A method and device for intelligent optimization design of cluster parameters of horizontal well staged fracturing

Abstract

The present invention discloses a method and device for intelligent optimization design of cluster parameters for staged fracturing sections in horizontal wells, including: dividing geological sweet spots based on well logging data, and dividing engineering sweet spots based on drilling and logging data; clustering the geological sweet spots to obtain geological sweet spot clustering results, and clustering the geological sweet spots and engineering sweet spots to obtain double sweet spot clustering results; designing the fracturing section based on the geological sweet spot clustering results, and designing the fracturing cluster positions within the fracturing section based on the double sweet spot clustering results, wherein the fracturing cluster positions include the geomechanical strength peak cluster positions; determining the perforation friction required for cluster positions other than the geomechanical strength peak cluster position, and optimizing the perforation parameters until the fracturing pressure at the other cluster positions reaches the fracturing pressure of the geomechanical strength peak cluster position. The present invention can accurately and intelligently design fracturing section cluster parameters, while also finely optimizing the design of fracturing cluster perforation parameters, thereby achieving the development of high-quality reservoirs and balanced fracturing and expansion of fractures.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir stimulation and transformation, and in particular to a method and device for intelligent optimization design of staged fracturing cluster parameters of a horizontal well. Background Art

[0002] The design of horizontal well fracturing cluster locations is a key factor influencing the effectiveness of unconventional reservoir stimulation. Its core objective is to achieve balanced fracture initiation and the effective development of high-quality reservoirs. Unconventional reservoirs generally face challenges such as strong heterogeneity, significant differences in initiation pressures, and difficulty in achieving balanced initiation across fracture clusters. Accurately demarcating geological and engineering sweet spots is a crucial prerequisite for fracturing cluster location design. Furthermore, carefully designing perforation parameters within the fracturing cluster, taking into account differences in initiation pressures and proppant migration, is crucial for guiding unconventional reservoir development.

[0003] Existing technologies still use geometric or single-design approaches for fracturing stage clusters, failing to fully account for variations in fracture initiation pressures between clusters. This makes it impossible to achieve precise, intelligent design of fracturing stage clusters. Furthermore, the design of perforation parameters within a fracturing stage cluster directly impacts fracturing effectiveness, but existing technologies typically fail to consider characteristics such as perforation friction, making it impossible to achieve balanced fracture initiation and propagation.

[0004] To address the above issues, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of this specification provide a method and device for intelligent optimization design of parameters of a horizontal well staged fracturing cluster to address the problem that the existing technology is unable to accurately and intelligently design pressure clusters, nor can it finely optimize the perforation parameters within the fracturing cluster, thereby failing to achieve balanced fracture initiation and expansion.

[0006] In a first aspect, the embodiments of this specification provide a method for intelligent optimization design of parameters of a horizontal well staged fracturing cluster, including:

[0007] Divide geological sweet spots based on well logging data, and divide engineering sweet spots based on drilling and logging data;

[0008] Cluster the geological sweet spots to obtain the geological sweet spot clustering results, and cluster the geological sweet spots and engineering sweet spots to obtain the double sweet spot clustering results;

[0009] Designing a fracturing section based on the geological sweet spot clustering results, and designing a fracturing cluster location within the fracturing section based on the double sweet spot clustering results, wherein the fracturing cluster location includes a geomechanical strength peak cluster location;

[0010] The perforation friction required for cluster positions other than the geomechanical strength peak cluster position is determined, and the perforation parameters are optimized until the fracturing pressures at other cluster positions reach the fracturing pressure of the geomechanical strength peak cluster.

[0011] In some embodiments, dividing geological sweet spots according to well logging data includes:

[0012] Calculate reservoir physical property parameters based on well logging data, process the reservoir physical property parameters, and obtain processed reservoir physical property parameters;

[0013] Clustering the processed reservoir physical property parameters to obtain reservoir physical property parameter clustering results;

[0014] Calculate the geological sweet spot index of each category in the clustering results of reservoir physical property parameters;

[0015] According to the geological dessert index of each category, each category is divided into a geological dessert of corresponding level.

[0016] In some embodiments, the reservoir physical property parameters include at least one of the following: shale content, porosity, oil saturation, and permeability; and the calculation of the geological sweet spot index of each category in the clustering results of the reservoir physical property parameters includes:

[0017] The geological sweet spot index of each category is calculated using the following formula:

[0018] f(V sh )=(V sh25％ +V sh75％ )

[0019]

[0020] Among them, V sh is the mud content; So is the oil saturation; K is the permeability; Φ is the porosity; V sh25％ V is the 25% percentile value of the mud content parameter in each category; sh75％ So is the 75% percentile value of the mud content parameter in each category; 25％ So is the 25% percentile value of the oil saturation parameter in each category; 75％ is the 75% percentile value of the oil saturation parameter in each category; K 25％ is the 25% quantile value of the permeability parameter in each category; K 75％ is the 75% quantile value of the permeability parameter in each category; Φ 25％ is the 25% quantile value of the porosity parameter in each category; Φ 75％ is the 75% quantile value of the porosity parameter in each category; f(V sh) is used to calculate the sum of the 25% and 75% percentile values ​​of the mud content parameter in each category; f(Φ,So,K) is used to calculate the mean of the sum of the 25% and 75% percentile values ​​of the porosity, oil saturation, and permeability parameters in each category; I Geo Represents the geological sweet spot index.

[0021] In some embodiments, dividing the engineering sweet spot according to the drilling and logging data and the well logging data includes:

[0022] Calculate the bottom hole mechanical specific energy based on drilling and logging data, and calculate the minimum horizontal ground stress based on logging data;

[0023] Determine the geomechanical strength based on the bottom hole mechanical specific energy and minimum horizontal ground stress;

[0024] Engineering sweet spots are divided according to geomechanical strength.

[0025] In some embodiments, the divided geological sweet spots have geological sweet spot classification labels along the well depth; accordingly, clustering the geological sweet spots to obtain the geological sweet spot clustering results includes:

[0026] The K-means clustering algorithm is used to cluster the geological sweet spot classification labels along the well depth to obtain the geological sweet spot clustering results;

[0027] Clustering the geological sweet spots and engineering sweet spots to obtain a double sweet spot clustering result includes:

[0028] The semi-supervised K-means clustering algorithm was used to cluster the geological sweet spots and engineering sweet spots, and the double sweet spot clustering results were obtained.

[0029] In some embodiments, clustering the geological sweet spot classification labels along the well depth using the K-means clustering algorithm to obtain the geological sweet spot clustering results includes:

[0030] constructing a data set based on hierarchical labels of geological sweet spots along the well depth, and selecting a preset number of sample points from the data set as initial cluster centers;

[0031] Divide each sample point in the data set into a corresponding cluster according to the Euclidean distance from the initial cluster center;

[0032] Calculate the average value of all sample points in the corresponding cluster as the new cluster center;

[0033] Repeat the process of dividing clusters and calculating the average values ​​of all sample points in the divided clusters until the sample center points of all clusters no longer change or the number of iterations reaches the preset iteration threshold, and output the geological sweet spot clustering results.

[0034] In some embodiments, designing a fracturing stage based on the geological sweet spot clustering results includes:

[0035] Traversing the clustered geological sweet spots of all well sections, identifying non-reservoir well sections, selecting non-reservoir well sections with a continuous length greater than a preset length as the segment spacing, and dividing the large fracturing sections according to the segment spacing;

[0036] Starting from the wellhead, the large fracture section is divided into small fracture sections, and the proportion of the same geological sweet spot cluster category in each small fracture section is greater than 50% of the total geological sweet spot cluster category in the small fracture section;

[0037] When there is a fracturing section with a length greater than 100 m in the small fracturing section, the fracturing section with a length greater than 100 m is divided into two sections according to the section length and the geological sweet spot category.

[0038] In some embodiments, designing the location of the fracturing cluster within the fracturing stage based on the double sweet spot clustering result includes:

[0039] Based on the double sweet spot clustering results, a fracturing cluster is arranged on the target well section, where the target well section represents the category with the best geological sweet spot and engineering sweet spot characteristics;

[0040] When the target well section accounts for a small proportion, a fracturing cluster is arranged on the first target well section or the second target well section. The first target well section represents a category with suboptimal geological sweet spot and engineering sweet spot characteristics, and the second target well section represents a category with average geological sweet spot and engineering sweet spot characteristics.

[0041] In a second aspect, the embodiments of this specification further provide a device for intelligent optimization design of parameters of a cluster of staged fracturing segments in a horizontal well, comprising:

[0042] Sweet spot division module, used to divide geological sweet spots according to well logging data, and to divide engineering sweet spots according to drilling and logging data;

[0043] Sweet spot clustering module, used to cluster geological sweet spots to obtain geological sweet spot clustering results, and cluster geological sweet spots and engineering sweet spots to obtain double sweet spot clustering results;

[0044] A fracturing segment cluster design module, configured to design fracturing segments based on the geological sweet spot clustering results and to design fracturing cluster locations within a fracturing segment based on the double sweet spot clustering results, wherein the fracturing cluster locations include geomechanical strength peak cluster locations;

[0045] The perforation parameter optimization module is used to determine the perforation friction required at other cluster positions except the geomechanical strength peak cluster position, and optimize the perforation parameters until the fracturing pressure at other cluster positions reaches the fracturing pressure of the geomechanical strength peak cluster.

[0046] In a third aspect, an embodiment of this specification further provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the above-mentioned method for intelligent optimization design of parameters of a cluster of staged fracturing segments in a horizontal well.

[0047] The embodiments of this specification provide a method and device for intelligent optimization design of cluster parameters of segmented fracturing sections of horizontal wells. First, geological sweet spots are divided according to well logging data, and engineering sweet spots are divided according to drilling and logging data. Secondly, the geological sweet spots are clustered to obtain geological sweet spot clustering results, and the geological sweet spots and engineering sweet spots are clustered to obtain double sweet spot clustering results. Then, the fracturing section is designed based on the geological sweet spot clustering results, and the fracturing cluster positions within the fracturing section are designed based on the double sweet spot clustering results, and the fracturing cluster positions include the geomechanical strength peak cluster positions. Finally, the borehole friction required for other cluster positions except the geomechanical strength peak cluster position is determined, and the perforation parameters are optimized until the fracturing pressure of other cluster positions reaches the fracturing pressure of the geomechanical strength peak cluster. In the embodiments of this specification, accurate, efficient, and low-cost division of geological sweet spots and engineering sweet spots can be achieved based on field logging data and drilling and logging data. On this basis, the fracturing section cluster can be designed accurately and efficiently. By clustering geological sweet spots, clustering geological and engineering sweet spots, designing fracturing stages based on the geological sweet spot clustering results, and designing fracturing cluster locations within a fracturing stage based on the dual sweet spot clustering results, intelligent fracturing stage cluster design can be achieved. Furthermore, by considering characteristics such as perforation friction, perforation parameters within the fracturing stage cluster can be refined and optimized, achieving balanced fracture initiation and propagation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0049] Figure 1 This is a flow chart of a method for intelligent optimization design of parameters of a cluster of staged fracturing segments for a horizontal well provided in an embodiment of this specification;

[0050] Figure 2 Schematic diagram of the double sweet spot clustering result provided in the embodiments of this specification;

[0051] Figure 3 Schematic diagram of the horizontal well hydraulic fracturing stage cluster design process provided in the embodiments of this specification;

[0052] Figure 4This is a schematic diagram of the structure of a device for intelligent optimization design of parameters of staged fracturing clusters for horizontal wells provided in an embodiment of this specification;

[0053] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0054] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0055] Currently, fracturing designs generally rely on geometric or single-design schemes, and differentiated and personalized segment cluster design has yet to be achieved. In existing research, many studies have constructed a coupled array of engineering sweet spots and geological sweet spots based on the physical meaning of reservoir properties. This array serves as the basis for reservoir classification and evaluation, and the fracturing segment clusters are then divided based on this array. Typically, the number of perforation clusters (or fracturing clusters) is increased during periods with favorable geological and engineering sweet spots, while reduced during unfavorable periods. However, this design approach fails to effectively address the issue of balanced fracture initiation. On the one hand, existing classification and evaluation criteria lack sufficient adaptability. On the other hand, while geological and engineering sweet spots are considered to some extent, the perforation cluster positioning at each stage still uses a geometric or single-design approach, failing to fully account for the variability in fracture initiation pressures between clusters. Furthermore, the design of perforation parameters (e.g., perforation hole count) directly influences fracturing performance, but existing designs often fail to consider perforation friction and proppant migration, making it impossible to achieve balanced fracture initiation and propagation.

[0056] In order to solve the above problems, the embodiments of this specification provide a method and device for intelligent optimization design of cluster parameters of segmented fracturing sections of horizontal wells. First, geological sweet spots are divided according to well logging data, and engineering sweet spots are divided according to drilling and logging data. Secondly, the geological sweet spots are clustered to obtain geological sweet spot clustering results, and the geological sweet spots and engineering sweet spots are clustered to obtain double sweet spot clustering results. Then, the fracturing section is designed based on the geological sweet spot clustering results, and the fracturing cluster positions within the fracturing section are designed based on the double sweet spot clustering results. The fracturing cluster positions include the geomechanical strength peak cluster positions. Finally, the borehole friction required for other cluster positions except the geomechanical strength peak cluster position is determined, and the perforation parameters are optimized until the fracturing pressures of other cluster positions reach the fracturing pressure of the geomechanical strength peak cluster.

[0057] This approach enables accurate, efficient, and cost-effective delineation of geological and engineering sweet spots based on field logging and drilling data. This allows for precise and efficient design of fracturing clusters. By clustering geological sweet spots, clustering both geological and engineering sweet spots, designing fracturing stages based on the clustering of geological sweet spots, and designing the location of fracturing clusters within a fracturing stage based on the clustering of dual sweet spots, intelligent fracturing cluster design is achieved. Furthermore, by taking into account characteristics such as perforation friction, perforation parameters within a fracturing cluster can be refined and optimized, ensuring closer alignment of the initiation pressures across clusters within the stage, thereby achieving balanced fracture initiation and propagation.

[0058] It should be noted that the terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, for the purposes of describing the embodiments of this application.

[0059] It is understood that the above methods provided in the embodiments of this specification can be applied to electronic devices, which can refer to electronic devices with data computing, processing, and storage capabilities. The electronic device can be a terminal such as a PC (Personal Computer), a tablet computer, a smartphone, a wearable device, an intelligent robot, etc.; it can also be a server. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0060] The following will introduce an intelligent optimization design method for stage cluster parameters of horizontal well staged fracturing provided by the embodiments of this specification in conjunction with the accompanying drawings.

[0061] Figure 1 It is a flow chart of a method for intelligent optimization design of parameters of clusters of staged fracturing segments of horizontal wells provided in an embodiment of this specification. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, more or fewer operation steps or module units may be included in the method or device based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure described is applied to an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiment or drawings (for example, in an environment of parallel processors or multi-threaded processing, or even in an implementation environment of distributed processing and server clusters). For specific implementation, please refer to Figure 1 As shown, the method may include the following contents.

[0062] S101: Divide geological sweet spots according to well logging data, and divide engineering sweet spots according to drilling and logging data and well logging data.

[0063] In some embodiments, the logging data may include natural gamma, acoustic wave, density, neutron, resistivity and other data, and the drilling logging data may include drilling pressure, rotation speed, drilling speed and other data, which are not specifically limited in this specification.

[0064] Based on field logging data and drilling and logging data, accurate, efficient and low-cost division of geological sweet spots and engineering sweet spots can be achieved, providing a good foundation for the subsequent differentiated, personalized and intelligent design of fracturing stage clusters.

[0065] In some embodiments, the above-mentioned S101 of dividing geological sweet spots according to well logging data may include:

[0066] Calculate reservoir physical property parameters based on well logging data, process the reservoir physical property parameters, and obtain processed reservoir physical property parameters;

[0067] Clustering the processed reservoir physical property parameters to obtain reservoir physical property parameter clustering results;

[0068] Calculate the geological sweet spot index of each category in the clustering results of reservoir physical property parameters;

[0069] According to the geological dessert index of each category, each category is divided into a geological dessert of corresponding level.

[0070] In some embodiments, the reservoir physical property parameters may include at least one of the following: shale content, porosity, oil saturation, and permeability. Calculating reservoir physical property parameters based on well logging data may include calculating shale content based on natural gamma ray, calculating porosity based on acoustic waves, density, and neutrons, calculating oil saturation based on resistivity, and determining permeability based on well logging curves. Specific calculation formulas can be found in existing technologies and are not detailed herein.

[0071] The aforementioned reservoir property parameter processing can include noise reduction and smoothing, and standardization of the smoothed reservoir property parameters. This noise reduction and smoothing process can mitigate significant errors in the evaluation of certain well sections caused by noise. Standardization can eliminate the impact of different parameter dimensions on the data while maintaining the data distribution characteristics. This provides a good dataset for subsequent unsupervised clustering models.

[0072] Among them, the wavelet variation can be sampled to perform noise reduction and smoothing on the reservoir physical property parameters. The specific process is as follows:

[0073] The curve of reservoir physical parameters is obtained by changing with the well depth. The data sequence arranged in spatial order can be regarded as a time series, and the time axis is the well depth at intervals of 0.125. The wavelet change denoising process includes function decomposition and wavelet reconstruction. Two or more wavelet basis functions are used to approximate the original function. x(t) is a square integrable signal, and its wavelet change is the signal and the wavelet function WT. x The inner product of (α, τ):

[0074]

[0075] Among them, WT x (α, τ) is the wavelet function; α is the scaling factor; τ is the translation factor; ψ * is the conjugate of ψ.

[0076] Wavelet-transformed function decomposition can perform multi-resolution decomposition of the original signal at different scales. The resulting signal contains all frequency bands of the original function, and each frequency band does not overlap, including both useful and noise signals. Since noise and useful signals have different time-frequency characteristics, selecting a reasonable threshold can effectively remove noise signals. This involves three basic steps:

[0077] 1) Optimize the wavelet basis and decomposition level, and calculate the wavelet decomposition coefficients at each level;

[0078] 2) Select the threshold of each decomposition level to set the frequency band where the noise is located to zero or extract the useful signal;

[0079] 3) Perform wavelet reconstruction on each layer to obtain the denoised signal.

[0080] The specific process of standardizing the reservoir physical property parameters after noise reduction and smoothing is as follows:

[0081] The following formula is used for normalization:

[0082]

[0083] Where z is the standardized data, x is the original data, μ is the mean of the original data, and σ is the standard deviation of the original data. Using the standardization method, each reservoir property parameter can be converted into a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0084] In some implementations, clustering the processed reservoir physical property parameters to obtain reservoir physical property parameter clustering results may include:

[0085] The processed reservoir physical property parameters are clustered using the probability-based Gaussian mixture model (GMM) to obtain the reservoir physical property parameter clustering results.

[0086] Specifically, the Gaussian mixture model (GMM) algorithm based on probability can be used to calculate the n 4-dimensional reservoir physical parameters D = {x ij |i=1,...,n;j=1,...4} for cluster analysis, where x ij represents the jth dimension of the reservoir property parameters for the i-th data point. These dimensions can include shale content, porosity, oil saturation, and permeability. By clustering these parameters, well sections with similar physical properties can be grouped into the same category, thereby identifying potential geological sweet spots within the well section. Ultimately, the reservoir property parameters for the horizontal well section were clustered into four categories.

[0087] The probability-based Gaussian mixture model (GMM) algorithm can model the probability distribution of data and identify subgroups of data by fitting N Gaussian distributions. The main process of the GMM clustering algorithm is as follows:

[0088] 1) Parameter setting: Select the number of components of the mixed distribution n_components(N), that is, the preset number of Gaussian distributions, each component represents the probability distribution of a cluster.

[0089] 2) Select the initial point: Initialize the Gaussian mixture model according to the selected number of components, including the mean, covariance matrix and mixing weight of each Gaussian distribution.

[0090] 3) Expectation-Maximization (EM) algorithm: Iterates the following steps until convergence: E-step: Calculates the probability (responsibility) of each data point belonging to each Gaussian component, based on the current model parameters. M-step: Based on the responsibility calculated in the E-step, updates the mean, covariance matrix, and mixing weights of each Gaussian distribution to maximize the log-likelihood function.

[0091] 4) Convergence judgment: When the change of model parameters is less than the set threshold or reaches the maximum number of iterations, the iteration is stopped.

[0092] 5) Output: After the algorithm is completed, the cluster label of each data point and the parameters of each Gaussian distribution (mean, covariance matrix and weight) are output.

[0093] Specifically, the Gaussian mixture model can be initialized; the probability (responsibility) of the Gaussian mixture model is calculated based on the processed reservoir physical property parameters; the Gaussian mixture model is updated based on the probability to determine whether a preset iteration number threshold (i.e., the maximum number of iterations) is reached. If so, the reservoir physical property parameter clustering result is output based on the currently updated Gaussian mixture model.

[0094] By clustering the processed reservoir physical property parameters, geological sweet spots can be accurately and effectively divided based on unsupervised classification.

[0095] In some embodiments, the above calculation of the geological sweet spot index of each category in the reservoir physical property parameter clustering result may include:

[0096] The geological sweet spot index of each category is calculated using the following formula:

[0097] f(V sh )=(V sh25％ +V sh75％ )

[0098]

[0099] Among them, V sh is the mud content; So is the oil saturation; K is the permeability; Φ is the porosity; V sh25％ V is the 25% percentile value of the mud content parameter in each category; sh75％ So is the 75% percentile value of the mud content parameter in each category; 25％ So is the 25% percentile value of the oil saturation parameter in each category; 75％ is the 75% percentile value of the oil saturation parameter in each category; K 25％ is the 25% quantile value of the permeability parameter in each category; K 75％ is the 75% quantile value of the permeability parameter in each category; Φ 25％ is the 25% quantile value of the porosity parameter in each category; Φ 75％ is the 75% quantile value of the porosity parameter in each category; f(V sh ) is used to calculate the sum of the 25% and 75% percentile values ​​of the mud content parameter in each category; f(Φ,So,K) is used to calculate the mean of the sum of the 25% and 75% percentile values ​​of the porosity, oil saturation, and permeability parameters in each category; I Geo Represents the geological sweet spot index.

[0100] Specifically, after the reservoir physical property parameters of the horizontal well section are clustered, the f(V sh ) and f(Φ,So,K) function, it can be obtained from the standard that when f(V sh ) values ​​and larger f(Φ,So,K) values, i.e., larger geological sweet spot indexes, indicate higher-quality geological sweet spots. To mitigate the influence of maximum and minimum values, the 25% to 75% percentile values ​​of each reservoir property parameter within each category were used for analysis.

[0101] Specifically, the geological sweet spot index for each category in the reservoir physical property clustering results can be calculated, and then the geological sweet spot indexes of each category can be compared and sorted in descending order. The category corresponding to the highest ranked geological sweet spot index (e.g., ranked first) can be considered the best geological sweet spot and classified as Category I, where the highest ranked geological sweet spot index is the largest. The category corresponding to the second-ranked geological sweet spot index is considered an excellent geological sweet spot and classified as Category II. The category corresponding to the third-ranked geological sweet spot index is considered a good geological sweet spot and classified as Category III. The category corresponding to the fourth-ranked geological sweet spot index is considered a poor geological sweet spot and classified as Category IV. {Category I, Category II, Category III, Category IV} can be referred to as the geological sweet spot classification labels along the well depth, which are important indicators for subsequent fracturing stage division.

[0102] In some embodiments, the above S101 divides the engineering sweet spots according to the drilling and logging data and the well logging data. In specific implementation, it may include:

[0103] Calculate the bottom hole mechanical specific energy based on drilling and logging data, and calculate the minimum horizontal ground stress based on logging data;

[0104] Determine the geomechanical strength based on the bottom hole mechanical specific energy and minimum horizontal ground stress;

[0105] Engineering sweet spots are divided according to geomechanical strength.

[0106] Specifically, the mechanical specific energy can be calculated based on data such as drilling pressure, rotation speed, and drilling speed. The Poisson's ratio and Young's modulus can be calculated based on the longitudinal and shear wave velocities, and the ground stress can be estimated in combination with the density data. The specific calculation formula can be referred to the existing technology, and this manual will not elaborate on it.

[0107] The sum of the bottom hole mechanical specific energy and the minimum horizontal ground stress can be calculated to determine the geomechanical strength. The calculation formula is as follows:

[0108] P Geo =MSE b +S hmin

[0109] Among them, P Geo is the geomechanical strength, MPa; MSE b is the bottom hole mechanical specific energy, MPa; S hmin is the minimum horizontal ground stress, MPa.

[0110] The fracture initiation pressure can be determined based on the geomechanical strength according to the following formula:

[0111] P' W ≥P Geo +ΔP pf =(MSE b +S hmin )max +ΔP pf

[0112] Among them, P′ W is the cracking pressure, MPa; P Geo is the geomechanical strength, MPa; ΔP pf is the hole friction, MPa; MSE b is the bottom hole mechanical specific energy, MPa; S hmin is the minimum horizontal ground stress, MPa.

[0113] Engineering sweet spots can be identified based on geomechanical strength and fracture initiation pressure. For example, areas with high rock strength and low fracture initiation pressure are designated as engineering sweet spots, as these areas are more amenable to fracturing and maintain good stability. Geomechanical strength, fracture initiation conditions, and various data can be integrated through laboratory testing, field testing, numerical simulation, and data analysis, ultimately combined with field verification to identify engineering sweet spots and determine the optimal development area.

[0114] The aforementioned bottomhole mechanical specific energy can be used as a proxy for the mechanical strength of reservoir rock and effectively assess its crack resistance under varying pressures. The aforementioned minimum horizontal in-situ stress plays a key role in the initiation and propagation of fractures, influencing rock deformation and failure modes. By comprehensively considering these two factors, a more comprehensive assessment of the reservoir's geomechanical characteristics can be achieved, providing a scientific basis for engineering design and ultimately determining the engineering sweet spot parameters.

[0115] S102: Clustering the geological sweet spots to obtain a geological sweet spot clustering result, and clustering the geological sweet spots and engineering sweet spots to obtain a double sweet spot clustering result.

[0116] S103: Designing a fracturing section based on the geological sweet spot clustering result, and designing a fracturing cluster position within the fracturing section based on the double sweet spot clustering result, wherein the fracturing cluster position includes a geomechanical strength peak cluster position.

[0117] In some embodiments, after the geological sweet spots are divided, unsupervised clustering can be performed on the geological sweet spots, and the fracturing segments can be designed based on the clustering results of the geological sweet spots, thereby realizing intelligent design of the fracturing segments. In addition, semi-supervised clustering can be performed on the geological sweet spots and engineering sweet spots, and the location of the fracturing cluster within the fracturing segment can be designed based on the clustering results of the double sweet spots, thereby realizing intelligent design of the fracturing cluster. Among them, the geological sweet spot clustering can classify well sections with similar geological sweet spots into the same category, and the geological sweet spot clustering results can serve as an important indicator for fracturing segment division or design. The double sweet spot clustering of geological sweet spots and engineering sweet spots can classify well sections with similar geomechanical strength within the segment and various types of geological sweet spots into different cluster categories, and the double sweet spot clustering results can serve as an important indicator for optimizing the location of the fracturing cluster.

[0118] In some embodiments, the divided geological sweet spots have geological sweet spot classification labels along the well depth; accordingly, clustering the geological sweet spots in S102 to obtain the geological sweet spot clustering results may include:

[0119] The K-means clustering algorithm is used to cluster the geological sweet spot classification labels along the well depth to obtain the geological sweet spot clustering results;

[0120] Clustering the geological sweet spots and engineering sweet spots in S102 to obtain a double sweet spot clustering result may include:

[0121] The semi-supervised K-means clustering algorithm was used to cluster the geological sweet spots and engineering sweet spots, and the double sweet spot clustering results were obtained.

[0122] Specifically, the K-means clustering algorithm is an unsupervised clustering algorithm that uses only unlabeled data for clustering. The semi-supervised K-means clustering algorithm (SS-Kmeans) is a semi-supervised clustering algorithm that combines a small amount of labeled data with a large amount of unlabeled data for clustering. Specifically, the geological sweet spot classification label and well depth can be used as input parameters, and the K-means clustering algorithm can be used to divide it into K clusters. The similarity between sample points is measured based on Euclidean geometric distance, which makes the similarity between samples in the clusters higher. Finally, the set D is divided into K clusters, and the optimal number of clusters K for the clustering model is determined based on the "elbow rule." A semi-supervised K-means clustering algorithm can be used to introduce geological and engineering double sweet spot labels to improve the clustering effect of unlabeled data. The geomechanical strength of each segment is divided into five sets using probability density distribution. The dividing point of each set is the engineering sweet spot cluster label. The geological sweet spot cluster label and the engineering sweet spot cluster label are combined to determine the optimal cluster number K. Other unlabeled data sets are integrated with the cluster labels, and each sample point in the segment is divided into clusters based on Euclidean geometric distance.

[0123] In some embodiments, the K-means clustering algorithm is used to cluster the geological sweet spot classification labels along the well depth to obtain the geological sweet spot clustering results. In specific implementation, the following steps may be included:

[0124] constructing a data set based on hierarchical labels of geological sweet spots along the well depth, and selecting a preset number of sample points from the data set as initial cluster centers;

[0125] Divide each sample point in the data set into a corresponding cluster according to the Euclidean distance from the initial cluster center;

[0126] Calculate the average value of all sample points in the corresponding cluster as the new cluster center;

[0127] Repeat the process of dividing clusters and calculating the average values ​​of all sample points in the divided clusters until the sample center points of all clusters no longer change or the number of iterations reaches the preset iteration threshold, and output the geological sweet spot clustering results.

[0128] Specifically, clustering the geological sweet spot classification labels along the well depth using the K-means clustering algorithm may include the following steps:

[0129] Step 1: A data set D can be constructed based on the hierarchical labels of geological sweet spots along the well depth. A preset number of sample points (e.g., 9 sample points) are randomly selected from the data set D as the initial cluster centers. The constructed data set D is as follows:

[0130]

[0131] Where D is the data set; Depth1, Depth2, Depth n is the corresponding well depth; Label Geo1 、Label Geo2 、Label Geon Label the corresponding geological dessert.

[0132] Step 2: Calculate the Euclidean distance between each sample point in the data set except the initial cluster center and the initial cluster center. Based on the Euclidean distance, divide each sample point into the minimum distance cluster to achieve the first clustering.

[0133] Step 3: Calculate the average value of all sample points in each cluster as the new cluster center.

[0134] Step 4: Repeat steps 2 and 3 until the center points of all clusters no longer change or the number of iterations reaches the preset iteration threshold (i.e., the maximum number of iterations is reached), clustering is completed, and the geological sweet spot clustering results are output.

[0135] The data set D can be divided into K clusters. The objects within the clusters are similar, and the greater the difference between clusters, the better. The sum of squared errors (SSE) is used as the criterion function:

[0136]

[0137] Where SSE(μ) is the sum of squared errors; n j is the number of samples in the jth cluster; K is the number of clusters; x i is the sample point; μ j is the jth cluster center.

[0138] The optimal number of clusters K for a clustering model can be determined based on the "elbow rule": when the selected K value is less than the optimal K value, the SSE value decreases significantly as the K value increases. When the selected K value is greater than the optimal K value, the SSE value no longer changes significantly, indicating that the optimal K value is at this inflection point. For example, if the optimal number of clusters K for a clustering model can be determined to be 9 based on the "elbow rule," then K can be restricted to [9, +∞].

[0139] In some embodiments, the semi-supervised K-means clustering algorithm is used to cluster the geological sweet spot and the engineering sweet spot to obtain a double sweet spot clustering result. Before the specific implementation, the following steps may be included:

[0140] Use the probability density distribution function to calculate the quantiles of the engineering sweet spot value to form the engineering sweet spot cluster label;

[0141] According to the geological dessert classification labels, geological dessert cluster labels are formed;

[0142] The geological sweet spot cluster labels and engineering sweet spot cluster labels are arranged and combined to determine the optimal number of clusters.

[0143] Accordingly, the semi-supervised K-means clustering algorithm is used to cluster the geological sweet spots and engineering sweet spots to obtain the double sweet spot clustering results. The specific implementation may include:

[0144] Initialize cluster centers based on geological sweet spot cluster labels and engineering sweet spot cluster labels;

[0145] Merge the geological sweet spot cluster labels and engineering sweet spot cluster labels with the unlabeled data into the overall dataset;

[0146] Calculate the distance between each sample point in the entire data set and the cluster center, and assign each sample point to the target cluster center whose distance is less than the distance threshold (that is, assign it to the nearest cluster center) based on the distance;

[0147] Update the cluster center to the mean of all sample points in the current cluster;

[0148] Repeat the steps or processes of assigning and updating until the cluster centers converge or the number of iterations reaches a preset iteration threshold (i.e., the maximum number of iterations is reached), and output the double sweet spot clustering result.

[0149] Specifically, the geological sweet spot classification labels {Class I, Class II, Class III, Class IV} can be labeled {1, 2, 3, 4} as geological sweet spot cluster labels, representing the four levels of geomechanical strength. The 20%, 40%, 60%, and 80% quantiles of the engineering sweet spot values ​​within each fracturing stage are calculated using a probability density distribution, forming the engineering sweet spot cluster labels [Pgeo20%, Pgeo40%, Pgeo60%, Pgeo80%]. The geological sweet spot cluster labels {1, 2, 3, 4} are permuted and combined with the engineering sweet spot cluster labels [Pgeo20%, Pgeo40%, Pgeo60%, Pgeo80%] to determine the optimal clustering number K, which is 16. The remaining unlabeled dataset is merged with the cluster labels to form the complete training dataset. The SS-Kmeans clustering algorithm is used to partition each sample point within the segment into 16 clusters based on Euclidean distance.

[0150] Specifically, the SS-Kmeans clustering algorithm clusters geological sweet spots and engineering sweet spots, which can include the following steps:

[0151] 1) Initialization: Calculate the initial cluster centers based on the geological sweet spot cluster labels and engineering sweet spot cluster labels, and integrate the geological sweet spot cluster labels and engineering sweet spot cluster labels with the unlabeled data into an overall dataset;

[0152] 2) Data distribution: For each sample point in the merged overall data set, calculate its distance from all cluster centers and assign it to the nearest cluster center;

[0153] 3) Update the center point: Update each cluster center to the mean of all sample points in its cluster;

[0154] 4) Iteration: Repeat the assignment and update steps until the cluster centers converge or the maximum number of iterations is reached;

[0155] 5) Result: Output the final double sweet spot clustering result.

[0156] The sample points in each fracturing section are divided into 16 clusters using the SS-Kmeans algorithm, and each cluster corresponds to a combination of geological sweet spots and engineering sweet spots.

[0157] In some embodiments, the design of fracturing stages based on the clustering results of geological sweet spots in S103 may include:

[0158] Traversing the clustered geological sweet spots of all well sections, identifying non-reservoir well sections, selecting non-reservoir well sections with a continuous length greater than a preset length as the segment spacing, and dividing the large fracturing sections according to the segment spacing;

[0159] Starting from the wellhead, the large fracture section is divided into small fracture sections, and the proportion of the same geological sweet spot cluster category in each small fracture section is greater than 50% of the total geological sweet spot cluster category in the small fracture section;

[0160] When there is a fracturing section with a length greater than 100 m in the small fracturing section, the fracturing section with a length greater than 100 m is divided into two sections according to the section length and the geological sweet spot category.

[0161] Specifically, the following steps may be included:

[0162] 1) Initial division: The clustered geological sweet spots of the entire well can be traversed to identify non-reservoir well sections. Non-reservoir well sections with a continuous length greater than a preset length (e.g., >3m) are selected as the segment spacing and bridge plugs are placed. Large fracturing sections are divided based on the segment spacing.

[0163] 2) Segmented Fracturing: Starting from the well's heel (usually the bottom of the well), the large fracturing section is divided into smaller sections. The proportion of clusters of the same geological sweet spot within each small fracturing section is greater than 50% of the total geological sweet spot clusters within the small fracturing section. When optimizing fracturing clusters, more clusters are placed in high-quality geological sweet spots and fewer clusters are placed in poor-quality geological sweet spots.

[0164] 3) Handling long sections: For sections longer than 100 m, the section length and geological sweet spot category are comprehensively considered to divide it into two sections, and the bridge plug position is fine-tuned considering the coupling position to ensure the stability of the bridge plug position.

[0165] Through the above steps, the fracturing stages can be reasonably divided based on the clustering of geological sweet spots. Then, the perforation clusters can be arranged based on the principle of optimizing the high-quality reservoir sections within the sections. The spacing between adjacent seams, the position of casing collars, and the distance between the bridge plug positions in each section and the perforation clusters can be comprehensively considered to further design the perforation cluster positions within the sections and improve the fracturing effect.

[0166] In some embodiments, the design of the fracturing cluster positions within the fracturing stage based on the double sweet spot clustering results in S103 may include:

[0167] Based on the double sweet spot clustering results, a fracturing cluster is arranged on the target well section, where the target well section represents the category with the best geological sweet spot and engineering sweet spot characteristics;

[0168] When the target well section accounts for a small proportion, a fracturing cluster is arranged on the first target well section or the second target well section. The first target well section represents a category with suboptimal geological sweet spot and engineering sweet spot characteristics, and the second target well section represents a category with average geological sweet spot and engineering sweet spot characteristics.

[0169] For details, see Figure 2As shown in the double sweet spot clustering results, the well sections corresponding to labels 1 and 2 (i.e., the target well sections mentioned above) represent the category with the best geological and engineering sweet spot characteristics, typically with the best reservoir quality and development potential. The well sections corresponding to labels 5 and 6 (i.e., the first target well sections mentioned above) represent the category with suboptimal geological and engineering sweet spot characteristics, with good reservoir quality and development potential. The well sections corresponding to labels 9, 10, 13, and 14 (i.e., the second target well sections mentioned above) represent the category with average geological and engineering sweet spot characteristics, with medium reservoir quality and development potential.

[0170] To develop high-quality reservoirs, perforation clusters (labeled 1 and 2) can be prioritized for target well sections within the segment. If the target well section is small and it's difficult to arrange sufficient clusters, clusters can be placed in the first target well section (labeled 5 and 6) or the second target well section (labeled 9, 10, 13, and 14). Minimize the geomechanical differences between clusters. The number of perforations in each cluster can be further designed to achieve balanced fracturing. Adjacent fractures should be spaced closely together, maintaining a spacing of 6 to 20 meters. Perforation clusters should be 2 to 3 meters long. A certain distance should be maintained between the casing collars, the bridge plugs in each section, and the perforation clusters to ensure casing penetration and bridge plug stability.

[0171] Based on the double sweet spot clustering results, fracturing clusters are preferably arranged at locations with similar geomechanical strength and better geological sweet spots, which can achieve the goals of balanced fracture initiation and development of high-quality reservoir properties.

[0172] S104: Determine the perforation friction required for cluster positions other than the geomechanical strength peak cluster position, and optimize perforation parameters until the fracturing pressures at the other cluster positions reach the fracturing pressure of the geomechanical strength peak cluster.

[0173] In some embodiments, after optimizing the design of the fracturing cluster positions, the difference in the initiation pressure of the cluster positions within each stage can be controlled within 10 MPa. To further reduce the difference in the initiation pressure, the perforation parameters, such as the number of perforation holes, can be refined to ensure a balanced distribution of the initiation pressure.

[0174] Specifically, since the cracks do not extend during fracturing, the stress interference between cracks is not considered for the time being. Therefore, the fracture initiation pressure difference at each cluster position in the segment will be balanced by adjusting the perforation friction resistance. The specific steps are as follows:

[0175] 1) First, find the geomechanical strength peak cluster in the fracturing cluster. Its location is in the fracturing cluster position. The initial perforation number of the geomechanical strength peak cluster can be set based on fracturing construction experience. Then, based on the initial perforation parameters, the perforation friction of the geomechanical strength peak cluster can be calculated according to the following formula:

[0176]

[0177] Where ΔPpf is the hole friction, MPa; q is the injection flow rate of the fracturing fluid, m 3 / min; ρ is the density of fracturing fluid, kg / m 3 ; C D is the hole flow coefficient, dimensionless; N is the initial hole number, dimensionless; d is the hole diameter, m.

[0178] 2) The geomechanical strength of the geomechanical strength peak cluster and the borehole friction of the geomechanical strength peak cluster are summed to obtain the equilibrium fracturing pressure of the fracturing section where the geomechanical strength peak cluster is located (i.e., the fracturing pressure of the geomechanical strength peak cluster mentioned above).

[0179] 3) At the locations of clusters other than the geomechanical strength peak cluster, the difference between the equilibrium fracturing pressure and the geomechanical strength corresponding to other clusters is used to determine the borehole friction required for the other clusters to compensate for the difference in fracturing pressure.

[0180] 4) Finally, by optimizing the perforation parameters (e.g., the number of perforations), the perforation friction at other cluster positions within the segment reaches the required perforation friction, thereby achieving a balanced distribution of the fracturing pressure within the segment and ensuring uniform fracturing.

[0181] Among them, numerical simulation software can be used to verify whether the adjusted perforation parameters (such as the number of perforation holes, perforation phase, perforation density, etc.) can achieve the required perforation friction resistance, which is not described in detail in this manual.

[0182] In some embodiments, by optimizing the number of perforations and perforation phases within each cluster, adjusting perforation friction, and optimizing proppant migration, the fracture initiation pressures of each cluster within a segment can be brought closer together, and proppant distribution can be more even, thereby achieving balanced fracture initiation and propagation. Proppant migration patterns under varying perforation friction can be analyzed, including sedimentation, suspension, and distribution. A model can be developed that correlates proppant migration with parameters such as flow rate, viscosity, and perforation friction. By maximizing the perforation friction within each cluster to an equilibrium value, proppant distribution can be more evenly distributed.

[0183] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. For details, please refer to the description of the aforementioned related processing embodiments, and no further description is given here.

[0184] The above describes the present invention. However, it is worth noting that this specific embodiment is only intended to better illustrate the present application and to describe specific embodiments of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0185] In a specific implementation scenario, see Figure 3 As shown in Figure 2, the process of designing a hydraulic fracturing cluster for a horizontal well can be as follows:

[0186] Intelligent optimization design process of fracturing stages based on unsupervised clustering of geological sweet spots:

[0187] 1) Data Processing and Parameter Calculation: Reservoir physical properties are calculated from well logging data to quantitatively evaluate and describe the reservoir. These parameters include shale content, porosity, permeability, and oil saturation. The grading or classification criteria for high-quality geological sweet spots are defined as "one low, three highs": low shale content, high porosity, high permeability, and high oil saturation. The resulting reservoir physical property curves, which vary with well depth, are then processed as a time series using wavelet smoothing to reduce noise and smooth the parameters. The parameters are then standardized to provide a robust dataset for the subsequent unsupervised clustering model.

[0188] 2) Model and method stage: The probability-based Gaussian mixture model (GMM) algorithm is preferred to calculate the n 4-dimensional reservoir physical property parameters D = {x ij |i=1,...,n;j=1,...4} cluster analysis was performed, and finally, the reservoir physical properties parameters of the horizontal well section were clustered into 4 categories. Then, f(V sh ) and f(Φ, So, K) functions, a geological sweet spot classification and evaluation model was established to characterize the distribution of geological sweet spots throughout the well section. Furthermore, the geological sweet spot classification labels {Class I, Class II, Class III, Class IV} were determined.

[0189] 3) Intelligent Optimization Design of Fracturing Stages: Using the geological sweet spot classification labels and well depth as input parameters, the K-means clustering algorithm is used to divide the fracturing stages into K clusters. The similarity between sample points is measured based on Euclidean distance, resulting in higher similarity between samples within each cluster. Finally, the data set D is divided into K clusters, and the optimal number of clusters K for the clustering model is determined based on the "elbow rule." Oilfield construction constraints can be considered when setting parameters. Fracturing stages are designed based on the geological sweet spot clustering results: Non-reservoir well segments are preferred as segment spacing, and bridge plug positions are set based on a comprehensive consideration of segment length and cluster classification to ensure stability.

[0190] Intelligent optimization design process of fracturing clusters based on geological engineering double sweet spot clustering:

[0191] 1) Data processing and parameter calculation stage: Calculate the bottom hole mechanical specific energy based on drilling and logging data, and calculate the minimum horizontal ground stress based on logging data.

[0192] 2) Model and method stage: Determine the geomechanical strength based on the bottomhole mechanical specific energy and the minimum horizontal ground stress; and determine the fracture initiation pressure based on the geomechanical strength. The specific formula can be as follows:

[0193] P Geo =MSE b +S hmin

[0194] P' W ≥P Geo +ΔP pf =(MSE b +S hmin ) max +ΔP pf

[0195] 3) Intelligent Fracturing Cluster Optimization Design: A semi-supervised K-means (SS-Kmeans) clustering algorithm is used, incorporating geo-engineering double sweet spot labels to improve the clustering of unlabeled data. The geomechanical strength of each segment is classified into five clusters using a probability density distribution. The cutoff points of each cluster are designated as engineering sweet spot cluster labels. The geo- and engineering sweet spot cluster labels are combined to determine the optimal number of clusters, K. The remaining unlabeled datasets are then integrated with the cluster labels, and each sample point within the segment is assigned to a cluster based on Euclidean distance. The geo-engineering double sweet spot clustering results are obtained. Finally, the perforation clusters are arranged based on the principle of optimizing high-quality reservoir sections within the segment. The perforation cluster locations within the segment are further designed, taking into account the spacing between adjacent fractures, the location of casing collars, and the distance between each segment's bridge plug and the perforation cluster. Based on this, the perforation parameters of each cluster within the segment are refined, taking into account perforation friction, to ensure balanced fracturing initiation.

[0196] Through this approach, with the goal of balanced fracturing and high-quality reservoir development, and by comprehensively considering the clustering results of the geological and engineering sweet spots, we can effectively consider reservoir physical properties and similar fracturing pressures to optimize segment and cluster locations. By optimizing the perforation parameters of each cluster, the differences in fracturing pressures between clusters can be more precisely adjusted and reduced, thereby achieving balanced fracture initiation. The developed computer software uses raw oilfield data as input, allowing engineers to set operation parameters and promote intelligent and automated optimization of fracturing segment cluster locations. This method provides new insights for optimizing horizontal well volume fracturing segment clusters in unconventional reservoirs, further improving the contribution efficiency and balanced treatment of fracturing perforation clusters.

[0197] Although this specification provides examples such as the following examples or the accompanying Figure 4 The method operation steps or device structure shown, but based on routine or no creative labor, the method or device may include more or fewer operation steps or module units after partial merger. In the steps or structures that do not logically have necessary causal relationships, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure described is applied to actual devices, servers or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or drawings (for example, in an environment of parallel processors or multi-threaded processing, or even in an implementation environment of distributed processing and server clusters). Based on the above-mentioned method for intelligent optimization design of cluster parameters of staged fracturing segments of horizontal wells, the embodiments of this specification also propose an embodiment of an intelligent optimization design device for cluster parameters of staged fracturing segments of horizontal wells. As Figure 4 As shown, the device may specifically include the following modules:

[0198] Sweet spot division module 401 can be used to divide geological sweet spots according to well logging data, and to divide engineering sweet spots according to drilling and logging data;

[0199] The sweet spot clustering module 402 can be used to cluster geological sweet spots to obtain geological sweet spot clustering results, and cluster geological sweet spots and engineering sweet spots to obtain double sweet spot clustering results;

[0200] The fracturing segment cluster design module 403 can be used to design fracturing segments based on the geological sweet spot clustering results and to design fracturing cluster locations within the fracturing segments based on the double sweet spot clustering results, wherein the fracturing cluster locations include geomechanical strength peak cluster locations;

[0201] The perforation parameter optimization module 404 can be used to determine the perforation friction required at cluster positions other than the geomechanical strength peak cluster position, and optimize the perforation parameters until the fracturing pressure at the other cluster positions reaches the fracturing pressure of the geomechanical strength peak cluster.

[0202] In some embodiments, the above-mentioned sweet spot division module 401 can be specifically used to calculate reservoir physical property parameters based on logging data, process the reservoir physical property parameters to obtain processed reservoir physical property parameters; cluster the processed reservoir physical property parameters to obtain reservoir physical property parameter clustering results; calculate the geological sweet spot index of each category in the reservoir physical property parameter clustering results; and divide each category into geological sweet spots of corresponding levels according to the geological sweet spot index of each category.

[0203] In some embodiments, the reservoir physical property parameters in the sweet spot division module 401 may include at least one of the following: shale content, porosity, oil saturation, and permeability; and may be used to calculate the geological sweet spot index of each category according to the following formula:

[0204] f(V sh )=(V sh25％ +V sh75％ )

[0205]

[0206] Among them, V sh is the mud content; So is the oil saturation; K is the permeability; Φ is the porosity; V sh25％ V is the 25% percentile value of the mud content parameter in each category; sh75％ So is the 75% percentile value of the mud content parameter in each category; 25％ So is the 25% percentile value of the oil saturation parameter in each category; 75％ is the 75% percentile value of the oil saturation parameter in each category; K 25％ is the 25% quantile value of the permeability parameter in each category; K 75％ is the 75% quantile value of the permeability parameter in each category; Φ 25％ is the 25% quantile value of the porosity parameter in each category; Φ 75％ is the 75% quantile value of the porosity parameter in each category; f(V sh ) is used to calculate the sum of the 25% and 75% percentile values ​​of the mud content parameter in each category; f(Φ,So,K) is used to calculate the mean of the sum of the 25% and 75% percentile values ​​of the porosity, oil saturation, and permeability parameters in each category; I Geo Represents the geological sweet spot index.

[0207] In some embodiments, the above-mentioned sweet spot division module 401 can be specifically used to calculate the bottom hole mechanical specific energy based on drilling and logging data, and calculate the minimum horizontal ground stress based on logging data; determine the geomechanical strength based on the bottom hole mechanical specific energy and the minimum horizontal ground stress; and divide the engineering sweet spots based on the geomechanical strength.

[0208] In some embodiments, the divided geological sweet spots have graded labels of geological sweet spots along the well depth; accordingly, the sweet spot clustering module 402 can be specifically used to cluster the graded labels of geological sweet spots along the well depth using a K-means clustering algorithm to obtain a geological sweet spot clustering result; and to cluster the geological sweet spots and engineering sweet spots using a semi-supervised K-means clustering algorithm to obtain a double sweet spot clustering result.

[0209] In some embodiments, the above-mentioned sweet spot clustering module 402 can also be specifically used to construct a data set based on the geological sweet spot classification labels along the well depth, select a preset number of sample points from the data set as the initial cluster center; divide each sample point in the data set into a corresponding cluster according to the Euclidean distance from the initial cluster center; calculate the average value of all sample points in the corresponding cluster as the new cluster center; repeat the process of dividing the cluster and calculating the average value of all sample points in the divided cluster until the sample center points of all clusters no longer change or the number of iterations reaches a preset iteration threshold, and output the geological sweet spot clustering result.

[0210] In some embodiments, the above-mentioned fracturing segment cluster design module 403 can be specifically used to traverse the geological sweet spots of the entire well section after clustering, identify non-reservoir well sections, select non-reservoir well sections with a continuous length greater than a preset length as the segment spacing, and divide the large fracturing segment according to the segment spacing; starting from the bottom end of the well, the large fracturing segment is divided into small fracturing segments, and the proportion of the same geological sweet spot clustering category in each small fracturing segment is greater than 50% of the total geological sweet spot clustering category in the small fracturing segment; when there is a fracturing segment with a length greater than 100m in the small fracturing segment, the fracturing segment with a length greater than 100m is divided into two segments according to the segment length and the geological sweet spot category.

[0211] In some embodiments, the above-mentioned fracturing segment cluster design module 403 can also be specifically used to arrange fracturing clusters on target well sections based on the double sweet spot clustering results, and the target well sections represent the category with the best geological sweet spot and engineering sweet spot characteristics; when the target well sections account for a small proportion, the fracturing clusters are arranged on the first target well section or the second target well section, and the first target well section represents the category with suboptimal geological sweet spot and engineering sweet spot characteristics, and the second target well section represents the category with average geological sweet spot and engineering sweet spot characteristics.

[0212] As can be seen from the above, a method and device for intelligent optimization design of parameters of a horizontal well segmented fracturing cluster provided in the embodiments of this specification can accurately, efficiently and intelligently design a fracturing cluster based on precisely divided geological sweet spots and engineering sweet spots by using supervised clustering and unsupervised distance. The perforation parameters within the fracturing cluster can then be refined and optimized to achieve balanced initiation and expansion of fractures.

[0213] The embodiments of this specification also provide an electronic device based on the above-mentioned method for intelligent optimization design of cluster parameters of staged fracturing sections of horizontal wells, including a processor and a memory for storing programs / instructions executable by the processor. When the processor is specifically implemented, it can perform the following steps according to the program / instructions: divide geological sweet spots according to logging data, and divide engineering sweet spots according to drilling and logging data and logging data; cluster the geological sweet spots to obtain geological sweet spot clustering results, and cluster the geological sweet spots and engineering sweet spots to obtain double sweet spot clustering results; design the fracturing section based on the geological sweet spot clustering results, and design the fracturing cluster position within the fracturing section based on the double sweet spot clustering results, wherein the fracturing cluster position includes the geomechanical strength peak cluster position; determine the borehole friction resistance required for other cluster positions except the geomechanical strength peak cluster position, and optimize the perforation parameters until the fracturing pressure of other cluster positions reaches the fracturing pressure of the geomechanical strength peak cluster.

[0214] In order to complete the above instructions more accurately, refer to Figure 5 As shown, an embodiment of this specification also provides another specific electronic device, wherein the electronic device includes a network communication port 501, a processor 502 and a memory 503, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0215] The processor 502 may be specifically configured to divide geological sweet spots according to well logging data, and to divide engineering sweet spots according to drilling and logging data and well logging data; cluster the geological sweet spots to obtain geological sweet spot clustering results, and cluster the geological sweet spots and engineering sweet spots to obtain double sweet spot clustering results; design a fracturing section based on the geological sweet spot clustering results, and design a fracturing cluster position within the fracturing section based on the double sweet spot clustering results, wherein the fracturing cluster position includes a geomechanical strength peak cluster position; determine the borehole friction required for other cluster positions except the geomechanical strength peak cluster position, and optimize the perforation parameters until the fracturing pressures at the other cluster positions reach the fracturing pressure of the geomechanical strength peak cluster;

[0216] The memory 503 may be specifically used to store corresponding instruction programs.

[0217] In this embodiment, the network communication port 501 can be a virtual port that is bound to different communication protocols, thereby being capable of sending or receiving different data. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. Furthermore, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wi-Fi chip; or it can be a Bluetooth chip.

[0218] In this embodiment, the processor 502 may be implemented in any suitable manner. For example, the processor may take the form of a microprocessor or a processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, an embedded microcontroller, etc. This specification is not intended to limit this.

[0219] In this embodiment, the memory 503 may include multiple levels. In a digital system, anything that can store binary data can be a memory. In an integrated circuit, a circuit with a storage function that has no physical form is also called a memory, such as RAM, FIFO, etc. In a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0220] The embodiments of this specification also provide a computer storage medium based on the above-mentioned method for intelligent optimization design of cluster parameters of staged fracturing sections of horizontal wells, wherein the computer storage medium stores a computer program / instruction, which, when executed, implements: dividing geological sweet spots according to logging data, and dividing engineering sweet spots according to drilling and logging data and logging data; clustering geological sweet spots to obtain geological sweet spot clustering results, and clustering geological sweet spots and engineering sweet spots to obtain double sweet spot clustering results; designing fracturing sections based on the geological sweet spot clustering results, and designing fracturing cluster positions within the fracturing sections based on the double sweet spot clustering results, wherein the fracturing cluster positions include geomechanical strength peak cluster positions; determining the borehole friction resistance required for other cluster positions except the geomechanical strength peak cluster position, and optimizing the perforation parameters until the fracturing pressures of other cluster positions reach the fracturing pressure of the geomechanical strength peak cluster.

[0221] In this embodiment, the storage medium includes, but is not limited to, random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD), or memory card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured in accordance with the standards specified by the communication protocol for network connection communication.

[0222] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer storage medium can be explained in comparison with other implementations and will not be repeated here.

[0223] Although this specification provides the method operation steps as described in the embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the device or client product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. Words such as first and second are used to represent names and do not represent any particular order.

[0224] Those skilled in the art will also appreciate that, in addition to implementing the controller in pure computer-readable program code, it is entirely possible to implement the same functionality by logically programming the method steps in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, and the like. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered structures within the hardware component. Alternatively, the devices for implementing various functions can be considered both software modules implementing the method and structures within the hardware component.

[0225] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0226] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that this specification can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of this specification can essentially be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of this specification.

[0227] The various embodiments in this specification are described in a progressive manner. References to the common or similar parts of the various embodiments are sufficient. Each embodiment focuses on the differences from the other embodiments. This specification can be used in a variety of general-purpose or specialized computer system environments or configurations. For example, personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments that include any of the above systems or devices.

[0228] Although the present specification has been described with reference to the embodiments, persons skilled in the art will appreciate that there are many variations to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims encompass such variations without departing from the spirit of the present specification.

Claims

1. A method for intelligent optimization design of stage cluster parameters for horizontal well staged fracturing, characterized in that: include: Divide geological sweet spots based on well logging data, and divide engineering sweet spots based on drilling and logging data; Cluster the geological sweet spots to obtain the geological sweet spot clustering results, and cluster the geological sweet spots and engineering sweet spots to obtain the double sweet spot clustering results; Designing a fracturing section based on the geological sweet spot clustering results, and designing a fracturing cluster location within the fracturing section based on the double sweet spot clustering results, wherein the fracturing cluster location includes a geomechanical strength peak cluster location; The perforation friction required for cluster positions other than the geomechanical strength peak cluster position is determined, and the perforation parameters are optimized until the fracturing pressures at other cluster positions reach the fracturing pressure of the geomechanical strength peak cluster.

2. The method according to claim 1, characterized in that The method of dividing geological sweet spots according to well logging data includes: Calculate reservoir physical property parameters based on well logging data, process the reservoir physical property parameters, and obtain processed reservoir physical property parameters; Clustering the processed reservoir physical property parameters to obtain reservoir physical property parameter clustering results; Calculate the geological sweet spot index of each category in the clustering results of reservoir physical property parameters; According to the geological dessert index of each category, each category is divided into a geological dessert of corresponding level.

3. The method according to claim 2, characterized in that The reservoir physical property parameters include at least one of the following: shale content, porosity, oil saturation, and permeability; the calculated geological sweet spot index of each category in the clustering results of the reservoir physical property parameters includes: The geological sweet spot index of each category is calculated using the following formula: f(V sh )=(V sh25％ +V sh75％ ) Among them, V sh is the mud content; So is the oil saturation; K is the permeability; Φ is the porosity; V sh25％ V is the 25% percentile value of the mud content parameter in each category; sh75％ So is the 75% percentile value of the mud content parameter in each category; 25％ So is the 25% percentile value of the oil saturation parameter in each category; 75％ is the 75% percentile value of the oil saturation parameter in each category; K 25％ is the 25% quantile value of the permeability parameter in each category; K 75％ is the 75% quantile value of the permeability parameter in each category; Φ 25％ is the 25% quantile value of the porosity parameter in each category; Φ 75％ is the 75% quantile value of the porosity parameter in each category; f(V sh ) is used to calculate the sum of the 25% and 75% percentile values ​​of the mud content parameter in each category; f(Φ,So,K) is used to calculate the mean of the sum of the 25% and 75% percentile values ​​of the porosity, oil saturation, and permeability parameters in each category; I Geo Represents the geological sweet spot index.

4. The method according to claim 1, wherein The division of engineering sweet spots according to drilling and logging data and well logging data includes: Calculate the bottom hole mechanical specific energy based on drilling and logging data, and calculate the minimum horizontal ground stress based on logging data; Determine the geomechanical strength based on the bottom hole mechanical specific energy and minimum horizontal ground stress; Engineering sweet spots are divided according to geomechanical strength.

5. The method according to claim 1, wherein The divided geological sweet spots have geological sweet spot classification labels along the well depth; accordingly, clustering the geological sweet spots to obtain the geological sweet spot clustering results includes: The K-means clustering algorithm is used to cluster the geological sweet spot classification labels along the well depth to obtain the geological sweet spot clustering results; Clustering the geological sweet spots and engineering sweet spots to obtain a double sweet spot clustering result includes: The semi-supervised K-means clustering algorithm was used to cluster the geological sweet spots and engineering sweet spots, and the double sweet spot clustering results were obtained.

6. The method according to claim 5, characterized in that The K-means clustering algorithm is used to cluster the geological sweet spot classification labels along the well depth to obtain the geological sweet spot clustering results, including: constructing a data set based on hierarchical labels of geological sweet spots along the well depth, and selecting a preset number of sample points from the data set as initial cluster centers; Divide each sample point in the data set into a corresponding cluster according to the Euclidean distance from the initial cluster center; Calculate the average value of all sample points in the corresponding cluster as the new cluster center; Repeat the process of dividing clusters and calculating the average values ​​of all sample points in the divided clusters until the sample center points of all clusters no longer change or the number of iterations reaches the preset iteration threshold, and output the geological sweet spot clustering results.

7. The method according to claim 1, characterized in that The method of designing a fracturing stage based on the geological sweet spot clustering results includes: Traversing the clustered geological sweet spots of all well sections, identifying non-reservoir well sections, selecting non-reservoir well sections with a continuous length greater than a preset length as the segment spacing, and dividing the large fracturing sections according to the segment spacing; Starting from the wellhead, the large fracture section is divided into small fracture sections, and the proportion of the same geological sweet spot cluster category in each small fracture section is greater than 50% of the total geological sweet spot cluster category in the small fracture section; When there is a fracturing section with a length greater than 100 m in the small fracturing section, the fracturing section with a length greater than 100 m is divided into two sections according to the section length and the geological sweet spot category.

8. The method according to claim 1, characterized in that The design of the fracturing cluster positions within the fracturing section based on the double sweet spot clustering results includes: Based on the double sweet spot clustering results, a fracturing cluster is arranged on the target well section, where the target well section represents the category with the best geological sweet spot and engineering sweet spot characteristics; When the target well section accounts for a small proportion, a fracturing cluster is arranged on the first target well section or the second target well section. The first target well section represents a category with suboptimal geological sweet spot and engineering sweet spot characteristics, and the second target well section represents a category with average geological sweet spot and engineering sweet spot characteristics.

9. An intelligent optimization design device for staged fracturing cluster parameters of horizontal wells, characterized by: include: Sweet spot division module, used to divide geological sweet spots according to well logging data, and to divide engineering sweet spots according to drilling and logging data; Sweet spot clustering module, used to cluster geological sweet spots to obtain geological sweet spot clustering results, and cluster geological sweet spots and engineering sweet spots to obtain double sweet spot clustering results; A fracturing segment cluster design module, configured to design fracturing segments based on the geological sweet spot clustering results and to design fracturing cluster locations within a fracturing segment based on the double sweet spot clustering results, wherein the fracturing cluster locations include geomechanical strength peak cluster locations; The perforation parameter optimization module is used to determine the perforation friction required at other cluster positions except the geomechanical strength peak cluster position, and optimize the perforation parameters until the fracturing pressure at other cluster positions reaches the fracturing pressure of the geomechanical strength peak cluster.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images