Method and device for segmenting and clustering horizontal well fracturing based on mechanical specific energy

Abstract

The present invention provides a method and device for segmented clustering of horizontal well fracturing based on mechanical specific energy, the method comprising: establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section; solving the engineering sweet spot model by clustering method to segment the target well section; in the segmentation results, using the Euclidean proximity method to optimize clustering within each section. The present invention can reduce the risk of forming invalid and inefficient cracks based on the corrected mechanical specific energy, and can provide accurate guidance for the setting of perforation positions for segmented clustered fracturing of horizontal wells. Practice has proved that adjusting the perforation position with reference to the mechanical specific energy allows the fractures of each cluster to develop evenly and the fracture transformation volume to be maximized, thereby achieving the purpose of reducing costs and increasing efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of horizontal well fracturing design, and in particular to a horizontal well fracturing segmentation and clustering method and device based on mechanical specific energy. Background Art

[0002] In the existing technology, the staged fracturing completion technology of horizontal wells plays an important role in giving full play to the role of horizontal wells in improving the productivity and recovery rate of unconventional reservoirs. Ideally, the perforation clusters with similar fractures and extensions are placed in one section to avoid partial clusters not being opened and large differences in fracture extension between clusters. The perforation clusters obtained by the ideal clustering technology are oil and gas-rich, most likely to be fractured, and most likely to form fracture networks. Reasonable staged clustering can avoid working in inefficient layers, avoid repeated construction in similar fracture networks, or ineffective fracturing in some layers, which is very important for improving the efficiency of volume fracturing.

[0003] The existing segmentation, clustering and sweet spot screening technologies are generally based on logging curves, which only consider the influence of reservoir oil and gas content, or use rock mechanical parameters calculated by logging data to select layers in segments, without considering the influence of rock mechanical properties, which play an important role in the expansion of fractures. In recent years, North America has proposed the use of mechanical specific energy to determine engineering sweet spots, combined with geological sweet spots, and then divided the fracturing stages, achieving better application results. Rock mechanical specific energy (Mechanical Specific Energy or MSE) was originally defined as the energy required to drill a unit volume of rock during drilling. This theory is usually applied in drilling process detection, prediction, drilling engineering design optimization, and evaluation of formation rock mechanical properties. This parameter reflects the drillability of rock. In recent years, North American researchers have begun to study the relationship between rock drillability and rock compressibility.

[0004] On the other hand, the existing segmentation, clustering and sweet spot screening methods are mostly manual, which puts multiple curves together and obtains them through manual comparison. When selecting layers, designers need to compare multiple data such as logging, mud logging and engineering to optimize the clustering and segmentation positions, which is a large workload and low efficiency. It is impossible to comprehensively consider the advantages and disadvantages of various curves, nor can it use mathematical methods to iterate to obtain the optimal results, and the research process cannot be intelligent. Due to the backwardness of mathematical methods and design concepts, it is easy to fail in layer selection and fail to select sweet spots. Summary of the invention

[0005] The method and device for staged and clustered horizontal well fracturing based on mechanical specific energy provided by the present invention can reduce the risk of forming invalid and inefficient cracks based on the corrected mechanical specific energy, and can provide accurate guidance for the setting of perforation positions for staged and clustered fracturing of horizontal wells. Practice has proved that adjusting the perforation positions with reference to the mechanical specific energy allows the balanced development of each cluster of cracks and maximizes the fracture transformation volume, thereby achieving the purpose of reducing costs and increasing efficiency.

[0006] In order to achieve the above objectives, the present invention discloses, on one hand, a horizontal well fracturing segmentation and clustering method based on mechanical specific energy, which comprises:

[0007] Establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section;

[0008] Solving the engineering sweet spot model by using a clustering method to segment the target well section;

[0009] In the segmentation results, the Euclidean closeness method is used to optimize clustering within each segment.

[0010] In one embodiment, before establishing the engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section, the method includes:

[0011] The raw data corresponding to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference are standardized.

[0012] In one embodiment, solving the engineering sweet spot model by clustering method to segment the target well section includes:

[0013] Perform the following iterative operations until the iteration stop condition is reached;

[0014] Randomly searching for multiple data as initial cluster centers among the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference;

[0015] Calculate the Euclidean distance between other data and these multiple cluster centers, and classify the data into the category with the closest Euclidean distance;

[0016] The arithmetic mean values ​​of the data in the plurality of clusters are respectively calculated as new cluster centers of the clusters.

[0017] In one embodiment, the iteration stopping condition includes: reaching a preset number of iterations and / or the new cluster center is the same as the previous cluster center.

[0018] In one embodiment, the horizontal well fracturing segmentation and clustering method based on mechanical specific energy further includes:

[0019] According to the segmentation results, the clustering results in each segment and the corresponding reservoir type curve data, segmentation and clustering result data are formed.

[0020] Correspondingly, the present invention also discloses a horizontal well fracturing segmentation and clustering device based on mechanical specific energy, the device comprising:

[0021] A model building module, used to build an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section;

[0022] A segmentation module, used for solving the engineering sweet spot model by clustering method to segment the target well section;

[0023] The clustering module is used to optimize clustering in each segment using the Euclidean proximity method in the segmentation results.

[0024] In one embodiment, the horizontal well fracturing segmentation and clustering device based on mechanical specific energy further includes:

[0025] The standardization module is used to standardize the raw data corresponding to the brittleness index, fracture toughness index and horizontal principal stress difference.

[0026] In one embodiment, the segmentation module includes:

[0027] An iterative operation unit, used to perform the following iterative operations until an iteration stop condition is reached;

[0028] Randomly searching for multiple data as initial cluster centers among the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference;

[0029] Calculate the Euclidean distance between other data and these multiple cluster centers, and classify the data into the category with the closest Euclidean distance;

[0030] The arithmetic mean values ​​of the data in the plurality of clusters are respectively calculated as new cluster centers of the clusters.

[0031] In one embodiment, the iteration stopping condition includes: reaching a preset number of iterations and / or the new cluster center is the same as the previous cluster center.

[0032] In one embodiment, the horizontal well fracturing segmentation and clustering device based on mechanical specific energy further includes:

[0033] The result data forming module is used to form segmentation and clustering result data according to the segmentation result, the clustering result in each segment and the corresponding reservoir type curve data.

[0034] In a third aspect, the present invention provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of a method for horizontal well fracturing segmentation and clustering based on mechanical specific energy.

[0035] In a fourth aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of a method for segmenting and clustering horizontal well fracturing based on mechanical specific energy are implemented.

[0036] In a fifth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for horizontal well fracturing segmentation and clustering based on mechanical specific energy.

[0037] From the above description, it can be seen that the horizontal well fracturing segmentation clustering method and device based on mechanical specific energy provided by the embodiment of the present invention, the corresponding method includes: first, establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section; then, using a clustering method to solve the engineering sweet spot model to segment the target well section; finally, in the segmentation results, using the Euclidean proximity method, optimizing clustering within each segment.

[0038] The beneficial effect of the present invention is that, compared with the prior art, the present invention can realize the use of mechanical specific energy as data already acquired during drilling, and directly use it in the horizontal well fracturing process to reduce the logging time. The logging data of some development wells is incomplete, and the traditional logging curve method for segmentation and clustering data is insufficient. The combination of mechanical specific energy is more comprehensive, and the mechanical specific energy is corrected in consideration of various situations. Compared with the prior art, the present invention can reduce the risk of forming invalid and inefficient cracks based on the corrected mechanical specific energy, and can provide precise guidance for the setting of cluster perforation schemes for staged fracturing of horizontal wells, adjust the perforation parameters, so that each cluster of cracks develops evenly and the fracture transformation volume is maximized, thereby achieving the purpose of reducing costs and increasing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 Schematic diagram of the process of the horizontal well fracturing segmentation clustering method based on mechanical specific energy in an embodiment of the present invention Figure 1 ;

[0041] Figure 2 Schematic diagram of the process of the horizontal well fracturing segmentation clustering method based on mechanical specific energy in an embodiment of the present invention Figure 2 ;

[0042] Figure 3 It is a flow chart of step 200 of the method for segmenting and clustering horizontal well fracturing based on mechanical specific energy in an embodiment of the present invention;

[0043] Figure 4 Schematic diagram of the process of the horizontal well fracturing segmentation clustering method based on mechanical specific energy in an embodiment of the present invention Figure 3 ;

[0044] Figure 5 It is a flow chart of a horizontal well fracturing segmentation and clustering system based on mechanical specific energy in a specific embodiment of the present invention;

[0045] Figure 6 The segmentation and clustering of a horizontal well based on mechanical specific energy in a specific embodiment of the present invention is shown in FIG. Figure 1 ;

[0046] Figure 7 The segmentation and clustering of a horizontal well based on mechanical specific energy in a specific embodiment of the present invention is shown in FIG. Figure 2 ;

[0047] Figure 8 The segmentation and clustering of a horizontal well based on mechanical specific energy in a specific embodiment of the present invention is shown in FIG. Figure 3 ;

[0048] Fig. 9 The segmentation and clustering of a horizontal well based on mechanical specific energy in a specific embodiment of the present invention is shown in FIG. Figure 4 ;

[0049] Fig.10 The embodiment of the present invention is a segmented clustering amplification of a horizontal well based on mechanical specific energy. Figure 1 ;

[0050] Fig.11 The embodiment of the present invention is a segmented clustering amplification of a horizontal well based on mechanical specific energy. Figure 2 ;

[0051] Fig.12 The embodiment of the present invention is a segmented clustering amplification of a horizontal well based on mechanical specific energy. Figure 3 ;

[0052] Fig.13 The embodiment of the present invention is a segmented clustering amplification of a horizontal well based on mechanical specific energy. Figure 4 ;

[0053] Fig.14It is a GR curve diagram of a horizontal well in a specific embodiment of the present invention;

[0054] Fig.15 This is a perforation cluster location diagram of the 20th segment in a specific embodiment of the present invention.

[0055] Fig.16 It is a segmented cluster diagram of the 3351-3308 meter well section in a specific embodiment of the present invention;

[0056] Fig.17 The horizontal well fracturing segmentation and clustering device based on mechanical specific energy in the embodiment of the present invention Figure 1 ;

[0057] Fig.18 The horizontal well fracturing segmentation and clustering device based on mechanical specific energy in the embodiment of the present invention Figure 2 ;

[0058] Fig.19 It is a block diagram of a segmentation module 20 of a horizontal well fracturing segmentation and clustering device based on mechanical specific energy in an embodiment of the present invention;

[0059] Fig. 20 The horizontal well fracturing segmentation and clustering device based on mechanical specific energy in the embodiment of the present invention Figure 3 ;

[0060] Fig.21 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] It should be noted that the terms "including" and "having" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In the absence of conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0064] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0065] See also Figure 1 The embodiment of the present invention provides a specific implementation of a horizontal well fracturing segmentation and clustering method based on mechanical specific energy, and the method specifically includes the following contents:

[0066] Step 100: establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section;

[0067] Specifically, the engineering sweet spot model of the target well section is established by using the mechanical specific energy method and comprehensively considering the brittleness index, fracture toughness and horizontal principal stress difference; further:

[0068] The calculation formula of mechanical specific energy is as follows:

[0069]

[0070] In the above formula: W = corrected drilling pressure, N; dB = drill bit diameter, m; RPM = rotation speed, r / min; Tb = corrected torque, Nm; ROP = mechanical drilling speed, m / min; E-mechanical specific energy, pa.

[0071] The correction of mechanical specific energy is carried out from the following two aspects:

[0072] 1. Considering the differences in drilling process conditions, accurate calculation of mechanical specific energy is performed to accurately reflect the fracture energy and fracturing properties of the formation:

[0073] (1) When using composite (screw) drilling tools, calibrate the speed and torque;

[0074] (2) Consider the hydraulic rock-breaking energy and superimpose it on the mechanical rock-breaking energy to accurately reflect the energy required for formation fracture;

[0075] (3) Consider the wear of the drill bit to avoid exaggerating the mechanical specific energy;

[0076] (4) Consider the changes in friction resistance in long and curved sections and make corrections to drilling pressure and torque, such as support pressure.

[0077] 2. Using the target well gamma ray, logging depth, non-confining compressive strength, brittleness calculation results and other data, combined with the experience of successful cases in the block, a dimensionless correction is performed through the multivariate linear regression algorithm.

[0078] Furthermore, the mechanical specific energy correction should also take into account the hydraulic rock breaking energy, drill bit wear, and changes in friction resistance in long well sections and curved well sections.

[0079] Step 200: solving the engineering sweet spot model by using a clustering method to segment the target well section;

[0080] Step 300: In the segmentation results, the Euclidean closeness method is used to optimize clustering within each segment.

[0081] Specifically, when clustering, the position with higher compressibility index and lower mechanical specific energy in the segment is preferably used as the position of the perforation cluster. Furthermore, when clustering in step S3, if the reservoir is a brittle reservoir, the number of clusters per segment is first 5 to 6 clusters, and then gradually increases to 8 to 10 clusters; if the reservoir is a plastic reservoir, the number of clusters per segment is 3 to 4 clusters.

[0082] From the above description, it can be seen that the horizontal well fracturing segmentation clustering method based on mechanical specific energy provided by an embodiment of the present invention includes: first, establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section; then, solving the engineering sweet spot model by using a clustering method to segment the target well section; finally, in the segmentation results, using the Euclidean proximity method to optimize clustering within each segment.

[0083] The beneficial effect of the present invention is that, compared with the prior art, the present invention can realize the use of mechanical specific energy as data already acquired during drilling, and directly use it in the horizontal well fracturing process to reduce the logging time. The logging data of some development wells is incomplete, and the traditional logging curve method for segmentation and clustering data is insufficient. The combination of mechanical specific energy is more comprehensive, and the mechanical specific energy is corrected in consideration of various situations. Compared with the prior art, the present invention can reduce the risk of forming invalid and inefficient cracks based on the corrected mechanical specific energy, and can provide precise guidance for the setting of cluster perforation schemes for staged fracturing of horizontal wells, adjust the perforation parameters, so that each cluster of cracks develops evenly and the fracture transformation volume is maximized, thereby achieving the purpose of reducing costs and increasing efficiency.

[0084] In some embodiments, see Figure 2 The horizontal well fracturing segmentation and clustering method based on mechanical specific energy also includes:

[0085] Step 400: Standardize the raw data corresponding to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference.

[0086] Before data analysis, it is usually necessary to normalize the data first, and use the normalized data for data analysis. Data normalization is the indexation of statistical data. Data normalization processing mainly includes two aspects: data homogeneity processing and dimensionless processing. Data homogeneity processing mainly solves the problem of data of different properties. Directly summing up indicators of different properties cannot correctly reflect the comprehensive results of different forces. It is necessary to first consider changing the properties of the inverse indicator data so that all indicators have the same force on the evaluation scheme, and then summing them up to get the correct result. Data dimensionless processing mainly solves the comparability of data. There are many methods for data standardization, and the commonly used ones are "minimum-maximum standardization", "Z-score standardization" and "standardization by decimal calibration". After the above-mentioned normalization processing, the original data are converted into dimensionless indicator evaluation values, that is, the values ​​of each indicator are at the same order of magnitude, and comprehensive evaluation and analysis can be performed. The present invention mainly adopts the following standardization methods:

[0087] 1. Min-max standardization

[0088] The min-max normalization method is to perform a linear transformation on the original data. Let minA and maxA be the minimum and maximum values ​​of attribute A respectively, and map an original value x of A to a value x' in the interval [0,1] through min-max normalization. The formula is:

[0089] New data = (original data - minimum value) / (maximum value - minimum value)

[0090] 2. z-score standardization

[0091] This method standardizes the data based on the mean and standard deviation of the original data. The original value x of A is standardized to x' using z-score. The z-score standardization method is suitable for situations where the maximum and minimum values ​​of attribute A are unknown, or when there are outlier data that exceed the value range.

[0092] New data = (original data - mean) / standard deviation

[0093] Here are the steps:

[0094] 1. Calculate the arithmetic mean (mathematical expectation) xi and standard deviation si of each variable (indicator);

[0095] 2. Standardization:

[0096] zij=(xij-xi) / si

[0097] Among them: zij is the standardized variable value; xij is the actual variable value.

[0098] 3. Swap the positive and negative signs before the inverse indicator.

[0099] The standardized variable value fluctuates around 0. A value greater than 0 indicates that it is above the average level, and a value less than 0 indicates that it is below the average level.

[0100] 3. Decimal scaling

[0101] This method normalizes the data by moving the decimal point. The number of decimal points moved depends on the maximum absolute value of the attribute A. The calculation method for normalizing the original value x of attribute A to x' using decimal scaling is:

[0102] x'=x / (10^j)

[0103] Wherein, j is the smallest integer that satisfies the condition. For example, assuming that the value of A ranges from -986 to 917, and the maximum absolute value of A is 986, in order to use decimal calibration and standardization, each value is divided by 1000 (i.e., j=3), so that -986 is normalized to -0.986. Note that standardization will change the original data, so it is necessary to save the parameters of the standardization method used in order to uniformly standardize subsequent data. In addition to the data standardization mentioned above, there are also log-logistic mode, fuzzy quantization mode, etc.: Log-logistic mode: new data = 1 / (1+e^(-original data)); fuzzy quantization mode: new data = 1 / 2+1 / 2sin[pi 3.1415 / (maximum value-minimum value)*(X-(maximum value-minimum value) / 2)]X is the original data.

[0104] In one embodiment, see Figure 3 , step 200 comprises:

[0105] Step 201: perform the following iterative operations until the iteration stop condition is reached;

[0106] Randomly searching for multiple data as initial cluster centers among the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference;

[0107] Calculate the Euclidean distance between other data and these multiple cluster centers, and classify the data into the category with the closest Euclidean distance;

[0108] The arithmetic mean values ​​of the data in the plurality of clusters are respectively calculated as new cluster centers of the clusters.

[0109] In step 201, specifically: randomly find K data as initial cluster centers; then calculate the Euclidean distance of other data from the K cluster centers, and classify the data into the category with the closest Euclidean distance; then calculate the arithmetic mean of the data in the K clusters respectively, as the new cluster center of each cluster; finally repeat the above steps until the specified number of iterations is completed or the new cluster center is the same as the previous cluster center, and the algorithm ends.

[0110] In one embodiment, the iteration stopping condition includes: reaching a preset number of iterations and / or the new cluster center is the same as the previous cluster center.

[0111] In one embodiment, see Figure 4 The horizontal well fracturing segmentation and clustering method based on mechanical specific energy also includes:

[0112] Step 500: generating segmentation and clustering result data according to the segmentation results, the clustering results in each segment and the corresponding reservoir type curve data.

[0113] From the above description, it can be seen that the present invention is aimed at the existing segmentation clustering and sweet spot screening technology, which is generally based on logging curves, and only considers the influence of reservoir oil and gas content, or uses rock mechanical parameters calculated by logging data to select layers in segments, but does not really consider the problem of rock mechanical properties. Specifically, the segmentation clustering and sweet spot screening methods in the prior art are mostly manual, putting multiple curves together and obtaining them through manual comparison. When selecting layers, designers need to compare logging, mud logging and engineering data at the same time to optimize the clustering and segmentation positions, which is a large workload and low efficiency. It can neither comprehensively consider the advantages and disadvantages of various curves, nor use mathematical means to obtain the optimal results through iteration, and the research process cannot be intelligent. Due to the backwardness of mathematical means and design concepts, it is easy to fail in layer selection and fail to select sweet spots. The horizontal well fracturing segmentation clustering method based on mechanical specific energy provided by the present invention can use the data obtained during drilling to calculate the mechanical specific energy for horizontal well fracturing segmentation clustering, thereby truly realizing the fracturing design while drilling, shortening the fracturing design time and improving the design efficiency. At the same time, the logging data of some development wells is incomplete, and the traditional logging curve method segmentation clustering data basis is insufficient. Combining mechanical specific energy makes the factors considered in segmentation clustering more comprehensive, and considers a variety of situations to correct the mechanical specific energy. Compared with the prior art, the present invention can reduce the risk of forming invalid and inefficient cracks based on the corrected mechanical specific energy, and can provide accurate guidance for the setting of the perforation position of the horizontal well segmentation clustering fracturing. Practice has proved that adjusting the perforation position with reference to the mechanical specific energy makes the fractures of each cluster develop evenly and maximizes the fracture transformation volume, thereby achieving the purpose of reducing costs and increasing efficiency.

[0114] In one embodiment, see Figure 5The present invention also provides a specific implementation of a horizontal well fracturing segmentation and clustering method based on mechanical specific energy, which specifically includes the following contents.

[0115] S1. Based on the mechanical specific energy method, the engineering sweet spot evaluation model is established by integrating the brittleness index, fracture toughness and horizontal principal stress difference;

[0116] The calculation formula of the corrected drilling pressure W in the mechanical specific energy formula is as follows:

[0117]

[0118] In the above formula: DGFH + hook load, N; qm = linear average weight of drill string in vertical well section, N / m; h = length of vertical well section, m; μ = friction coefficient of drill tool in casing section; ρ = radius of curvature, m; qi = linear average weight of drill string in deflection section, N / m; qh = linear average weight of drill string in horizontal section, N / m; f = friction coefficient of drill tool in open hole section.

[0119] The friction coefficient μ of the casing section drill tool is 0.12, and the friction coefficient f of the open hole section drill tool is 0.4.

[0120] S2. Construct a multi-source evaluation matrix, standardize the original data, establish a comprehensive evaluation model for dimensionality reduction of geological engineering sweet spots, use multi-source parameter dimensionality reduction to approximate the ideal solution, and establish a comprehensive evaluation model for continuous profiles of fracturability;

[0121] S3, using clustering method to segment, and then using Euclidean closeness to sort and select clusters within the segment, and complete the optimization calculation of perforation cluster setting;

[0122] Specifically, the mechanical specific energy is segmented to divide the well sections with similar fracturing difficulty into one section. First, the cluster efficiency within the section is guaranteed. Combined with the comprehensive compressibility index, positions with relatively large compressibility index are selected for perforation. At the same time, these positions correspond to positions with smaller mechanical specific energy. The compressibility index also reflects the oil and gas properties to a certain extent. The higher the compressibility index, the better the oil and gas properties. Combined with the mechanical specific energy, the cluster efficiency is guaranteed and the production effect after compression is guaranteed.

[0123] S4. Use the fracturing section, perforation cluster and reservoir type curve data to form segmentation and clustering results data.

[0124] Among them, the judgment matrix is ​​constructed by using the hierarchical analysis method for the main geological factors affecting artificial fractures, and the rock mechanical parameters, porosity, permeability, and hydrocarbon content are calculated based on logging data and mechanical specific energy. The difference coefficient method is used to calculate the weights of various factors such as mechanical specific energy, rock brittleness, GR, and formation stress, and the weights of various geological and engineering factors are clarified. Combined with the geological characteristics of the reservoir and engineering requirements, the calculation method of the compressibility index is established by using experiments and numerical simulation analysis. This index indicates whether the formation has the economic value of fracturing.

[0125] In addition, after step S4, the influence of reservoir anisotropy and seepage effect can be considered, and the tension / shear failure criterion can be combined to establish a fracture initiation-fracture network extension model that couples seepage and stress damage.

[0126] In addition, a method to improve the fracturing simulation speed and multi-dimensional parameter search accuracy under segmented multi-cluster fracturing can be established. According to the heterogeneity of the reservoir and geomechanical conditions, a database of cluster lengths, transformation volumes, and construction pressures under different displacement, cluster positions, pore sizes, pore densities, and cluster lengths is constructed. A Kriging proxy model of fracture length, transformation volume, and construction pressure is constructed to quickly perform multi-objective parallel optimization of fracture length, transformation volume, and construction pressure, so that each cluster of fractures develops evenly and the fracture transformation volume is maximized.

[0127] See also Figures 6 to 9 , from the front to the right in the figure, they reflect the K-Means clustering situation, the comprehensive compressibility index, the brittleness index and the mechanical specific energy.

[0128] K-Means clustering: Overall, the cluster identification of all horizontal sections is consistent and strong, indicating that there is no large heterogeneity in the formation, and there are certain differences between the 2750-2990 well section and the other well sections.

[0129] Comprehensive compressibility index: The change range of the entire horizontal section is not large, the changes in the 2750-2990m and 3140-3199m sections are large, and the compressibility index of 3240-3340 is relatively small.

[0130] Brittleness index: The change range of the whole horizontal section is not large, and the brittleness index is distributed in the range of 33-57. The brittleness of 2750-2990 meters changes greatly. The brittleness of 3090-3190 meters and 3240-3340 meters sections is relatively large. The brittleness index of most sections is more than 30.

[0131] Mechanical specific energy: The mechanical specific energy of 2750-2990 meters is relatively large, while that of other sections is relatively small.

[0132] See also Fig.10 Compared with the 2750-2990 meter section, the difference is that the mechanical specific energy of 2750-2990 is higher. In terms of crack initiation, we analyzed that 2750-2990 is more difficult to crack than 3240-3340.

[0133] Comprehensive compressibility index: The compressibility index of 3240-3340 is relatively small. The reason for the small mechanical specific energy is that the well section has good brittleness, but the oil and gas content is relatively low, so it is necessary to make a judgment based on the comprehensive compressibility index.

[0134] See also Fig.11 , Comprehensive compressibility index: the change range of the entire horizontal section is not large, while the change range of the 3140-3199 meter well section is relatively large.

[0135] See also Fig.12 , the mechanical specific energy compressibility index of the 3140-3199m section changes greatly. From the GR curve, we can see the reason for the large change in the lithology of this section. Overall, the whole section of the well has not changed much. These sections are only relatively changed sections. The mechanical specific energy of the first three sections is large, corresponding to a low compressibility index and difficult formation fracture. Relatively speaking, the section with small mechanical specific energy has a higher compressibility index.

[0136] See also Fig.13 , calculate the comprehensive compressible index, and on the basis of clustering and segmenting the mechanical specific energy, select the points with relatively high compressible index and low mechanical specific energy as the perforation positions. There are 27 sections in total, with 3-4 clusters in each section. The mechanical specific energy is used to segment the well sections with similar fracturing difficulty into one section. First, the cluster efficiency in the section is guaranteed. Combined with the comprehensive compressible index, perforation is performed at positions with relatively large compressible index. At the same time, these positions correspond to positions with smaller mechanical specific energy. The compressible index also reflects the oil and gas properties to a certain extent. The higher the compressible index, the better the oil and gas properties. Combined with the mechanical specific energy, the cluster efficiency is guaranteed and the production effect after fracturing is guaranteed.

[0137] See also Figures 14 to 16 Before considering the mechanical specific energy, 3351-3308, i.e. the black frame position, is divided into a fracturing section, and the perforation positions 1 and 3 of this section are both positions with relatively high mechanical specific energy. After considering the mechanical specific energy, we avoid positions 1 and 3.

[0138] From the above description, it can be seen that the horizontal well fracturing segmentation clustering method based on mechanical specific energy provided by an embodiment of the present invention includes: first, establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section; then, solving the engineering sweet spot model by using a clustering method to segment the target well section; finally, in the segmentation results, using the Euclidean proximity method to optimize clustering within each segment.

[0139] The present invention can reduce the risk of forming invalid and inefficient cracks based on the corrected mechanical specific energy, and can provide accurate guidance for the setting of perforation positions for staged and clustered fracturing in horizontal wells. Practice has proved that adjusting the perforation positions with reference to the mechanical specific energy allows each cluster of cracks to develop evenly and maximizes the fracture transformation volume, thereby achieving the purpose of reducing costs and increasing efficiency.

[0140] Based on the same inventive concept, the embodiments of the present application also provide a horizontal well fracturing segmentation clustering device based on mechanical specific energy, which can be used to implement the method described in the above embodiments, such as the following embodiments. Since the principle of solving the problem by the horizontal well fracturing segmentation clustering device based on mechanical specific energy is similar to the horizontal well fracturing segmentation clustering method based on mechanical specific energy, the implementation of the horizontal well fracturing segmentation clustering device based on mechanical specific energy can refer to the implementation of the horizontal well fracturing segmentation clustering method based on mechanical specific energy, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0141] The embodiment of the present invention first provides a specific implementation of a horizontal well fracturing segmentation clustering method based on mechanical specific energy, see Fig.17 The horizontal well fracturing segmentation and clustering device based on mechanical specific energy specifically includes the following contents:

[0142] A model building module 10 is used to build an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section;

[0143] A segmentation module 20, for solving the engineering sweet spot model by using a clustering method to segment the target well section;

[0144] The clustering module 30 is used to optimize clustering in each segment by using the Euclidean closeness method in the segmentation results.

[0145] In one embodiment, see Fig.18 The horizontal well fracturing segmentation and clustering device based on mechanical specific energy also includes:

[0146] The standardization module 40 is used to standardize the original data corresponding to the brittleness index, the fracture toughness index and the horizontal principal stress difference.

[0147] In one embodiment, see Fig.19 , the segmentation module 20 comprises:

[0148] The iteration operation unit 201 is used to perform the following iteration operation until the iteration stop condition is reached;

[0149] Randomly searching for multiple data as initial cluster centers among the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference;

[0150] Calculate the Euclidean distance between other data and these multiple cluster centers, and classify the data into the category with the closest Euclidean distance;

[0151] The arithmetic mean values ​​of the data in the plurality of clusters are respectively calculated as new cluster centers of the clusters.

[0152] In one embodiment, the iteration stopping condition includes: reaching a preset number of iterations and / or the new cluster center is the same as the previous cluster center.

[0153] In one embodiment, see Fig. 20 The horizontal well fracturing segmentation and clustering device based on mechanical specific energy also includes:

[0154] The achievement data forming module 50 is used to form segmentation and clustering achievement data according to the segmentation results, the clustering results in each segment and the corresponding reservoir type curve data.

[0155] From the above description, it can be seen that the horizontal well fracturing segmentation and clustering device based on mechanical specific energy provided by an embodiment of the present invention includes: first, establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section; then, solving the engineering sweet spot model by using a clustering method to segment the target well section; finally, in the segmentation results, using the Euclidean proximity method to optimize clustering within each section.

[0156] The beneficial effect of the present invention is that, compared with the prior art, the present invention can realize the use of mechanical specific energy as data already acquired during drilling, and directly use it in the horizontal well fracturing process to reduce the logging time. The logging data of some development wells is incomplete, and the traditional logging curve method for segmentation and clustering data is insufficient. The combination of mechanical specific energy is more comprehensive, and the mechanical specific energy is corrected in consideration of various situations. Compared with the prior art, the present invention can reduce the risk of forming invalid and inefficient cracks based on the corrected mechanical specific energy, and can provide precise guidance for the setting of cluster perforation schemes for staged fracturing of horizontal wells, adjust the perforation parameters, so that each cluster of cracks develops evenly and the fracture transformation volume is maximized, thereby achieving the purpose of reducing costs and increasing efficiency.

[0157] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps in the horizontal well fracturing segmentation clustering method based on mechanical specific energy in the above embodiments, see Fig.21 , electronic equipment specifically includes the following:

[0158] Processor (processor) 1201, memory (memory) 1202, communication interface (CommunicationsInterface) 1203 and bus 1204;

[0159] The processor 1201, the memory 1202, and the communication interface 1203 communicate with each other through the bus 1204; the communication interface 1203 is used to realize information transmission between the server device and the client device and other related devices;

[0160] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, all steps in the horizontal well fracturing segmentation and clustering method based on mechanical specific energy in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0161] Step 100: establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section;

[0162] Step 200: solving the engineering sweet spot model by using a clustering method to segment the target well section;

[0163] Step 300: In the segmentation results, the Euclidean closeness method is used to optimize clustering within each segment.

[0164] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the horizontal well hydraulic fracturing segmentation clustering method based on mechanical specific energy in the above embodiments. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps in the horizontal well hydraulic fracturing segmentation clustering method based on mechanical specific energy in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0165] Step 100: establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section;

[0166] Step 200: solving the engineering sweet spot model by using a clustering method to segment the target well section;

[0167] Step 300: In the segmentation results, the Euclidean closeness method is used to optimize clustering within each segment.

[0168] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0169] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0170] Although the present application provides method operation steps such as embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative labor. 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 actual device or client product is executed, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0171] For the convenience of description, the above devices are described in terms of functions and are divided into various modules. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0172] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0173] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0174] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0175] The present specification embodiments may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present specification embodiments may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0176] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, in the absence of contradiction, a person skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0177] The above are only examples of the embodiments of the present specification and are not intended to limit the embodiments of the present specification. For those skilled in the art, the embodiments of the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification shall be included in the scope of the claims of the embodiments of the present specification.

Claims

1. A horizontal well fracturing segmentation and clustering method based on mechanical specific energy, characterized in that: include: Establishing an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section; Solving the engineering sweet spot model by using a clustering method to segment the target well section; In the segmentation results, the Euclidean closeness method is used to select the optimal clusters within each segment; The method of solving the engineering sweet spot model by using a clustering method to segment the target well section includes: Perform the following iterative operations until the iteration stop condition is reached; Randomly searching for multiple data as initial cluster centers among the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference; Calculate the Euclidean distance between other data and these multiple cluster centers, and classify the data into the category with the closest Euclidean distance; The arithmetic mean values ​​of the data in the plurality of clusters are respectively calculated as new cluster centers of the clusters.

2. The horizontal well fracturing segmentation and clustering method according to claim 1, characterized in that: Before establishing the engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section, the method includes: The raw data corresponding to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference are standardized.

3. The horizontal well fracturing segmentation and clustering method according to claim 1, characterized in that: The iteration stopping condition includes: reaching a preset number of iterations and / or the new cluster center is the same as the previous cluster center.

4. The horizontal well fracturing segmentation and clustering method according to claim 1, characterized in that: Also includes: According to the segmentation results, the clustering results in each segment and the corresponding reservoir type curve data, segmentation and clustering result data are formed.

5. A horizontal well fracturing segmentation and clustering device based on mechanical specific energy, characterized in that: include: A model building module, used to build an engineering sweet spot model of the target well section according to the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference of the target well section; A segmentation module, used for solving the engineering sweet spot model by clustering method to segment the target well section; A clustering module is used to select the optimal clusters in each segment using the Euclidean closeness method in the segmentation results; The segmentation module comprises: An iterative operation unit, used to perform the following iterative operations until an iteration stop condition is reached; Randomly searching for multiple data as initial cluster centers among the mechanical specific energy, brittleness index, fracture toughness index and horizontal principal stress difference; Calculate the Euclidean distance between other data and these multiple cluster centers, and classify the data into the category with the closest Euclidean distance; The arithmetic mean values ​​of the data in the plurality of clusters are respectively calculated as new cluster centers of the clusters.

6. The horizontal well fracturing segmentation and clustering device according to claim 5, characterized in that: Also includes: The standardization module is used to standardize the raw data corresponding to the brittleness index, fracture toughness index and horizontal principal stress difference.

7. The horizontal well fracturing segmentation and clustering device according to claim 5, characterized in that: The iteration stopping condition includes: reaching a preset number of iterations and / or the new cluster center is the same as the previous cluster center.

8. The horizontal well fracturing segmentation and clustering device according to claim 5, characterized in that: Also includes: The result data forming module is used to form segmentation and clustering result data according to the segmentation result, the clustering result in each segment and the corresponding reservoir type curve data.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the method for horizontal well fracturing segmentation and clustering based on mechanical specific energy as described in any one of claims 1 to 4 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the horizontal well fracturing segmentation and clustering method based on mechanical specific energy as described in any one of claims 1 to 4 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the horizontal well fracturing segmentation and clustering method based on mechanical specific energy described in any one of claims 1 to 4 are implemented.

Images