Reservoir seepage barrier determination method, device and equipment, storage medium and product

Through clustering model and well logging phase propagation technology, the problem of seepage barrier hindering fluid flow in the reservoir is solved, the accuracy and efficiency of seepage barrier are improved, and reservoir development is promoted.

CN118958954APending Publication Date: 2024-11-15PETROCHINA CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310545174.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-15
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The seepage barriers present in the reservoir hinder the flow of underground oil, gas and water fluids, resulting in a low degree of production. It is difficult for the existing technology to efficiently determine and spread seepage barrier information, affecting the effect of reservoir development.

Method used

By obtaining the logging curve and core information of the core well, training of clustering models is carried out to determine multiple logging phases and propagating them to non-core wells to accurately locate the seepage barrier of the reservoir.

Benefits of technology

The accuracy and determination efficiency of the seepage barrier are improved, and efficient identification and propagation of the seepage barrier in the reservoir is achieved, which improves the effect of reservoir development.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118958954A_ABST
    Figure CN118958954A_ABST
Patent Text Reader

Abstract

The invention provides a determination method, device and equipment of a reservoir seepage barrier, a storage medium and a product, and belongs to the technical field of reservoirs. The method comprises the steps that multiple first well logging curves of a coring well in a work area and core information of multiple depth points are obtained; determining a plurality of sample vectors based on the plurality of first logging curves; training based on the plurality of sample vectors to obtain a clustering model, and determining a clustering cluster to which the depth point belongs from a plurality of clustering clusters; based on the core information of a plurality of clusters and a plurality of depth points in the clustering model, determining a plurality of types of logging facies; and determining the seepage barrier of the reservoir where the non-coring well is located based on the multiple types of logging facies, the multiple sample vectors and the multiple second logging curves of the non-coring well in the work area. According to the method, the reservoir seepage barrier is determined on the logging curve point by point, the precision of the determined seepage barrier is improved, the logging facies determined by the coring well are propagated to the non-coring well, and the determination efficiency of the seepage barrier is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of reservoir technology, and in particular to a method, device, equipment, storage medium and product for determining a reservoir seepage barrier. Background Art

[0002] There are seepage barriers of various origins in the reservoir, which hinder the flow of underground oil, gas, water and other fluids. After the reservoir enters the oilfield development stage, the seepage barriers hinder the flow of fluids, resulting in local residual fluid enrichment and low fluid recovery. Therefore, determining the seepage barriers in the reservoir is very important to improve the effect of reservoir development. Summary of the invention

[0003] The embodiment of the present application provides a method, device, equipment, storage medium and product for determining a reservoir seepage barrier. The method determines the reservoir seepage barrier point by point based on the logging curve, thereby improving the accuracy of the determined seepage barrier and propagating the logging phase determined by the coring well to the non-coring well, thereby improving the efficiency of determining the seepage barrier. The technical solution is as follows:

[0004] In one aspect, a method for determining a reservoir seepage barrier is provided, the method comprising:

[0005] Acquire multiple first well logging curves and core information of multiple depth points of coring wells in the work area, wherein the multiple first well logging curves correspond to different types of well logging values, and each first well logging curve includes the well logging values ​​of the multiple depth points;

[0006] Based on the plurality of first well logging curves, determining a plurality of sample vectors, each sample vector comprising a plurality of well logging values ​​at a same depth point in the plurality of first well logging curves;

[0007] Performing training based on the multiple sample vectors to obtain a clustering model, the clustering model including multiple clustering clusters, the clustering model being used to determine the clustering cluster to which the depth point belongs from the multiple clustering clusters based on multiple well logging values ​​of the depth point;

[0008] Based on the multiple clusters in the clustering model and the core information of the multiple depth points, multiple types of logging phases are determined, wherein the multiple clusters in each type of logging phase correspond to the core information of the same type, and the multiple types of logging phases respectively indicate the reservoir and the seepage barrier of the reservoir;

[0009] Based on the multiple types of logging phases, the multiple sample vectors and the multiple second logging curves of the non-coring wells in the work area, the seepage barrier of the reservoir where the non-coring wells are located is determined.

[0010] In some embodiments, determining multiple types of logging phases based on the multiple clusters in the clustering model and the core information of the multiple depth points includes:

[0011] Based on the core information of the multiple depth points, determine a lithology curve and a configuration curve, wherein the lithology curve includes lithology quantification values ​​of the multiple depth points, and the configuration curve includes configuration quantification values ​​of the multiple depth points;

[0012] Based on the multiple clusters, the lithology curves and the configuration curves, the multiple clusters are clustered to obtain the multiple types of logging phases, and each type of logging phase includes multiple clusters corresponding to lithology quantization values ​​within the same reference range and configuration quantization values ​​within the same reference range.

[0013] In some embodiments, determining the lithology curve and the configuration curve based on the core information of the multiple depth points includes:

[0014] Based on the lithology particle size and oil content level in the core information of the multiple depth points, determine the lithology quantification values ​​of the multiple depth points to obtain the lithology curve, and the lithology quantification value of each depth point is positively correlated with the lithology particle size and oil content level of the depth point;

[0015] Based on the configuration information in the core information of the multiple depth points, the configuration quantization values ​​of the multiple depth points are determined to obtain the configuration curve.

[0016] In some embodiments, determining the seepage barrier of the reservoir where the non-coring well is located based on the multiple types of logging phases, the multiple sample vectors and the multiple second logging curves of the non-coring wells in the work area includes:

[0017] Based on the plurality of second logging curves, determining a plurality of logging vectors, each logging vector comprising a plurality of logging values ​​at a same depth point in the plurality of second logging curves;

[0018] For each well logging vector, determining the distances between the well logging vector and the plurality of sample vectors;

[0019] Determine the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors;

[0020] Based on the logging phases to which the multiple logging vectors respectively belong, the seepage barrier of the area where the non-coring well is located is determined.

[0021] In some embodiments, determining the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors includes:

[0022] Based on the distances respectively corresponding to the multiple sample vectors, the multiple sample vectors are sorted, and the order of each sample vector is positively correlated with the distance corresponding to the sample vector;

[0023] Determine a plurality of target sample vectors ranked after the target number of digits from the plurality of sample vectors;

[0024] The logging phase to which the plurality of target sample vectors belong to the most among the plurality of logging phases is taken as the logging phase to which the logging vector belongs.

[0025] In some embodiments, the plurality of clusters are arranged in sequence, the distance between the feature vectors of adjacent clusters is smaller than the distance between the feature vectors of non-adjacent clusters, and the feature vectors are used to describe the clusters; the determining of multiple types of logging phases based on the plurality of clusters in the cluster model and the core information of the plurality of depth points comprises:

[0026] Based on the core information of the multiple depth points, determining multiple segmentation nodes in the multiple clusters, the clusters before and after the segmentation nodes correspond to different types of core information;

[0027] The plurality of clusters are divided based on the plurality of segmentation nodes to obtain the plurality of logging phases, each of which includes a plurality of continuous clusters.

[0028] In another aspect, a device for determining a reservoir seepage barrier is provided, the device comprising:

[0029] An acquisition module, used to acquire multiple first well logging curves and core information of multiple depth points of coring wells in a work area, wherein the multiple first well logging curves correspond to different types of well logging values, and each first well logging curve includes the well logging values ​​of the multiple depth points;

[0030] A first determination module, configured to determine a plurality of sample vectors based on the plurality of first logging curves, each sample vector comprising a plurality of logging values ​​at a same depth point in the plurality of first logging curves;

[0031] A training module, used for performing training based on the multiple sample vectors to obtain a clustering model, wherein the clustering model includes multiple clusters, and the clustering model is used for determining the cluster to which the depth point belongs from the multiple clusters based on multiple well logging values ​​of the depth point;

[0032] A second determination module is used to determine multiple types of logging phases based on the multiple clusters in the clustering model and the core information of the multiple depth points, wherein the multiple clusters in each type of logging phase correspond to the core information of the same type, and the multiple types of logging phases respectively indicate the reservoir and the seepage barrier of the reservoir;

[0033] The third determination module is used to determine the seepage barrier of the reservoir where the non-coring well is located based on the multiple types of logging phases, the multiple sample vectors and the multiple second logging curves of the non-coring wells in the work area.

[0034] In some embodiments, the second determining module is used to:

[0035] Based on the core information of the multiple depth points, determine a lithology curve and a configuration curve, wherein the lithology curve includes lithology quantification values ​​of the multiple depth points, and the configuration curve includes configuration quantification values ​​of the multiple depth points;

[0036] Based on the multiple clusters, the lithology curves and the configuration curves, the multiple clusters are clustered to obtain the multiple types of logging phases, and each type of logging phase includes multiple clusters corresponding to lithology quantization values ​​within the same reference range and configuration quantization values ​​within the same reference range.

[0037] In some embodiments, the second determining module is used to:

[0038] Based on the lithology particle size and oil content level in the core information of the multiple depth points, determine the lithology quantification values ​​of the multiple depth points to obtain the lithology curve, and the lithology quantification value of each depth point is positively correlated with the lithology particle size and oil content level of the depth point;

[0039] Based on the configuration information in the core information of the multiple depth points, the configuration quantization values ​​of the multiple depth points are determined to obtain the configuration curve.

[0040] In some embodiments, the third determining module is used to:

[0041] Based on the plurality of second logging curves, determining a plurality of logging vectors, each logging vector comprising a plurality of logging values ​​at a same depth point in the plurality of second logging curves;

[0042] For each well logging vector, determining the distances between the well logging vector and the plurality of sample vectors;

[0043] Determine the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors;

[0044] Based on the logging phases to which the multiple logging vectors respectively belong, the seepage barrier of the area where the non-coring well is located is determined.

[0045] In some embodiments, the third determining module is used to:

[0046] Based on the distances respectively corresponding to the multiple sample vectors, the multiple sample vectors are sorted, and the order of each sample vector is positively correlated with the distance corresponding to the sample vector;

[0047] Determine a plurality of target sample vectors ranked after the target number of digits from the plurality of sample vectors;

[0048] The logging phase to which the plurality of target sample vectors belong to the most among the plurality of logging phases is taken as the logging phase to which the logging vector belongs.

[0049] In some embodiments, the plurality of clusters are arranged in sequence, the distance between feature vectors of adjacent clusters is smaller than the distance between feature vectors of non-adjacent clusters, and the feature vectors are used to describe the clusters; the second determination module is used to:

[0050] Based on the core information of the multiple depth points, determining multiple segmentation nodes in the multiple clusters, the clusters before and after the segmentation nodes correspond to different types of core information;

[0051] The plurality of clusters are divided based on the plurality of segmentation nodes to obtain the plurality of logging phases, each of which includes a plurality of continuous clusters.

[0052] On the other hand, a computer device is provided, which includes one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the method for determining the reservoir seepage barrier described in any of the above-mentioned implementation methods.

[0053] On the other hand, a computer-readable storage medium is provided, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to implement the method for determining the reservoir seepage barrier described in any of the above implementations.

[0054] On the other hand, a computer program product is provided, which includes a computer program code, wherein the computer program code is stored in a computer-readable storage medium, a processor of a computer device reads the computer program code from the computer-readable storage medium, and the processor executes the computer program code, so that the computer device executes the method for determining the reservoir seepage barrier described in any of the above-mentioned implementations.

[0055] The beneficial effects of the technical solution provided by the embodiments of the present application include at least:

[0056] The present application provides a method for determining a reservoir seepage barrier. The method performs clustering based on multiple logging curves of a coring well to obtain a clustering model including multiple cluster clusters, so that depth points with different logging values ​​in the logging curves are classified and divided, and then the multiple cluster clusters are further divided based on the core information of the multiple depth points to obtain multiple logging phases, and the logging phases can indicate the reservoir and the seepage barrier, and then the logging phases determined based on the coring wells are propagated to non-coring wells. Based on multiple logging curves of the non-coring wells, the seepage barrier of the reservoir where the coring well is located can be obtained; the method determines the reservoir seepage barrier point by point on the logging curves, thereby improving the accuracy of the determined seepage barrier, and propagates the logging phases determined by the coring wells to the non-coring wells, thereby improving the efficiency of determining the seepage barrier. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 It is a flow chart of a method for determining a reservoir seepage barrier provided in an embodiment of the present application;

[0059] Figure 2 is a flow chart of another method for determining a reservoir seepage barrier provided in an embodiment of the present application;

[0060] Figure 3 is a schematic diagram of a self-organizing feature mapping neural network model provided in an embodiment of the present application;

[0061] Figure 4 It is a box plot comparing a configuration and lithology with a cluster provided in an embodiment of the present application;

[0062] Figure 5 It is a comparison histogram of a clustering cluster and a well logging curve provided in an embodiment of the present application;

[0063] Figure 6 is a schematic diagram of a KNN algorithm provided in an embodiment of the present application;

[0064] Figure 7 It is a coring well reservoir seepage barrier determination and core information comparison verification diagram provided in an embodiment of the present application;

[0065] Figure 8 It is a schematic diagram of determining a reservoir seepage barrier for a non-coring well provided in an embodiment of the present application;

[0066] Fig. 9It is a flow chart of a method for determining a reservoir seepage barrier provided in an embodiment of the present application;

[0067] Fig.10 is a block diagram of a device for determining a reservoir seepage barrier provided in an embodiment of the present application;

[0068] Fig.11 It is a block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0070] It should be noted that the user information involved in this application (including but not limited to user device information, user personal information, etc.) is information authorized by the user or fully authorized by all parties.

[0071] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0072] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions. For example, the well logging curves and core information involved in this disclosure are all obtained with full authorization.

[0073] The present application embodiment provides a method for determining a reservoir seepage barrier, see Figure 1 , the method comprises the following steps:

[0074] 101. The computer device obtains multiple first logging curves and core information of multiple depth points of the coring wells in the work area. The multiple first logging curves correspond to different types of logging values, and each first logging curve includes logging values ​​of multiple depth points.

[0075] In the embodiment of the present application, the plurality of first logging curves include at least one of a spentaneous potential curve (SP) curve, a gamma-ray (GR) curve, an acoustic time difference (AC) curve, a density (DEN) curve, and a neutron curve (CN), etc. The spentaneous potential curve and the gamma-ray curve are used to reflect the mud content of the reservoir, and the acoustic time difference curve, the density curve, and the neutron curve are used to reflect the physical properties of the reservoir.

[0076] In the embodiment of the present application, the core information includes at least one of the lithology particle size, bedding structure, degree of cementation, oil content level and configuration information of the reservoir. Among them, the lithology particle size includes mudstone, silty mudstone (mudstone siltstone), siltstone, fine sandstone, medium sandstone, coarse sandstone, etc. from small to large. Bedding structure includes horizontal bedding, parallel bedding, wavy bedding, cross bedding, transitional bedding, rhythmic bedding, blocky bedding, etc. The oil content level includes oil trace level, oil spot level and oil immersion level, etc. The oil trace level refers to the very small amount of oil contained in the core, the oil spot level refers to the uneven oil content, which is distributed in spots, but the oil content can be clearly seen by the naked eye, and the oil immersion level refers to the loose and porous rock formation, which is full and uniform in oil content. Configuration information includes underwater diversion channels, estuary dams (dam bodies), inner edges of dams, outer edges of dams and mud between dams.

[0077] 102. The computer device determines a plurality of sample vectors based on the plurality of first logging curves, each sample vector comprising a plurality of logging values ​​at the same depth point in the plurality of first logging curves.

[0078] In the embodiment of the present application, multiple logging values ​​at the same depth point are combined into a sample vector, and the order of the multiple logging values ​​in the sample vector can be set and changed as needed. For example, if there are 4 first logging curves, the sample vector is a 4-dimensional vector.

[0079] 103. The computer device performs training based on multiple sample vectors to obtain a clustering model, wherein the clustering model includes multiple clustering clusters, and the clustering model is used to determine the clustering cluster to which the depth point belongs from multiple clustering clusters based on multiple logging values ​​of a depth point.

[0080] In the embodiment of the present application, each cluster includes multiple sample vectors, and the distance between sample vectors in the same cluster is within a reference range; optionally, the distance is a Euclidean distance.

[0081] 104. The computer device determines multiple types of logging phases based on multiple clusters in the clustering model and core information of multiple depth points. Multiple clusters in each type of logging phase correspond to the same type of core information. The multiple types of logging phases respectively indicate the reservoir and the seepage barrier of the reservoir.

[0082] In the embodiment of the present application, each cluster includes multiple sample vectors. Based on the core information of the depth points where the multiple sample vectors are located, the multiple clusters are clustered to obtain multiple types of logging phases.

[0083] In an embodiment of the present application, multiple types of logging phases can be named as Class 1, Class 2, Class 3, Class 4 and Class 5 logging phases, respectively, and the multiple types of logging phases respectively indicate non-reservoir, invalid reservoir, first-level reservoir, second-level reservoir and third-level reservoir, etc. Non-reservoir and invalid reservoir belong to seepage barriers, first-level reservoir, second-level reservoir and third-level reservoir belong to reservoirs, and the reservoir quality increases in sequence, that is, the reservoir quality of the first-level reservoir is poor, the reservoir quality of the second-level reservoir is medium, and the reservoir quality of the third-level reservoir is good.

[0084] 105. The computer equipment determines the seepage barrier of the reservoir where the non-coring wells are located based on multiple types of logging phases, multiple sample vectors and multiple second logging curves of non-coring wells in the work area.

[0085] In an embodiment of the present application, the computer device can determine the logging phases to which multiple depth points of the non-coring wells belong based on multiple types of logging phases, multiple sample vectors and multiple second logging curves, and then determine the seepage barrier of the reservoir where the non-coring wells are located.

[0086] The present application provides a method for determining a reservoir seepage barrier. The method performs clustering based on multiple logging curves of a coring well to obtain a clustering model including multiple cluster clusters, so that depth points with different logging values ​​in the logging curves are classified and divided, and then the multiple cluster clusters are further divided based on the core information of the multiple depth points to obtain multiple logging phases, and the logging phases can indicate the reservoir and the seepage barrier, and then the logging phases determined based on the coring wells are propagated to non-coring wells. Based on multiple logging curves of the non-coring wells, the seepage barrier of the reservoir where the coring well is located can be obtained; the method determines the reservoir seepage barrier point by point on the logging curves, thereby improving the accuracy of the determined seepage barrier, and propagates the logging phases determined by the coring wells to the non-coring wells, thereby improving the efficiency of determining the seepage barrier.

[0087] Figure 1 This is the basic process for determining the reservoir seepage barrier. Figure 2 The detailed process of determining the seepage barrier is described. Figure 2 , is a flow chart of a method for determining a reservoir seepage barrier provided in an embodiment of the present application, the method comprising the following steps.

[0088] 201. The computer equipment determines the lithology curve and configuration curve based on the core information of multiple depth points of the coring wells in the work area.

[0089] In an embodiment of the present application, the work area includes multiple coring wells; optionally, the computer equipment determines the lithology curve and configuration curve of each coring well based on the core information of multiple depth points of each coring well.

[0090] In some embodiments, the process of determining the lithology curve and the configuration curve based on the core information of multiple depth points of the coring wells in the work area by the above-mentioned computer device includes the following steps: the computer device determines the lithology quantification values ​​of multiple depth points based on the lithology particle size and oil content level in the core information of the multiple depth points to obtain the lithology curve, and the lithology quantification value of each depth point is positively correlated with the lithology particle size and oil content level of the depth point. The computer device determines the configuration quantification values ​​of multiple depth points based on the configuration information in the core information of the multiple depth points to obtain the configuration curve. In this embodiment, since the lithology particle size and the oil content level are both related to the reservoir quality, the lithology quantification value is determined based on the lithology particle size and the oil content level, which ensures the representativeness and accuracy of the lithology quantification value. The configuration quantification value is determined based on the configuration information, which realizes the quantification of the configuration, and then facilitates the subsequent determination of the reservoir seepage barrier based on the configuration curve.

[0091] In this embodiment, based on the detailed description of the core of the coring well (section), the comprehensive reservoir quality of the coring well is graded and quantified based on the core and logging data, lithology and sedimentary configuration, and a lithology or configuration curve consistent with the sampling interval of the logging curve is generated to facilitate comparative analysis with the cluster clusters after subsequent point-by-point clustering. Before the core and configuration assignment quantification of the coring well section is performed in this step, the core homing process is performed first.

[0092] The computer device determines a first lithology quantification value based on the lithology particle size at the depth point, and determines a second lithology quantification value based on the oil content level at the depth point for each depth point; the first lithology quantification value and the second lithology quantification value are accumulated to obtain the core quantification value at the depth point. Optionally, mudstone, silty mudstone (mudstone siltstone), siltstone, fine sandstone, medium sandstone, coarse sandstone, etc. are assigned quantification values ​​of 1, 2, 3, 4, 5, 6 in order according to the size of the lithology particle size, and the oil spot level and oil immersion level are assigned quantification values ​​of 1 and 2 respectively, and for the oil trace level and below, a quantification value of 0 is assigned.

[0093] Taking the reference work area as an example, the lithology particle size is divided into seven levels: mudstone, muddy siltstone (silty mud) rock, siltstone, fine sandstone, oil-stained fine sandstone, oil-stained medium sandstone (oil-immersed fine sandstone), and oil-immersed medium sandstone, and the quantitative values ​​​​are assigned from 1 to 7 respectively.

[0094] Among them, the computer equipment determines the configuration quantization value for each depth point based on the configuration information of the depth point; the configuration quantization value of each depth point can reflect the possibility that the depth point is an effective reservoir, and the larger the configuration quantization value, the greater the possibility of being an effective reservoir. For example, continuing to take the reference work area as an example, according to the core information of the reference work area, it is determined that the target reservoir of the reference work area is a delta front deposit dominated by an estuary bar, and its configuration is divided into underwater distributary channels, estuary bars (dam bodies), inner edges of dams, outer edges of dams, and mud between dams. Underwater distributary channels and estuary bars (dam bodies) are the main configurations of effective reservoir distribution, and are assigned quantitative values ​​of 5 and 4 respectively; the inner edge of the dam and the outer edge of the dam are flanking phases, and are assigned quantitative values ​​of 3 and 2 respectively; the mud between dams is assigned a quantitative value of 1.

[0095] In some embodiments, the computer device may assign a lithology quantification value and a configuration quantification value to each depth point of the reservoir, and then generate a lithology curve and a configuration curve based on multiple depth points corresponding to the sampling interval of the logging curve, and optionally, the sampling interval is 0.125m. In other embodiments, the computer device directly determines the lithology quantification value and the configuration quantification value of multiple depth points corresponding to the sampling interval of the logging curve, and generates the lithology curve and the configuration curve, so that only the lithology quantification value and the configuration quantification value of multiple depth points need to be generated, without generating the lithology quantification value and the configuration quantification value of each depth point, thereby improving efficiency.

[0096] 202. The computer device determines multiple sample vectors based on multiple first logging curves of the coring well, each sample vector includes multiple logging values ​​of the same depth point in the multiple first logging curves, the multiple first logging curves correspond to different types of logging values, and each first logging curve includes logging values ​​of multiple depth points.

[0097] In an embodiment of the present application, the work area includes multiple coring wells; optionally, the computer equipment determines multiple sample vectors for each of the multiple coring wells based on multiple first logging curves of each coring well; this can increase the data volume of the sample vector, and thus improve the training effect based on multiple sample vectors.

[0098] In some embodiments, based on the coverage of logging curves in the entire work area and the analysis of logging curves, lithology and configuration, four curves of the target layer segments of the core wells, SP, GR, AC, and RT, are selected for clustering. These four curves have good coverage of the wells in the entire area, which facilitates subsequent propagation to non-coring wells to determine the seepage barrier.

[0099] It should be noted that the serial numbers of the above steps 201-202 are only for ease of description and are not used to limit the execution order of step 201 and step 202. Step 201 can be executed before step 202, or after step 202, or simultaneously with step 202, and no specific limitation is made here.

[0100] In some embodiments, in order to make the convergence efficiency in the model training process faster, before obtaining the sample vector, that is, before the computer device executes step 202, the multiple well logging curves in the whole area are first standardized and normalized. Optionally, the computer device uses a histogram method or a trend surface method to standardize the well logging curves. Optionally, the computer device uses a range normalization method to normalize the multiple well logging curves. For example, see the following formula (1).

[0101]

[0102] Among them, for each type of well log curve, X i represents the logging value, i=1, 2, ...n, n represents the number of logging values ​​on this type of logging curve. If the same type of logging curve includes logging curves of multiple coring wells, then n represents the number of logging values ​​on multiple logging curves of the same type, which is an integer greater than 0; X min Indicates the minimum logging value corresponding to this type of logging curve; X max Indicates the maximum logging value corresponding to this type of logging curve; X ′ i It indicates the logging value after range normalization, ranging from 0 to 1.

[0103] Continuing with the reference work area as an example, the SP, GR, AC, and RT of all wells in the area were first normalized, and the normalized logging curves were named SPZF, GRZF, ACZZ, and RTZZ, respectively. Optionally, the first three logging curves use the maximum and minimum value normalization method, and the normalized logging value range is 0 to 1, that is, the normalization method shown in formula (1). The resistivity curve uses the logarithmic maximum and minimum value normalization method, and the normalized logging value range is 0 to 1. It should be noted that the 0 value of the normalized SPZF and GRZF curves corresponds to the maximum value of the original curve, and the 1 value corresponds to the minimum value. The ACZZ curve is normally normalized, which ensures that the reservoir attribute trends represented by the four normalized logging curves are consistent.

[0104] 203. The computer device performs training based on multiple sample vectors to obtain a clustering model, wherein the clustering model includes multiple clustering clusters, and the clustering model is used to determine the clustering cluster to which the depth point belongs from multiple clustering clusters based on multiple logging values ​​of a depth point.

[0105] In some embodiments, a computer device is trained using a self-organizing map (SOM) algorithm to obtain a clustering model, which is a self-organizing feature map neural network model. Among them, the self-organizing feature map neural network model maps high-dimensional data to low dimensions through self-organizing maps to achieve dimensionality reduction and clustering. The self-organizing feature map neural network model includes an input layer and an output layer (competition layer), and the input layer and the output layer respectively include multiple input nodes and multiple output nodes, and the multiple output nodes of the output layer are a topological structure; a one-dimensional output layer, multiple output nodes are connected in sequence into a line, and a two-dimensional topological output layer, multiple output nodes form a plane. The input layer corresponds to a high-dimensional input vector, and its dimension is the same as the number of multiple input nodes. In an embodiment of the present application, the input vector is a sample vector or a logging vector. The output layer is composed of a series of ordered nodes organized on a two-dimensional network, and the input nodes and output nodes are connected by weight vectors, such as Figure 3 As shown, Figure 3 This is a schematic diagram of a self-organizing feature mapping neural network model provided by an embodiment of the present application. During the training process of the model, for each input vector, the output node with the shortest distance to it is found from multiple output nodes, that is, the winning node is obtained, and the feature vector of the winning node is updated; at the same time, the feature vectors of the output nodes in the vicinity of the winning node are updated, and finally multiple output nodes that maintain the topological features of the input vector are obtained, and each node of the output layer represents a cluster.

[0106] Before training the model, the model parameters that need to be preset include the network topology of the output layer, the number of hidden layers, and the iteration threshold. Optionally, for well logging data, the number of hidden layers is set to 2 and the iteration threshold is set to 1000. The network topology of the output layer determines the structure of the final output layer and the number of output nodes, and the number of output nodes is set as large as possible to better obtain the topological structure of multiple well logging values. The network topology can be selected according to the dimension of the input well logging vector, that is, the number of well logging curves, but since the well logging values ​​of the well logging curves are generally related, for n well logging curves, a network structure of not less than n*n is generally selected, and the network structure cannot be too large or too small. Optionally, the network topology of the output layer is adjusted multiple times, and the initial clustering models under multiple network topologies are trained. Multiple initial clustering models are verified based on core information, and the initial clustering model with the best classification effect is selected as the clustering model, thereby ensuring the accuracy and classification effect of the determined clustering model.

[0107] In the embodiment of the present application, the reference work area is used as an example for explanation, wherein SPZF, GRZF, ACZZ, and RTZZ are used as the main variables, and the configuration curve FACODE is used as the covariate for clustering. In the clustering process, the main variables participate in clustering to generate sample vectors, and the covariates do not participate in clustering. The covariates are used to compare with the cluster clusters obtained after clustering. Among them, the clustering model selects a 5*5 network topology structure, with a default setting of 2 hidden layers and a maximum number of iterations of 1000 times, and 25 cluster clusters are obtained through clustering.

[0108] In the embodiment of the present disclosure, multiple clusters obtained based on the SOM clustering algorithm are arranged in sequence, and adjacent distance clusters in the multiple clusters have similarities. Then, there may be clusters in the multiple clusters that do not meet the similarity characteristics. Therefore, optionally, after obtaining the optimal clustering model, the computer device adjusts the clusters in sequence according to the median of the logging curve attributes corresponding to each cluster and at least one of the corresponding lithology and configuration characteristics, while trying not to change the association between the original multiple clusters. The serial number value of each cluster is determined to be able to quantify the reservoir during classification, that is, the multiple clusters satisfy that the distance between the feature vectors of adjacent clusters is less than the distance between the feature vectors of non-adjacent clusters, and the feature vectors are used to describe the clusters.

[0109] 204. The computer device clusters the multiple clusters based on the multiple clusters, lithology curves and configuration curves to obtain multiple types of logging phases, and each type of logging phase includes multiple clusters corresponding to lithology quantization values ​​within the same reference range and configuration quantization values ​​within the same reference range.

[0110] Among them, the lithology quantification values ​​within the same reference range correspond to the same reservoir quality, and the configuration quantification values ​​within the same reference range correspond to the same reservoir quality.

[0111] In some embodiments, multiple clusters are arranged in sequence, and the distance between the feature vectors of adjacent clusters is smaller than the distance between the feature vectors of non-adjacent clusters. Accordingly, the process of determining multiple types of logging phases by a computer device based on multiple clusters in a clustering model and core information of multiple depth points includes the following steps: the computer device determines multiple splitting nodes in the multiple clusters based on the core information of multiple depth points, and the clusters before and after the splitting nodes correspond to different core information; the computer device divides the multiple clusters based on the multiple splitting nodes to obtain multiple types of logging phases, and each type of logging phase includes multiple continuous clusters.

[0112] Optionally, the characteristic vector of the cluster is determined based on multiple sample vectors in the cluster; for example, the characteristic vector of the cluster is the mean of multiple sample vectors in the cluster. Each segmentation node is located between two clusters. In this embodiment, adjacent clusters have similarities, and multiple segmentation nodes are determined to facilitate the division of clusters and improve clustering efficiency.

[0113] Continuing with the reference work area as an example, the number of clusters is 25, numbered 1-25. Figure 4 , Figure 4 is a box plot comparing configuration, lithology and clustering provided in the embodiment of the present application, from Figure 4 It can be seen that according to the core curve and configuration curve, multiple clusters can be divided into 4 categories. Among them, the clusters with numbers less than 9 are mainly distributed in the inter-bar mud in terms of configuration, and the lithological distribution is mainly mudstone, muddy siltstone and most siltstone. The clusters numbered 9 to 11 are mainly distributed in the outer edge of some bars in terms of configuration, and the lithological distribution is mainly the transition range from siltstone to a small amount of oil-free fine sandstone. The clusters numbered 12 to 15 are mainly distributed in the outer edge and inner edge of some bars in terms of configuration, and the lithological distribution is a small amount of siltstone and oil-free fine sandstone. The clusters numbered 16 and above are mainly distributed in the main distribution range of the dam body and the underwater diversion channel in terms of configuration, and the lithological distribution is mainly fine sandstone above the oil spot level and a small amount of oil-free sandstone.

[0114] In some embodiments, in order to further improve the clustering effect, clustering is also performed in combination with well logging curves. Figure 5 , Figure 5 is a comparison histogram of a clustering cluster and a logging curve provided in an embodiment of the present application, from Figure 5 It can be seen from the clustering results based on multiple sample vectors that due to the use of a 5*5 network topology, multiple clusters can be directly divided into 5 categories according to the distribution of the SPZF curve, and each category includes clusters numbered 1 to 5, 6 to 10, 11 to 15, 16 to 20, and 21 to 25. From the distribution of the configuration curves corresponding to multiple clusters, the configuration phase distribution corresponding to clusters from 1 to 25 shows a trend of gradually increasing from inter-dam mud to the main dam body and underwater diversion channel.

[0115] Finally, the well logging curves, configurations and lithological characteristics on the histogram and box plot are integrated to divide the clusters into five logging phases: 1, 2, 3, 4 and 5, according to 1 to 8, 9 to 11, 12 to 15, 16 to 20 and 21 to 25. For example, see Table 1 below.

[0116]

[0117]

[0118] From the perspective of lithology and configuration, these five types of logging phases can characterize the reservoir quality to a certain extent. The first and second types of logging phases are non-reservoirs and invalid reservoirs. From the perspective of seepage barrier, they can be directly divided into interlayers, which are absolute seepage barriers. The third, fourth and fifth types of logging phases correspond to the three levels of poor, medium and good reservoir quality respectively. The contact surface between the third, fourth and fifth types of logging phases is the interface of the superposition of sand bodies inside the single sand layer.

[0119] In the embodiment of the present application, according to the determined logging phase and reservoir seepage barrier determination and division standards, the reservoir seepage barrier of the core well is determined, and the effect of the reservoir seepage barrier determination is evaluated from the vertical section of the single well. The interlayers of 7 core wells in the work area are determined and the internal configuration interface of the reservoir is divided by the method provided by the implementation of this application. The interlayers determined by this method are highly consistent with the interlayers determined from the core. Among them, 105 interlayers composed of mudstone, muddy siltstone and siltstone can be determined by this method, with a determination rate of up to 97%. The thickness of the 3 interlayers that have not been determined is less than 1m, and they are determined to be the third type of logging phase. In addition, the interface between the third, fourth and fifth types of logging phases can also correspond well to the lithological interface under the core phase. From the verification of the coring well, this method can effectively determine the reservoir seepage barrier and the single sand body superposition interface inside the reservoir.

[0120] The SOM clustering algorithm is an unsupervised algorithm that can fully explore the topological structure of data. There are correlations between various logging curves, and multidimensional logging data also have this topological structure. Therefore, the SOM clustering algorithm can objectively classify the differences in logging data, and on this basis, compare with lithology and configuration information, scientifically determine the division criteria of output nodes, i.e., clusters, and obtain logging phase classification standards that can standardize reservoir quality differences, and then determine the reservoir seepage barrier.

[0121] In this embodiment, the logging values ​​of the logging curves are clustered point by point using the SOM neural network. The multidimensional attributes composed of multiple logging curves are reduced to a two-dimensional plane topological structure through clustering, thereby realizing the conversion of multidimensional attributes to clusters of final output nodes, thereby improving the comprehensive characterization capability of logging curves for reservoir quality differences. Then, through the comparison of lithology and configuration, the classification boundaries of the output nodes, i.e., the clusters, i.e., the criteria for determining the division of the reservoir seepage barrier are determined, thereby achieving the effect of improving the accuracy of determining the reservoir seepage barrier.

[0122] In an embodiment of the present application, the computer device implements the process of determining multiple types of logging phases based on the core information of multiple clusters and multiple depth points in the clustering model through steps 201 and 204; in this embodiment, the lithology curve and the configuration curve are determined through the core information, and the quantification of the lithology and configuration is achieved, which facilitates the clustering of multiple clusters based on the lithology and configuration information, thereby improving the convenience and efficiency of clustering.

[0123] 205. The computer device determines a plurality of logging vectors based on a plurality of second logging curves of non-cored wells in the work area, each logging vector including a plurality of logging values ​​at the same depth point in the plurality of second logging curves.

[0124] Among them, the number of logging curves of the multiple second logging curves of the non-coring wells and the logging curve types of the multiple first logging curves of the coring wells are the same. For example, if the multiple first logging curves are SP, GR, AC, and RT curves, then the multiple second logging curves are also SP, GR, AC, and RT curves. And the type order of the multiple logging values ​​in the logging vector is the same as the type order of the multiple logging values ​​in the sample vector, thereby ensuring the consistency of the logging vector and the sample vector. For example, if the multiple logging values ​​in the sample vector are the logging values ​​on the SP, GR, AC, and RT curves in sequence, then the multiple logging values ​​in the logging vector are also the logging values ​​on the SP, GR, AC, and RT curves in sequence. Correspondingly, if the multiple first logging curves have been standardized and normalized, then the multiple second logging curves have also been standardized and normalized.

[0125] 206. The computer device determines, for each well logging vector, the distances between the well logging vector and a plurality of sample vectors.

[0126] Optionally, the distance between the logging vector and the sample vector is a Euclidean distance.

[0127] 207. The computer device determines the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors.

[0128] In some embodiments, the process of determining the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors by the above-mentioned computer device includes the following steps: the computer device sorts the multiple sample vectors based on the distances respectively corresponding to the multiple sample vectors, and the order of each sample vector is positively correlated with the distance corresponding to the sample vector; multiple target sample vectors with the last target bit number in the sorting are determined from the multiple sample vectors; the logging phase to which the multiple target sample vectors belong to the most in the multiple types of logging phases is taken as the logging phase to which the logging vector belongs. In this embodiment, if most of the K most adjacent samples of a sample in the feature space belong to a certain category, then the sample also belongs to this category and has the characteristics of the samples in this category. Therefore, it is reasonable and accurate to take the logging phase to which the multiple target sample vectors belong to the most as the logging phase to which the logging vector belongs; that is, the category is determined mainly by the limited adjacent samples around, rather than by the method of discriminating the class domain. The method is simple, easy to understand, and easy to implement.

[0129] 208. The computer device determines the seepage barrier in the area where the non-coring well is located based on the logging phases to which the multiple logging vectors respectively belong.

[0130] In the disclosed embodiment, the above steps 205-208 implement a process of determining the seepage barrier of the reservoir where the non-cored wells are located based on multiple types of logging phases, multiple sample vectors and multiple second logging curves of the non-cored wells in the work area. In this embodiment, a logging vector similar to the sample vector is generated based on the multiple second logging curves, and then based on the distance between the logging vector and the sample vector, the logging phase characteristics of the sample vector are propagated to the logging vector, thereby realizing the classification of the logging vector and determining the seepage barrier of the non-cored wells.

[0131] Among them, the computer equipment determines the seepage barrier in the area where the non-coring wells are located based on the logging phases to which the multiple logging vectors belong. Since the logging phase indicates the reservoir and the seepage barrier, as shown in Table 1, after determining the logging phase corresponding to each depth point based on the logging vector of each depth point, the seepage barrier in multiple depth points can be determined, and then the seepage barrier in the area where the non-coring wells are located can be obtained.

[0132] After verification by the coring wells, the SOM clustering clusters were first propagated to the non-coring wells through the KNN (KNN, K-NearestNeighbor, nearest neighbor) algorithm, and the reservoir seepage barrier and reservoir internal interface of the non-coring wells were determined according to the logging phase classification, i.e., the reservoir seepage barrier determination standard. From the application results of non-coring wells, the interlayer and reservoir internal interface determined by the embodiment of the present application are consistent with the original logging interpretation sand body results as a whole, and the reservoir internal interface determined and divided by this method is more refined, especially for the thicker sand bodies that were not divided by the original logging interpretation. The application of this method can more finely divide the single sand bodies inside the reservoir, which is of great significance for the subsequent fine geological modeling work based on reservoir configuration or flow unit.

[0133] The KNN algorithm uses all known samples as references, calculates the distance between the unknown sample and all known samples, and selects the K known samples with the closest distance, where K is an integer greater than 0; according to the majority voting rule, the unknown sample and the K nearest neighbor samples with the largest proportion of categories are classified into one category, as shown in Figure 6 , Figure 6 This is a schematic diagram of a KNN algorithm provided in an embodiment of the present application. This method mainly determines the category of the sample to be classified based on the category of one or several nearest known samples in the classification decision, basically does not require learning, and has the characteristics of rapid propagation.

[0134] In an embodiment of the present application, the trained logging SOM clustering model is propagated to non-coring wells by applying the KNN algorithm, and the reservoir seepage barrier of the non-coring wells is determined and divided according to the standard of the reservoir seepage barrier determined by the logging phase output node. Most of the work is done by computers to improve work efficiency.

[0135] The KNN algorithm is a supervised machine learning algorithm with a simple algorithm structure. It has excellent application effects in the classification and regression prediction of big data. Since both the KNN algorithm and the SOM clustering algorithm use Euclidean distance to evaluate the similarity of data in the process of evaluating data, the two can be well combined. On the basis of SOM clustering, the KNN algorithm is used to propagate the SOM neural network clustering model of the coring well to the non-coring well, solving the problem of the difficulty of applying the coring well to the non-coring well, while reducing the steps of manual participation and scientifically and rationally improving the work efficiency.

[0136] Compared with the semi-supervised interlayer determination method based on autoencoder, the semi-supervised interlayer determination method based on autoencoder only determines the absolute seepage barrier interlayer, while this method not only determines the interlayer, but also classifies the internal seepage units of the reservoir to realize the determination of the internal seepage difference interface.

[0137] The SOM neural network clustering and KNN algorithm involved in the present invention are relatively mature machine learning algorithms. The algorithm program can be implemented in algorithm platforms such as Matlab, Python, and some commonly used logging interpretation software (such as the Facimage (image making) module in GEOLOG logging interpretation software). Through actual application comparison, the application of this method can determine 102 of the 105 interlayers on the core, with an effective determination rate of up to 97%. In addition, the internal seepage difference interface of the reservoir can basically correspond to the lithology change interface one by one, and the division effect of the internal seepage interface of the reservoir is good, as shown in FIG. Figure 7 , Figure 7 This is a coring well reservoir seepage barrier determination and core information comparison verification diagram provided in the embodiment of the present application. Through the method of the present invention, on the basis of ensuring the accuracy of reservoir seepage barrier determination, the reservoir seepage barrier determination and division work of more than 320 wells in the work area was completed efficiently, as shown in Figure 8 , Figure 8 It is a schematic diagram for determining a reservoir seepage barrier for a non-coring well provided in an embodiment of the present application.

[0138] Through the method provided in the embodiment of the present application, 102 of the 105 interlayers on the core can be determined, with an effective determination rate of up to 97%. In addition, the determined internal seepage difference interface of the reservoir can basically correspond to the lithological changes of the reservoir, and the division effect of the internal seepage interface of the reservoir is good. Through the method provided in the embodiment of the present application, on the basis of ensuring the accuracy of determining the reservoir seepage barrier, the determination and division of the reservoir seepage barrier of more than 320 wells in the work area are efficiently completed.

[0139] In an embodiment of the present application, the trained clustering model is propagated to non-coring wells by applying the KNN algorithm, and the reservoir seepage barriers of the non-coring wells are determined and divided according to the criteria for determining the reservoir seepage barriers by clustering clusters, without the need for manual intervention, thereby improving work efficiency.

[0140] It should be noted that compared with the traditional method for determining seepage barriers, the method provided in the embodiment of the present application is more accurate and efficient. The present application introduces a machine learning algorithm, which clusters the logging curves point by point, and after calibrating with the core information of the coring well, it is more sensitive to the interface of the reservoir seepage barrier, and the reservoir internal seepage barrier interface can be automatically determined by the method provided in the embodiment of the present application. Compared with the semi-supervised interlayer determination method based on the autoencoder, the semi-supervised interlayer determination method based on the autoencoder is only for the absolute seepage barrier interlayer determination, and the method provided in the embodiment of the present application can not only determine the interlayer, but also classify the seepage units inside the reservoir, and realize the determination of the internal seepage difference interface.

[0141] See also Fig. 9 , Fig. 9 This is a flow chart of a method for determining a reservoir seepage barrier provided in an embodiment of the present application. First, a computer device performs a detailed description of the core of a coring well and a configuration division, performs core placement, and standardizes the logging curve; then, the lithology and configuration are quantitatively assigned, and the logging curve is optimized and normalized to obtain the normalized logging value; then, clustering is performed through a SOM neural network to obtain multiple clusters, and the lithology and configuration curves are compared with the clusters to obtain the logging phase classification boundary, i.e., the reservoir seepage barrier identification standard. Then, the logging phase of the coring well is extended to the non-coring well through the KNN algorithm, so as to realize the logging phase classification of the non-coring well and the determination and division of the reservoir seepage barrier.

[0142] The SOM clustering algorithm is an unsupervised algorithm that can fully explore the topological structure of the data. There is a correlation between each series of logging curves, and multidimensional logging data also has this topological structure. Therefore, the SOM clustering algorithm can objectively classify the differences in logging data, and on this basis, compare with the core and configuration, scientifically determine the logging phase neural unit division standard, obtain the logging phase classification standard that can characterize the difference in reservoir quality, and then determine the reservoir seepage barrier.

[0143] The method provided in the embodiment of the present application introduces an artificial intelligence machine learning algorithm and proposes a method for quantitatively determining a reservoir seepage barrier based on a self-organizing neural network and a KNN algorithm. The method mainly classifies multiple logging curves of the coring wells point by point based on the core description and configuration division of the coring wells through a self-organizing neural network clustering method, thereby improving the ability of the logging curves to characterize reservoir quality differences, establishing a reservoir seepage barrier determination standard, and thereby improving the accuracy of determining the reservoir seepage barrier; the KNN algorithm is used to propagate the self-organizing neural network clustering model established using the coring wells to non-coring wells, and the non-coring wells are determined using the reservoir seepage barrier determination standard, thereby improving the efficiency of determining the reservoir seepage barrier.

[0144] The present application provides a method for determining a reservoir seepage barrier. The method performs clustering based on multiple logging curves of a coring well to obtain a clustering model including multiple cluster clusters, so that depth points with different logging values ​​in the logging curves are classified and divided, and then the multiple cluster clusters are further divided based on the core information of the multiple depth points to obtain multiple logging phases, and the logging phases can indicate the reservoir and the seepage barrier, and then the logging phases determined based on the coring wells are propagated to non-coring wells. Based on multiple logging curves of the non-coring wells, the seepage barrier of the reservoir where the coring well is located can be obtained; the method determines the reservoir seepage barrier point by point on the logging curves, thereby improving the accuracy of the determined seepage barrier, and propagates the logging phases determined by the coring wells to the non-coring wells, thereby improving the efficiency of determining the seepage barrier.

[0145] The present application also provides a device for determining a reservoir seepage barrier, see Fig.10 , the device comprises:

[0146] The acquisition module 1001 is used to acquire multiple first logging curves and core information of multiple depth points of the coring wells in the work area, where the multiple first logging curves correspond to different types of logging values, and each first logging curve includes logging values ​​of multiple depth points;

[0147] A first determination module 1002 is used to determine a plurality of sample vectors based on a plurality of first logging curves, each sample vector comprising a plurality of logging values ​​at a same depth point in the plurality of first logging curves;

[0148] A training module 1003 is used to perform training based on multiple sample vectors to obtain a clustering model, wherein the clustering model includes multiple clustering clusters, and the clustering model is used to determine the clustering cluster to which the depth point belongs from the multiple clustering clusters based on multiple well logging values ​​of a depth point;

[0149] The second determination module 1004 is used to determine multiple types of logging phases based on multiple clusters in the clustering model and core information of multiple depth points, wherein multiple clusters in each type of logging phase correspond to core information of the same type, and the multiple types of logging phases respectively indicate reservoirs and seepage barriers of the reservoirs;

[0150] The third determination module 1005 is used to determine the seepage barrier of the reservoir where the non-coring wells are located based on multiple types of logging phases, multiple sample vectors and multiple second logging curves of the non-coring wells in the work area.

[0151] In some embodiments, the second determining module 1004 is configured to:

[0152] Based on the core information at multiple depth points, a lithology curve and a configuration curve are determined, wherein the lithology curve includes lithology quantification values ​​at multiple depth points, and the configuration curve includes configuration quantification values ​​at multiple depth points;

[0153] Based on multiple clusters, lithology curves and configuration curves, multiple clusters are clustered to obtain multiple types of logging phases, and each type of logging phase includes multiple clusters corresponding to lithology quantization values ​​within the same reference range and configuration quantization values ​​within the same reference range.

[0154] In some embodiments, the second determining module 1004 is configured to:

[0155] Based on the lithology grain size and oil content level in the core information of multiple depth points, the lithology quantification values ​​of multiple depth points are determined to obtain a lithology curve. The lithology quantification value of each depth point is positively correlated with the lithology grain size and oil content level of the depth point.

[0156] Based on the configuration information in the core information at the multiple depth points, the configuration quantization values ​​at the multiple depth points are determined to obtain the configuration curve.

[0157] In some embodiments, the third determining module 1005 is configured to:

[0158] Based on the plurality of second logging curves, determining a plurality of logging vectors, each logging vector comprising a plurality of logging values ​​at the same depth point in the plurality of second logging curves;

[0159] For each well logging vector, determining the distances between the well logging vector and a plurality of sample vectors respectively;

[0160] Determine the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors;

[0161] Based on the logging phases to which the multiple logging vectors respectively belong, the seepage barrier in the area where the non-cored wells are located is determined.

[0162] In some embodiments, the third determining module 1005 is configured to:

[0163] Based on the distances corresponding to the multiple sample vectors, the multiple sample vectors are sorted, and the order of each sample vector is positively correlated with the distance corresponding to the sample vector;

[0164] Determine a plurality of target sample vectors ranked after the target number of digits from the plurality of sample vectors;

[0165] The logging phase to which the target sample vectors belong to the most among the multiple types of logging phases is taken as the logging phase to which the logging vector belongs.

[0166] In some embodiments, multiple clusters are arranged in sequence, the distance between feature vectors of adjacent clusters is smaller than the distance between feature vectors of non-adjacent clusters, and the feature vectors are used to describe the clusters; the second determination module 1004 is used to:

[0167] Based on the core information of multiple depth points, multiple segmentation nodes in multiple clusters are determined, and the clusters before and after the segmentation nodes correspond to different types of core information;

[0168] Based on the multiple split nodes, multiple clusters are divided to obtain multiple types of logging phases, each type of logging phase includes multiple continuous clusters.

[0169] The present application provides a device for determining a reservoir seepage barrier, which performs clustering based on multiple logging curves of a coring well to obtain a clustering model including multiple cluster clusters, so that depth points with different logging values ​​in the logging curve are classified and divided, and then the multiple cluster clusters are further divided based on the core information of the multiple depth points to obtain multiple logging phases, and the logging phases can indicate the reservoir and the seepage barrier, and then the logging phases determined based on the coring well are propagated to the non-coring wells, and based on the multiple logging curves of the non-coring wells, the seepage barrier of the reservoir where the coring well is located can be obtained; the method determines the reservoir seepage barrier point by point on the logging curve, thereby improving the accuracy of the determined seepage barrier, and propagates the logging phases determined by the coring well to the non-coring wells, thereby improving the efficiency of determining the seepage barrier.

[0170] Fig.11 The block diagram of the structure of a computer device 1100 provided by an exemplary embodiment of the present application is shown. The computer device 1100 may be a portable mobile computer device, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The computer device 1100 may also be called a user device, a portable computer device, a laptop computer device, a desktop computer device, or other names.

[0171] Typically, the computer device 1100 includes a processor 1101 and a memory 1102 .

[0172] The processor 1101 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1101 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1101 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 1101 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1101 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0173] The memory 1102 may include one or more computer-readable storage media, which may be non-transitory. The memory 1102 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1102 is used to store at least one computer program, which is used to be executed by the processor 1101 to implement the method for determining the reservoir seepage barrier provided in the method embodiment of the present application.

[0174] In some embodiments, the computer device 1100 may also optionally include: a peripheral device interface 1103 and at least one peripheral device. The processor 1101, the memory 1102 and the peripheral device interface 1103 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1103 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 1104, a display screen 1105, a camera assembly 1106, an audio circuit 1107 and a power supply 1108.

[0175] The peripheral device interface 1103 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 1101 and the memory 1102. In some embodiments, the processor 1101, the memory 1102, and the peripheral device interface 1103 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1101, the memory 1102, and the peripheral device interface 1103 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0176] The radio frequency circuit 1104 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1104 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1104 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1104 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 1104 can communicate with other computer devices through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1104 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0177] The display screen 1105 is used to display a UI (User Interface). The UI may include graphics, text, icons, multimedia resources, and any combination thereof. When the display screen 1105 is a touch display screen, the display screen 1105 also has the ability to collect touch signals on the surface or above the surface of the display screen 1105. The touch signal can be input to the processor 1101 as a control signal for processing. At this time, the display screen 1105 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1105 can be one, arranged on the front panel of the computer device 1100; in other embodiments, the display screen 1105 can be at least two, respectively arranged on different surfaces of the computer device 1100 or in a folding design; in other embodiments, the display screen 1105 can be a flexible display screen, arranged on a curved surface or a folding surface of the computer device 1100. Even, the display screen 1105 can also be arranged as a non-rectangular irregular figure, that is, a special-shaped screen. The display screen 1105 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0178] The camera assembly 1106 is used to collect images or multimedia resources. Optionally, the camera assembly 1106 includes a front camera and a rear camera. Usually, the front camera is set on the front panel of the computer device, and the rear camera is set on the back of the computer device. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1106 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0179] The audio circuit 1107 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 1101 for processing, or input them into the radio frequency circuit 1104 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the computer device 1100. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 1101 or the radio frequency circuit 1104 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 1107 may also include a headphone jack.

[0180] The power supply 1108 is used to power various components in the computer device 1100. The power supply 1108 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1108 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged through a wired line, and a wireless rechargeable battery is a battery that is charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0181] In some embodiments, the computer device 1100 further includes one or more sensors 1109 , including but not limited to: an acceleration sensor 1110 , a gyroscope sensor 1111 , a pressure sensor 1112 , an optical sensor 1113 , and a proximity sensor 1114 .

[0182] The acceleration sensor 1110 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the computer device 1100. For example, the acceleration sensor 1110 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 1101 can control the display screen 1105 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 1110. The acceleration sensor 1110 can also be used to collect motion data of games or users.

[0183] The gyro sensor 1111 can detect the body direction and rotation angle of the computer device 1100, and the gyro sensor 1111 can cooperate with the acceleration sensor 1110 to collect the user's 3D actions on the computer device 1100. The processor 1101 can implement the following functions based on the data collected by the gyro sensor 1111: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0184] The pressure sensor 1112 may be provided at the side frame of the computer device 1100 and / or the lower layer of the display screen 1105. When the pressure sensor 1112 is provided at the side frame of the computer device 1100, it may detect the user's gripping signal of the computer device 1100, and the processor 1101 may perform left and right hand recognition or shortcut operation according to the gripping signal collected by the pressure sensor 1112. When the pressure sensor 1112 is provided at the lower layer of the display screen 1105, the processor 1101 may control the operability controls on the UI interface according to the user's pressure operation on the display screen 1105. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0185] The optical sensor 1113 is used to collect the ambient light intensity. In one embodiment, the processor 1101 can control the display brightness of the display screen 1105 according to the ambient light intensity collected by the optical sensor 1113. Specifically, when the ambient light intensity is high, the display brightness of the display screen 1105 is increased; when the ambient light intensity is low, the display brightness of the display screen 1105 is reduced. In another embodiment, the processor 1101 can also dynamically adjust the shooting parameters of the camera assembly 1106 according to the ambient light intensity collected by the optical sensor 1113.

[0186] The proximity sensor 1114, also called a distance sensor, is usually disposed on the front panel of the computer device 1100. The proximity sensor 1114 is used to collect the distance between the user and the front of the computer device 1100. In one embodiment, when the proximity sensor 1114 detects that the distance between the user and the front of the computer device 1100 is gradually decreasing, the processor 1101 controls the display screen 1105 to switch from the screen-on state to the screen-off state; when the proximity sensor 1114 detects that the distance between the user and the front of the computer device 1100 is gradually increasing, the processor 1101 controls the display screen 1105 to switch from the screen-off state to the screen-on state.

[0187] Those skilled in the art will understand that Fig.11 The structure shown in the figure does not constitute a limitation on the computer device 1100, and the computer device 1100 may include more or less components than shown in the figure, or combine some components, or adopt a different component arrangement.

[0188] An embodiment of the present application also provides a computer-readable storage medium, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to implement the method for determining a reservoir seepage barrier of any of the above-mentioned implementation modes.

[0189] An embodiment of the present application also provides a computer program product, which includes a computer program code. The computer program code is stored in a computer-readable storage medium. A processor of a computer device reads the computer program code from the computer-readable storage medium, and the processor executes the computer program code, so that the computer device executes the method for determining the reservoir seepage barrier of any of the above-mentioned implementations.

[0190] In some embodiments, the computer program product involved in the embodiments of the present application may be deployed and executed on a computer device, or on multiple computer devices located at one location, or on multiple computer devices distributed at multiple locations and interconnected by a communication network. Multiple computer devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

Claims

1. A method for determining a reservoir seepage barrier, characterized in that: The method comprises: Acquire multiple first well logging curves and core information of multiple depth points of coring wells in the work area, wherein the multiple first well logging curves correspond to different types of well logging values, and each first well logging curve includes the well logging values ​​of the multiple depth points; Based on the plurality of first well logging curves, determining a plurality of sample vectors, each sample vector comprising a plurality of well logging values ​​at a same depth point in the plurality of first well logging curves; Performing training based on the multiple sample vectors to obtain a clustering model, the clustering model including multiple clustering clusters, the clustering model being used to determine the clustering cluster to which the depth point belongs from the multiple clustering clusters based on multiple well logging values ​​of the depth point; Based on the multiple clusters in the clustering model and the core information of the multiple depth points, multiple types of logging phases are determined, wherein the multiple clusters in each type of logging phase correspond to the core information of the same type, and the multiple types of logging phases respectively indicate the reservoir and the seepage barrier of the reservoir; Based on the multiple types of logging phases, the multiple sample vectors and the multiple second logging curves of the non-coring wells in the work area, the seepage barrier of the reservoir where the non-coring wells are located is determined.

2. The method according to claim 1, characterized in that The determining of multiple types of logging phases based on the multiple clusters in the clustering model and the core information of the multiple depth points includes: Based on the core information of the multiple depth points, determine a lithology curve and a configuration curve, wherein the lithology curve includes lithology quantification values ​​of the multiple depth points, and the configuration curve includes configuration quantification values ​​of the multiple depth points; Based on the multiple clusters, the lithology curves and the configuration curves, the multiple clusters are clustered to obtain the multiple types of logging phases, and each type of logging phase includes multiple clusters corresponding to lithology quantization values ​​within the same reference range and configuration quantization values ​​within the same reference range.

3. The method according to claim 2, characterized in that The determining of the lithology curve and the configuration curve based on the core information of the plurality of depth points comprises: Based on the lithology particle size and oil content level in the core information of the multiple depth points, determine the lithology quantification values ​​of the multiple depth points to obtain the lithology curve, and the lithology quantification value of each depth point is positively correlated with the lithology particle size and oil content level of the depth point; Based on the configuration information in the core information of the multiple depth points, the configuration quantization values ​​of the multiple depth points are determined to obtain the configuration curve.

4. The method according to claim 1, characterized in that: The determining the seepage barrier of the reservoir where the non-coring well is located based on the multiple types of logging phases, the multiple sample vectors and the multiple second logging curves of the non-coring wells in the work area includes: Based on the plurality of second logging curves, determining a plurality of logging vectors, each logging vector comprising a plurality of logging values ​​at a same depth point in the plurality of second logging curves; For each well logging vector, determining the distances between the well logging vector and the plurality of sample vectors; Determine the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors; Based on the logging phases to which the multiple logging vectors respectively belong, the seepage barrier of the area where the non-coring well is located is determined.

5. The method according to claim 4, characterized in that The determining the logging phase to which the logging vector belongs based on the distances respectively corresponding to the multiple sample vectors and the logging phases respectively corresponding to the multiple sample vectors comprises: Sorting the multiple sample vectors based on the distances respectively corresponding to the multiple sample vectors, wherein the order of each sample vector is positively correlated with the distance corresponding to the sample vector; Determine a plurality of target sample vectors ranked after the target number of digits from the plurality of sample vectors; The logging phase to which the plurality of target sample vectors belong to the most among the plurality of logging phases is taken as the logging phase to which the logging vector belongs.

6. The method according to claim 1, characterized in that The multiple clusters are arranged in sequence, the distance between the feature vectors of adjacent clusters is smaller than the distance between the feature vectors of non-adjacent clusters, and the feature vectors are used to describe the clusters; the multiple types of logging phases are determined based on the multiple clusters in the cluster model and the core information of the multiple depth points, including: Based on the core information of the multiple depth points, determining multiple segmentation nodes in the multiple clusters, the clusters before and after the segmentation nodes correspond to different types of core information; The plurality of clusters are divided based on the plurality of segmentation nodes to obtain the plurality of logging phases, each of which includes a plurality of continuous clusters.

7. A device for determining a reservoir seepage barrier, characterized in that: The device comprises: An acquisition module, used to acquire multiple first well logging curves and core information of multiple depth points of coring wells in a work area, wherein the multiple first well logging curves correspond to different types of well logging values, and each first well logging curve includes the well logging values ​​of the multiple depth points; A first determination module, configured to determine a plurality of sample vectors based on the plurality of first logging curves, each sample vector comprising a plurality of logging values ​​at a same depth point in the plurality of first logging curves; A training module, used for performing training based on the multiple sample vectors to obtain a clustering model, wherein the clustering model includes multiple clusters, and the clustering model is used for determining the cluster to which the depth point belongs from the multiple clusters based on multiple well logging values ​​of the depth point; A second determination module is used to determine multiple types of logging phases based on the multiple clusters in the clustering model and the core information of the multiple depth points, wherein the multiple clusters in each type of logging phase correspond to the core information of the same type, and the multiple types of logging phases respectively indicate the reservoir and the seepage barrier of the reservoir; The third determination module is used to determine the seepage barrier of the reservoir where the non-coring well is located based on the multiple types of logging phases, the multiple sample vectors and the multiple second logging curves of the non-coring wells in the work area.

8. A computer device, characterized in that: The computer device includes one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the method for determining the reservoir seepage barrier as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: At least one program code is stored in the storage medium, and the at least one program code is loaded and executed by the processor to implement the method for determining the reservoir seepage barrier according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes a computer program code, which is stored in a computer-readable storage medium. A processor of a computer device reads the computer program code from the computer-readable storage medium, and the processor executes the computer program code, so that the computer device executes the method for determining a reservoir seepage barrier as described in any one of claims 1 to 6.