A method for establishing a prediction model of fracturing sand plug, a prediction method and device

Abstract

The application provides a method, a method and a device for establishing a fracturing sand plug prediction model, wherein the method comprises the following steps: obtaining a plurality of fracturing parameters and sand plug information in a fracturing operation process to form a fracturing sand plug data table; dividing the plurality of fracturing parameters into continuous parameters and discrete parameters according to the nature of the fracturing parameters; analyzing the relationship between all continuous parameters and sand plug information to obtain sensitive parameters in the continuous parameters, wherein the sensitive parameters are used to reflect the sand plug information; analyzing the relationship between all discrete parameters and sand plug information to obtain main control parameters in the discrete parameters, wherein the main control parameters are used to reflect the sand plug information; taking the sensitive parameters and the main control parameters as samples, taking the sand plug information as sample labels, training a machine learning model, and obtaining a prediction model for predicting fracturing sand plug. The fracturing sand plug prediction model can be established, and the sand plug result obtained by the model has high precision and strong generalization ability.

Description

Technical Field

[0001] This invention relates to the field of sand plugging prediction, and in particular, to a method for establishing a prediction model, a prediction method, and an apparatus for fracturing sand plugging. Background Technology

[0002] Due to geological and engineering factors, unconventional reservoirs such as tight oil and shale oil are prone to sand plugging accidents during hydraulic fracturing. Currently, the analysis of sand plugging accidents influenced by multiple factors generally relies on manual qualitative analysis methods, lacking effective methods for quantitative analysis of high-dimensional, multi-parameter data. With the rapid development of big data and artificial intelligence technologies, utilizing these technologies to solve the problem of analyzing and intelligently predicting the main controlling factors of fracturing sand plugging has become a hot research topic in the industry. However, conventional machine learning suffers from significant uncertainties in data analysis and processing, resulting in low accuracy and poor generalization ability of sand plugging prediction models.

[0003] Therefore, there is an urgent need for a method to establish a prediction model for fracturing sand plugging, which can be used to establish a prediction model for fracturing sand plugging. The sand plugging results predicted by this model have high accuracy and strong generalization ability. Summary of the Invention

[0004] The purpose of this embodiment is to provide a method, method and device for establishing a prediction model for fracturing sand plugging, so that the sand plugging results predicted by this model have high accuracy and strong generalization ability.

[0005] To achieve the above objectives, this paper provides a method for establishing a predictive model for fracturing sand plugging, including:

[0006] Multiple fracturing parameters and sand plugging information are obtained during the fracturing operation to form a fracturing sand plugging data table;

[0007] Based on the nature of the fracturing parameters, the multiple fracturing parameters are divided into continuous parameters and discrete parameters;

[0008] The relationship between all continuous parameters and sand blockage information is analyzed to obtain sensitive parameters among the continuous parameters, wherein the sensitive parameters are used to reflect the sand blockage information;

[0009] The relationship between all discrete parameters and sand blockage information is analyzed to obtain the main control parameters among the discrete parameters, wherein the main control parameters are used to reflect the sand blockage information;

[0010] Using the sensitive parameters and the main control parameters as samples, and the sand plugging information as sample labels, the machine learning model is trained to obtain a prediction model for predicting fracturing sand plugging.

[0011] Preferably, the fracturing parameters include: drilling parameters, geological parameters, and fracturing engineering parameters.

[0012] Preferably, the analysis of the relationship between all continuous parameters and sand blockage information to obtain sensitive parameters among the continuous parameters further includes:

[0013] Each continuous parameter in the fracturing process is meshed using a meshing method to form meshed parameters;

[0014] The mesh density is calculated on the meshing parameters to obtain the overlap coefficient of the meshing parameters under different sand blockage information;

[0015] When the overlap coefficient is less than the sensitivity parameter threshold, the continuous parameter is the sensitivity parameter.

[0016] Preferably, the step of analyzing the relationship between all discrete parameters and sand blockage information to obtain the main control parameters among the discrete parameters further includes:

[0017] Based on the event probability difference algorithm, the event probability difference between each discrete parameter and different sand blockage information is calculated;

[0018] When the event probability difference is greater than the master control parameter threshold, the discrete parameter is the master control parameter.

[0019] Preferably, the calculation of the event probability difference between each discrete parameter and different sand blockage information based on the event probability difference algorithm further includes:

[0020] The event probability difference between each discrete parameter and different sand blockage information is calculated using the following formula:

[0021]

[0022] Where M is the event probability difference, S1 and S2 are the occurrence times of two different sand plugging information during fracturing operations, and V is the occurrence time of each discrete parameter during fracturing operations.

[0023] Preferably, the calculation of the event probability difference between each discrete parameter and different sand blockage information based on the event probability difference algorithm further includes:

[0024] The event probability difference between each discrete parameter and different sand blockage information is calculated using the following formula:

[0025]

[0026] Where M is the event probability difference, S1 and S2 are the occurrence times of two different sand plugging information during fracturing operations, V is the occurrence time of each discrete parameter during fracturing operations, and |·| is the absolute value.

[0027] On the other hand, the embodiments in this paper provide a method for predicting fracturing sand plugging, including:

[0028] Obtain the sensitive and key parameters during the current fracturing operation;

[0029] The sensitive parameters and the main control parameters are input into the above prediction model to predict the sand plugging information in the current fracturing process.

[0030] On another front, this embodiment provides a predictive model establishment device for fracturing sand plugging, the device comprising:

[0031] The acquisition module is used to acquire multiple fracturing parameters and sand plugging information during the fracturing operation, and form a fracturing sand plugging data table.

[0032] A partitioning module is used to divide the multiple fracturing parameters into continuous parameters and discrete parameters according to their properties;

[0033] The first analysis module is used to analyze the relationship between all continuous parameters and sand blockage information to obtain sensitive parameters among the continuous parameters, wherein the sensitive parameters are used to reflect the sand blockage information;

[0034] The second analysis module is used to analyze the relationship between all discrete parameters and sand blockage information to obtain the main control parameters among the discrete parameters, wherein the main control parameters are used to reflect the sand blockage information;

[0035] The model building module is used to train the machine learning model by using the sensitive parameters and the main control parameters as samples and the sand plugging information as sample labels, so as to obtain a prediction model for predicting sand plugging in fracturing.

[0036] In another aspect, embodiments of this document also provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the computer program, when executed by the processor, performs instructions of any of the methods described above.

[0037] In another aspect, the embodiments herein also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of a computer device, performs instructions for any of the methods described above.

[0038] As can be seen from the technical solutions provided in the embodiments above, the methods described in these embodiments do not require all fracturing parameters to be used as samples. Instead, they first classify the fracturing parameters based on their properties, dividing them into continuous and discrete parameters. Then, they analyze and obtain the sensitive parameters among the continuous parameters and the main control parameters among the discrete parameters. Using the sensitive parameters and main control parameters as samples, a machine learning model is trained, ultimately obtaining a prediction model for predicting sand plugging in fracturing. Since both the sensitive parameters and the main control parameters are used to reflect sand plugging information, the prediction model established by the method described in these embodiments has high accuracy and strong generalization ability.

[0039] To make the above and other objects, features and advantages of this document more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments or prior art described herein, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this article. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A flowchart illustrating a method for establishing a prediction model for fracturing sand plugging provided in this embodiment is shown.

[0042] Figure 2 This document illustrates a flowchart of an embodiment for analyzing the relationship between all continuous parameters and sand blockage information to obtain sensitive parameters among the continuous parameters.

[0043] Figure 3 This document shows a schematic diagram of the continuous parameter meshing provided in the embodiments of this paper;

[0044] Figure 4 This document illustrates a flowchart of the process provided in the embodiments of this paper for analyzing the relationship between all discrete parameters and sand blockage information to obtain the main control parameters among the discrete parameters;

[0045] Figure 5 The figures show the ratio of sand plugging and normal (non-sand plugging) conditions for the two perforation guns (Type A and Type B) provided in the embodiments of this article during fracturing operations;

[0046] Figure 6 A flowchart illustrating a method for predicting fracturing sand plugging provided in this embodiment is shown.

[0047] Figure 7This document shows a schematic diagram of the module structure of a predictive model building device for fracturing sand plugging provided in an embodiment of the present invention;

[0048] Figure 8 This document shows a schematic diagram of the module structure of a fracturing sand plugging prediction device provided in an embodiment of the invention;

[0049] Figure 9 A schematic diagram of the structure of the computer device provided in the embodiments of this article is shown.

[0050] Explanation of symbols in the attached drawings:

[0051] 100. Acquisition Module;

[0052] 200. Divide into modules;

[0053] 300. First Analysis Module;

[0054] 400. Second Analysis Module;

[0055] 500. Model building module;

[0056] 600. Parameter Acquisition Module;

[0057] 700. Prediction Module

[0058] 902. Computer equipment;

[0059] 904, Processor;

[0060] 906. Memory;

[0061] 908. Drive mechanism;

[0062] 910. Input / Output Module;

[0063] 912. Input devices;

[0064] 914. Output devices;

[0065] 916. Presentation equipment;

[0066] 918. Graphical User Interface;

[0067] 920. Network interface;

[0068] 922. Communication link;

[0069] 924. Communication bus. Detailed Implementation

[0070] The technical solutions in the embodiments described below will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, and not all of the embodiments. Based on the embodiments described herein, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this document.

[0071] Due to geological and engineering factors, unconventional reservoirs such as tight oil and shale oil are prone to sand plugging accidents during hydraulic fracturing. Currently, the analysis of sand plugging accidents influenced by multiple factors generally relies on manual qualitative analysis methods, lacking effective methods for quantitative analysis of high-dimensional, multi-parameter data. With the rapid development of big data and artificial intelligence technologies, utilizing these technologies to solve the problem of analyzing and intelligently predicting the main controlling factors of fracturing sand plugging has become a hot research topic in the industry. However, conventional machine learning suffers from significant uncertainties in data analysis and processing, resulting in low accuracy and poor generalization ability of sand plugging prediction models.

[0072] To address the aforementioned issues, this paper presents a method for establishing a predictive model for fracturing sand plugging. Figure 1 This is a flowchart illustrating a method for establishing a predictive model for fracturing sand plugging, as provided in the embodiments of this document. This specification provides the operational steps described in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or device products, the methods shown in the embodiments or accompanying drawings can be executed sequentially or in parallel.

[0073] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0074] Reference Figure 1 This paper discloses a method for establishing a prediction model for fracturing sand plugging, including:

[0075] S101: Obtain multiple fracturing parameters and sand plugging information during the fracturing operation to form a fracturing sand plugging data table;

[0076] S102: According to the nature of the fracturing parameters, the plurality of fracturing parameters are divided into continuous parameters and discrete parameters;

[0077] S103: Analyze the relationship between all continuous parameters and sand blockage information to obtain sensitive parameters among the continuous parameters, wherein the sensitive parameters are used to reflect the sand blockage information;

[0078] S104: Analyze the relationship between all discrete parameters and sand blockage information to obtain the main control parameters among the discrete parameters, wherein the main control parameters are used to reflect the sand blockage information;

[0079] S105: Using the sensitive parameters and the main control parameters as samples, and the sand plugging information as sample labels, train the machine learning model to obtain a prediction model for predicting fracturing sand plugging.

[0080] Multiple fracturing parameters during fracturing operations include drilling parameters, geological parameters, and fracturing engineering parameters. Sand plugging information can include sand plugging and non-sand plugging. Drilling parameters include logging curves, drilling curves, and well logging curves. Geological parameters include formation parameters and lithological parameters. Fracturing engineering parameters include slickwater type, perforation gun type, number of perforations, perforation thickness, number of perforation clusters, perforation angle, diameter, and number of holes.

[0081] Generally speaking, drilling parameters are continuous parameters, while geological parameters and fracturing engineering parameters are discrete parameters. Among continuous parameters, there may be sensitive parameters, and among discrete parameters, there may be master control parameters. Whether they are sensitive parameters or master control parameters, they are used to reflect sand blockage information. It can be understood that the parameter values ​​of sensitive parameters and master control parameters will reflect whether sand blockage has occurred.

[0082] Sensitive parameters and master control parameters are used as samples, and sand blockage information, i.e. whether sand blockage occurs, is used as the sample label. Intelligent optimization algorithms or genetic algorithms are applied to train and optimize multiple machine learning models, reducing the uncertainty of artificial machine learning methods and parameter selection, and finally training a machine learning model for intelligent prediction of sand blockage in fracturing.

[0083] The method described in this embodiment does not require using all fracturing parameters as samples. Instead, it first classifies fracturing parameters based on their properties, dividing them into continuous and discrete parameters. Then, it analyzes and obtains the sensitive parameters within the continuous parameters and the main control parameters within the discrete parameters. Using the sensitive parameters and main control parameters as samples, it trains a machine learning model, ultimately obtaining a predictive model for predicting sand plugging in fracturing. Since both the sensitive parameters and the main control parameters reflect sand plugging information, the predictive model established by the method described in this embodiment has high accuracy and strong generalization ability.

[0084] In the embodiments described herein, reference is made to Figure 2 The analysis of the relationship between all continuous parameters and sand blockage information reveals that the sensitive parameters among the continuous parameters further include:

[0085] S201: Each continuous parameter in the fracturing process is gridded using a gridding method to form gridded parameters;

[0086] S202: Perform grid density calculation on the gridding parameters to obtain the superposition coefficient of the gridding parameters under different sand blockage information;

[0087] S203: When the overlap coefficient is less than the sensitivity parameter threshold, the continuous parameter is the sensitivity parameter.

[0088] The basic principle of the gridding algorithm is: dataset S = {S m1 S m2 S mn} is a dataset with m rows and n dimensions; for a subset X = {X1, X2, ..., Xn} of dataset S, ... i2 , ..., X in} is a dataset with i rows and n dimensions; for a subset Y of dataset S, Y = {Y} j1 Y j2 , ..., Y jn} is a data set with j rows and n dimensions, satisfying

[0089] The gridding method divides each dimension of an n-dimensional dataset S into k segments, thereby transforming the spatial quantity of the object into finite data units. The parameter k is the number of grid divisions. Dividing a certain feature dimension of the dataset S into k equal segments according to their numerical values ​​is a parameter for constructing a spatial grid. After the spatial grid is divided, it is used to count the number of data points within the grid to calculate the grid density.

[0090] The number of grid cells significantly impacts the effectiveness of clustering algorithms: when k is too large, underfitting occurs because the grid is too small to connect clusters effectively, resulting in sparse, isolated objective functions for each cluster that fail to adequately represent the distribution of data clusters. Conversely, when k is too small, overfitting occurs because the grid cells are too large to effectively represent the shape of data clusters, and the influence range of each cell is too wide, preventing the density distribution of data clusters from being effectively expressed by the grid, leading to excessive overlap of objective functions between different clusters. The choice of k should ensure minimal grid connectivity, primarily controlled by the data distribution density. Lower data density allows for larger k values. When the number of grid cells is set to k, a systematic error of grid length (100 / k) appears in each dimension of two m-dimensional data clusters, with the difference between the two clusters less than 1 / k. The optimal number of grid cells is primarily controlled by the data distribution density. Higher data density results in a smaller optimal number of grid cells and a smaller systematic error. Conversely, lower data density results in a larger optimal number of grid cells and a larger systematic error. The interval for choosing the grid parameter k is usually half of the maximum interval between data points in a certain dimension and half of the minimum interval. Half of the average interval is usually appropriate.

[0091] Reference Figure 3 Therefore, each continuous parameter in the fracturing process is meshed using a meshing method to form a meshed parameter. Each continuous parameter corresponds to a meshed parameter, and the meshed parameter represents all parameter values ​​of each continuous parameter in the fracturing process through the data points in the mesh.

[0092] Under different sand plugging information, the overlap coefficient of the meshing parameters is the ratio of the number of overlapping grid data points to the total number of grid data points under different sand plugging information. In this paper, different sand plugging information includes sand plugging and no sand plugging. Assuming the continuous parameters are drilling parameters, after meshing the drilling parameters to obtain the drilling meshed parameters, i.e., grid data points, the grid density is calculated. The density of set X is the number of grid data points corresponding to sand plugging during fracturing operation (i.e., Figure 3 The number of points in the middle circle can be represented as J(X), and the density of the set Y is the number of grid data points corresponding to the absence of sand plugging during the fracturing operation (i.e., Figure 3 The number of points in the rhombus can be represented as J(Y), and the intersection density of sets X and Y can be represented as J(X∩Y). Then, the overlap coefficient when sand blockage occurs is J(X∩Y) / J(X), and the overlap coefficient when sand blockage does not occur is J(X∩Y) / J(Y).

[0093] The smaller the overlap coefficient, the more sensitive the continuous parameter is to sand blockage information. When the overlap coefficient is less than the preset threshold of sensitive parameters, the continuous parameter is a sensitive parameter.

[0094] In the embodiments described herein, reference is made to Figure 4 The analysis of the relationship between all discrete parameters and sand blockage information, yielding the main control parameters among the discrete parameters, further includes:

[0095] S301: Calculate the event probability difference between each discrete parameter and different sand blockage information based on the event probability difference algorithm;

[0096] S302: When the event probability difference is greater than the master control parameter threshold, the discrete parameter is the master control parameter.

[0097] Specifically, the event probability difference between each discrete parameter and different sand blockage information can be calculated using the following formula:

[0098]

[0099] Where M is the event probability difference, S1 and S2 are the number of times the two different sand plugging information occurs during the fracturing operation, and V is the number of times each discrete parameter occurs during the fracturing operation.

[0100] The difference in event probability between each discrete parameter and different sand blockage information can also be calculated using the following formula:

[0101]

[0102] Where M is the event probability difference, S1 and S2 are the number of times the two different sand plugging information occurs during the fracturing operation, V is the number of times each discrete parameter occurs during the fracturing operation, and |·| is the absolute value.

[0103] S1 can be the total number of times sand plugging occurred during the fracturing operation, S2 can be the total number of times sand plugging did not occur during the fracturing operation, and V can be the number of times each discrete parameter occurred during the fracturing operation.

[0104] Reference Figure 5 For example, a discrete parameter might be defined as the current perforation gun type being A, where V represents the number of times the perforation gun type is A during fracturing operations. Figure 5 The diagram shows the proportions of sand plugging and normal (non-sand plugging) conditions during fracturing operations for Type A and Type B perforating guns. For Type A perforating guns, if S1 represents sand plugging and S2 represents normal conditions... It is 15.15. It is 84.82.

[0105] If the event probability difference calculated by any of the above formulas for a certain discrete parameter is greater than the pre-set threshold of the master control parameter, then the discrete parameter is the master control parameter.

[0106] After analyzing and obtaining the sensitive parameters and main control parameters, these parameters can be used as samples. These samples can be divided into training, validation, and test sets. The training set is used for model training. The parameters that minimize the prediction residuals on the validation set are used as the iterative optimization parameters. The algorithm that minimizes the prediction residuals on the test set is used as the iterative optimization algorithm. The final output is a prediction model with the lowest prediction error and highest prediction accuracy for fracturing operation conditions.

[0107] Based on the above-mentioned method for establishing a prediction model for fracturing sand plugging, referring to... Figure 6 This embodiment also provides a method for predicting fracturing sand plugging, including:

[0108] S401: Obtain sensitive parameters and key control parameters during the current fracturing operation;

[0109] S402: Input the sensitive parameters and the main control parameters into the above prediction model to predict the sand plugging information in the current fracturing process.

[0110] During fracturing operations on new wells, sensitive parameters and key control parameters can be acquired. These parameters are then input into the aforementioned prediction model to predict sand plugging information during the current fracturing process, i.e., whether sand plugging will occur. This invention effectively solves the problem of intelligent prediction of sand plugging in oilfield fracturing. This technology is of practical significance for deeply exploring sensitive parameters and key control factors of sand plugging, maximizing the accuracy of sand plugging prediction, and minimizing the risk of sand plugging in new wells. It also provides clear guidance for improving the design level of fracturing schemes and reducing production operation costs.

[0111] Based on the aforementioned method for establishing a predictive model for fracturing sand plugging, this embodiment also provides an apparatus for establishing such a model. The apparatus may include a system (including a distributed system), software (application), module, component, server, client, etc., using the method described in this embodiment, combined with necessary hardware implementation. Based on the same innovative concept, the apparatuses in one or more embodiments provided in this embodiment are as described in the following embodiments. Since the implementation schemes and methods for solving the problem are similar, the implementation of the specific apparatus in this embodiment can refer to the implementation of the aforementioned method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0112] Specifically, Figure 7 This is a schematic diagram of the module structure of an embodiment of a fracturing sand plugging prediction model building device provided in this article, with reference to... Figure 7As shown in the embodiment of this paper, a predictive model establishment device for fracturing sand plugging includes: an acquisition module 100, a division module 200, a first analysis module 300, a second analysis module 400, and a model establishment module 500.

[0113] The acquisition module 100 is used to acquire multiple fracturing parameters and sand plugging information during the fracturing operation, and form a fracturing sand plugging data table.

[0114] The partitioning module 200 is used to partition the plurality of fracturing parameters into continuous parameters and discrete parameters according to the nature of the fracturing parameters;

[0115] The first analysis module 300 is used to analyze the relationship between all continuous parameters and sand blockage information to obtain sensitive parameters among the continuous parameters, wherein the sensitive parameters are used to reflect the sand blockage information;

[0116] The second analysis module 400 is used to analyze the relationship between all discrete parameters and sand blockage information to obtain the main control parameters among the discrete parameters, wherein the main control parameters are used to reflect the sand blockage information.

[0117] The model building module 500 is used to train the machine learning model by using the sensitive parameters and the main control parameters as samples and the sand plugging information as sample labels, so as to obtain a prediction model for predicting sand plugging in fracturing.

[0118] Based on the aforementioned method for predicting fracturing sand plugging, this article provides a schematic diagram of the module structure of an embodiment of a fracturing sand plugging prediction device, referring to... Figure 8 As shown in the embodiment of this paper, a prediction device for fracturing sand plugging includes: a parameter acquisition module 600 and a prediction module 700.

[0119] The parameter acquisition module 600 is used to acquire sensitive parameters and main control parameters during the current fracturing operation.

[0120] The prediction module 700 is used to input the sensitive parameters and the main control parameters into the prediction model to predict the sand plugging information in the current fracturing process.

[0121] Reference Figure 9As shown, based on the aforementioned method for establishing a prediction model for fracturing sand plugging or a method for predicting fracturing sand plugging, one embodiment of this paper also provides a computer device 902, wherein the above-described method runs on the computer device 902. The computer device 902 may include one or more processors 904, such as one or more central processing units (CPUs) or graphics processing units (GPUs), each processing unit may implement one or more hardware threads. The computer device 902 may also include any memory 906 for storing any kind of information such as code, settings, data, etc. In one specific embodiment, a computer program is stored in the memory 906 and can run on the processor 904. When the computer program is run by the processor 904, it can execute instructions according to the above-described method.

[0122] Non-limiting, for example, memory 906 may include any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Furthermore, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of computer device 902. In one case, when processor 904 executes associated instructions stored in any memory or combination of memories, computer device 902 can perform any operation of the associated instructions. Computer device 902 also includes one or more drive mechanisms 908 for interacting with any memory, such as hard disk drive mechanisms, optical disk drive mechanisms, etc.

[0123] Computer device 902 may also include an input / output module 910 (I / O) for receiving various inputs (via input device 912) and providing various outputs (via output device 914). A specific output mechanism may include a presentation device 916 and an associated graphical user interface 918 (GUI). In other embodiments, the input / output module 910 (I / O), input device 912, and output device 914 may be omitted, and the device may function solely as a computer device within a network. Computer device 902 may also include one or more network interfaces 920 for exchanging data with other devices via one or more communication links 922. One or more communication buses 924 couple the components described above together.

[0124] Communication link 922 can be implemented in any way, such as via a local area network (LAN), a wide area network (WAN) (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 922 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0125] Corresponding to Figure 1 , Figure 2 , Figure 4 and Figure 6 In addition to the methods described above, this embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the above-described methods.

[0126] This embodiment also provides a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to perform the following: Figure 1 , Figure 2 , Figure 4 and Figure 6 The method shown.

[0127] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0128] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0129] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0130] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0131] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0132] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0133] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0134] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0135] Based on this understanding, the technical solutions presented herein, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this paper. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] This document uses specific embodiments to illustrate the principles and implementation methods of this document. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this document. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this document. Therefore, the content of this specification should not be construed as a limitation of this document.

Claims

1. A method for establishing a predictive model for fracturing sand plugging, characterized in that, include: Multiple fracturing parameters and sand plugging information are obtained during the fracturing operation to form a fracturing sand plugging data table; Based on the nature of the fracturing parameters, the multiple fracturing parameters are divided into continuous parameters and discrete parameters; For each of the continuous parameters, the continuous parameter is divided into k segments using a gridding method to form a corresponding gridded parameter; where k is determined based on the data distribution density of the continuous parameter. The meshing parameters are subjected to mesh density calculation to determine the overlap coefficient of the meshing parameters under different sand plugging information; wherein, the mesh data points corresponding to sand plugging during fracturing are defined as set X, and the mesh data points corresponding to sand plugging without sand plugging during fracturing are defined as set Y. The density of set X is represented by J(X), the density of set Y is represented by J(Y), the intersection density of set X and set Y is represented by J(X∩Y), the overlap coefficient when sand plugging occurs is J(X∩Y) / J(X), and the overlap coefficient when sand plugging does not occur is J(X∩Y) / J(Y); When the overlap coefficient is less than the sensitivity parameter threshold, the continuous parameter is determined as the sensitivity parameter; For each of the discrete parameters, the event probability difference between each discrete parameter and different sand blockage information is calculated using the following formula: M= ； Where M is the event probability difference, S1 and S2 are the occurrence times of two different sand plugging information during the fracturing operation, and V is the occurrence time of each discrete parameter during the fracturing operation. When the event probability difference is greater than the master control parameter threshold, the discrete parameter is the master control parameter; The sensitive parameters and the main control parameters are used as samples, the sand blockage information is used as sample labels, and the samples are divided into training set, validation set and test set; Multiple machine learning models are trained and optimized using intelligent optimization algorithms or genetic algorithms. The training set is used for model training, the minimum prediction residual of the validation set is used as the basis for parameter iterative optimization, and the minimum prediction residual of the test set is used as the basis for algorithm iterative optimization. The fracturing sand plugging prediction model with the lowest prediction error under fracturing construction conditions is determined.

2. The method for establishing a prediction model for fracturing sand plugging according to claim 1, characterized in that, The fracturing parameters include: drilling parameters, geological parameters, and fracturing engineering parameters.

3. A method for predicting fracturing sand plugging, characterized in that, include: Obtain the sensitive and key parameters during the current fracturing operation; The sensitive parameters and the main control parameters are input into the prediction model according to any one of claims 1-2 to predict the sand plugging information in the current fracturing process.

4. A device for establishing a predictive model for fracturing sand plugging, characterized in that, The device includes: The acquisition module is used to acquire multiple fracturing parameters and sand plugging information during the fracturing operation, and form a fracturing sand plugging data table. A partitioning module is used to divide the multiple fracturing parameters into continuous parameters and discrete parameters according to their properties; The first analysis module is used to divide each continuous parameter into k segments using a gridding method to form a corresponding gridded parameter; where k is determined based on the data distribution density of the continuous parameter. The meshing parameters are subjected to mesh density calculation to determine the overlap coefficient of the meshing parameters under different sand plugging information; wherein, the mesh data points corresponding to sand plugging during fracturing are defined as set X, and the mesh data points corresponding to sand plugging without sand plugging during fracturing are defined as set Y. The density of set X is represented by J(X), the density of set Y is represented by J(Y), the intersection density of set X and set Y is represented by J(X∩Y), the overlap coefficient when sand plugging occurs is J(X∩Y) / J(X), and the overlap coefficient when sand plugging does not occur is J(X∩Y) / J(Y); When the overlap coefficient is less than the sensitivity parameter threshold, the continuous parameter is determined as the sensitivity parameter; For each of the discrete parameters, the event probability difference between each discrete parameter and different sand blockage information is calculated using the following formula: M= ； Where M is the event probability difference, S1 and S2 are the occurrence times of two different sand plugging information during the fracturing operation, and V is the occurrence time of each discrete parameter during the fracturing operation. When the event probability difference is greater than the master control parameter threshold, the discrete parameter is the master control parameter; The model building module is used to take the sensitive parameters and the main control parameters as samples, the sand blockage information as sample labels, and divide the samples into training set, validation set and test set; Multiple machine learning models are trained and optimized using intelligent optimization algorithms or genetic algorithms. The training set is used for model training, the minimum prediction residual of the validation set is used as the basis for parameter iterative optimization, and the minimum prediction residual of the test set is used as the basis for algorithm iterative optimization. The fracturing sand plugging prediction model with the lowest prediction error under fracturing construction conditions is determined.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the computer program is run by the processor, it executes the instructions of the method according to any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor of the computer device, it executes the instructions of the method according to any one of claims 1-3.

Images