calibration period, each model instance is allowed to run from the last calibration time to the current time with its respective state vector as the initial condition, thereby performing numerical simulation respectively, obtaining a set of predicted values of the state vectors {X^f_i} and a set of predicted values of the observation vectors {Y^f_i} corresponding thereto, where i = 1, 2,..., N; In step S303, the actual observation vector Y^obs at the current time is obtained; according to the update equation of the ensemble Kalman filter, the difference between the actual observation vector Y^obs and the observation prediction set {Y^f_i} is used to correct each member in the state prediction set {X^f_i}, and a set of analysis updated state vectors {X^a_i} is calculated; In step S304, the arithmetic mean value of the analysis updated state vector set {X^a_i} is taken as the optimal estimation value of the fracture geometric parameters and the proppant settling coefficient at the current time, and the value is used to update the corresponding parameters of the multi-scale fracture propagation-proppant migration coupling model for decision-making in step S4.

[0015] As an optional embodiment of the present application, in the method for optimizing the proppant injection strategy under the multi-layer fracture distribution, the inversion and online calibration in step S3 is triggered periodically at a fixed time interval Δt, or triggered when a set engineering event is monitored; the set engineering event includes: a mutation of downhole pressure exceeding a threshold value, monitoring of a proppant concentration peak reaching a certain set sensor position, or a microseismic event occurrence rate exceeding a threshold value.

[0016] The application also provides a proppant injection strategy optimization system under multi-layer fracture distribution, comprising: a data acquisition and potential calculation module, which acquires a static attribute set and a dynamic response potential set of multi-layer fractures of a target well; the static attribute set at least includes the permeability, porosity, average width, length, tortuosity and branch density of each layer fracture; the dynamic response potential set is obtained by inputting the static attribute set into a pre-trained multi-scale fracture expansion-proppant migration coupling model, and is used to represent the expansion trend and proppant carrying capacity of the fracture under different injection conditions; the multi-scale fracture expansion-proppant migration coupling model at least includes a macroscopic fracture expansion sub-model, a proppant migration and settlement sub-model and a fracture conductivity prediction sub-model which are coupled with each other, wherein the macroscopic fracture expansion sub-model is used to simulate the dynamic geometric change of the fracture in the stress field, and the output at least includes the time-varying fracture length, height and dynamic width distribution; the proppant migration and settlement sub-model takes the fracture dynamic geometry output by the macroscopic fracture expansion sub-model as the input field, simulates the transport, settlement and sand dam formation process of the proppant with different particle sizes; and the fracture conductivity prediction sub-model calculates the equivalent permeability and conductivity of the fracture according to the final proppant placement concentration and distribution output by the proppant migration and settlement sub-model; an optimization decision module, which is in communication connection with the data acquisition and potential calculation module, applies an optimization algorithm to solve a function with multi-objectives of equalization of the conductivity of each layer fracture and maximization of the effective filling volume of the proppant based on the dynamic response potential set, and outputs an initial injection parameter combination for different fracture layers of the target well; the initial injection parameter combination includes the injection flow rate, injection pressure and median proppant particle size which match the dynamic response potential of each layer fracture; a real-time monitoring and model calibration module, which is in communication connection with a downhole monitoring network, acquires real-time monitoring data of each layer fracture of the target well through the downhole monitoring network in real time during the injection process, the real-time monitoring data includes the inlet pressure, proppant concentration distribution and microseismic event data; and inputs the real-time monitoring data into the multi-scale fracture expansion-proppant migration coupling model to perform inversion and online calibration on the fracture geometric parameters and proppant settlement coefficients of the model; a dynamic execution and feedback control module, which is in communication connection with the optimization decision module, the real-time monitoring and model calibration module and a field injection equipment control system respectively; after receiving a signal that the model calibration is completed, triggers the optimization decision module to perform optimization solving again by using the calibrated model, generates an updated injection parameter combination, and sends a control instruction to the field injection equipment control system according to the updated injection parameter combination; the control instruction is used to drive the adjustment operation of switching the injection fluid characteristics between different layer positions or realizing the time sequence change of the proppant particle size in the same injection fluid, so as to adapt to the dynamic evolution of the fracture.

[0017] This invention provides an optimization method for proppant injection strategy under multi-layer fracture distribution. Through precise analysis of inter-layer fracture properties, formulation of multi-layer injection optimization strategies, and establishment of a real-time feedback adjustment mechanism, it accurately simulates the proppant migration process based on a multi-scale fracture propagation-proppant migration coupling model. This solves the problem of uneven proppant distribution in multi-layer fractures in existing technologies, and has the following technical effects: Improving the uniformity of proppant distribution: By accurately analyzing the properties of interlayer cracks and implementing multi-layer injection optimization strategies, the injection parameters of proppant can be reasonably controlled according to the characteristics of different crack layers, so that the proppant can be more uniformly distributed in each crack layer, avoiding the problems of local accumulation and insufficient support.

[0018] Enhanced fracture conductivity: The uniform distribution of proppant effectively improves the conductivity of fractures, allowing oil and gas to flow more smoothly from the formation to the wellbore, thereby increasing the production and efficiency of oil and gas wells.

[0019] Improving the success rate of fracturing operations: The real-time feedback adjustment mechanism can adjust the injection parameters in a timely manner according to the actual injection effect, ensuring that the proppant exists stably in each fracture layer, reducing the risk of fracturing failure due to unreasonable parameters, and improving the success rate of fracturing operations.

[0020] Achieving efficient oil and gas resource extraction: The application of the method of this invention can more fully develop the potential of multi-layer fractured reservoirs, improve the recovery rate of oil and gas resources, reduce extraction costs, and achieve efficient extraction and sustainable utilization of oil and gas resources. Attached Figure Description

[0021] Figure 1 This invention provides a flowchart of a proppant injection strategy optimization method for multi-layered crack distribution. Figure One ; Figure 2 This invention provides a flowchart of a proppant injection strategy optimization method for multi-layered crack distribution. Figure Two . Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0023] Therefore, the following detailed description of embodiments of the present invention is not intended to limit the scope of the claimed invention, but merely illustrates some embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0024] It should be noted that the embodiments in the present application and the features and technical solutions in the embodiments can be combined with each other without conflict.

[0025] It should be noted that: similar reference numbers and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0026] In the description of the present application, it should be noted that the terms "upper", "lower", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship commonly placed when the product of the present application is used, or the orientation or positional relationship commonly understood by those skilled in the art, such terms are only for the convenience of describing the present application and simplifying the description, and are not intended to indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", and the like are only used for differentiation and cannot be understood as indicating or implying relative importance.

[0027] As shown in Figures 1-2 The present application provides a proppant injection strategy optimization method under multi-layer fracture distribution, which comprises: Step S1, obtaining a static attribute set and a dynamic response potential set of the multi-layer fractures of the target well; the static attribute set at least includes the permeability, porosity, average width, length, tortuosity and branch density of each layer fracture; the dynamic response potential set is calculated by inputting the static attribute set into a pre-trained multi-scale fracture expansion-proppant migration coupling model, and is used to represent the expansion trend and proppant carrying capacity of the fracture under different injection conditions; Step S2, based on the dynamic response potential set, applying an optimization algorithm to solve a function with the multi-objective of equalizing the conductivity of each layer fracture and maximizing the effective filling volume of the proppant, and outputting an initial injection parameter combination for different fracture layers of the target well; the initial injection parameter combination includes injection flow rate, injection pressure and median proppant particle size matched with the dynamic response potential of each layer fracture; Step S3, during the injection process, real-time monitoring data of each layer fracture of the target well is obtained through a downhole monitoring network, the real-time monitoring data includes inlet pressure, proppant concentration distribution and microseismic event data; the real-time monitoring data is input into the multi-scale fracture expansion-proppant migration coupling model, and the fracture geometric parameters and proppant settling coefficients of the model are inverted and calibrated online; Step S4, using the calibrated multi-scale fracture propagation-proppant migration coupling model, re-executing the optimization solving process of step S2 to generate an updated injection parameter combination, and adjusting the field injection equipment in real time; the adjustment includes switching the injection fluid characteristics between different layer positions, or realizing the time sequence change of the proppant particle size in the same injection fluid to adapt to the dynamic evolution of the fractures.

[0028] The proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment of the application solves the problem of uneven distribution of proppants in multi-layer fractures by accurately simulating the migration process of proppants based on a multi-scale fracture propagation-proppant migration coupling model, and has the following technical effects: Improve the uniformity of proppant distribution: by accurately analyzing the interlayer fracture properties and implementing the multi-layer injection optimization strategy, the injection parameters of proppants can be reasonably controlled according to the characteristics of different fracture layers, so that the proppants are more evenly distributed in each layer of fractures, avoiding the problems of local accumulation and insufficient support.

[0029] Enhance fracture conductivity: the uniform distribution of proppants effectively improves the conductivity of fractures, making oil and gas flow more smoothly from the formation to the wellbore, thereby improving the production and production efficiency of oil and gas wells.

[0030] Improve the success rate of fracturing operation: the real-time feedback adjustment mechanism can adjust the injection parameters in time according to the actual injection effect, ensure the stable existence of proppants in each layer of fractures, reduce the risk of fracturing failure caused by unreasonable parameters, and improve the success rate of fracturing operation.

[0031] Achieve efficient exploitation of oil and gas resources: the application of the method of the embodiment of the application can more fully develop the potential of multi-layer fracture reservoirs, improve the recovery rate of oil and gas resources, reduce the cost of exploitation, and realize the efficient exploitation and sustainable utilization of oil and gas resources.

[0032] The proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment of the application, in step S1, the multi-scale fracture propagation-proppant migration coupling model at least includes a macroscopic fracture propagation sub-model, a proppant migration and settlement sub-model, and a fracture conductivity prediction sub-model; The macroscopic crack propagation sub-model is used for simulating dynamic geometric changes of cracks in a stress field, and outputs at least crack length, height and dynamic width distribution changing over time; the proppant migration and settlement sub-model takes the crack dynamic geometry output by the macroscopic crack propagation sub-model as an input field, and simulates the transport, settlement and sand dam formation process of proppants of different particle sizes therein; and the crack conductivity prediction sub-model calculates the equivalent permeability and conductivity of the crack according to the final proppant placement concentration and distribution output by the proppant migration and settlement sub-model.

[0033] The present application overcomes the prediction distortion problem caused by the isolated or simply connected models in the traditional method by constructing and applying a multi-scale model deeply coupling macroscopic crack propagation, proppant migration and settlement and crack conductivity prediction, thereby realizing closed-loop feedback and collaborative calculation among crack dynamic geometry, proppant distribution and final conductivity for the first time in simulation, and providing a real and reliable physical basis for subsequent model-based optimization decisions.

[0034] Specifically, in the proppant injection strategy optimization method under multi-layer crack distribution of the embodiment, the macroscopic crack propagation sub-model, the proppant migration and settlement sub-model and the crack conductivity prediction sub-model are coupled with each other, including: The macroscopic crack propagation sub-model transmits the updated crack dynamic width distribution w(x, y, t) to the proppant migration and settlement sub-model at each calculation time step as its migration space field; The local proppant concentration c(x, y, t) and the formed sand dam height calculated by the proppant migration and settlement sub-model are fed back to the macroscopic crack propagation sub-model for correcting the effective mechanical width and flow resistance of the crack in the local area; The crack conductivity prediction sub-model is started after the construction simulation ends, and its input is completely dependent on the final output of the proppant migration and settlement sub-model.

[0035] In the proppant injection strategy optimization method under multi-layer crack distribution of the embodiment, in the macroscopic crack propagation sub-model, the dynamic width calculation of the crack considers the influence of the proppant concentration, and adopts a correction formula in the following form: w_eff(x, t) = w_h(x, t) - β × c(x, t); Where w_eff(x, t) is the effective hydraulic width at position x at time t, w_h(x, t) is the theoretical hydraulic width calculated by rock mechanics and fluid pressure, c(x, t) is the proppant volume concentration at the same position and time, and β is an embedding / plugging correction coefficient related to the proppant particle size and rock hardness.

[0036] The modified formula of the embodiment realizes reverse coupling from the proppant concentration field to the fracture geometry field.

[0037] In the proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment, the proppant migration and settlement sub-model is realized by solving the following coupled equation groups: Continuity equation: ; Momentum equation: ; Proppant settling velocity: v_s = f(d_p, ρ_p, ρ_f, μ, c); Wherein, is a partial differential symbol, t is time, is a vector differential operator (Nabla operator), w is the fracture width, c is the proppant concentration, v is the average flow rate of the sand-carrying fluid, μ is the viscosity of the fracturing fluid, p is the pressure in the fracture, v_s is the proppant settling velocity, and d_p, ρ_p, ρ_f, μ, and c are functions of the proppant particle size d_p, the proppant and fracturing fluid density ρ_p, ρ_f, the viscosity μ, and the local concentration c.

[0038] The coupled equation groups of the embodiment explicitly take the fracture width w as the key parameter of the dynamic geometry of the fracture, and embody the strong coupling with the macroscopic propagation model.

[0039] The multi-scale fracture propagation-proppant migration coupling model of the embodiment is obtained by the following steps: a) Historical data collection: Collect complete data packages of multiple implemented fracturing wells, including pre-treatment logging and seismic interpretation attributes (input), pumping program and real-time monitoring data during treatment (intermediate input / verification), and production logging or tracer measured production profile of each layer after treatment (label); b) Model initial construction: Based on physical principles, the framework of the multi-scale fracture propagation-proppant migration coupling model is built, and a set of default physical parameters is initialized; c) Backpropagation training: Taking the pre-treatment attributes and the pumping program as the input, the multi-scale fracture propagation-proppant migration coupling model is driven to calculate; the proppant distribution or production profile predicted by the model is compared with the actual output profile label, and the loss function is calculated; the key uncertain parameters (such as the modified coefficient β, the empirical coefficient in the settling velocity function f, and the initial fracture efficiency) in the model are adjusted in reverse by using gradient descent or evolutionary algorithm until the loss function is minimized; d) Model solidification and application: The model parameter set trained to best reflect the geological and engineering characteristics of the region is solidified as the pre-trained model, which is used for dynamic response potential prediction of new blocks.

[0040] This embodiment provides a proppant injection strategy optimization method under multi-layer fracture distribution. In step S1, the physical properties of the fractures, such as permeability, porosity, average width, length, and orientation, are obtained using geological exploration technology and data analysis methods. The curvature and branch density of the fractures are obtained by performing digital image processing and fracture skeleton extraction algorithms on wellbore imaging logging data.

[0041] In this embodiment, a proppant injection strategy optimization method under multi-layered fracture distribution is proposed. In step S2, the function with multiple objectives—equalizing the conductivity of each fracture layer and maximizing the effective proppant filling volume—is as follows: Maximize: F = α × F_volume + (1-α) × F_balance; Where F_volume = (∑ V_i ) / V_total represents the normalized value of the total effective filling volume, V_i is the predicted effective proppant filling volume of the i-th fracture layer, which is calculated by the multi-scale fracture propagation-proppant transport coupling model based on the combination of injection parameters, ∑ V_i represents the summation of i from 1 to n, and V_total is the sum of the volumes of all fracture layers; F_balance = 1 / (1 + σ(C_i) / μ(C_i)), representing the conductivity balance index, where C_i is the predicted dimensionless conductivity of the i-th layer of fracture, and σ(C_i) and μ(C_i) are the standard deviation and mean of the conductivity of each layer, respectively. The closer the conductivity balance index value is to 1, the more balanced it is. α is a preset weighting coefficient, ranging from 0.3 to 0.7, used to adjust the relative importance of the two optimization objectives.

[0042] Furthermore, in the proppant injection strategy optimization method under multi-layered fracture distribution of this embodiment, step S2 involves applying an optimization algorithm to solve a multi-objective function that aims to equalize the conductivity of each fracture layer and maximize the effective filling volume of the proppant, including: Step S201: Encode the initial injection parameter combination for different fracture layers into a solution vector. The solution vector includes at least the injection flow rate, injection pressure, and median proppant particle size for each layer. Initialize a population containing multiple solution vectors by random generation or heuristic generation based on historical construction cases. Step S202: For each solution vector in the population, input it into the multi-scale crack propagation-proppane transport coupling model to calculate the predicted effective proppant filling volume V_i and the predicted dimensionless conductivity C_i for each layer; then, calculate the fitness value of the solution vector according to the multi-objective function F. Step S203, based on the fitness value of the solution vector, the advantage individual is selected by using the tournament selection method, and simulated binary crossover and polynomial mutation operations are performed on it to generate a new offspring population; Step S204, repeating step S202 and step S203 until the fitness value of the optimal solution vector in the population meets the preset value within a continuous preset number of generations, or the maximum number of iterations is reached, and the optimal solution vector at this time is decoded and output as the initial injection parameter combination.

[0043] The initial injection parameter combination generated in step S2 of the proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment, the difference of each layer parameter is determined by the following mapping rule and the dynamic response potential set obtained in step S1: For the fracture layer classified as "high extension and low closure stress" in the dynamic response potential set, the matching proppant median particle size (d50) range is 0.8-1.2 mm, and the injection pressure is set to 80%-100% of the design upper limit; For the fracture layer classified as "low extension and high filtration risk", the matching proppant median particle size (d50) range is 0.2-0.4 mm, and the fracturing fluid system containing a filtration reducer is matched; For the fracture layer classified as "moderate extension, but with complex bending and branching", the matching proppant median particle size (d50) adopts a bimodal distribution, i.e. 0.3-0.5 mm and 0.7-0.9 mm are mixed in a predetermined proportion to balance the main fracture support and micro-fracture entry capability.

[0044] Through the above limitations, the optimization step S2 of the embodiment of the present application realizes the following key technical progress: Objective function quantification: The macroscopic optimization target (balance, maximum) is converted into a specific, calculable mathematical expression. In particular, the construction of F_balance skillfully quantifies "balance" using statistical concepts, making it a target that the algorithm can directly handle.

[0045] Algorithm process explicitization: A complete evolutionary algorithm optimization process is clearly outlined, including key steps such as encoding, evaluation, iteration, and convergence. This not only explains "how to optimize", but also emphasizes its iterative optimization characteristics, distinguishing it from simple rule matching or single calculation.

[0046] Potential-parameter mapping concretization: An exemplary mapping rule from abstract "potential" to specific engineering parameters is provided. Although these numerical ranges are examples, the claim structure protects the core method of "differential parameter matching based on potential classification". In particular, the introduction of "bimodal particle size distribution" to deal with complex fracture networks is a very specific and creative technical means.

[0047] The proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment, in step S3, the real-time monitoring data includes direct monitoring data and indirect inversion data: The direct monitoring data at least includes temperature, acoustic vibration frequency and strain data at the entrance of each fracture section obtained by a downhole distributed optical fiber sensing (DTS / DAS) system; The indirect inversion data at least includes microseismic event point cloud obtained by a surface or downhole microseismic monitoring array, for inverting the space-time profile of fracture propagation; The inversion calibration of the fracture geometric parameters mainly depends on the indirect inversion data, and the inversion calibration of the proppant settling coefficient mainly depends on the time sequence signal reflecting the arrival time of the sand-carrying fluid and the proppant accumulation characteristics in the direct monitoring data.

[0048] The proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment, in step S3, the real-time monitoring data is input into the multi-scale fracture propagation-proppant migration coupling model, and the inversion and online calibration of the fracture geometric parameters and the proppant settling coefficient of the model include: Step S301, define a state vector X, which at least contains a subset of fracture geometric parameters and a proppant settling coefficient λ to be calibrated in the multi-scale fracture propagation-proppant migration coupling model, and the subset of fracture geometric parameters includes the fracture half-length of each layer and the dynamic width distribution coefficient; define an observation vector Y, the elements of which correspond to the obtained real-time monitoring data; Step S302, initialize a set containing N model instances, where N is an integer greater than 1; each model instance is a copy of the multi-scale fracture propagation-proppant migration coupling model, but a random disturbance value based on a preset probability distribution of prior knowledge is given to each component of the state vector X of each model instance, thereby generating N different initial state vectors X_1, X_2,..., X_N; in the current calibration period, let each model instance take its respective state vector as the initial condition, run from the last calibration time to the current time, and respectively perform numerical simulation, thereby obtaining a set of predicted values {X^f_i} of the state vector and a set of predicted values {Y^f_i} of the observation vector corresponding thereto, where i = 1, 2,..., N; Step S303, obtain the actual observation vector Y^obs at the current time; according to the update equation of the ensemble Kalman filter, the difference between the actual observation vector Y^obs and the observation prediction set {Y^f_i} is used to correct each member in the state prediction set {X^f_i}, and a set of analysis updated state vectors {X^a_i} is calculated. Step S304, the arithmetic mean of the updated state vector set {X^a_i} is taken as the optimal estimation value of the fracture geometric parameter and the proppant settling coefficient at the current time, and the corresponding parameter of the multi-scale fracture propagation-proppant migration coupling model used for decision making in step S4 is updated with the value.

[0049] The proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment, in step S3, the inversion and online calibration are periodically triggered at a fixed time interval Δt, or triggered when a set engineering event is monitored; the set engineering event includes: a sudden change of downhole pressure exceeding a threshold, monitoring of a proppant concentration peak reaching a certain set sensor position, or a microseismic event occurrence rate exceeding a threshold.

[0050] The proppant injection strategy optimization method under the multi-layer fracture distribution of the embodiment, in step S3, the updated proppant settling coefficient λ obtained through inversion calibration is directly used to correct the objective function calculation relied on by the optimization algorithm in step S4; specifically, the updated λ is substituted into the settling velocity function f of the proppant migration and settling sub-model, so that in the re-optimization of step S4, a model that can better reflect the real behavior of the current downhole fluid and proppant is used for prediction.

[0051] Through the above definition, the step S3 of the application achieves the following technical effects: Data specificity: the data source used for calibration and its correspondence with the calibration target are clearly defined, reflecting the fine design of multi-source data fusion to solve specific inversion problems.

[0052] Algorithm advancement: the "ensemble Kalman filter (EnKF)" which is a high-efficiency data assimilation algorithm suitable for nonlinear systems is introduced as an implementation means. This is not a simple parameter adjustment, but an optimal data fusion process based on statistical estimation theory, with high technical content and essential difference from "trial and error method" or simple regression adjustment.

[0053] Trigger mechanism intelligence: calibration is not a simple timing task, but is combined with engineering event driving, reflecting the intelligent perception and response of the system to the construction state.

[0054] Closed loop deepening: it is emphasized that the calibration result not only updates the model, but also directly and immediately feeds back to the optimization decision loop, truly realizing the deep closed loop of "perception-cognition-decision", and the value of calibration is maximized.

[0055] The embodiment of the application also provides a proppant injection strategy optimization system under multi-layer fracture distribution, comprising: The data acquisition and potential calculation module acquires the static attribute set and dynamic response potential set of the multi-layer fractures in the target well. The static attribute set includes at least the permeability, porosity, average width, length, tortuosity, and branch density of each fracture layer. The dynamic response potential set is obtained by inputting the static attribute set into a pre-trained multi-scale fracture propagation-proppane migration coupling model, and is used to characterize the fracture propagation trend and proppant carrying capacity under different injection conditions. The optimization decision module is communicatively connected to the data acquisition and potential calculation module. Based on the dynamic response potential set, it applies an optimization algorithm to solve a function with multiple objectives, namely balancing the conductivity of each fracture layer and maximizing the effective filling volume of the proppant. The module outputs a combination of initial injection parameters for different fracture layers in the target well. The initial injection parameter combination includes the injection flow rate, injection pressure, and median proppant particle size that match the dynamic response potential of each fracture layer. The real-time monitoring and model calibration module is connected to the downhole monitoring network. During the injection process, it acquires real-time monitoring data of fractures in each layer of the target well through the downhole monitoring network. The real-time monitoring data includes inlet pressure, proppant concentration distribution, and microseismic event data. The real-time monitoring data is input into the multi-scale fracture propagation-proppant migration coupled model to invert and calibrate the fracture geometric parameters and proppant settlement coefficient of the model online. The dynamic execution and feedback control module is communicatively connected to the optimization decision module, the real-time monitoring and model calibration module, and the field injection equipment control system, respectively. Upon receiving a signal indicating model calibration completion, it triggers the optimization decision module to re-optimize the solution using the calibrated model, generating updated injection parameter combinations, and accordingly sending control commands to the field injection equipment control system. These control commands drive the execution of adjustments such as switching injection fluid characteristics between different layers or implementing temporal changes in proppant particle size within the same injection fluid, to adapt to the dynamic evolution of the fracture. Example

[0056] Reservoir conditions: A certain reservoir has three fracture layers. The upper fracture layer has a permeability of 10 mD, a porosity of 15%, an average fracture width of 3 mm, and a length of about 80 m. The middle fracture layer has a permeability of 5 mD, a porosity of 12%, an average fracture width of 2 mm, and a length of about 60 m. The lower fracture layer has a permeability of 15 mD, a porosity of 18%, an average fracture width of 4 mm, and a length of about 100 m.

[0057] Implementation process: Interlayer crack attribute analysis and region division: Based on the attribute analysis of the three layers of cracks, the upper layer cracks are defined as the general injection area, the middle layer cracks as the fine injection area, and the lower layer cracks as the key injection area.

[0058] Multi-layer injection optimization strategy formulation and implementation: For the lower layer key injection area, set the injection flow rate to 30 m³ / min, the injection pressure to 40 MPa, and the proppant particle size to 0.8-1.2 mm; for the upper layer general injection area, set the injection flow rate to 20 m³ / min, the injection pressure to 30 MPa, and the proppant particle size to 0.6-0.8 mm; for the middle layer fine injection area, set the injection flow rate to 15 m³ / min, the injection pressure to 25 MPa, and the proppant particle size to 0.4-0.6 mm.

[0059] Real-time feedback adjustment: During the injection process, it was found through real-time monitoring that the proppant distribution in the local area of the middle layer fracture was uneven, so the injection pressure was immediately reduced to 22 MPa and the flow rate was adjusted to 12 m³ / min to gradually uniform the proppant distribution.

[0060] Implementation effect: After the injection was completed, it was found through evaluation that the proppant distribution in the three-layer fracture was uniform, and the fracture conductivity was increased by about 35% compared with the traditional injection strategy, and the oil and gas well production was increased by 30%. Embodiment

[0061] Reservoir conditions: A certain reservoir has four layers of fractures, the first layer of fractures has a permeability of 8 mD, a porosity of 14%, an average fracture width of 2.5 mm, and a length of about 70 m; the second layer of fractures has a permeability of 3 mD, a porosity of 10%, an average fracture width of 1.5 mm, and a length of about 50 m; the third layer of fractures has a permeability of 12 mD, a porosity of 16%, an average fracture width of 3.5 mm, and a length of about 90 m; the fourth layer of fractures has a permeability of 6 mD, a porosity of 13%, an average fracture width of 2 mm, and a length of about 65 m.

[0062] Implementation process: Interlayer fracture property analysis and region division: After analysis, the first layer of fractures is divided into a general injection area, the second layer of fractures is a special fine injection area, the third layer of fractures is a key injection area, and the fourth layer of fractures is a secondary key injection area.

[0063] Multi-layer injection optimization strategy formulation and implementation: The third layer key injection area uses an injection flow rate of 35 m³ / min, an injection pressure of 45 MPa, and a proppant particle size of 0.9-1.2 mm; the first layer general injection area uses an injection flow rate of 22 m³ / min, an injection pressure of 32 MPa, and a proppant particle size of 0.6-0.8 mm; the fourth layer secondary key injection area uses an injection flow rate of 18 m³ / min, an injection pressure of 28 MPa, and a proppant particle size of 0.5-0.7 mm; the second layer special fine injection area uses an injection flow rate of 10 m³ / min, an injection pressure of 20 MPa, and a proppant particle size of 0.3-0.5 mm.

[0064] Real-time feedback adjustment: monitoring during injection found that the proppant advancing speed in the fourth layer fracture partial area was slow, the injection pressure was increased to 30 MPa, and the flow rate was adjusted to 20 m³ / min, so that the proppant was filled smoothly.

[0065] Implementation effect: through evaluation, the proppant distribution in each layer fracture is reasonable, the overall fracture conductivity is improved by about 40%, and the oil and gas well production is increased by 35%.

[0066] The above examples are only used to illustrate the present application and not to limit the technical solutions described in the present application. Although the present application has been described in detail with reference to the above embodiments, the present application is not limited to the above specific embodiments. Therefore, any modification or equivalent replacement of the present application; and all technical solutions and improvements without departing from the spirit and scope of the application are all included in the scope of the claims of the present application.

Claims

1. A method for optimizing proppant injection strategies under multi-layered fracture distribution, characterized in that, include: Step S1: Obtain the static attribute set and dynamic response potential set of the multi-layer fractures in the target well; the static attribute set includes at least the permeability, porosity, average width, length, tortuosity and branch density of each fracture layer. The dynamic response potential set is obtained by inputting the static attribute set into a pre-trained multi-scale fracture propagation-proppane migration coupled model. It is used to characterize the propagation trend of fractures and the proppane carrying capacity under different injection conditions. The multi-scale fracture propagation-proppane migration coupled model includes at least three coupled sub-models: a macroscopic fracture propagation sub-model, a proppane migration and settlement sub-model, and a fracture conductivity prediction sub-model. The macroscopic fracture propagation sub-model simulates the dynamic geometric changes of fractures in a stress field, and its output includes at least the time-varying fracture length, height, and dynamic width distribution. The proppane migration and settlement sub-model uses the fracture dynamic geometry output by the macroscopic fracture propagation sub-model as its input field to simulate the transport, settlement, and sandbar formation process of proppants of different particle sizes. The fracture conductivity prediction sub-model calculates the equivalent permeability and conductivity of the fracture based on the final proppant concentration and distribution output by the proppane migration and settlement sub-model. Step S2: Based on the dynamic response potential set, apply an optimization algorithm to solve a function with multiple objectives, namely equalizing the conductivity of each fracture layer and maximizing the effective filling volume of the proppant, and output the initial injection parameter combination for different fracture layers in the target well; the initial injection parameter combination includes the injection flow rate, injection pressure and median proppant particle size that match the dynamic response potential of each fracture layer. Step S3: During the injection process, real-time monitoring data of fractures in each layer of the target well is acquired through the downhole monitoring network. The real-time monitoring data includes inlet pressure, proppant concentration distribution, and microseismic event data. The real-time monitoring data is input into the multi-scale fracture propagation-proppant migration coupled model, and the fracture geometric parameters and proppant settlement coefficient of the model are inverted and calibrated online. Step S4: Using the calibrated multi-scale fracture propagation-proppane migration coupling model, re-execute the optimization solution process of step S2 to generate an updated combination of injection parameters and adjust the on-site injection equipment in real time. The adjustment includes switching the characteristics of the injection fluid between different layers or realizing the temporal variation of the proppant particle size in the same injection fluid to adapt to the dynamic evolution of the fracture.

2. The method for optimizing proppant injection strategy under multi-layered crack distribution according to claim 1, characterized in that, The macroscopic crack propagation sub-model, proppant migration and sedimentation sub-model, and crack conductivity prediction sub-model are coupled together, including: At each computation time step, the macroscopic crack propagation sub-model transmits the updated crack dynamic width distribution w(x, y,t) to the proppant migration and settlement sub-model as its migration space field. The local proppant concentration c(x, y, t) and the height of the sand embankment formed, calculated by the proppant migration and sedimentation sub-model, are fed back to the macroscopic crack propagation sub-model to correct the effective mechanical width and flow resistance of the cracks in the local area. The crack conductivity prediction sub-model is activated after the construction simulation is completed, and its input depends entirely on the final output of the proppant migration and settlement sub-model.

3. The method for optimizing proppant injection strategy under multi-layered crack distribution according to claim 2, characterized in that, In the macroscopic crack propagation sub-model, the dynamic width calculation of the crack takes into account the influence of proppant concentration, and adopts the following modified formula: w_eff(x, t) = w_h(x, t) - β×c(x, t); Where w_eff(x, t) is the effective hydraulic width at position x at time t, w_h(x, t) is the theoretical hydraulic width calculated from rock mechanics and fluid pressure, c(x, t) is the proppant volume concentration at the same position and time, and β is the embedding / clogging correction coefficient related to proppant particle size and rock hardness.

4. The method for optimizing proppant injection strategy under multi-layered crack distribution according to claim 2 or 3, characterized in that, The proppant transport and sedimentation sub-model is achieved by solving the following set of coupled equations: Continuity equation: ; Momentum equation: ; Proppant settling velocity: v_s = f(d_p, ρ_p, ρ_f, μ, c); in, The symbol is for partial differential, and t is time. Let w be the vector differential operator, c be the proppant concentration, v be the average velocity of the proppant-carrying fluid, μ be the fracturing fluid viscosity, p be the intra-fracture pressure, and v_s be the proppant settling velocity. v_s is a function of the proppant particle size d_p, the proppant and fracturing fluid densities ρ_p and ρ_f, the viscosity μ, and the local concentration c.

5. The method for optimizing proppant injection strategy under multi-layered crack distribution according to claim 1, characterized in that, In step S2, the function with the multi-objective goals of equalizing the conductivity of each fracture layer and maximizing the effective proppant filling volume is: Maximize: F = α × F_volume + (1-α) × F_balance; Where F_volume = (∑ V_i ) / V_total represents the normalized value of the total effective filling volume, V_i is the predicted effective proppant filling volume of the i-th fracture layer, which is calculated by the multi-scale fracture propagation-proppant transport coupling model based on the combination of injection parameters, ∑ V_i represents the summation of i from 1 to n, and V_total is the sum of the volumes of all fracture layers; F_balance = 1 / (1 + σ(C_i) / μ(C_i)), representing the conductivity balance index, where C_i is the predicted dimensionless conductivity of the i-th layer of fracture, and σ(C_i) and μ(C_i) are the standard deviation and mean of the conductivity of each layer, respectively. The closer the conductivity balance index value is to 1, the more balanced it is. α is a preset weighting coefficient, ranging from 0.3 to 0.7, used to adjust the relative importance of the two optimization objectives.

6. The method for optimizing proppant injection strategy under multi-layered crack distribution according to claim 5, characterized in that, In step S2, an optimization algorithm is applied to solve a multi-objective function that aims to equalize the conductivity of fractures in each layer and maximize the effective volume of proppant filling, including: Step S201: Encode the initial injection parameter combination for different fracture layers into a solution vector. The solution vector includes at least the injection flow rate, injection pressure, and median proppant particle size for each layer. Initialize a population containing multiple solution vectors by random generation or heuristic generation based on historical construction cases. Step S202: For each solution vector in the population, input it into the multi-scale crack propagation-proppane transport coupling model to calculate the predicted effective proppant filling volume V_i and the predicted dimensionless conductivity C_i for each layer; then, calculate the fitness value of the solution vector according to the multi-objective function F. Step S203: Based on the fitness value of the solution vector, select dominant individuals using tournament selection, and perform simulated binary crossover and polynomial mutation operations on them to generate a new offspring population. Step S204: Repeat steps S202 and S203 until the fitness value of the optimal solution vector in the population meets the preset value within a consecutive preset number of generations, or reaches the maximum number of iterations. Then, decode the optimal solution vector at this time and output it as the initial injection parameter combination.

7. The method for optimizing proppant injection strategy under multi-layered crack distribution according to claim 6, characterized in that, In step S3, the real-time monitoring data is input into the multi-scale crack propagation-proppane migration coupled model, and the crack geometric parameters and proppane settlement coefficient of the model are inverted and calibrated online, including: Step S301: Define a state vector X, which includes at least a subset of crack geometric parameters to be calibrated and the proppant settlement coefficient λ in the multi-scale crack propagation-proppant transport coupling model. The subset of crack geometric parameters includes the half-length of cracks in each layer and the dynamic width distribution coefficient. Define an observation vector Y, whose elements correspond to the acquired real-time monitoring data. Step S302: Initialize a set containing N model instances, where N is an integer greater than 1; each model instance is a copy of the multi-scale crack propagation-proppant transport coupled model, but each component of the state vector X of each model instance is assigned a random perturbation value based on a preset probability distribution of prior knowledge, thereby generating N different initial state vectors X_1, X_2, ..., X_N; within the current calibration period, let each model instance use its own state vector as the initial condition, run from the previous calibration time to the current time, and perform numerical simulations respectively, thereby obtaining a set of predicted values ​​of state vectors {X^f_i} and a set of predicted values ​​of observation vectors {Y^f_i}, where i = 1, 2, ..., N; Step S303: Obtain the actual observation vector Y^obs at the current time; according to the update equation of the ensemble Kalman filter, use the difference between the actual observation vector Y^obs and the observation prediction set {Y^f_i} to correct each member in the state prediction set {X^f_i}, and calculate a set of updated state vectors {X^a_i}. Step S304: Take the arithmetic mean of the updated state vector set {X^a_i} as the optimal estimate of the crack geometry parameters and proppant settlement coefficient at the current moment, and use this value to update the corresponding parameters of the multi-scale crack propagation-proppant migration coupling model used for decision-making in step S4.

8. The method according to claim 7, characterized in that, The inversion and online calibration in step S3 are triggered periodically at a fixed time interval Δt, or when a set engineering event is detected; the set engineering events include: a sudden change in downhole pressure exceeding a threshold, the detection of a proppant concentration peak reaching a certain set sensor position, or the occurrence rate of microseismic events exceeding a threshold.

9. A proppant injection strategy optimization system for multi-layered fracture distribution, characterized in that, include: The data acquisition and potential calculation module acquires the static attribute set and dynamic response potential set of the multi-layer fractures in the target well; the static attribute set includes at least the permeability, porosity, average width, length, tortuosity and branch density of each fracture layer. The dynamic response potential set is obtained by inputting the static attribute set into a pre-trained multi-scale fracture propagation-proppane migration coupled model. It is used to characterize the propagation trend of fractures and the proppane carrying capacity under different injection conditions. The multi-scale fracture propagation-proppane migration coupled model includes at least three coupled sub-models: a macroscopic fracture propagation sub-model, a proppane migration and settlement sub-model, and a fracture conductivity prediction sub-model. The macroscopic fracture propagation sub-model simulates the dynamic geometric changes of fractures in a stress field, and its output includes at least the time-varying fracture length, height, and dynamic width distribution. The proppane migration and settlement sub-model uses the fracture dynamic geometry output by the macroscopic fracture propagation sub-model as its input field to simulate the transport, settlement, and sandbar formation process of proppants of different particle sizes. The fracture conductivity prediction sub-model calculates the equivalent permeability and conductivity of the fracture based on the final proppant concentration and distribution output by the proppane migration and settlement sub-model. The optimization decision module is communicatively connected to the data acquisition and potential calculation module. Based on the dynamic response potential set, it applies an optimization algorithm to solve a function with multiple objectives, namely balancing the conductivity of each fracture layer and maximizing the effective filling volume of the proppant. The module outputs a combination of initial injection parameters for different fracture layers in the target well. The initial injection parameter combination includes the injection flow rate, injection pressure, and median proppant particle size that match the dynamic response potential of each fracture layer. The real-time monitoring and model calibration module is connected to the downhole monitoring network. During the injection process, it acquires real-time monitoring data of fractures in each layer of the target well through the downhole monitoring network. The real-time monitoring data includes inlet pressure, proppant concentration distribution, and microseismic event data. The real-time monitoring data is input into the multi-scale fracture propagation-proppant migration coupled model to invert and calibrate the fracture geometric parameters and proppant settlement coefficient of the model online. The dynamic execution and feedback control module is communicatively connected to the optimization decision module, the real-time monitoring and model calibration module, and the field injection equipment control system, respectively. Upon receiving a signal indicating model calibration completion, it triggers the optimization decision module to re-optimize the solution using the calibrated model, generating updated injection parameter combinations, and accordingly sending control commands to the field injection equipment control system. These control commands drive the execution of adjustments such as switching injection fluid characteristics between different layers or implementing temporal changes in proppant particle size within the same injection fluid, to adapt to the dynamic evolution of the fracture.

Images