A segmented clustering method and device for oil wells, a computer device and a storage medium

Abstract

The present specification relates to the field of well logging technology, and particularly relates to a segmented and clustered method and device for oil wells, a computer device and a storage medium. The segmented and clustered method for oil wells comprises: processing each well logging data set in a plurality of well logging data sets of a to-be-processed oil well by using a plurality of target weights corresponding to a plurality of index factors to determine target data corresponding to each well logging data set; clustering the plurality of target data to determine at least one target data set; taking, as a segmented target data set, each target data set that meets a preset condition in the at least one target data set; and taking a scale section formed by scale values associated with each well logging data set in the segmented target data set as a fracturing section, and taking the plurality of scale values as fracturing clusters. By performing weighted calculation and clustering on the plurality of well logging data sets, the accuracy of segmentation and clustering is improved by using the embodiments of the present specification.

Description

Technical Field

[0001] This specification relates to the field of well logging technology, and in particular to a method, apparatus, computer equipment and storage medium for segmenting and clustering oil wells. Background Technology

[0002] Segmentation and clustering are crucial steps in oil well fracturing operations. Currently, determining the fracturing segments and clusters for oil wells often involves constraining the segmentation and clustering based on reservoir type, average segment length, number of segments, number of perforation clusters, and casing collar position to obtain the optimal fracturing segments and clusters. However, this segmentation and clustering process only considers the influence of the oil well's reservoir type and casing collar position on segmentation and clustering, resulting in low accuracy when applied to actual operating conditions, leading to less than ideal oil production.

[0003] How to obtain a highly accurate segmentation and clustering scheme based on well logging data is a problem that urgently needs to be solved in the current technology. Summary of the Invention

[0004] To address the problems in the prior art, embodiments of this specification provide a method, apparatus, computer equipment, and storage medium for segmenting and clustering oil wells, which performs weighted calculations and clustering on multiple logging data sets, thereby improving the accuracy of segmentation and clustering.

[0005] To solve the above-mentioned technical problems, the specific technical solution in this specification is as follows:

[0006] On the one hand, the embodiments of this specification provide a method for segmenting and clustering oil wells, including,

[0007] By utilizing multiple target weights corresponding to multiple indicator factors, each well logging data set in multiple well logging data sets of the oil well to be processed is processed to determine the target data corresponding to each well logging data set, thereby obtaining multiple target data;

[0008] Cluster the multiple target data sets to determine at least one target data set;

[0009] For each of the at least one target data set, the target data sets that meet preset conditions are divided into segmented target data sets; and

[0010] The scale segment formed by the scale value associated with each well logging data set in the segmented target data set is taken as the fracturing segment, and the scale value associated with each well logging data set in the segmented target data set is taken as the fracturing cluster.

[0011] Furthermore, the method for determining the target weight further includes,

[0012] Based on historical data from multiple target oil wells, several key indicators were determined.

[0013] From the historical data, select multiple sub-historical data that are associated with the fractured section or fractured cluster;

[0014] Based on the number of sub-historical data points and the numerical values ​​corresponding to each indicator factor, determine the pre-target weight for each indicator factor; and

[0015] Normalize the weights for each pre-target to determine multiple target weights.

[0016] Furthermore, based on historical data from multiple oil wells, several key indicators were identified, including:

[0017] Based on historical data from multiple oil wells, several first-level pre-indicator factors corresponding to asynchronous fracturing, several second-level pre-indicator factors corresponding to non-uniform fluid ingress, and several third-level pre-indicator factors corresponding to the production profile were identified; and

[0018] Multiple pre-indicator factors that exist in all of the multiple first pre-indicator factors, the multiple second pre-indicator factors, and the multiple third pre-indicator factors are identified as multiple indicator factors.

[0019] Furthermore, determining the pre-target weight corresponding to each indicator factor based on the number of the multiple sub-historical data and the numerical value corresponding to each indicator factor further includes,

[0020] Based on the multiple sub-historical data and the numerical values ​​corresponding to each indicator factor, at least one target indicator factor corresponding to each sub-historical data is determined;

[0021] For the multiple sub-historical data, determine the first number of each target indicator factor, resulting in multiple first numbers; and

[0022] Based on the first number and the number of the plurality of sub-historical data, determine the pre-target weight corresponding to each indicator factor.

[0023] Furthermore, these multiple indicators include gas measurement values, compensated neutron values, brittleness index, and minimum horizontal principal stress.

[0024] Furthermore, the preset conditions further include that the difference between any two target data in the target data set is less than a first preset threshold, the difference between the scale values ​​associated with any two target data is greater than or equal to a second preset threshold and less than or equal to a third preset threshold, and the number of target data in the target set is less than or equal to a fourth preset threshold.

[0025] Furthermore, the clustering of the multiple target data to determine at least one target data set further includes,

[0026] Obtain multiple initial data;

[0027] For each target data point among the plurality of target data points, the difference between the target data point and each initial data point is determined, resulting in a plurality of differences;

[0028] Based on the target initial data corresponding to the minimum difference among multiple differences for each target data, at least one pre-target data set is determined; and

[0029] Based on the optimization function, the multiple initial data are updated, the steps of obtaining multiple initial data are returned, and finally at least one target data set is obtained.

[0030] On the other hand, embodiments of this specification also provide a segmentation and clustering device for oil wells, including,

[0031] The processing unit is used to process each logging data set in multiple logging numerical control sets of the oil well to be processed by using multiple target weights corresponding to multiple index factors, to determine the target data corresponding to each logging data set, and to obtain multiple target data.

[0032] Clustering unit, used to cluster the multiple target data to determine at least one target data set;

[0033] The first determining unit is used to, for each of the at least one target data set, divide the target data sets that meet the preset conditions into segmented target data sets;

[0034] The second determining unit is used to take the scale segment formed by the scale value associated with each well logging data set in the segmented target data set as the fracturing segment, and to take the scale value associated with each well logging data set in the segmented target data set as the fracturing cluster.

[0035] On the other hand, embodiments of this specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0036] On the other hand, embodiments of this specification also provide a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-described method.

[0037] Using the embodiments in this specification, historical data from multiple target oil wells are analyzed to determine multiple indicator factors characterizing the segmentation and clustering effect, and the degree of influence of each indicator factor on the segmentation and clustering effect (target weight). After receiving multiple logging data sets from the oil wells to be processed, multiple indicator factors and target weights are used to perform weighted calculations on each of the multiple logging data sets to obtain target data corresponding to each logging data set. Then, the target data is clustered and judged to determine the segmented target data sets. Finally, based on the scale value corresponding to each logging data set in the segmented target data set, the fracturing segment and fracturing cluster are determined. By using historical data from multiple target oil wells to determine multiple indicator factors and target weights, and then using these multiple indicator factors and target weights to perform weighted calculations and clustering on multiple logging data sets to determine the segmentation and clustering scheme, the accuracy of segmentation and clustering is improved. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 The figure shown is a schematic diagram of the implementation system of a segmentation and clustering method for oil wells according to an embodiment of this specification;

[0040] Figure 2 The diagram shown is a flowchart of a segmentation and clustering method for an oil well according to an embodiment of this specification;

[0041] Figure 3 The diagram shown is a flowchart of another embodiment of a segmentation and clustering method for an oil well in this specification;

[0042] Figure 4 The diagram shown is a schematic diagram of a segmentation and clustering method for an oil well according to an embodiment of this specification.

[0043] Figure 5A The diagram shown is a flowchart of another embodiment of a segmentation and clustering method for an oil well in this specification;

[0044] Figure 5B The diagram shown is a schematic diagram of a historical data analysis embodiment of this specification.

[0045] Figure 5C The diagram shown is a schematic diagram of the principle of analyzing the influencing factors of asynchronous crack initiation according to an embodiment of this specification;

[0046] Figure 5DThe diagram shown is a schematic diagram of the principle of analyzing the influencing factors of non-uniform liquid inlet in an embodiment of this specification.

[0047] Figure 5E The diagram shown is a schematic diagram of a filtering principle according to an embodiment of this specification;

[0048] Figure 5F The diagram shown is a schematic diagram of a normalization method according to an embodiment of this specification.

[0049] Figure 5G The diagram shown is a schematic diagram of a segmentation and clustering scheme according to an embodiment of this specification;

[0050] Figure 5H The diagram shown is a parameter diagram of a segmentation and clustering scheme according to an embodiment of this specification;

[0051] Figure 6 The diagram shown is a structural schematic of a segmented clustering device for an oil well according to an embodiment of this specification.

[0052] Figure 7 This is a schematic diagram of the structure of a computer device according to an embodiment of this specification.

[0053] [Explanation of Labels in the Attached Image]

[0054] 101. User terminal;

[0055] 102. Server;

[0056] 400. Oil well;

[0057] 401, First Depth;

[0058] 402, Second Depth;

[0059] 403, Third Depth;

[0060] 404, Fourth Depth;

[0061] 405, Fifth Depth;

[0062] 406, Sixth Depth;

[0063] 501. Historical Data;

[0064] 502. Multiple indicator factors;

[0065] 503. Multiple sub-historical data;

[0066] 504. Multiple target weights;

[0067] 511. Multiple sets of raw well logging data;

[0068] 512. Multiple well logging datasets;

[0069] 513. Multiple target data;

[0070] 514. At least one target dataset;

[0071] 515. At least one segmented target data set;

[0072] 516. At least one fracturing section and multiple fracturing clusters;

[0073] 610. Processing Unit;

[0074] 620. Clustering unit;

[0075] 630. First Determined Unit;

[0076] 640. Second Determined Unit;

[0077] 702. Computer equipment;

[0078] 704. Processing equipment;

[0079] 706. Storage resources;

[0080] 708. Drive mechanism;

[0081] 710. Input / Output Module;

[0082] 712. Input devices;

[0083] 714. Output devices;

[0084] 716. Presentation equipment;

[0085] 718. Graphical User Interface;

[0086] 720. Network interface;

[0087] 722. Communication link;

[0088] 724. Communication bus. Detailed Implementation

[0089] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0090] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0091] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0092] like Figure 1 The diagram illustrates an implementation system for a well logging signal demodulation method according to an embodiment of this specification. The system may include a user terminal 101 and a server 102. The user terminal 101 and server 102 communicate via a network, which may include a Local Area Network (LAN), a Wide Area Network (WAN), the Internet, or a combination thereof, and is connected to a website, user equipment (e.g., a computing device), and a backend system. The server 102 can determine at least one fracturing segment and multiple fracturing clusters based on multiple well logging data sets obtained from the user terminal 101. Then, it sends these at least one fracturing segment and multiple fracturing clusters to the user terminal 101 via the network. The user terminal 101 displays the at least one fracturing segment and multiple fracturing clusters provided by the server 102, allowing the user corresponding to the user terminal 101 to view them on the user terminal 101. Optionally, the server 102 may be a node in a cloud computing system (not shown in the diagram), or each server 102 may be a separate cloud computing system, including multiple computers interconnected by a network and operating as a distributed processing system.

[0093] In one optional embodiment, the user terminal 101 is not limited to electronic devices such as smartphones, data acquisition devices, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. Optionally, the operating system running on the electronic device may include, but is not limited to, Android, iOS, Linux, and Windows.

[0094] In addition, it should be noted that, Figure 1 The example shown is merely one application environment provided in this manual. In actual applications, it may include multiple user terminals 101, and this manual does not impose any restrictions.

[0095] like Figure 2 The diagram shows a flowchart of a segmentation and clustering method for an oil well according to an embodiment of this specification. This diagram illustrates the segmentation and clustering process of an oil well, but based on conventional or non-inventive labor, it may include more or fewer operational steps. The order of steps listed in the embodiment is merely one possible execution order among many and does not represent the only possible execution order. In actual system or device products, the methods shown in the embodiment or the accompanying drawings can be executed sequentially or in parallel. Specifically, as shown... Figure 2 As shown, the method may include:

[0096] S210, using multiple target weights corresponding to multiple indicator factors, processes each well logging data set in multiple well logging data sets of the oil well to be processed, determines the target data corresponding to each well logging data set, and obtains multiple target data;

[0097] S220, clustering multiple target data to determine at least one target data set;

[0098] S230, for each target data set in at least one target data set, the target data sets that meet the preset conditions are divided into segmented target data sets;

[0099] S240, the scale segment formed by the scale value associated with each well logging data set in the segmented target data set is taken as the fracturing segment, and the scale value associated with each well logging data set in the segmented target data set is taken as the fracturing cluster.

[0100] After receiving multiple logging data sets from the wells to be processed, the system uses multiple indicator factors and target weights to perform weighted calculations on each set, obtaining target data corresponding to each set. This target data is then clustered and judged to determine segmented target data sets. Finally, based on the scale values ​​corresponding to each logging data set within each segmented target data set, the fracturing sections and clusters are determined. By using multiple indicator factors and target weights to perform weighted calculations and clustering on multiple logging data sets to determine the segmentation and clustering scheme, the accuracy of segmentation and clustering is improved.

[0101] According to embodiments of this specification, multiple index factors are the main factors affecting the oil production effect of wells after segmentation and clustering. Specifically, these multiple index factors may include, for example, at least one of multiple first main factors affecting asynchronous fracture initiation within a segment, multiple second main factors affecting non-uniform fluid ingress within a segment, and multiple third main factors affecting the production profile of multiple fractures within a segment. The multiple index factors may also include, for example, a target main factor that exists in all of the multiple first main factors, multiple second main factors, and multiple third main factors.

[0102] Each target weight indicates the degree of influence of the index factor on the oil production effect of the well after segmentation and clustering. For example, multiple index factors include the brittleness index and the minimum horizontal principal stress. The target weight corresponding to the brittleness index is 0.4, and the target weight corresponding to the minimum horizontal principal stress is 0.6. This indicates that the brittleness index and the minimum horizontal principal stress affect the oil production effect of the well after segmentation and clustering, and the degree of influence of the brittleness index on the oil production effect of the well after segmentation and clustering is 0.4, while the degree of influence of the minimum horizontal principal stress on the oil production effect of the well after segmentation and clustering is 0.6.

[0103] Multiple indicator factors constitute an indicator factor set. Each indicator factor set can be associated with a corresponding region, for example. Each indicator factor set can also be associated with corresponding geological conditions or crude oil type, for example.

[0104] A well logging dataset can be, for example, the raw well logging data obtained downhole using well logging instruments. Alternatively, it can be a dataset consisting of processed data obtained after preprocessing the raw well logging data obtained downhole. This well logging dataset can also be determined based on multiple indicator factors. For example, after determining multiple indicator factors, for each indicator factor, it is determined whether the indicator factor is raw well logging data directly obtained using well logging instruments. If it is determined that the indicator factor is not raw well logging data directly obtained using well logging instruments, the processing rule corresponding to the indicator factor and the corresponding raw well logging data are obtained. The processing rule is then used to process the raw well logging data to obtain the data corresponding to the indicator factor. If it is determined that the indicator factor is raw well logging data directly obtained using well logging instruments, the raw well logging data is determined to be the data corresponding to the indicator factor.

[0105] Each logging dataset is associated with a corresponding scale value. For example, if the well depth is 8 meters, the resulting dataset is A. A is then identified as the logging dataset, and this logging dataset is associated with the scale value 8.

[0106] When determining the segmentation and clustering scheme, multiple logging data sets of the oil wells to be processed are obtained. Based on the oil well information of the oil wells to be processed, a corresponding set of indicator factors is determined, which includes multiple indicator factors. Oil well information may include, for example, the location region of the oil well, the geological conditions of the oil well, or the type of crude oil produced by the oil well. By using multiple indicator factors and multiple target weights obtained from the analysis of target oil wells similar to the oil wells to be processed, the accuracy of the determined indicator factors and target weights is improved, thereby improving the accuracy of segmentation and clustering.

[0107] Using multiple target weights corresponding to various indicator factors, each well logging dataset from multiple well logging datasets of the well to be treated is processed to determine the target data corresponding to each dataset. This process can be, for example, by using the target weights to perform a weighted calculation on each data point in the well logging dataset to obtain a target data point corresponding to that dataset. For instance, if the multiple indicator factors are brittleness index and minimum horizontal principal stress, with target weights of 0.4 and 0.6 respectively, and the brittleness index in the well logging dataset corresponding to scale value 8 is 36 and the minimum horizontal stress is 21, then the processing would be to calculate 36 × 0.4 + 21 × 0.6 to determine the target data point corresponding to that well logging dataset or scale value 8 as 27. Similarly, the well logging datasets corresponding to each scale value of the well to be treated are processed to determine the target data point corresponding to each well logging dataset or scale value.

[0108] After identifying multiple target data points, a clustering algorithm is used to process these data points, determining at least one cluster, and each cluster is then used as a set of target data. This clustering algorithm can be, for example, any algorithm that clusters multiple datasets.

[0109] For each identified target data set, an evaluation is performed to determine whether it meets preset conditions. If the target data set meets the preset conditions, it is determined to be a segmented target data set. If the target data set does not meet the preset conditions, the scale value corresponding to that target data set is not considered as a fracturing segment or fracturing cluster.

[0110] For each segment of the target data set, determine the scale value corresponding to each target data point within that segment. For each segment, based on multiple scale values, determine the scale segment corresponding to that segment, designating it as the fracturing segment, and each scale value as a fracturing cluster. For example, if the segmented target data set includes target data m, n, and o, and the scale values ​​corresponding to m, n, and o are 56, 71, and 86, then the fracturing segment is determined to be 56-86, and the fracturing clusters are 56, 71, and 86, respectively.

[0111] According to another embodiment of this specification, multiple index factors may include, for example, gas measurement values, compensated neutron values, brittleness index, and minimum horizontal principal stress.

[0112] According to another embodiment of this specification, clustering multiple target data to determine at least one target data set may include, for example,: acquiring multiple initial data; for each target data in the multiple target data, determining the difference between the target data and each initial data to obtain multiple differences; determining at least one pre-target data set based on the target initial data corresponding to the minimum difference among the multiple differences for each target data; and updating the multiple initial data according to an optimization function, returning to the step of acquiring multiple initial data, and finally obtaining at least one target data set.

[0113] The initial data can be randomly set, or it can be determined after pre-clustering multiple target data. For each target data, the difference between the target data and each initial data is calculated, resulting in multiple differences corresponding to each target data. For each target data, the minimum difference among the multiple differences corresponding to that target data is determined, and the initial data corresponding to that minimum difference is determined, and the target data and the initial data are grouped into the same class. Similarly, each target data is processed to determine at least one pre-target data set. The corresponding optimization function is obtained and processed on the multiple differences and the initial data to obtain second data, which is then used to update the initial data. The above steps are repeated using the second data as the initial data until the conditions in the optimization function are met. Then, multiple classes that meet the conditions are output, and all of these classes are used as the target data set.

[0114] The optimization function could be, for example, a silhouette coefficient function. The conditions could be, for example, that the sequence of silhouette coefficients generated by multiple iterations converges, or that the silhouette coefficients satisfy a preset threshold.

[0115] Figure 3 The diagram shown is a flowchart of another embodiment of a segmentation and clustering method for oil wells in this specification. Specifically, as follows... Figure 3 As shown, the method may include:

[0116] S310 determines multiple indicator factors based on historical data from multiple target oil wells;

[0117] S320, in the historical data, select multiple sub-historical data related to the fractured section or fractured cluster;

[0118] S330, based on the number of multiple historical data and the value corresponding to each indicator factor, determine the pre-target weight corresponding to each indicator factor;

[0119] S340 normalizes each pre-target weight to determine multiple target weights.

[0120] The method described in this specification analyzes historical data from multiple target oil wells to determine multiple index factors characterizing the segmentation and clustering effect, and the degree of influence of each index factor on the segmentation and clustering effect (target weight). This weight is used to perform weighted processing on the logging data set of the oil wells to be processed, thereby determining the segmentation and clustering scheme and improving the accuracy of segmentation and clustering.

[0121] According to another embodiment of this specification, the target oil well may be, for example, a well that has been segmented, clustered, and fractured. The target oil well may also be, for example, a segmented, clustered, and fractured oil well that meets the well selection criteria. These well selection criteria may include, for example, the same or similar region, the same or similar geological conditions, or the same or similar crude oil type. Thus, by analyzing historical data from similar oil wells for different categories of oil wells, the accuracy of the determined indicator factors and target weights is improved, thereby enhancing the accuracy of segmentation and clustering.

[0122] After identifying the target oil well, historical data for that well is acquired. This historical data includes historical logging datasets and historical fiber optic datasets. Historical logging data may include, for example, in-situ stress, Young's modulus, Poisson's ratio, and brittleness index. Historical fiber optic data may include, for example, real-time acoustic and temperature data acquired during oil production.

[0123] The historical data of the target oil well is processed to identify the main factors affecting the oil production effect after segmentation and clustering, and these main factors are used as indicator factors. Processing the historical data of the target oil well may include, for example, analyzing acoustic and temperature data from the fiber optic dataset, using the fact that fracture fluid injection is proportional to the acoustic and temperature signal intensity to inversely calculate the variation data of oil and gas flow rates in different downhole fracturing clusters. For each fracturing cluster, based on the oil and gas flow rate variation data and the logging dataset, the correlation between the fluid injection rate of each fracturing cluster and each logging data point is determined. Furthermore, for each fracturing cluster, at least one target correlation is determined from multiple correlations, resulting in at least one target correlation set corresponding to each fracturing cluster. Based on multiple fracturing clusters and multiple target correlation sets, multiple indicator correlations are determined, and the logging data indicators corresponding to the indicator correlations are used as indicator factors. The number of at least one target correlation can be related to a set indicator threshold, for example, if the indicator threshold is 3, then multiple correlations are sorted from largest to smallest, and the top three correlations are determined as target correlations. The relevance of an indicator can be, for example, the relevance included in the union of multiple sets of relevance to the target, or the relevance included in the intersection of multiple sets of relevance to the target.

[0124] In historical data, based on the scale values ​​of fractured segments and clusters, multiple sub-historical data points associated with the fractured segments or clusters are identified. The number of these sub-historical data points is determined using the scale values ​​as a dimension. The numerical value corresponding to each indicator factor is obtained from each sub-historical data point. Based on the oil and gas flow rate variation data corresponding to each sub-historical data point and the data corresponding to the multiple indicator factors, at least one target indicator factor is identified from these multiple indicator factors. This target indicator factor is the indicator factor that has a significant impact on the oil and gas flow rate variation data. Therefore, each sub-historical data point is associated with at least one target indicator factor.

[0125] For multiple sub-historical data sets, the number of factors for each target indicator is counted. Based on the number of factors for each target indicator and the data from the sub-historical data sets, the pre-target weight corresponding to each indicator factor is determined. After determining the pre-target weights, these multiple pre-target weights are normalized to obtain multiple target weights.

[0126] According to another embodiment of this specification, determining multiple index factors based on historical data from multiple oil wells may include, for example, determining multiple first pre-index factors corresponding to asynchronous fracturing, multiple second pre-index factors corresponding to non-uniform fluid ingress, and multiple third pre-index factors corresponding to production profiles based on historical data from multiple oil wells; and determining multiple pre-index factors that exist in all of the multiple first, multiple second, and multiple third pre-index factors as multiple index factors.

[0127] When determining the pre-indicator factors corresponding to asynchronous fracturing, non-uniform fluid ingress, and production profiles, the analysis was conducted for each corresponding stage. For example, in the fracturing initiation stage, the influencing factors were determined based on the historical data set and the corresponding fiber optic data set, using the change in fracturing cluster oil and gas flow rate as the metric; in the fluid ingress stage, the influencing factors were determined based on the historical data set and the corresponding fiber optic data set, using the change in fracturing cluster oil and gas flow rate as the metric; and in the production profile stage, the influencing factors were determined based on the historical data set and the corresponding fiber optic data set, using the change in fracturing cluster oil and gas flow rate as the metric.

[0128] After determining the set of pre-indicator factors for each stage, the intersection of multiple pre-indicator factor sets is determined as the indicator factor. This set of pre-indicator factor factors includes multiple pre-indicator factors.

[0129] Historical logging data and historical fiber optic data were used to analyze the segmentation and clustering schemes of historical oil wells. Compared with the current method of analyzing the segmentation and clustering schemes of historical oil wells based solely on logging data, the identified index factors are more accurate.

[0130] According to another embodiment of this specification, determining the pre-target weight corresponding to each indicator factor based on the number of multiple sub-historical data and the value corresponding to each indicator factor includes: determining at least one target indicator factor corresponding to each sub-historical data based on the multiple sub-historical data and the value corresponding to each indicator factor; determining a first number for each target indicator factor for the multiple sub-historical data to obtain multiple first numbers; and determining the pre-target weight corresponding to each indicator factor based on the first number and the number of multiple sub-historical data.

[0131] For each sub-historical data point, based on the corresponding value of each indicator factor, determine the degree of influence of that indicator factor on the fracturing oil production effect, and based on this degree of influence, determine at least one target indicator factor. This degree of influence can be, for example, relatively large, large, medium, or small. The indicator factor with the largest degree of influence is selected as the target indicator factor.

[0132] For multiple sub-historical data points, calculate the first number corresponding to each target indicator factor. For each target indicator factor, determine the quotient between the first number and the number of sub-historical data points. The pre-target weight can be this quotient, or it can be an integer multiple of this quotient.

[0133] For example, given 100 sub-historical data points, if the target indicator factor S is associated with 20 sub-historical data points, then the first number corresponding to the target indicator factor S is determined to be 20, and the total number of sub-historical data points is 100. The pre-target weight corresponding to the indicator factor S can be either 0.2 or 2.

[0134] According to another embodiment of this specification, the pre-target weights may include, for example, gas measurement values, compensated neutron values, brittleness index, and minimum horizontal principal stress, with corresponding pre-target weights of 2, 3, 4, and 4, respectively.

[0135] According to another embodiment of this specification, the target weights may include, for example, the target weights for multiple index factors such as gas measurement values, compensated neutron values, brittleness index, and minimum horizontal principal stress, with corresponding target weights of 0.15, 0.23, 0.31, and 0.31, respectively.

[0136] Figure 4 The diagram shown is a schematic diagram of a segmentation and clustering method for oil wells according to an embodiment of this specification.

[0137] According to another embodiment of this specification, the preset conditions may be, for example, that the difference between any two target data in the target data set is less than a first preset threshold, the difference between the scale values ​​associated with any two target data is greater than or equal to a second preset threshold and less than or equal to a third preset threshold, and the number of target data in the target set is less than or equal to a fourth preset threshold.

[0138] The first preset threshold can be, for example, 1; the second preset threshold can be, for example, 15 or 25; the third preset threshold can be, for example, 35; and the fourth preset threshold can be, for example, 6, to improve the oil production effect of the fracturing section and fracturing cluster.

[0139] For well 400, weighted calculations and clustering were performed on the logging data sets at the first depth (401), second depth (402), third depth (403), fourth depth (404), fifth depth (405), and sixth depth (406) to determine two target data sets. One target data set includes target data corresponding to the first depth (401), second depth (402), third depth (403), and sixth depth (406). The other target data set includes target data corresponding to the fourth depth (404) and fifth depth (405).

[0140] For a target dataset comprising four target data points, the differences between all target data points are determined to be less than 1. Specifically, the differences D1 between the first depth (401) and the second depth (402) are 16; the differences D2 between the second depth (402) and the third depth (403) are 16; the differences D3 between the first depth (401) and the third depth (403) are 32; the differences D4 between the first depth (401) and the sixth depth (406) are 89; the differences D5 between the second depth (402) and the sixth depth (406) are 73; and the differences D6 between the third depth (403) and the sixth depth (406) are 67. Since the differences between the first depth (401), the second depth (402), the third depth (403), and the sixth depth (406) do not satisfy the second and third thresholds, the corresponding scale values ​​for this target dataset are not considered as fracturing segments or fracturing clusters.

[0141] Similarly, another target data set is evaluated. It is determined that this target data set includes two target data points, the difference between the target data points is less than 1, and the difference D7 between the fourth depth (404) and the fifth depth (405) is 28. Therefore, this other target data set meets the preset conditions and is determined to be a segmented target data set. The section from the fourth depth (404) to the fifth depth (405) is designated as the fracturing segment, and the fourth depth (404) and the fifth depth (405) are designated as fracturing clusters.

[0142] It should be noted that in this embodiment, the Nth depth of the scale value can be any depth, and N can be any integer greater than zero. The six scale values ​​in the above example are for illustration only and do not constitute an actual limitation.

[0143] Figure 5A The diagram shown is a flowchart of another embodiment of a segmentation and clustering method for an oil well in this specification. Figure 5B The diagram shown is a schematic diagram of a historical data analysis embodiment of this specification. Figure 5C The diagram shown is a schematic diagram of the principle of analyzing the influencing factors of asynchronous crack initiation in an embodiment of this specification. Figure 5DThe diagram shown is a schematic diagram of the principle of analyzing the influencing factors of non-uniform liquid inlet in an embodiment of this specification. Figure 5E The diagram shown is a schematic diagram of a filtering principle according to an embodiment of this specification. Figure 5E In the graph, the graph corresponding to the QL value (gas measurement value) is a graph of the series corresponding to the gas measurement value of the index factor; the graph corresponding to the CNL value (compensated neutron value) is a graph of the series corresponding to the compensated neutron value of the index factor; the graph corresponding to the BRIT value (brittleness index) is a graph of the series corresponding to the brittleness index of the index factor; and the graph corresponding to the SH value (minimum horizontal principal stress) is a graph of the series corresponding to the minimum horizontal principal stress of the index factor. Figure 5F The diagram shown is a schematic diagram of a normalization method according to an embodiment of this specification. Figure 5G The diagram shown is a schematic diagram of a segmentation and clustering scheme according to an embodiment of this specification. Figure 5H The diagram shown is a parameter diagram of a segmentation and clustering scheme according to an embodiment of this specification.

[0144] According to another embodiment of this specification, the historical logging data set and historical fiber optic data set in the historical data 501 of the target oil well are analyzed. Based on the acoustic and temperature data in the historical fiber optic data set, the variation data of oil and gas flow rates of different fracturing clusters in the well are calculated by inversion, and plotted as follows. Figure 5B The diagram shown illustrates the principle of historical data analysis (a comprehensive comparison of well logging data and fiber optic monitoring results). Based on this diagram, multiple indicator factors 502 are identified. Specifically, the following diagram is drawn... Figure 5C and Figure 5D A schematic diagram was drawn to analyze the influencing factors of asynchronous crack initiation and non-uniform liquid inlet. Similarly, a schematic diagram was drawn to analyze the influencing factors of the production profile. Based on the multiple schematic diagrams, multiple index factors 502 were determined.

[0145] From historical data 501, identify multiple sub-historical data 503 associated with the fractured segments or fractured clusters. Based on the multiple sub-historical data 503 and multiple indicator factors 502, determine multiple target weights 504 corresponding to the multiple indicator factors 502.

[0146] When determining a segmentation and clustering scheme for a well to be processed, multiple sets of original logging data 511 corresponding to that well are obtained. These sets of original logging data can be, for example, data acquired by logging instruments. Due to the influence of complex downhole formations and human error during logging, data preprocessing is necessary to eliminate interference and errors from non-formation information as much as possible, thereby providing reliable basic data for well segmentation and ensuring the accuracy and effectiveness of clustering results. Therefore, preprocessing is performed on these multiple sets of original logging data 511 to obtain multiple sets of logging data 512. Preprocessing can be, for example, filtering and normalizing the data set corresponding to each index factor. For instance, for the multiple sets of original logging data 511, the brittleness index associated with each scale value is extracted to obtain a brittleness index series. Median filtering is then applied to this brittleness index series to eliminate spike interference and effectively suppress noise. Similarly, filtering is performed on the series corresponding to each index factor to obtain... Figure 5E The diagram illustrates the filtering principle. Because the physical meanings of each indicator factor are different and the data dimensions are inconsistent, comparison and comprehensive calculations are inconvenient, making it difficult to obtain correct conclusions. Therefore, the maximum-minimum normalization method is used to normalize the median-filtered sequences corresponding to each indicator factor (e.g., ...). Figure 5F (The normalization principle diagram shown) is used to obtain multiple well logging data sets 512.

[0147] After determining multiple logging data sets 512, multiple index factors 502 and multiple target weights 504 associated with the well to be processed are determined. The multiple target weights 504 are used to perform weighted calculations on the multiple logging data sets 512 to determine the target data corresponding to each logging data set, resulting in multiple target data sets 513. Clustering is performed on the multiple target data sets 513 to obtain at least one target data set 514. For each target data set in the at least one target data set 514, a judgment is made. If the target data set meets preset conditions, it is determined to be a segmented target data set, resulting in at least one segmented target data set 515. Finally, at least one fracturing segment and multiple fracturing clusters 516 are determined based on the at least one segmented target data set 515. Based on the at least one fracturing segment and multiple fracturing clusters 516, a segmentation and clustering scheme is determined. The principle diagram of this segmentation and clustering scheme can be illustrated as follows: Figure 5G As shown, and a schematic diagram of the parameters of this segmentation and clustering scheme, for example, can be seen as follows: Figure 5H As shown.

[0148] Figure 6 The diagram shown is a structural schematic of a segmented clustering device for an oil well, according to an embodiment of this specification. Figure 6 As shown, including,

[0149] The processing unit 610 is used to process each logging data set in multiple logging numerical control sets of the oil well to be processed by using multiple target weights corresponding to multiple index factors, to determine the target data corresponding to each logging data set, and to obtain multiple target data.

[0150] Clustering unit 620 is used to cluster multiple target data to determine at least one target data set;

[0151] The first determining unit 630 is used to divide the target data sets that meet preset conditions into segmented target data sets for each target data set in at least one target data set;

[0152] The second determining unit 640 is used to take the scale segment formed by the scale value associated with each well logging data set in the segmented target data set as the fracturing segment, and to take the scale value associated with each well logging data set in the segmented target data set as the fracturing cluster.

[0153] Since the principle of the above-mentioned device in solving the problem is similar to that of the above-mentioned method, the implementation of the above-mentioned device can refer to the implementation of the above-mentioned method, and the repeated parts will not be described again.

[0154] like Figure 7 The diagram illustrates the structure of a computer device according to an embodiment of this specification. The apparatus described in this specification can be the computer device in this embodiment, performing the methods described above. The computer device 702 may include one or more processing devices 704, such as one or more central processing units (CPUs), each of which can implement one or more hardware threads. The computer device 702 may also include any storage resource 706 for storing information of any kind, such as code, settings, data, etc. Without limitation, for example, the storage resource 706 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any storage resource can use any technology to store information. Furthermore, any storage resource can provide volatile or non-volatile retention of information. Further, any storage resource may represent a fixed or removable component of the computer device 702. In one case, when the processing device 704 executes associated instructions stored in any storage resource or combination of storage resources, the computer device 702 can perform any operation of the associated instructions. The computer device 702 also includes one or more drive mechanisms 708 for interacting with any storage resource, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0155] Computer device 702 may also include an input / output module 710 (I / O) for receiving various inputs (via input device 712) and providing various outputs (via output device 714). A specific output mechanism may include a presentation device 716 and an associated graphical user interface (GUI) 718. In other embodiments, the input / output module 710 (I / O), input device 712, and output device 714 may be omitted, and the device may function solely as a computer device within a network. Computer device 702 may also include one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722. One or more communication buses 724 couple the components described above together.

[0156] Communication link 722 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 722 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0157] This specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0158] This specification also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method.

[0159] Those skilled in the art will understand that embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied 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.

[0160] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0161] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0162] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0163] The above specific embodiments further illustrate the purpose, technical solutions, and beneficial effects of this specification. It should be understood that the above are merely specific embodiments of this specification and are not intended to limit the scope of protection of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A method for segmenting and clustering oil wells, characterized in that, include: By utilizing multiple target weights corresponding to multiple indicator factors, each well logging data set in multiple well logging data sets of the oil well to be processed is processed to determine the target data corresponding to each well logging data set, thereby obtaining multiple target data; The method for determining the target weight includes: determining multiple indicator factors based on historical data of multiple target oil wells; selecting multiple sub-historical data associated with fractured sections or fractured clusters from the historical data; determining the pre-target weight corresponding to each indicator factor based on the number of the multiple sub-historical data and the value corresponding to each indicator factor; and normalizing each pre-target weight to determine multiple target weights. Cluster the multiple target data sets to determine at least one target data set; For each target data set in the at least one target data set, the target data sets that satisfy preset conditions are divided into segmented target data sets; the preset conditions include: the difference between any two target data sets in the target data set is less than a first preset threshold, the difference between the scale values ​​associated with any two target data sets is greater than or equal to a second preset threshold and less than or equal to a third preset threshold, and the number of target data sets in the target data set is less than or equal to a fourth preset threshold; and The scale segment formed by the scale value associated with each well logging data set in the segmented target data set is taken as the fracturing segment, and the scale value associated with each well logging data set in the segmented target data set is taken as the fracturing cluster.

2. The method according to claim 1, characterized in that, The determination of multiple indicator factors based on historical data from multiple oil wells includes: Based on historical data from multiple oil wells, several first-level pre-indicator factors corresponding to asynchronous fracturing, several second-level pre-indicator factors corresponding to non-uniform fluid ingress, and several third-level pre-indicator factors corresponding to the production profile were identified; and Multiple pre-indicator factors that exist in all of the multiple first pre-indicator factors, the multiple second pre-indicator factors, and the multiple third pre-indicator factors are identified as multiple indicator factors.

3. The method according to claim 1, characterized in that, The step of determining the pre-target weight corresponding to each indicator factor based on the number of the multiple sub-historical data and the value corresponding to each indicator factor includes: Based on the multiple sub-historical data and the numerical values ​​corresponding to each indicator factor, at least one target indicator factor corresponding to each sub-historical data is determined; For the multiple sub-historical data, determine the first number of each target indicator factor, resulting in multiple first numbers; and Based on the first number and the number of the plurality of sub-historical data, determine the pre-target weight corresponding to each indicator factor.

4. The method according to any one of claims 1-3, characterized in that, The multiple indicators include gas measurement values, compensated neutron values, brittleness index, and minimum horizontal principal stress.

5. The method according to claim 1, characterized in that, The step of clustering the multiple target data to determine at least one target data set includes: Obtain multiple initial data; For each target data point among the plurality of target data points, the difference between the target data point and each initial data point is determined, resulting in a plurality of differences; Based on the target initial data corresponding to the minimum difference among multiple differences for each target data, at least one pre-target data set is determined; and Based on the optimization function, the multiple initial data are updated, the steps of obtaining multiple initial data are returned, and finally at least one target data set is obtained.

6. A segmented clustering device for an oil well, characterized in that, include, The processing unit is used to process each logging data set in multiple logging numerical control sets of the oil well to be processed by using multiple target weights corresponding to multiple index factors, to determine the target data corresponding to each logging data set, and to obtain multiple target data. The method for determining the target weight includes: determining multiple indicator factors based on historical data of multiple target oil wells; selecting multiple sub-historical data associated with fractured sections or fractured clusters from the historical data; determining the pre-target weight corresponding to each indicator factor based on the number of the multiple sub-historical data and the value corresponding to each indicator factor; and normalizing each pre-target weight to determine multiple target weights. Clustering unit, used to cluster the multiple target data to determine at least one target data set; The first determining unit is configured to, for each of the at least one target data set, divide the target data sets that meet preset conditions into segmented target data sets; the preset conditions include: the difference between any two target data sets in the target data set is less than a first preset threshold, the difference between the scale values ​​associated with any two target data sets is greater than or equal to a second preset threshold and less than or equal to a third preset threshold, and the number of target data sets in the target data set is less than or equal to a fourth preset threshold. The second determining unit is used to take the scale segment formed by the scale value associated with each well logging data set in the segmented target data set as the fracturing segment, and to take the scale value associated with each well logging data set in the segmented target data set as the fracturing cluster.

7. A computer 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 computer program, it implements the method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the method of any one of claims 1-5.

Images