An adaptive shale gas reservoir intelligent classification and evaluation method and system

By adopting an adaptive intelligent classification and evaluation method for shale gas reservoirs, and based on the sweet spot screening evaluation parameters for shale reservoirs, multiple subsystems are constructed and dynamically adjusted. This solves the problem of poor evaluation adaptability in existing technologies, achieves high-precision shale gas reservoir classification, and supports exploration and development decisions.

CN123069159APending Publication Date: 2026-11-10OIL & GAS SURVEY CGS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611529110.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-30
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Existing shale gas reservoir evaluation methods are not suitable for complex structural areas, ignore the coupling and synergistic relationship of multiple factors, resulting in a large deviation between the evaluation results and the actual development effect. They lack dynamic correction and adaptive capabilities and cannot meet the exploration and development needs of different regions and strata.

Method used

An adaptive intelligent classification and evaluation method for shale gas reservoirs is adopted. Evaluation parameters are selected based on the strong correlation of sweet spots in shale reservoirs. Multiple evaluation subsystems are constructed, and dynamic adjustments are made using the entropy weight method, CRITIC method, and Fisher optimal segmentation method. The contour coefficient method is combined for feedback optimization to achieve intelligent classification.

Benefits of technology

It improves the accuracy and applicability of evaluation results, adapts to the heterogeneity differences of different regions and strata, reduces human intervention, and provides reliable support for exploration and development decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123069159A_ABST
    Figure CN123069159A_ABST
Patent Text Reader

Abstract

The application provides a kind of shale gas reservoir intelligent classification evaluation method and system, it is related to shale gas exploration and development technical field, including: determining a plurality of core identification evaluation parameters, and then dynamically constructing evaluation subsystem from shale gas enrichment condition, engineering compressibility, economic recoverability;The target shale gas layer is divided into a plurality of effective target evaluation intervals;Intelligent classification of shale gas reservoir is carried out on the plurality of effective target evaluation intervals by using the evaluation subsystem, and the reservoir classification result corresponding to each effective target evaluation interval is determined;Based on the profile coefficient method and / or actual gas test results data, the reservoir classification result is dynamically fed back and optimized and tested until the reservoir classification result meets the expected requirements.The application realizes intelligent and dynamic classification and evaluation of shale gas reservoir in different regions, different layer series and different drilling through full-process adaptive and intelligent design, reduces manual intervention, and improves the accuracy and applicability of the evaluation results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of shale gas exploration and development technology, and in particular to an adaptive intelligent classification and evaluation method and system for shale gas reservoirs. Background Technology

[0002] Shale gas is an important unconventional natural gas resource and a valuable supplement to conventional natural gas. However, exploration and development are challenging in areas with complex shale gas geology. Shale gas production mainly comes from the Upper Ordovician Wufeng Formation to the Lower Silurian Longmaxi Formation shale system. As exploration and development gradually expand from within the basin to outside the basin, from shallow to deep layers, from single-layer systems to multi-layer systems, and from simple structural areas to complex structural areas, the industry faces numerous challenges in increasing reserves and production.

[0003] Reservoir classification and evaluation is a core technology for shale gas exploration and development. Currently, most mainstream shale gas reservoir evaluation methods and related patents in China rely on static parameters from a single geological or engineering dimension for evaluation, using simple methods such as linear weighting and quantitative matching to determine reservoirs. These technologies generally have significant shortcomings, neglecting the coupled and synergistic relationships among multiple factors such as shale gas enrichment conditions, engineering compressibility, and economic recoverability. They lack multi-factor dynamic coupling quantitative analysis methods and cannot adapt to differentiated geological reservoir conditions, ultimately leading to significant discrepancies between evaluation results and actual development outcomes.

[0004] While some studies at present have attempted to combine geological and engineering indicators for comprehensive evaluation by constructing coupling coefficients and introducing grey relational analysis, the relevant technologies still mainly rely on simple superposition of static indicators and fixed similarity matching calculations. They cannot achieve objective quantitative calculation of the weights of multiple types of parameters and multi-level evaluation systems, nor do they have the ability to dynamically correct or adaptively adjust, thus limiting the accuracy and universality of the evaluation.

[0005] Furthermore, the current shale gas reservoir evaluation standards are only applicable to the geological characteristics of the shallow and medium-depth Wufeng Formation-Longmaxi Formation shale in the Sichuan Basin. Outside the basin, shale reservoirs in complex structural areas exhibit diverse stratigraphic systems, significant differences in geological conditions, and strong reservoir heterogeneity. The existing fixed evaluation standards cannot accurately reflect the reservoir enrichment characteristics and parameter response patterns, making it difficult for the evaluation results to objectively reflect the true quality of the reservoirs. Therefore, the industry urgently needs a dynamic, intelligent, and adaptive reservoir evaluation method to meet the exploration and development evaluation needs of shale gas in complex structural areas under different basins, stratigraphic systems, and drilling scenarios. Summary of the Invention

[0006] In view of this, the purpose of this application is to provide at least one adaptive intelligent classification and evaluation method and system for shale gas reservoirs. By screening the evaluation parameters in the evaluation area based on the sweet spots of shale reservoirs and then further constructing an evaluation subsystem, the method solves the problem of poor adaptability of the current evaluation standards, realizes intelligent and dynamic classification and evaluation of shale gas reservoirs in different regions, different formations and different wells, and improves the accuracy and applicability of the evaluation results.

[0007] This application mainly includes the following aspects: In a first aspect, embodiments of this application provide an adaptive intelligent classification and evaluation method for shale gas reservoirs. The method includes: acquiring evaluation data for the same target shale gas layer from at least one exploration well distributed in the evaluation area and processing the data to form a standardized evaluation dataset; adaptively filtering the standardized evaluation dataset based on its strong correlation with the sweet spot of the shale reservoir to determine multiple core identification and evaluation parameters, and then dynamically constructing an evaluation subsystem from the aspects of shale gas enrichment conditions, engineering compressibility, and economic recoverability; dividing the target shale gas layer into multiple effective target evaluation segments; using the evaluation subsystem to perform intelligent classification of shale gas reservoirs in the multiple effective target evaluation segments, and determining the reservoir classification result corresponding to each effective target evaluation segment; and dynamically optimizing and verifying the reservoir classification result based on the profile coefficient method and / or actual gas testing results until the reservoir classification result meets the expected requirements.

[0008] In one possible implementation, the evaluation data includes multiple evaluation parameters and measurement value sequences of each evaluation parameter under different exploration wells. The standardized evaluation dataset is formed through the following steps: Multiple evaluation parameters are intelligently classified according to a preset evaluation parameter classification table to determine the evaluation parameter category corresponding to each parameter. Evaluation parameter categories include identification evaluation parameters and auxiliary evaluation parameters. The measurement value sequences of each evaluation parameter under different exploration wells are pre-processed based on missing and outlier data to obtain pre-processed measurement value sequences for each evaluation parameter under different exploration wells. Under the constraints of auxiliary evaluation parameters, the pre-processed measurement value sequences of identification evaluation parameters are encrypted using an adaptive interpolation method to obtain encrypted measurement value sequences corresponding to the identification evaluation parameters. Based on a preset parameter directionality comprehensive judgment table and the reservoir characteristics of the area to be evaluated, the directionality of each identification evaluation parameter is determined. Directionality includes positive, negative, intermediate, and interval types. According to the directionality of the identification evaluation parameters, the encrypted measurement value sequences of the identification evaluation parameters are standardized using the corresponding standardized calculation formula to obtain standardized sequences corresponding to the identification evaluation parameters. The standardized sequences are then subjected to consistency verification, and the standardized sequences that have passed consistency verification form the standardized evaluation dataset.

[0009] In one possible implementation, the standardized calculation formula for the identification evaluation parameter with positive directionality is:

[0010] For the identification and evaluation parameters with negative directionality, the corresponding standardized calculation formula is:

[0011] For the identification and evaluation parameters with intermediate directionality, the corresponding standardized calculation formula is:

[0012] For identification and evaluation parameters with interval-type directionality, the corresponding standardized calculation formula is:

[0013] in, Indicates the first The evaluation parameters for identification are in the first stage. Standardized values ​​at each depth Indicates the first The evaluation parameters for identification are in the first stage. Measurements at various depths Indicates the first The maximum value of a discrimination evaluation parameter among all its corresponding measurements. Indicates the first The minimum value of the identification evaluation parameter among all its corresponding measurements. This represents a very small value, taking the value 0.001. Indicates the first The optimal value of the evaluation parameter among all its corresponding measurements. and The respective The lower and upper limits of the optimal measurement range indicated by all the measured values ​​corresponding to the evaluation parameters.

[0014] In one possible implementation, the evaluation subsystem is constructed as follows: Based on the standardized sequence corresponding to each evaluation parameter, an adaptive correlation analysis algorithm is used to determine the correlation between the evaluation parameters. Based on the correlation, parameters with no correlation, weak correlation, or high correlation are eliminated to obtain multiple core evaluation parameters. According to a preset evaluation parameter classification table, the multiple core evaluation parameters are further divided into enriched evaluation parameters, compressibility evaluation parameters, and adoptability evaluation parameters, and the corresponding enriched evaluation subsystem, compressibility evaluation subsystem, and adoptability evaluation subsystem are dynamically constructed. The effectiveness of the evaluation subsystem is verified in terms of the number of evaluation subsystems and the completeness of the evaluation parameters corresponding to the evaluation subsystems, resulting in an evaluation subsystem that passes the consistency check.

[0015] In one possible implementation, the step of dividing the target shale gas layer into multiple effective target evaluation segments includes: obtaining the user's pre-entered division requirements for the target shale gas layer; dividing the target shale gas layer into multiple target evaluation segments according to the division requirements; and performing validity verification on the multiple target evaluation segments based on the segment thickness and the number of segments to obtain multiple effective target evaluation segments.

[0016] In one possible implementation, the reservoir classification result corresponding to each effective target evaluation segment is determined as follows: Using the entropy weight method, the weight of each core identification evaluation parameter within its respective evaluation subsystem is determined; based on the standardized sequence of the core identification evaluation parameter in the well and its weight within its respective evaluation subsystem, the comprehensive evaluation index of the evaluation subsystem under different effective target evaluation segments is calculated; using the CRITIC method, the system weight coefficient of each evaluation subsystem in the well is determined; based on the comprehensive evaluation index of the evaluation subsystem under different effective target evaluation segments, the coupling coordination degree of each evaluation subsystem under different effective target evaluation segments is determined; for each effective target evaluation segment, the arithmetic mean of the coupling coordination degrees calculated from multiple wells under that effective target evaluation segment is determined as the target coupling coordination degree of that effective target evaluation segment; based on the target coupling coordination degree of the effective target evaluation segment, Fisher's optimal segmentation is applied to adaptively determine the reservoir classification result for each effective target evaluation segment.

[0017] In one possible implementation, the weight of each core identification evaluation parameter within its respective evaluation subsystem is determined by the following formula:

[0018] This represents the weight of the i-th core identification evaluation parameter within its respective evaluation subsystem. This represents the total number of core identification evaluation parameters corresponding to the evaluation subsystem to which the i-th type of core identification evaluation parameter belongs. The information entropy represents the i-th type of core identification and evaluation parameter. This indicates the evaluation subsystem to which the i-th type of core identification evaluation parameter belongs. Information entropy of core identification and evaluation parameters;

[0019] in, Indicates the first The ratio between the j-th standardized value of a core identification and evaluation parameter and the sum of its corresponding standardized values. This represents the total number of standardized values ​​corresponding to the core identification and evaluation parameters.

[0020]

[0021] In this formula, Indicates the first The k-th standardized value of the core identification and evaluation parameters, Indicates the first The evaluation parameters for identification are in the first stage. Standardized values ​​at each depth.

[0022] In one possible implementation, the comprehensive evaluation index of each evaluation subsystem under different effective target evaluation levels is determined by the following formula:

[0023] In this formula, Indicates the first The evaluation subsystem in the first... A comprehensive evaluation index under each effective target evaluation segment. Indicates the first The number of measurement values ​​collected in each effective target evaluation segment. Indicates the first The first evaluation subsystem The core identification and evaluation parameters in the first The weights within the evaluation subsystem, m represents the weight of the i-th evaluation subsystem. The number of core identification and evaluation parameters corresponding to each evaluation subsystem No. The j-th standardized value of the i-th core identification evaluation parameter under the evaluation subsystem.

[0024] In one possible implementation, the step of determining the system weight coefficient of each evaluation subsystem in the well using the CRITIC method includes: calculating the standard deviation of the comprehensive evaluation index of each evaluation subsystem in the well; calculating the system correlation coefficient of each evaluation subsystem in the well using the correlation coefficient method; calculating the information content-conflict comprehensive index of each evaluation subsystem in the well based on the standard deviation of the comprehensive evaluation index of each evaluation subsystem in the well and the system correlation coefficient of each evaluation subsystem in the well; and calculating the system weight coefficient of each evaluation subsystem in the well based on the information content-conflict comprehensive index of each evaluation subsystem in the well.

[0025] In one possible implementation, the coupling coordination degree of each evaluation subsystem under each effective target evaluation segment is determined by the following formula:

[0026] In the formula, Let M be the coupling degree of each evaluation subsystem at the k-th effective target evaluation segment, and M be the number of evaluation subsystems. For the first The comprehensive evaluation index of the evaluation subsystem under the k-th effective target evaluation segment. The degree of coordination among the evaluation subsystems at the k-th effective target evaluation level. To evaluate the subsystem The system weighting coefficients in the corresponding exploration wells The degree of coupling coordination of each evaluation subsystem under the kth effective target evaluation segment.

[0027] In one possible implementation, the reservoir classification result for each effective target evaluation segment is determined as follows: the target coupling coordination degree corresponding to each effective target evaluation segment is sorted in ascending order to form a coupling coordination degree sequence; the subset sum of squared deviations corresponding to the coupling coordination degree sequence is determined; a dynamic programming table is constructed based on the minimum total sum of squared deviations by pre-setting the number of segment classifications and the number of effective target evaluation segments, and recursive operations are used to determine the reservoir classification result for the effective target evaluation segment.

[0028] In one possible implementation, the steps of dynamically optimizing and verifying reservoir classification results based on the profile coefficient method and / or actual gas testing data until the reservoir classification results meet the expected requirements include: calculating the overall profile coefficient corresponding to all effective target evaluation segments within each type of reservoir; comparing the reservoir classification results with the actual gas testing data of exploration wells in the area to be evaluated; if the overall profile coefficient meets the overall profile coefficient standard and the reservoir classification results are consistent with the actual gas testing data of exploration wells in the area to be evaluated, then the reservoir classification results are output as the final classification results; if the overall profile coefficient does not meet the overall profile coefficient standard, or the reservoir classification results are inconsistent with the actual gas testing data of exploration wells in the area to be evaluated, then a parameter adjustment prompt is generated; in response to the parameter adjustment operation, the process is returned to re-execution.

[0029] Secondly, this application also provides an adaptive intelligent classification and evaluation system for shale gas reservoirs. The system includes a data acquisition and processing module, a subsystem construction module, an evaluation layer segment division module, a reservoir classification and evaluation module, and a feedback optimization module. The data acquisition and processing module is used to acquire evaluation data for the same target shale gas layer from at least one exploration vessel distributed in the evaluation area and process the data to form a standardized evaluation dataset. The subsystem construction module is used to adaptively filter the standardized evaluation dataset based on the strong correlation with the sweet spots of the shale reservoir, determining multiple core... The system identifies evaluation parameters and then dynamically constructs an evaluation subsystem based on shale gas enrichment conditions, engineering compressibility, and economic recoverability. An evaluation segment division module is used to divide the target shale gas layer into multiple effective target evaluation segments. A reservoir classification evaluation module is used to intelligently classify shale gas reservoirs from multiple effective target evaluation segments using the evaluation subsystem, determining the reservoir classification result for each effective target evaluation segment. A feedback optimization module is used to dynamically optimize and verify the reservoir classification results based on the profile coefficient method and / or actual gas testing data, until the reservoir classification results meet the expected requirements.

[0030] This application provides an adaptive intelligent classification and evaluation method and system for shale gas reservoirs, comprising: adaptively filtering a standardized evaluation dataset based on a strong correlation with the sweet spot of shale reservoirs to determine multiple core identification and evaluation parameters, and then dynamically constructing an evaluation subsystem from the aspects of shale gas enrichment conditions, engineering compressibility, and economic recoverability; dividing the target shale gas layer into multiple effective target evaluation segments; using the evaluation subsystem to perform intelligent classification of shale gas reservoirs in multiple effective target evaluation segments, and determining the reservoir classification result corresponding to each effective target evaluation segment; and dynamically optimizing and verifying the reservoir classification results based on the profile coefficient method and / or actual gas testing results, until the reservoir classification results meet the expected requirements.

[0031] The advantages of this application are: The technical solution provided in this application, through full-process adaptive and intelligent design, realizes dynamic adjustment of shale gas reservoir classification and evaluation, and can adapt to the heterogeneity differences of reservoirs in different regions and strata.

[0032] The weights of different evaluation subsystems are objectively calculated using the entropy weight method and the CRITIC method. The synergistic effect of multiple subsystems is quantified by combining the coupling coordination degree model. The classification threshold is adaptively determined using the Fisher optimal segmentation method, thereby improving the accuracy of classification evaluation.

[0033] By using the profile coefficient method for feedback optimization and combining it with a user-initiated adjustment mechanism, the rationality and applicability of the evaluation results are further ensured. The entire process reduces human intervention and solves the problems of poor adaptability and large classification bias in traditional evaluation methods, providing reliable technical support for shale gas reservoir exploration and development decisions.

[0034] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 The flowchart of an adaptive shale gas reservoir intelligent classification and evaluation method provided in an embodiment of this application is shown. Figure 2 A flowchart illustrating a data processing procedure provided in an embodiment of this application is shown; Figure 3 A flowchart illustrating an evaluation subsystem construction method provided in an embodiment of this application is shown; Figure 4 This document illustrates a flowchart of an effective target evaluation segmentation method provided in an embodiment of this application. Figure 5 A flowchart illustrating a method for determining reservoir classification results provided in an embodiment of this application is shown; Figure 6 A flowchart of a reservoir classification result evaluation and processing method provided in an embodiment of this application is shown; Figure 7 The diagram illustrates the functional modules of an adaptive shale gas reservoir intelligent classification and evaluation system provided in an embodiment of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0038] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0039] This application provides an adaptive intelligent classification and evaluation method and system for shale gas reservoirs. This application solves the problems of poor adaptability, excessive manual intervention, and low classification accuracy in traditional shale gas reservoir evaluation methods. It can adaptively adapt to the heterogeneity differences of shale reservoirs in different regions and strata, realizing intelligent and dynamic shale reservoir classification and evaluation, and providing a reliable basis for shale gas exploration and development decisions. Specifically, as follows: Please see Figure 1 , Figure 1 A flowchart illustrating an adaptive intelligent classification and evaluation method for shale gas reservoirs provided in an embodiment of this application is shown. Figure 1 As shown, the method provided in this application embodiment includes the following steps: S100. For at least one exploration well distributed in the area to be evaluated, obtain evaluation data of the same target shale gas layer and process the data to form a standardized evaluation dataset.

[0040] S200, based on the strong correlation with the sweet spot of shale reservoirs, adaptively filters the standardized evaluation dataset to determine multiple core identification and evaluation parameters, and then dynamically constructs an evaluation subsystem from the aspects of shale gas enrichment conditions, engineering compressibility, and economic recoverability.

[0041] S300: Divide the target shale gas layer into multiple effective target evaluation segments.

[0042] S400. The evaluation subsystem is used to perform intelligent classification of shale gas reservoirs for multiple effective target evaluation segments, and the reservoir classification result corresponding to each effective target evaluation segment is determined.

[0043] S500, based on the profile coefficient method and / or actual gas testing results, performs dynamic feedback optimization and verification of reservoir classification results until the reservoir classification results meet the expected requirements.

[0044] Taking shale gas exploration block A as an example, a Permian Dalong Formation shale gas layer is developed within shale gas exploration block A, and three exploration wells, namely exploration well a1, exploration well a2, and exploration well a3, are distributed within shale gas exploration block A to explore the target shale gas layer. The target shale gas layer is located within the target depth range, for example, 2800 m to 3200 m. The reservoir exhibits strong heterogeneity, with significant vertical differences in gas content and physical properties. The existing evaluation standards provided by the technology are poorly adapted to shale gas exploration block A. Therefore, the target shale gas layer within shale gas exploration block A is evaluated through the steps S100 to S400 provided in this application. Specifically, before executing steps S100 to S500, the following steps are performed: A regional geological database must be established, which includes geological background data of the Dalong Formation shale reservoir in shale gas exploration block A, a pre-set evaluation parameter classification table, a pre-set parameter directionality comprehensive judgment table, the number of pre-set reservoir classifications, and each reservoir type (for example, the number of reservoir classifications is 3, and the reservoir types include high-quality sweet spots, potential sweet spots, and non-sweet spots), as well as the pre-set rationality judgment criteria for reservoir classification. For example, the pre-set rationality judgment criteria for reservoir classification is an overall profile coefficient ≥ 0.7.

[0045] The predefined parameters are as follows: Based on the target depth range of the target shale gas layer (exemplary, 2800 m-3200 m), the necessary evaluation parameter types and data densities are predefined. Specifically, the user-inputted identification evaluation parameters must include organic carbon content, porosity, and brittleness index, a total of 3, which are called necessary identification evaluation parameters. The depth range of the above parameter data points must completely cover the target depth range, and the data density must be no less than 1 data point per 2 meters. The user-inputted auxiliary evaluation parameters must include natural gamma, deep lateral resistivity, compensated neutrons, compensated density, acoustic transit time, and total hydrocarbon value, a total of 6, which are called core auxiliary evaluation parameters. The data density must be no less than 5 data points per 1 meter. The remaining parameters do not need to be manually preset and are determined adaptively by the method.

[0046] After the above data entry is completed, proceed to steps S100 to S500, which specifically include: In step S100, the data for evaluation includes a plurality of evaluation parameters and a measured value sequence of each evaluation parameter under different exploration wells, wherein, within the target depth interval (2800m~3200m) covering the target shale gas layer, for each exploration well, the measured values of each evaluation parameter are collected in advance according to a given data acquisition density, so as to obtain the measured value sequence corresponding to each evaluation parameter.

[0047] Exemplarily, the plurality of evaluation parameters include total organic carbon content, gas saturation, brittleness index, Young's modulus, porosity, permeability, total gas logging hydrocarbon value, shale content, natural gamma ray, deep lateral resistivity, acoustic transit time and compensated neutron.

[0048] In a preferred embodiment, please refer to Figure 2 , Figure 2 which shows a flowchart of a data processing and procedure provided by the embodiment of the present application. As shown in Figure 2 , step S100 further includes: S1001: Perform intelligent classification on the plurality of evaluation parameters according to a preset evaluation parameter classification table, and determine the evaluation parameter category corresponding to each evaluation parameter.

[0049] S1002: Perform pre-processing based on missing and abnormal data on the measured value sequence of each evaluation parameter under different exploration wells, so as to obtain a pre-processed measured value sequence of each evaluation parameter under different exploration wells.

[0050] S1003: Under the constraint of auxiliary evaluation parameters, perform densification on the pre-processed measured value sequence of the identification evaluation parameter according to an adaptive interpolation method, so as to obtain a densified measured value sequence corresponding to the identification evaluation parameter.

[0051] S1004: Determine the directionality of each identification evaluation parameter based on a preset parameter directionality comprehensive determination table and the reservoir characteristics of the to-be-evaluated area.

[0052] Preferably, the directionality includes positive type, negative type, intermediate type and interval type; S1005: According to the directionality of the identification evaluation parameter, adopt a corresponding standardization calculation formula to perform standardization processing on the densified measured value sequence of the identification evaluation parameter, so as to obtain a standardized sequence corresponding to the identification evaluation parameter.

[0053] S1006: Perform consistency verification on the standardized sequence, and form a standardized evaluation dataset from the standardized sequences that have passed the consistency verification.

[0054] In a specific embodiment, a preset evaluation parameter classification table is pre-entered, which describes multiple preset evaluation parameters and the parameter category to which each preset evaluation parameter belongs. The parameter categories are divided into identification evaluation parameters and auxiliary evaluation parameters. The multiple evaluation parameters are automatically classified and organized according to the preset evaluation parameter classification table. The multiple identification evaluation parameters include organic carbon content, gas saturation, brittleness index, Young's modulus, porosity, permeability, and clay content. The multiple auxiliary evaluation parameters include gas logging total hydrocarbon value, natural gamma, deep lateral resistivity, sonic transit time, and compensated neutrons. Among them, natural gamma, deep lateral resistivity, sonic transit time, compensated neutrons, and compensated density are logging auxiliary parameters, and gas logging total hydrocarbon value is logging auxiliary parameter. Since exploration well a1 does not provide compensated density, and compensated density is a core auxiliary evaluation parameter, it needs to be supplemented in step S1002 before participating in subsequent processing.

[0055] In a preferred embodiment, step S1002 further includes: Based on the pre-entered necessary evaluation parameters (indicating the evaluation parameters that the user must provide) and the predefined data interval density for each evaluation parameter, missing value detection is performed on the measurement value sequence to obtain missing value detection results. The missing value detection results are used to describe whether there are missing measurement value sequences for necessary evaluation parameters and whether there are missing values ​​in the test value sequence. According to the reasonable distribution range of the measurement values ​​predefined by the evaluation parameters, outlier detection is performed on the corresponding measurement value sequences to obtain outlier detection results. Based on the missing value detection results and outlier detection results for each evaluation parameter, a preprocessing prompt is generated to instruct the user to correct the measurement value sequences containing missing and outlier values. In response to the measurement value sequence correction operation performed by the user under the preprocessing prompt, a preprocessed measurement value sequence is obtained.

[0056] In one specific embodiment, for example, the following issues are detected: a missing measurement value sequence corresponding to the compensated density provided by exploration well a1; three missing values ​​in the porosity data sequence provided by exploration well a2 within the 2950m-2960m depth range, causing the porosity data sequence provided by exploration well a2 to fail to meet the requirement of one data collection point every 2 meters; and one outlier value of 25.2% in the measurement value sequence corresponding to the organic carbon content provided by exploration well a3, far exceeding the reasonable distribution range of 3%-8% for organic carbon content in shale gas exploration block A. Based on these detected problems, a corresponding pre-processing prompt is generated. Specifically, the pre-processing prompt advises the user to "supplement the measurement value sequence of the compensated density provided by exploration well a1, supplement the missing values ​​in the measurement value sequence of the porosity provided by exploration well a2, and check the outlier value in the measurement value sequence of the organic carbon content provided by exploration well a3." Ultimately, a pre-processed measurement value sequence is obtained.

[0057] In step S1003, with the core auxiliary evaluation parameters as constraints, based on the pre-processed test value sequence corresponding to the identified evaluation parameters, an adaptive interpolation method is established according to the longitudinal gradient, fluctuation degree and variation characteristics of the data. The data interval indicated by the adaptive interpolation method is used to encrypt the pre-processed test value sequence. For example, an adaptive interpolation method based on a longitudinal local window is used, specifically according to a data interval of 0.25 meters, to encrypt the pre-processed test value sequence corresponding to the identified evaluation parameters, thus obtaining the encrypted measurement value sequence corresponding to the identified evaluation parameters.

[0058] In step S1004, the preset parameter directionality comprehensive judgment table describes the following: For each identification and evaluation parameter, if its larger measured value indicates better shale reservoir quality, it is judged as a positive parameter; if its smaller value indicates better shale reservoir quality, it is judged as a negative parameter; if its value indicates optimal shale reservoir quality at a specific measured value, it is judged as an intermediate parameter; and if its value indicates optimal shale reservoir quality within a specific measured value range, it is judged as a range parameter. Based on the preset parameter directionality comprehensive judgment table, among the multiple identification and evaluation parameters, organic carbon content is positive, gas saturation is positive, brittleness index is intermediate, Young's modulus is range, porosity is positive, permeability is positive, and clay content is negative.

[0059] In a preferred embodiment, in step S1005, the standardized calculation formula for the identification evaluation parameter with positive directionality is:

[0060] For the identification and evaluation parameters with negative directionality, the corresponding standardized calculation formula is:

[0061] For the identification and evaluation parameters with intermediate directionality, the corresponding standardized calculation formula is:

[0062] For identification and evaluation parameters with interval-type directionality, the corresponding standardized calculation formula is:

[0063] in, Indicates the first The evaluation parameters for identification are in the first stage. Standardized values ​​at each depth Indicates the first The evaluation parameters for identification are in the first stage. Measurements at various depths Indicates the first The maximum value of a discrimination evaluation parameter among all its corresponding measurements. Indicates the first The minimum value of the identification evaluation parameter among all its corresponding measurements. This represents a very small value, taking the value 0.001. Indicates the first The optimal value of the evaluation parameter among all its corresponding measurements. and The respective The lower and upper limits of the optimal measurement range indicated by all the measured values ​​corresponding to the evaluation parameters.

[0064] Since parameter standardization is a common data processing method in this field, its specific method will not be elaborated. After standardization, all measurement values ​​in the encrypted measurement value sequence are converted to the [0,1] interval. For example, in the measurement value sequence of organic carbon content provided by exploration well a1, a certain original measurement value is 6.2%, which is 0.75 after standardization, and a certain porosity original measurement value is 4.2%, which is 0.68 after standardization.

[0065] In step S1006, the standardized sequences are subjected to consistency verification. After confirming that the standardized sequences have no omissions, no abnormalities, no biases, and the intervals are the same, and the data pass rate reaches 100%, the standardized sequences are determined to have passed the consistency verification. The standardized sequences that have passed the consistency verification form a standardized evaluation dataset, which is used for the subsequent construction of the evaluation subsystem.

[0066] In a preferred embodiment, please refer to Figure 3 , Figure 3 A flowchart illustrating a construction method for an evaluation subsystem provided in an embodiment of this application is shown. Figure 3 As shown, step S200 further includes: S2001. Based on the standardized sequence corresponding to each identification and evaluation parameter, an adaptive correlation analysis algorithm is used to determine the correlation between each identification and evaluation parameter. Based on the correlation, parameters with no correlation, weak correlation, or high correlation are eliminated to obtain multiple core identification and evaluation parameters.

[0067] S2002. According to the preset evaluation parameter classification table, the multiple core identification evaluation parameters are further divided into enrichment identification parameters, compressibility identification parameters and adoptability identification parameters, and the corresponding enrichment evaluation subsystem, compressibility evaluation subsystem and adoptability evaluation subsystem are dynamically constructed.

[0068] S2003. The effectiveness of the evaluation subsystem is verified in terms of the number of evaluation subsystems and the completeness of the identification parameters corresponding to the evaluation subsystems, so as to obtain the evaluation subsystem that passes the consistency verification.

[0069] In a specific embodiment provided in step S2001: Assuming that for the identification and evaluation parameters, the correlation coefficient between Young's modulus and brittleness index is 0.89, indicating that the two are highly correlated and have redundant correlation, the correlation coefficient between clay content and organic carbon content is 0.12, indicating that the two are weakly correlated, and the correlation coefficients between the remaining identification and evaluation parameters are all <0.6, then parameter screening is carried out based on the correlation coefficients between each identification and evaluation parameter, and Young's modulus and clay content are eliminated to obtain multiple core identification and evaluation parameters. In the specific embodiment provided in this application, for example, the multiple core identification and evaluation parameters include organic carbon content, porosity, gas saturation, brittleness index and permeability.

[0070] In step S2002, enrichment evaluation subsystems, compressibility evaluation subsystems, and mineability evaluation subsystems are dynamically constructed based on enrichment identification parameters, respectively. Specifically, enrichment identification parameters include organic carbon content and gas saturation, compressibility identification parameters include brittleness index, and mineability identification parameters include porosity and permeability.

[0071] In step S2003, the consistency check applies to all evaluation subsystems. Specifically, it includes checking the number of evaluation subsystems and the number of parameters for each evaluation subsystem. For example, if it is detected that the number of evaluation subsystems is 3, the number of enrichment identification parameters is 2, the number of compressibility identification parameters is 1, and the number of adoptability identification parameters is 2, then the number of evaluation subsystems meets the requirement of ≥1, the number of enrichment identification parameters and the number of adoptability identification parameters meet the requirement of ≥2, and the number of compressibility identification parameters does not meet the requirement of ≥2. At this time, a consistency check prompt for the evaluation subsystems is automatically generated. For example, the generated consistency check prompt specifically instructs the user that "Three evaluation subsystems have been constructed: enrichment, compressibility, and adoptability. Among them, the compressibility evaluation subsystem is invalid. Please supplement the input compressibility identification parameters."

[0072] For example, under the above-mentioned consistency verification prompt for the evaluation subsystem, the user supplements the measurement value sequence of the compressibility identification parameter "rupture pressure" under different exploration wells. After the supplement is completed, the user performs the processing of steps S1002 to S1006 and step S200 on the measurement value sequence. After confirming that the standardized sequence corresponding to the compressibility identification parameter is valid, the user includes "rupture pressure" in the compressibility identification parameter and verifies the number of compressibility identification parameters again until the compressibility evaluation subsystem is confirmed to be valid.

[0073] In a preferred embodiment, please refer to Figure 4 , Figure 4 A flowchart illustrating an effective target evaluation segmentation method provided in an embodiment of this application is shown. Figure 4 As shown, step S300 further includes: S3001. Obtain the user's pre-entered requirements for the division of the target shale gas layer.

[0074] S3002. Based on the classification requirements, the target shale gas layer is divided into multiple target evaluation segments.

[0075] S3003. Validate the effectiveness of multiple target evaluation segments based on segment thickness and number of segments to obtain multiple valid target evaluation segments.

[0076] In step S3001, the division of requirements describes the depth range of multiple target evaluation segments, including the top boundary depth value and the bottom boundary depth value.

[0077] In step S3002, for example, based on the depth range of the six target evaluation segments input by the user, six target evaluation segments are divided into six segments, including segment b1 (depth range of 2800m-2850m), segment b2 (depth range of 2850m-2900m), segment b3 (depth range of 2900m-2975m), segment b4 (depth range of 2975m-3000m), segment b5 (depth range of 3000m-3108m), and segment b6 (depth range of 3108m-3200m).

[0078] In step S3002, the validity verification of the target evaluation segments includes segment thickness verification and segment quantity verification. Specifically, if the thickness of each target evaluation segment is greater than or equal to the target segment thickness threshold, and the number of target evaluation segments is greater than or equal to the preset segment quantity threshold, then the division of multiple target evaluation segments is determined to be valid, a corresponding valid segment division prompt is generated, and multiple target evaluation segments are obtained. If the thickness of any target evaluation segment is less than the target segment thickness threshold, or the number of target evaluation segments is less than the preset segment quantity threshold, then the division of multiple target evaluation segments is determined to be invalid, and a corresponding invalid segment division prompt is generated.

[0079] In one specific embodiment, for example, the target segment thickness threshold is 10 meters, and the preset segment number threshold is 2. If the thickness of each target evaluation segment is ≥10 meters and the number of target evaluation segments is ≥2, a valid segment division prompt is generated, specifically "Target evaluation segment division is valid". If any target evaluation segment thickness is <10 meters or the number of target evaluation segments is <2, an invalid segment division prompt is generated, for example, "Target evaluation segment division is invalid, please check the input depth range".

[0080] In a preferred embodiment, please refer to Figure 5 , Figure 5 A flowchart illustrating a method for determining reservoir classification results provided in an embodiment of this application is shown. Figure 5 As shown, for each exploration well, step S400 includes: S4001. Using the entropy weight method, determine the weight of each core identification and evaluation parameter within its respective evaluation subsystem.

[0081] S4002. Based on the standardized sequence of the core identification and evaluation parameters in the well and their weights in the evaluation subsystem, calculate the comprehensive evaluation index of the evaluation subsystem under different effective target evaluation segments.

[0082] S4003. Use the CRITIC method to determine the system weight coefficients of each evaluation subsystem in this exploration well.

[0083] S4004. Based on the comprehensive evaluation index of the evaluation subsystem under different effective target evaluation levels, determine the coupling coordination degree of each evaluation subsystem under different effective target evaluation levels.

[0084] S4005. For each effective target evaluation layer, the arithmetic mean of the coupling coordination degree calculated by multiple exploration wells under the effective target evaluation layer is determined as the target coupling coordination degree of the effective target evaluation layer.

[0085] S4006. Based on the target coupling coordination degree of the effective target evaluation segment, Fisher's optimal segmentation is applied to adaptively determine the reservoir classification result for each effective target evaluation segment.

[0086] In one specific embodiment, in step S4001, the weight of each core identification evaluation parameter within its respective evaluation subsystem is determined using the following formula:

[0087] This represents the weight of the i-th core identification evaluation parameter within its respective evaluation subsystem. This represents the total number of core identification evaluation parameters corresponding to the evaluation subsystem to which the i-th type of core identification evaluation parameter belongs. The information entropy represents the i-th type of core identification and evaluation parameter. This indicates the evaluation subsystem to which the i-th type of core identification evaluation parameter belongs. Information entropy of core identification and evaluation parameters.

[0088] In one specific embodiment:

[0089] in, Indicates the first The ratio between the j-th standardized value of a core identification and evaluation parameter and the sum of its corresponding standardized values. This represents the total number of standardized values ​​corresponding to the core identification and evaluation parameters.

[0090]

[0091] In this formula, Indicates the first The k-th standardized value of the core identification and evaluation parameter.

[0092] In a preferred embodiment, for example, the weight calculation results corresponding to each core identification parameter are as follows: in the enrichment evaluation subsystem, the weight of organic carbon content is 0.48 and the weight of gas saturation is 0.52; in the compressibility evaluation subsystem, the weight of brittleness index is 0.55 and the weight of fracture pressure is 0.45; in the mineability evaluation subsystem, the weight of porosity is 0.62 and the weight of permeability is 0.38.

[0093] In specific implementation, step S4002 determines the comprehensive evaluation index of the evaluation subsystem under different effective target evaluation levels using the following formula:

[0094] In this formula, Indicates the first The evaluation subsystem in the first... A comprehensive evaluation index under each effective target evaluation segment. Indicates the first The number of measurement values ​​collected in each effective target evaluation segment. Indicates the first The first evaluation subsystem The core identification and evaluation parameters in the first The weights within the evaluation subsystem, m represents the weight of the i-th evaluation subsystem. The number of core identification and evaluation parameters corresponding to each evaluation subsystem No. The j-th standardized value of the i-th core identification evaluation parameter under the evaluation subsystem.

[0095] In a preferred embodiment, the comprehensive evaluation index of each evaluation subsystem in the above six effective target evaluation segments is, for example, as follows: based on the standardized sequence corresponding to each core identification evaluation parameter provided by exploration well a1, the comprehensive evaluation index of the enrichment evaluation subsystem in the effective target evaluation segment b1 is 0.87, the comprehensive evaluation index of the compressibility evaluation subsystem in the effective target evaluation segment b1 is 0.82, and the comprehensive evaluation index of the recoverability evaluation subsystem in the effective target evaluation segment b1 is 0.85.

[0096] In one example, step S4003 further includes: For each exploration well, the standardized sequence corresponding to the core identification and evaluation parameters is executed as follows: S40031. Calculate the standard deviation of the comprehensive evaluation index for each evaluation subsystem in the well.

[0097] S40032. Calculate the system correlation coefficient of each evaluation subsystem in this exploration well using the correlation coefficient method.

[0098] S40033. Based on the standard deviation of the comprehensive evaluation index of the evaluation subsystem in the well and the system correlation coefficient of each evaluation subsystem in the well, calculate the information content-conflict comprehensive index of each evaluation subsystem in the well.

[0099] S40034. Based on the information content-conflict comprehensive index of each evaluation subsystem in the well, calculate the system weight coefficient of each evaluation subsystem in the well.

[0100] In one specific embodiment, in step S40031, the standard deviation of the comprehensive evaluation index for each evaluation subsystem is calculated using the following formula:

[0101] In this formula, based on each exploration well, Indicates the first The standard deviation of the comprehensive evaluation index of the evaluation subsystem in this exploration well. Indicates the first The evaluation subsystem in the first... The comprehensive evaluation index of each effective target evaluation segment. Indicates the first The average comprehensive evaluation index of each evaluation subsystem across all effective target evaluation segments, where N represents the number of effective target evaluation segments.

[0102] For example, the standard deviation of the comprehensive evaluation index calculated by the enrichment evaluation subsystem in exploration well a1 is σ=0.12, the standard deviation of the comprehensive evaluation index calculated by the compressibility evaluation subsystem in exploration well a1 is σ=0.09, and the standard deviation of the comprehensive evaluation index calculated by the recoverability evaluation subsystem in exploration well a1 is σ=0.11.

[0103] In a preferred embodiment, in step S40032, the correlation coefficient method can be the Pearson correlation coefficient method, specifically calculated using the following formula for the system correlation coefficient of each evaluation subsystem in the well:

[0104] In this formula, Representation of the evaluation subsystem With evaluation subsystem The systematic correlation coefficient between them Representation of the evaluation subsystem In the The comprehensive evaluation index of each effective target evaluation segment. Representation of the evaluation subsystem The average of the comprehensive evaluation index across all valid target evaluation segments, where N represents the number of valid target evaluation segments. Representation of the evaluation subsystem In the The comprehensive evaluation index of each effective target evaluation segment. Representation of the evaluation subsystem The average value of the comprehensive evaluation index across all valid target evaluation segments.

[0105] For example, the correlation coefficient between the enrichment evaluation subsystem and the compressibility evaluation subsystem in exploration well a1 is r=0.65, the correlation coefficient between the enrichment evaluation subsystem and the recoverability evaluation subsystem in exploration well a1 is r=0.78, and the correlation coefficient between the compressibility evaluation subsystem and the recoverability evaluation subsystem in exploration well a1 is r=0.59.

[0106] In a preferred embodiment, in step S40033, the information content—conflict comprehensive index—of each evaluation subsystem in the corresponding exploration well is calculated using the following formula:

[0107] In this formula, To evaluate the subsystem Information content—conflict composite index To evaluate the number of subsystems; Representation of the evaluation subsystem The standard deviation of the comprehensive evaluation index in the corresponding exploration well. Representation of the evaluation subsystem With evaluation subsystem The systematic correlation coefficient between them.

[0108] For example, the information content and conflict-related comprehensive index of the enrichment evaluation subsystem in exploration well a1. =0.12×(1-0.65+1-0.78+1-0.59)=0.12×0.98=0.1176, Information content of the compressibility evaluation subsystem in exploration well a1—Comprehensive index of conflict. =0.09×(1-0.65+1-0.59+1-0.78)=0.09×0.98=0.0882, the information content of the recoverability evaluation subsystem in exploration well a1—the comprehensive index of conflict. =0.11×(1-0.78+1-0.59+1-0.65)=0.11×0.98=0.1078.

[0109] Furthermore, in step S40034, the system weight coefficient of each evaluation subsystem in the corresponding exploration well is calculated using the following formula:

[0110] In this formula, To evaluate the subsystem The system weighting coefficients in the corresponding exploration wells To evaluate the subsystem Information content—conflict composite index This indicates the number of evaluation subsystems.

[0111] Based on the aforementioned calculation results, the system weight coefficient of the enrichment evaluation subsystem in exploration well a1 is 0.1176 / (0.1176+0.0882+0.1078)=0.38, the system weight coefficient of the compressibility evaluation subsystem in exploration well a1 is 0.0882 / (0.1176+0.0882+0.1078)=0.28, and the system weight coefficient of the recoverability evaluation subsystem in exploration well a1 is 0.1078 / (0.1176+0.0882+0.1078)=0.34.

[0112] In a preferred embodiment, for each target effective layer segment, step S4004 further includes: Based on the comprehensive evaluation index of each evaluation subsystem under the effective target evaluation layer, the coupling degree of each evaluation subsystem under the effective target evaluation layer is calculated. Based on the comprehensive evaluation index of each evaluation subsystem under the effective target evaluation layer and the system weight coefficient of each evaluation subsystem under the corresponding exploration well, the coordination degree of each evaluation subsystem under the effective target evaluation layer is calculated. The product of the coupling degree and the coordination degree is determined as the coupling coordination degree of each evaluation subsystem under the effective target evaluation layer.

[0113] Specifically, the coupling coordination degree of each evaluation subsystem at each effective target evaluation level is determined by the following formula:

[0114] In the formula, Let M be the coupling degree of each evaluation subsystem at the k-th effective target evaluation segment, and M be the number of evaluation subsystems. For the first The comprehensive evaluation index of the evaluation subsystem under the k-th effective target evaluation segment. The degree of coordination among the evaluation subsystems at the k-th effective target evaluation level. To evaluate the subsystem The system weighting coefficients in the corresponding exploration wells The degree of coupling coordination of each evaluation subsystem under the kth effective target evaluation segment.

[0115] In a preferred embodiment, step S4006 further includes: S40061. Sort the target coupling coordination degree corresponding to each effective target evaluation segment in ascending order to form a coupling coordination degree sequence.

[0116] S40062. Determine the sum of squared deviations of the subsets corresponding to the coupling coordination degree sequence.

[0117] S40063. By presetting the number of layer classifications and the number of effective target evaluation layers, a dynamic programming table is constructed based on the minimum total sum of squared deviations. Recursive operations are then used to determine the reservoir classification results for the effective target evaluation layers.

[0118] For example, coupling coordination sequence Represented as:

[0119] N represents the number of effective target evaluation segments. Taking 6 effective target evaluation segments as an example, the coupling coordination degree of each effective target evaluation segment is as follows: segment b1 is 0.83, segment b2 is 0.79, segment b3 is 0.71, segment b4 is 0.65, segment b5 is 0.32, and segment b6 is 0.38. In step S40061, the above coupling coordination degrees are sorted in ascending order to form a coupling coordination degree sequence. =[0.32,0.38,0.65,0.71,0.79,0.83].

[0120] In step S40062, the sum of squared deviations of the subsets corresponding to the coupling coordination degree sequence is calculated using the following formula:

[0121]

[0122] In this formula, For the coupling coordination degree sequence subset of The mean of all elements, for subset The sum of squared deviations of all elements.

[0123] In one specific embodiment, For the above coupling coordination degree sequence The subset formed by the first 5 elements has a sum of squared deviations of 0.045.

[0124] In one specific embodiment, step S40063 further includes: Define a dynamic programming table DP[n][k], which means to couple the sequence of coordination degrees. The minimum total sum of squared deviations of the pre-defined number (n) target segments divided into multiple classes (K) is specifically expressed as follows:

[0125] In particular, when When =1, it is:

[0126] In the above formula, N represents the number of effective target evaluation segments.

[0127] Divide the N effective target evaluation segments into The class needs to be calculated -1 split points, and its recursive algorithm is as follows: For the (K-1)th split point : ; ... For the second split point : ; For the first split point : ; Specifically, based on the example given above, taking the number of effective target evaluation segments N=6 as an example, and the preset number of classifications K=3, the recursive algorithm is as follows: Dividing the six effective target evaluation segments into three categories requires calculating two segmentation points; For the second split point :

[0128] For the first split point :

[0129] The split point can be determined by recursively calculating the least total sum of squared deviations. =2、 =4.

[0130] Based on the above coupling coordination degree sequence For example, it is divided into three coupling coordination degree ranges, including: D≤0.38, 0.38<D<0.79 and D≥0.79. Among them, D≤0.38 is a non-sweet spot layer, 0.38<D<0.79 is a potential sweet spot layer, and D≥0.79 is a high-quality sweet spot layer. According to the divided coupling coordination degree range, the reservoir type of each effective target evaluation segment is determined.

[0131] In a preferred embodiment, please refer to Figure 6 , Figure 6 A flowchart illustrating a reservoir classification result evaluation and processing method provided in an embodiment of this application is shown. Figure 6 As shown, step S500 further includes: S5001. Calculate the overall profile coefficient corresponding to all effective target evaluation segments within each type of reservoir.

[0132] S5002. Compare the reservoir classification results with the actual gas testing results of the exploration wells in the area to be evaluated for consistency.

[0133] S5003. If the overall profile coefficient meets the overall profile coefficient standard, and the reservoir classification result is consistent with the actual gas testing results of the exploration wells in the area to be evaluated, then the reservoir classification result will be output as the final classification result.

[0134] S5004. If the overall profile coefficient does not meet the overall profile coefficient standard, or if the reservoir classification results are inconsistent with the actual gas testing results of the exploration wells in the area to be evaluated, a parameter adjustment prompt will be generated.

[0135] S5005. In response to the parameter adjustment operation, return to re-execute step S100.

[0136] In step S5001, the independent profile coefficients of each effective target evaluation segment within each type of reservoir are first determined. Specifically, the independent profile coefficients of each effective target evaluation segment within each type of reservoir are determined using the following formula:

[0137] In this formula, This represents the average difference in coupling coordination degree between the i-th valid target evaluation segment and other segments in its reservoir classification. This represents the minimum difference in coupling coordination degree between the i-th effective target evaluation segment and the effective target evaluation segments corresponding to other reservoir classifications besides its own. This represents the profile coefficient of the i-th effective target evaluation segment. The overall profile coefficient represents the average profile coefficient of all valid target evaluation segments. The closer the profile coefficient is to 1, the more reasonable the classification is. The closer it is to -1, the more likely it is to be misclassified. If it is near 0, it indicates that there is overlap between classes.

[0138] In a specific embodiment, for example, the overall contour coefficient =0.736, which meets the overall profile coefficient standard, where the overall profile coefficient standard indicates the overall profile coefficient. ≥0.7.

[0139] In step S5002, specifically, the actual gas testing results data include the measured gas production obtained by the exploration wells under each effective target layer. In this application, for the three exploration wells in area A, for each effective target evaluation layer, the average value of the measured gas production of the three exploration wells is calculated as the actual comparative data of the effective target evaluation layer. Based on this, for example, assuming that the coupling coordination degree of the effective target evaluation layer b1 is 0.83, it is classified as a high-quality sweet spot layer, the average measured gas production is 12.5×104 m³ / d, and the effective thickness is 10.2m, the measured data meets the characteristics of a high-quality sweet spot layer. Assuming that the coupling coordination degrees of the effective target evaluation layers b5 and b6 are 0.32 and 0.38 respectively, they are classified as non-sweet spot layers, the measured gas production is less than 200 m³ / d, which meets the characteristics of a non-sweet spot layer. This indicates that the reservoir classification results have a high degree of consistency with the measured data, that is, the reservoir classification results are consistent with the actual gas testing results data of the exploration wells in the area to be evaluated.

[0140] In steps S5004 to S5005, if the overall profile coefficient is less than 0.7, or if the reservoir classification result is inconsistent with the actual gas testing results of the exploration wells in the area to be evaluated, a parameter adjustment prompt is generated. For example, the parameter adjustment prompt is "Check the type and quantity of evaluation parameters, adjust the layer boundary depth or the number of reservoir classifications". After the user has adjusted the parameters according to the parameter adjustment prompt, the evaluation process is restarted until the classification result is reasonable and reliable.

[0141] In a preferred embodiment, the adaptive intelligent classification and evaluation method for shale gas reservoirs provided in this application can realize intelligent and dynamic classification and evaluation of shale gas reservoir exploration data obtained from different regions, different formations and different exploration wells, thereby improving the accuracy and applicability of the final reservoir classification and evaluation results.

[0142] Based on the same application concept, this application also provides an adaptive shale gas reservoir intelligent classification and evaluation system corresponding to the adaptive shale gas reservoir intelligent classification and evaluation method provided in the above embodiments. Since the principle of the device in this application embodiment is similar to the adaptive shale gas reservoir intelligent classification and evaluation method in the above embodiments of this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0143] Please see Figure 7 , Figure 7 This diagram illustrates the functional modules of an adaptive shale gas reservoir intelligent classification and evaluation system provided in an embodiment of this application. Figure 7 As shown, the system includes: a data acquisition and processing module 600, a subsystem construction module 610, an evaluation layer segmentation module 620, a reservoir classification and evaluation module 630, and a feedback optimization module 640.

[0144] Preferably, the data acquisition and processing module 600 is used to acquire evaluation data of the same target shale gas layer from at least one exploration well distributed in the area to be evaluated, and to process the data to form a standardized evaluation dataset.

[0145] The subsystem construction module 610 is used to adaptively filter standardized evaluation datasets based on strong correlation with shale reservoir sweet spots, determine multiple core identification and evaluation parameters, and then dynamically construct an evaluation subsystem from the aspects of shale gas enrichment conditions, engineering compressibility, and economic recoverability.

[0146] The evaluation segment division module 620 is used to divide the target shale gas layer into multiple effective target evaluation segments.

[0147] The reservoir classification and evaluation module 630 is used to intelligently classify shale gas reservoirs by multiple valid target evaluation segments using the evaluation subsystem, and determine the reservoir classification result corresponding to each valid target evaluation segment.

[0148] The feedback optimization module 640 is used to dynamically optimize and verify the reservoir classification results based on the profile coefficient method and / or actual gas testing results data, until the reservoir classification results meet the expected requirements.

[0149] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0150] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0151] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0152] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0153] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An adaptive intelligent classification and evaluation method for shale gas reservoirs, characterized in that, The method includes: For at least one exploration well distributed in the area to be evaluated, obtain evaluation data of the same target shale gas layer and process the data to form a standardized evaluation dataset. Based on the strong correlation with the sweet spot of shale reservoirs, adaptive data filtering is performed on the standardized evaluation dataset to determine multiple core identification and evaluation parameters. Then, an evaluation subsystem is dynamically constructed from the aspects of shale gas enrichment conditions, engineering compressibility, and economic recoverability. The target shale gas layer is divided into multiple effective target evaluation segments. The evaluation subsystem is used to perform intelligent shale gas reservoir classification on the multiple effective target evaluation segments, and the reservoir classification result corresponding to each effective target evaluation segment is determined. Based on the profile coefficient method and / or actual gas testing results, the reservoir classification results are dynamically optimized and verified until the reservoir classification results meet the expected requirements.

2. The method according to claim 1, characterized in that, The evaluation data includes multiple evaluation parameters and a sequence of measurement values ​​for each evaluation parameter in different exploration wells. The standardized evaluation dataset is formed in the following ways: According to the preset evaluation parameter classification table, the multiple evaluation parameters are intelligently classified to determine the evaluation parameter category corresponding to each evaluation parameter. The evaluation parameter category includes identification evaluation parameters and auxiliary evaluation parameters. The measurement value sequence of each evaluation parameter under different exploration wells is pre-processed based on missing and outlier data to obtain the pre-processed measurement value sequence of each evaluation parameter under different exploration wells. Under the constraints of auxiliary evaluation parameters, the pre-processed measurement value sequence of the identification evaluation parameters is encrypted according to the adaptive interpolation method to obtain the encrypted measurement value sequence corresponding to the identification evaluation parameters. Based on the preset parameter directionality comprehensive judgment table and the reservoir characteristics of the region to be evaluated, the directionality of each judgment and evaluation parameter is determined. The directionality includes positive, negative, intermediate and interval types. Based on the directionality of the identification and evaluation parameters, the encrypted measurement value sequence of the identification and evaluation parameters is standardized using the corresponding standardized calculation formula to obtain the standardized sequence corresponding to the identification and evaluation parameters. The standardized sequences are validated for consistency, and a standardized evaluation dataset is formed from the validated standardized sequences.

3. The method according to claim 2, characterized in that, For the identification and evaluation parameters with positive directionality, the corresponding standardized calculation formula is: For the identification and evaluation parameters with negative directionality, the corresponding standardized calculation formula is: For the identification and evaluation parameters with intermediate directionality, the corresponding standardized calculation formula is: For identification and evaluation parameters with interval-type directionality, the corresponding standardized calculation formula is: in, Indicates the first The evaluation parameters for identification are in the first stage. Standardized values ​​at each depth Indicates the first The evaluation parameters for identification are in the first stage. Measurements at various depths Indicates the first The maximum value of a discrimination evaluation parameter among all its corresponding measurements. Indicates the first The minimum value of the identification evaluation parameter among all its corresponding measurements. This represents a very small value, taking the value 0.

001. Indicates the first The optimal value of the evaluation parameter among all its corresponding measurements. and The respective The lower and upper limits of the optimal measurement range indicated by all the measured values ​​corresponding to the evaluation parameters.

4. The method according to claim 1, characterized in that, The evaluation subsystem is constructed in the following manner: Based on the standardized sequence corresponding to each identification and evaluation parameter, an adaptive correlation analysis algorithm is used to determine the correlation between each identification and evaluation parameter. Based on the correlation, parameters with no correlation, weak correlation, or high correlation are eliminated to obtain multiple core identification and evaluation parameters. According to the preset evaluation parameter classification table, multiple core identification evaluation parameters are further divided into enrichment identification parameters, compressibility identification parameters and adoptability identification parameters, and the corresponding enrichment evaluation subsystem, compressibility evaluation subsystem and adoptability evaluation subsystem are dynamically constructed. The effectiveness of the evaluation subsystems is verified by considering the number of evaluation subsystems and the completeness of the corresponding judgment parameters, resulting in evaluation subsystems that pass the consistency check.

5. The method according to claim 1, characterized in that, The step of dividing the target shale gas layer into multiple effective target evaluation segments includes: Obtain the user's pre-entered requirements for the division of the target shale gas layer; Based on the aforementioned classification requirements, the target shale gas layer is divided into multiple target evaluation segments; The validity of the multiple target evaluation segments is verified based on the segment thickness and the number of segments to obtain multiple valid target evaluation segments.

6. The method according to claim 1, characterized in that, The reservoir classification result corresponding to each valid target evaluation segment is determined using the following method: The entropy weight method is used to determine the weight of each core identification and evaluation parameter within its respective evaluation subsystem; Based on the standardized sequence of core identification and evaluation parameters in the well and their weights in the evaluation subsystem, the comprehensive evaluation index of the evaluation subsystem under different effective target evaluation segments is calculated. The CRITIC method was used to determine the system weight coefficients of each evaluation subsystem in this exploration well. Based on the comprehensive evaluation index of the evaluation subsystem under different effective target evaluation levels, the coupling coordination degree of each evaluation subsystem under different effective target evaluation levels is determined. For each effective target evaluation layer, the arithmetic mean of the coupling coordination degree calculated by multiple exploration wells under that effective target evaluation layer is determined as the target coupling coordination degree of that effective target evaluation layer. Based on the target coupling coordination degree of the effective target evaluation segment, Fisher's optimal segmentation is applied to adaptively determine the reservoir classification result for each effective target evaluation segment.

7. The method according to claim 6, characterized in that, The weight of each core identification evaluation parameter within its respective evaluation subsystem is determined using the following formula: This represents the weight of the i-th core identification evaluation parameter within its respective evaluation subsystem. This represents the total number of core identification evaluation parameters corresponding to the evaluation subsystem to which the i-th type of core identification evaluation parameter belongs. The information entropy represents the i-th type of core identification and evaluation parameter. This indicates the evaluation subsystem to which the i-th type of core identification evaluation parameter belongs. Information entropy of core identification and evaluation parameters; in, Indicates the first The ratio between the j-th standardized value of a core identification and evaluation parameter and the sum of its corresponding standardized values. This represents the total number of standardized values ​​corresponding to the core identification and evaluation parameters; In this formula, Indicates the first The k-th standardized value of the core identification and evaluation parameters, Indicates the first The evaluation parameters for identification are in the first stage. Standardized values ​​at each depth.

8. The method according to claim 6, characterized in that, The comprehensive evaluation index of each evaluation subsystem under different effective target evaluation levels is determined by the following formula: In this formula, Indicates the first The evaluation subsystem in the first... A comprehensive evaluation index under each effective target evaluation segment. Indicates the first The number of measurement values ​​collected in each effective target evaluation segment. Indicates the first The first evaluation subsystem The core identification and evaluation parameters in the first The weights within the evaluation subsystem, m represents the weight of the i-th evaluation subsystem. The number of core identification and evaluation parameters corresponding to each evaluation subsystem No. The j-th standardized value of the i-th core identification evaluation parameter under the evaluation subsystem.

9. The method according to claim 6, characterized in that, The steps for determining the system weight coefficients of each evaluation subsystem in this exploration well using the CRITIC method include: Calculate the standard deviation of the comprehensive evaluation index for each evaluation subsystem in this exploration well. The correlation coefficient method was used to calculate the system correlation coefficient of each evaluation subsystem in this exploration well. Based on the standard deviation of the comprehensive evaluation index of the evaluation subsystem in the well and the system correlation coefficient of each evaluation subsystem in the well, calculate the information content-conflict comprehensive index of each evaluation subsystem in the well. Based on the information content and conflict comprehensive index of each evaluation subsystem in the well, calculate the system weight coefficient of each evaluation subsystem in the well.

10. The method according to claim 6, characterized in that, The coupling coordination degree of each evaluation subsystem at each effective target evaluation level is determined by the following formula: In the formula, Let M be the coupling degree of each evaluation subsystem at the k-th effective target evaluation segment, and M be the number of evaluation subsystems. For the first The comprehensive evaluation index of the evaluation subsystem under the k-th effective target evaluation segment. The degree of coordination among the evaluation subsystems at the k-th effective target evaluation level. To evaluate the subsystem The system weighting coefficients in the corresponding exploration wells The degree of coupling coordination of each evaluation subsystem under the kth effective target evaluation segment.

11. The method according to claim 6, characterized in that, The reservoir classification results for each valid target evaluation segment are determined using the following method: The target coupling coordination degree corresponding to each effective target evaluation segment is sorted in ascending order to form a coupling coordination degree sequence. Determine the sum of squared deviations of the subsets corresponding to the coupling coordination degree sequence; By pre-setting the number of layer classifications and the number of effective target evaluation layers, a dynamic programming table is constructed based on the minimum total sum of squared deviations. Recursive operations are then used to determine the reservoir classification results for the effective target evaluation layers.

12. The method according to claim 1, characterized in that, The step of dynamically optimizing and verifying the reservoir classification results based on the profile coefficient method and / or actual gas testing data until the reservoir classification results meet the expected requirements includes: Calculate the overall profile coefficient corresponding to all effective target evaluation segments within each type of reservoir; The consistency of the reservoir classification results is compared with the actual gas testing results of the exploration wells in the area to be evaluated. If the overall profile coefficient meets the overall profile coefficient standard, and the reservoir classification result is consistent with the actual gas testing results of the exploration wells in the area to be evaluated, then the reservoir classification result will be output as the final classification result. If the overall profile coefficient does not meet the overall profile coefficient standard, or if the reservoir classification result is inconsistent with the actual gas testing results of the exploration wells in the area to be evaluated, a parameter adjustment prompt will be generated. In response to parameter adjustment operations, return and re-execute.

13. An adaptive intelligent classification and evaluation system for shale gas reservoirs, characterized in that, The system includes a data acquisition and processing module, a subsystem construction module, an evaluation layer segmentation module, a reservoir classification and evaluation module, and a feedback optimization module. The data acquisition and processing module is used to process the data from at least one well in the area to be evaluated that has the same target shale gas layer, and to form a standardized evaluation dataset. The subsystem construction module is used to adaptively filter the standardized evaluation dataset based on the strong correlation with the sweet spot of shale reservoirs, determine multiple core identification and evaluation parameters, and then dynamically construct the evaluation subsystem from the aspects of shale gas enrichment conditions, engineering compressibility, and economic recoverability. The evaluation segment division module is used to divide the target shale gas layer into multiple effective target evaluation segments; The reservoir classification and evaluation module is used to intelligently classify shale gas reservoirs using the evaluation subsystem, and determine the reservoir classification result corresponding to each effective target evaluation segment. The feedback optimization module is used to dynamically optimize and verify the reservoir classification results based on the profile coefficient method and / or actual gas testing results data, until the reservoir classification results meet the expected requirements.