Method, device, equipment and medium for determining multi-phase coupled reservoir sweet spots

Abstract

The application discloses a kind of multi-phase coupling reservoir sweet spot determination method, device, equipment and medium, comprising: obtaining the original reservoir data corresponding to target research reservoir, and determining target reservoir data according to original reservoir data;According to target reservoir data, determine the reservoir classification basis corresponding to target research reservoir;Based on target reservoir data, establish the target classification identification model corresponding to reservoir classification basis;Based on target classification identification model, the logging data of target well is processed to obtain the reservoir sweet spot prediction result corresponding to target well.Based on the above technical solution, the target classification identification model of multiple classification basis is established by fusing logging data and logging data, and the reservoir sweet spot prediction result of target well is determined according to the target classification identification model, the continuous identification of low porosity and permeability reservoir diagenetic facies is realized, reservoir classification evaluation and accurate prediction of favorable reservoir sweet spot, which provides reliable technical support for exploration and development of low porosity and permeability oil and gas reservoir.

Description

Technical Field

[0001] This invention relates to the field of reservoir evaluation technology, and in particular to a method, apparatus, equipment and medium for determining sweet spots in multiphase coupled reservoirs. Background Technology

[0002] Reservoir evaluation is a key technical step in oil and gas exploration and development, and its results directly affect well location deployment and development plan optimization. As oil and gas exploration extends into deeper and tighter reservoirs, low-porosity and permeability reservoirs have become key targets for increasing reserves and production. However, the sedimentary-diagenetic processes of such reservoirs are complex and highly heterogeneous, posing many challenges to traditional evaluation methods.

[0003] Existing reservoir evaluation methods mainly include core analysis, conventional logging interpretation, sedimentary facies analysis, diagenesis research, and pore structure evaluation. These methods typically focus on single-factor analysis or local data interpretation, making it difficult to achieve continuous identification and comprehensive evaluation of reservoirs. They have significant limitations: (1) Reservoir evaluation relies excessively on core and experimental data. Due to limitations in core coverage and cost, it is difficult to achieve continuous vertical evaluation of reservoirs and cannot meet the needs of fine exploration of low-porosity and permeable reservoirs; (2) Logging and well logging data are mostly used for simple lithological identification. Lithofacies identification methods are imperfect and lack quantitative classification standards. They are difficult to accurately reflect the differences in reservoir sedimentary environment and compositional maturity, and ignore lithology. —The basic control of lithology on diagenetic facies development; (3) The division of diagenetic facies relies heavily on subjective judgment, lacks unified quantitative classification standards and supporting logging quantitative identification methods, and makes it difficult to continuously identify diagenetic facies in wells without core sampling, thus failing to accurately reveal the control mechanism of diagenesis on reservoir properties; (4) There is a lack of systematic coupling analysis methods between lithology-lithology, diagenetic facies and pore structure, making it difficult to reveal the sedimentary-diagenetic synergistic control mechanism of low porosity and permeability reservoir development; (5) Existing evaluation methods are mostly single-factor identification or simple combination evaluation, lacking quantitative coupling mechanisms, making it difficult to form a standardized, quantitative, and continuous evaluation method applicable to deep tight reservoirs, resulting in low accuracy of reservoir prediction. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for determining sweet spots in multiphase coupled reservoirs. By integrating well logging data and well logging data, a target classification and identification model based on multiple classification criteria is established. Based on this target classification and identification model, the predicted sweet spot of the target well is determined, thereby achieving continuous identification of diagenetic facies, reservoir classification evaluation, and accurate prediction of favorable sweet spots in low-porosity and permeable reservoirs. This provides reliable technical support for the exploration and development of low-porosity and permeable oil and gas reservoirs.

[0005] According to one aspect of the present invention, a method for determining sweet spots in a multiphase coupled reservoir is provided, comprising:

[0006] Obtain raw reservoir data corresponding to the target reservoir, and determine the target reservoir data based on the raw reservoir data;

[0007] Based on the target reservoir data, the reservoir classification criteria corresponding to the target research reservoir are determined. The reservoir classification criteria include lithological and lithofacies classification criteria, diagenetic facies classification criteria, and pore structure classification criteria.

[0008] Establish a target classification and identification model based on target reservoir data and corresponding reservoir classification criteria;

[0009] Based on the target classification and recognition model, the logging data of the target well is processed to obtain the reservoir sweet spot prediction results corresponding to the target well.

[0010] According to another aspect of the present invention, an apparatus for determining the sweet spot of a multiphase coupled reservoir is provided, comprising:

[0011] The reservoir data processing module is used to acquire raw reservoir data corresponding to the target reservoir and determine the target reservoir data based on the raw reservoir data.

[0012] The classification criteria determination module is used to determine the reservoir classification criteria corresponding to the target research reservoir based on the target reservoir data. The reservoir classification criteria include lithological and lithofacies classification criteria, diagenetic facies classification criteria, and pore structure classification criteria.

[0013] The classification and identification model building module is used to establish a target classification and identification model corresponding to the reservoir classification criteria based on the target reservoir data.

[0014] The reservoir prediction module is used to process the logging data of the target well based on the target classification and recognition model to obtain the reservoir sweet spot prediction result corresponding to the target well.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the method for determining the sweet spot of a multiphase coupled reservoir according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute a method for determining a multiphase coupled reservoir sweet spot according to any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring original reservoir data corresponding to the target reservoir, determining the target reservoir data based on the original reservoir data, determining the reservoir classification criteria corresponding to the target reservoir based on the target reservoir data, establishing a target classification identification model corresponding to the reservoir classification criteria based on the target reservoir data, and processing the logging data of the target well based on the target classification identification model to obtain the reservoir sweet spot prediction result corresponding to the target well. Based on the above technical solution, by fusing logging data and well logging data to establish a multi-classification target classification identification model, and determining the reservoir sweet spot prediction result of the target well based on the target classification identification model, continuous identification of diagenetic facies of low-porosity and permeability reservoirs, reservoir classification evaluation, and accurate prediction of favorable reservoir sweet spots are achieved, providing reliable technical support for the exploration and development of low-porosity and permeability oil and gas reservoirs.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a method for determining sweet spots in a multiphase coupled reservoir provided in an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of the lithology-lithofacies classification standard provided in the embodiments of the present invention;

[0025] Figure 3 This is a schematic diagram of the diagenetic facies classification standard provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of pore structure classification provided in an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of lithology-lithofacies identification provided in an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of diagenetic facies logging identification provided in an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram of the stratigraphic classification standard provided in an embodiment of the present invention;

[0030] Figure 8 This is a flowchart of a method for determining sweet spots in multiphase coupled reservoirs provided in an embodiment of the present invention;

[0031] Figure 9 This is a flowchart of a method for determining sweet spots in a multiphase coupled reservoir provided in an embodiment of the present invention;

[0032] Figure 10 This is a schematic diagram of the structure of a device for determining the sweet spot of a multiphase coupled reservoir provided in an embodiment of the present invention;

[0033] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] Figure 1 This is a flowchart illustrating a method for determining sweet spots in multiphase coupled reservoirs according to an embodiment of the present invention. This embodiment is applicable to situations where well logging data from a target well is processed using a target classification and identification model to obtain reservoir sweet spot prediction results. This method can be executed by a device for determining sweet spots in multiphase coupled reservoirs. This device can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method specifically includes the following steps:

[0037] S110. Obtain the original reservoir data corresponding to the target reservoir and determine the target reservoir data based on the original reservoir data.

[0038] The target reservoir can be understood as the oil and gas reservoir block for which reservoir classification and sweet spot evaluation are to be carried out. The raw reservoir data can be multi-source reservoir basic data obtained from field measurements and experimental tests. The target reservoir data can be a standardized dataset that can be directly used for feature extraction and modeling.

[0039] Specifically, various types of raw reservoir data for the target research reservoir are collected by specialization and item. Five categories of raw data are summarized sequentially: conventional logging, imaging logging, X-ray diffraction logging, core thin sections, and high-pressure physical property testing. During the acquisition process, the well location, depth range, and sampling conditions corresponding to the data are simultaneously labeled. After the raw data is collected, standardized processing is carried out according to preset specifications, including depth correction, outlier removal, and dimensional normalization. Depth correction unifies the depth coordinates of various data types from logging, core, and logging, eliminating depth misalignment caused by logging instrument errors and core depth deviations. Outlier removal relies on core-logging cross-comparison rules to screen out distorted data caused by instrument malfunctions and sampling errors. Dimensional normalization unifies different dimensional parameters such as permeability, porosity, and mineral content into a dimensionless standard range. After all processing is completed, various standardized data are integrated to form the target reservoir data.

[0040] Based on the above technical solution, the target reservoir data is determined according to the original reservoir data, including: standardizing the original reservoir data to obtain the target reservoir data.

[0041] Conventional logging includes continuous downhole measurement curves such as natural gamma, density, neutron, acoustic wave, and resistivity. Imaging logging provides wellbore image data for identifying sedimentary structures. X-ray diffraction logging provides quantitative testing data of rock cuttings and minerals. Core thin sections provide microscopic observation data of cast bodies and ordinary thin sections. High-pressure property testing provides reservoir porosity and permeability property data such as mercury intrusion porosimetry and nuclear magnetic resonance. Depth correction is a processing method used to standardize the depth scale of various data. Outlier removal is a method of filtering out distorted and invalid data. Dimensional normalization is a standardization operation to unify the dimensions of physical parameters.

[0042] Specifically, data optimization is performed step-by-step according to the order of standardization. The first step is to carry out depth correction of the entire well section. Based on the measured depth of the core, the depth deviation of the logging curve and the logging sampling point is corrected to achieve one-to-one correspondence of multi-source data at the same depth. The second step is to carry out outlier removal. The results of thin section experiments are used to benchmark the logging parameters at the corresponding depth. Sampling points that deviate from the geological regularity are directly marked and removed. The third step is to carry out dimension normalization. Data with different units of measurement, such as mineral percentage content, porosity and permeability values, and diagenetic parameters, are standardized in intervals. All data after correction, screening and normalization are integrated and packaged to generate target reservoir data with a unified structure.

[0043] For example, multi-source data acquisition and standardized preprocessing: Acquire multiple types of data from the target low-porosity reservoir, including: Well logging data: conventional well logging data (neutron logging CNL, density logging DEN, natural gamma ray logging GR, resistivity logging RT, sonic transit time AC, etc.), imaging well logging data (FMI, etc.); Well logging data: X-ray diffraction logging data, gas logging data, cuttings logging description data; Experimental analysis data: core observation and description data, grain size analysis data, cast thin section analysis data, scanning electron microscopy analysis data, high-pressure mercury intrusion porosimetry experimental data, nuclear magnetic resonance experimental data, and diagenetic parameter test data (compaction rate, cementation rate, dissolution porosity, etc.). The above data underwent standardized preprocessing: 1. Logging curve processing: Depth realignment, wellbore environment correction (well diameter influence correction, mud invasion correction), and outlier removal were completed to ensure the accuracy of the logging data; 2. Data standardization: Data from different sources and with different dimensions were standardized to establish depth correspondences between logging data, core data, and experimental data, forming a unified data evaluation system; 3. Data quality control: Outlier data were removed through cross-validation methods (such as core-logging data calibration, thin section-logging data comparison) to ensure data reliability and lay the foundation for subsequent quantitative modeling.

[0044] The technical solution of this invention uses hierarchical standardization to organize multi-source measured data, thereby standardizing massive heterogeneous reservoir data and reducing data errors in subsequent reservoir classification and model construction from the source.

[0045] S120. Determine the reservoir classification criteria corresponding to the target research reservoir based on the target reservoir data.

[0046] The classification criteria for reservoirs include lithological and lithofacies classification, diagenetic facies classification, and pore structure classification. Reservoir classification can be based on quantitative standards derived from measured data, encompassing lithology, lithofacies, diagenetic facies, and pore structure. Lithological and lithofacies classification is a criterion for determining reservoir sedimentary types based on sedimentary characteristics. Diagenetic facies classification is a criterion for determining diagenetic types based on the degree of diagenetic alteration. Pore structure classification is a criterion for determining pore throat types based on pore throat parameters.

[0047] Specifically, based on standardized target reservoir data, the intrinsic characteristics of the reservoir are extracted one by one from three dimensions, and corresponding classification criteria are established. First, based on X-ray diffraction, core thin sections, and imaging logging data, lithological and lithofacies characteristics such as mineral composition, sedimentary structures, and grain size distribution are extracted. Then, combined with sedimentary evolution patterns, different lithological and lithofacies types such as underwater distributary channels and mouth bars are classified, forming a lithological and lithofacies classification basis, such as... Figure 2As shown; based on thin sections of cast bodies, scanning electron microscopy, and diagenetic property test data, diagenetic parameters such as compaction rate, cementation rate, and the proportion of dissolution pores are extracted. Multiple diagenetic facies are classified according to the intensity of compaction, cementation, and dissolution alteration, forming a basis for diagenetic facies classification, such as... Figure 3 As shown; based on parameters such as displacement pressure and maximum pore throat radius obtained from high-pressure mercury intrusion and nuclear magnetic resonance experiments, different pore structure types are classified, and a classification basis for pore structures is established, such as... Figure 4 As shown.

[0048] Based on the above technical solution, the reservoir classification criteria corresponding to the target research reservoir are determined according to the target reservoir data, including: extracting lithological and lithofacies characteristics corresponding to the target research reservoir from the target reservoir data, and determining the lithological and lithofacies classification criteria based on the lithological and lithofacies characteristics; extracting diagenetic facies characteristics corresponding to the target research reservoir from the target reservoir data, and determining the diagenetic facies classification criteria based on the diagenetic facies characteristics; and extracting pore structure characteristics corresponding to the target research reservoir from the target reservoir data, and determining the pore structure classification criteria based on the pore structure characteristics.

[0049] Among them, lithological and lithofacies characteristics include mineral composition, grain size parameters, and imaging logging sedimentary structures, which characterize the sedimentary environment. Diagenetic facies characteristics include compaction coefficient, cement content, and the proportion of dissolution porosity, which characterize diagenetic alteration. Pore structure characteristics include maximum pore throat radius, displacement pressure, and bound water saturation, which characterize pore throat development.

[0050] Specifically, X-ray diffraction, imaging logging, and core grain size data from the target reservoir data are screened to extract lithological and lithofacies characteristics such as felsic content, clay content, and bedding structure. Combined with the sedimentary facies evolution law, parameter thresholds for different lithological and lithofacies are defined to form a standardized lithological and lithofacies classification basis. Thin section, high-pressure physical property, and diagenetic test data are retrieved to extract diagenetic facies characteristics such as compaction rate, content of various cementing minerals, and degree of dissolution pore development. Based on the threshold of diagenetic intensity, five types of diagenetic facies are classified to determine the diagenetic facies classification basis. Pore throat-related characteristic parameters are extracted from mercury intrusion porosimetry and nuclear magnetic resonance experimental data. Based on the quality of pore throats, pore structure grading thresholds are defined to form a pore structure classification basis.

[0051] For example, based on core observation, thin section analysis, and sedimentary microfacies research results, combined with grain size parameters (median grain size), mineral composition characteristics (content of felsic minerals, clay minerals, and carbonate minerals), and imaging logging sedimentary structural characteristics (scour surfaces, cross-bedding, parallel bedding, etc.), a quantitative classification standard for lithology-facies suitable for the target area is established (e.g., coarse sandstone facies, fine sandstone facies, and fine sandstone facies of estuary bars / sand flats, etc.), clarifying the sedimentary environment and physical basis of different lithology-facies. By comprehensively analyzing the characteristics of conventional logging curves, X-ray diffraction logging mineral content information, gas logging anomaly characteristics, and imaging logging sedimentary structural characteristics, lithology-facies sensitive logging parameters are extracted, and a lithology-facies logging identification model is constructed to achieve continuous vertical division of the target reservoir's lithology-facies in a single well, clarifying the sedimentary basis favorable for diagenetic facies development.

[0052] The technical solution of this invention extracts three types of features step by step and establishes quantitative classification criteria, realizing the quantification of the classification standards of three key dimensions: reservoir sedimentation, diagenesis, and pore throat, and providing accurate annotation rules for the subsequent construction of identification models.

[0053] S130. Establish a target classification and identification model based on the target reservoir data and the reservoir classification criteria.

[0054] Among them, the target classification and identification model can be a multi-factor coupled identification model composed of three sub-models: lithology and lithofacies, diagenetic facies, and pore structure.

[0055] Specifically, based on the target reservoir data, sensitive logging parameters and measured labels corresponding to each category are selected, and lithology and lithofacies identification models, diagenetic facies identification models, and pore structure identification models are constructed separately in sequence. It should be noted that the diagenetic facies model adopts a multi-layer feedforward neural network structure, with five fixed conventional logging curves as input and the diagenetic facies type as the model output. The other two sub-models are constructed based on the parameter response law to build quantitative discrimination models.

[0056] S140. Based on the target classification and recognition model, the logging data of the target well is processed to obtain the reservoir sweet spot prediction result corresponding to the target well.

[0057] In this context, the target well can be understood as an exploration and development well for which sweet spot evaluation is to be conducted. The target well logging data can be conventional and imaging logging data from the entire well section of a single well. The reservoir sweet spot prediction result is the vertical stratification of high-quality reservoirs based on a comprehensive analysis of the three identification results.

[0058] Specifically, a complete set of measured logging data from the target well is collected and preprocessed according to previously standardized rules. The normalized logging data is then completely imported into the integrated target classification and identification model. The model automatically outputs three individual identification results for the entire well section: lithology and lithofacies, diagenetic facies, and pore structure. Based on preset physical property coefficients and classification weights, a weighted coupling calculation is performed on the three individual results to obtain a comprehensive evaluation result. This result is then compared with pre-defined reservoir classification standards to distinguish between sweet spots, conventional reservoirs, and inferior reservoirs. Finally, a prediction result for the sweet spots of the reservoir in the entire well section of the target well is generated. The individual identification results for lithology and lithofacies are as follows: Figure 5 As shown, the individual identification results of the diagenetic facies are as follows: Figure 6 As shown.

[0059] For example, the established lithology-lithofacies identification model, diagenetic facies logging identification model, pore structure identification model, and three-phase coupled reservoir classification and evaluation model are applied to well data in the study area to achieve continuous vertical prediction of target reservoir lithology-lithofacies, diagenetic facies, and pore structure, as well as continuous reservoir type classification. Furthermore, favorable "sweet spot" reservoirs are predicted planarly based on sedimentary facies distribution characteristics. The model prediction results are validated using core analysis data, thin section identification results, and production test data. Based on the validation results, the model parameters are optimized and adjusted to improve the reliability of reservoir classification and evaluation and favorable "sweet spot" reservoir prediction.

[0060] Based on the above technical solution, the logging data of the target well is processed according to the target classification and recognition model to obtain the reservoir sweet spot prediction result corresponding to the target well. This includes: acquiring the logging data corresponding to the target well and inputting the logging data into the target classification and recognition model; acquiring the single recognition result corresponding to the target well output by the target classification and recognition model; and determining the reservoir sweet spot prediction result corresponding to the target well based on the single recognition result.

[0061] Among them, the individual identification results are three independent identification results for each well at each depth: lithology and lithofacies, diagenetic facies, and pore structure.

[0062] Specifically, various measured logging data of the target well are collected on-site and preprocessed in a standardized manner to eliminate data interference from the wellbore and mud. The preprocessed logging data is then input into the target classification and identification model in batches. The three sub-models within the model are used to calculate the lithology, lithofacies, diagenetic facies, and pore structure of each depth point in the longitudinal direction of the entire well. The comprehensive score is calculated by combining the physical property coefficients and weight parameters corresponding to various reservoirs. The sweet spot development intervals are distinguished by comparing with the preset classification standards. Finally, the sweet spot prediction results of the entire well reservoir are summarized.

[0063] Based on the above technical solution, the reservoir sweet spot prediction result corresponding to the target well is determined based on the individual identification results, including: determining the physical property coefficient corresponding to each individual identification result and obtaining the weight value corresponding to each individual identification result; determining the comprehensive evaluation result based on the weight value and physical property coefficient; and determining the reservoir sweet spot prediction result corresponding to the target well based on the comprehensive evaluation result and the preset classification standard.

[0064] Among them, the physical property coefficient can be understood as the normalized coefficient of reservoir physical properties corresponding to various reservoir types. The weight value can be the proportion coefficient of the three types of indicators—lithology and lithofacies, diagenetic facies, and pore structure—in the comprehensive evaluation. The comprehensive evaluation result can be understood as the quantitative score of reservoir quality after weighting multiple indicators. The preset classification standard is the sweet spot score threshold determined based on actual oil test data.

[0065] Specifically, based on a large amount of oil testing and core physical property measurement data, the average porosity and permeability parameters corresponding to different lithologies, lithofacies, diagenetic facies, and pore structures are statistically analyzed. The normalized physical property coefficients corresponding to each type are calculated based on the optimal reservoir physical properties. At the same time, combined with the sedimentary-diagenetic reservoir control mechanism, the evaluation weights of lithologies, lithofacies, diagenetic facies, and pore structures are determined. Weighted calculations are carried out based on the weights and corresponding physical property coefficients, and the comprehensive evaluation score is calculated for each depth. The calculated comprehensive evaluation results are compared with the preset classification standards. The layers with scores reaching the sweet spot threshold are classified as reservoir sweet spots, and the rest are classified as conventional or tight reservoirs.

[0066] For example, the synergistic control mechanism of "lithology-lithofacies controlling diagenetic facies development, diagenetic facies shaping pore structure, and pore structure determining reservoir properties" is clearly defined: Lithology-lithofacies is the foundation: coarse sandstone and fine sandstone facies in underwater distributary channels / tidal channels provide favorable sedimentary foundations and good material conditions; Diagenetic facies is key: residual intergranular pores + weakly dissolved facies and unstable component dissolved facies are constructive diagenetic facies, improving reservoir properties; carbonate cementing facies, clay mineral filling facies, and compacted dense facies are destructive diagenetic facies, reducing reservoir quality; Pore structure is the characterization: Type I and Type II pore structures correspond to high-quality permeability, while Type III and Type IV correspond to poor permeability. Integrating these three core factors—lithology-lithofacies, diagenetic facies, and pore structure—and combining them with the sedimentary-diagenetic evolution laws of the target reservoir, a synergistic control relationship of "lithology-lithofacies controlling diagenetic facies development, diagenetic facies shaping pore structure, and pore structure determining reservoir properties" is established. The reservoir classification evaluation parameter (RPF) is constructed by selecting lithology-lithofacies weight (20%), diagenetic facies weight (40%), and pore structure weight (40%): RPF = 0.2 × a1 + 0.4 × a2 + 0.4 × a3; where a1 is the lithology-lithofacies property normalization coefficient, a2 is the diagenetic facies property normalization coefficient, and a3 is the pore structure property normalization coefficient. Each coefficient is determined by the ratio of the average permeability of the corresponding type to the average permeability of the worst type. Figure 7As shown, based on RPF values ​​and actual production test data, the reservoir is divided into 4 major categories and 6 subcategories, achieving precise quantitative grading of reservoir quality.

[0067] Can be combined Figure 8 To further understand the technical solution of the present invention, such as... Figure 8 As shown, this invention, based on the completion of three-phase continuous identification, constructs reservoir classification and evaluation parameters (RPF) and combines them with actual production test data to achieve reservoir quality grading. This helps to identify the combination relationships of constructive diagenetic facies, favorable pore structure, and high-quality sedimentary facies, thereby improving the reliability of predictions for favorable reservoirs and "sweet spot" reservoirs. Simultaneously, this invention comprehensively utilizes logging data and rock physics experimental data to form a complete technical process from data preprocessing, parameter optimization, model construction to comprehensive evaluation, which can be used for the fine exploration and development evaluation of deep, low-porosity, and low-permeability reservoirs.

[0068] The technical solution of this invention involves acquiring original reservoir data corresponding to the target reservoir, determining the target reservoir data based on the original reservoir data, determining the reservoir classification criteria corresponding to the target reservoir based on the target reservoir data, establishing a target classification identification model corresponding to the reservoir classification criteria based on the target reservoir data, and processing the logging data of the target well based on the target classification identification model to obtain the reservoir sweet spot prediction result corresponding to the target well. Based on the above technical solution, by fusing logging data and well logging data to establish a multi-classification target classification identification model, and determining the reservoir sweet spot prediction result of the target well based on the target classification identification model, continuous identification of diagenetic facies of low-porosity and permeability reservoirs, reservoir classification evaluation, and accurate prediction of favorable reservoir sweet spots are achieved, providing reliable technical support for the exploration and development of low-porosity and permeability oil and gas reservoirs.

[0069] In one possible implementation of the present invention Figure 9 This invention provides a flowchart of a method for determining sweet spots in multiphase coupled reservoirs. The invention further describes a technical solution for establishing a target classification and identification model based on target reservoir data and corresponding to reservoir classification criteria. Figure 9 As shown, the method includes:

[0070] S910. Determine the sensitive logging parameters corresponding to the lithology and lithofacies, and construct a lithology and lithofacies identification model based on the sensitive logging parameters and the lithology and lithofacies classification criteria.

[0071] Among them, sensitive logging parameters can be logging and well logging characteristic parameters that show obvious responses to changes in lithology, minerals, and sedimentary structures. The lithology and lithofacies identification model can be understood as a computational model that achieves automatic lithology and lithofacies identification based on optimized sensitive parameters.

[0072] Specifically, from standardized target reservoir data, combined with X-ray diffraction mineral data and imaging logging structural information, logging parameters sensitive to changes in different sedimentary facies are selected. Mineral content-related logging indicators and characteristic logging parameters are retained as model inputs, and lithology and facies labels obtained from core calibration are used as output constraints to build a lithology and facies identification model.

[0073] For example, based on core observation, thin section analysis, and sedimentary microfacies research results, combined with grain size parameters (median grain size), mineral composition characteristics (content of felsic minerals, clay minerals, and carbonate minerals), and imaging logging sedimentary structural characteristics (scour surfaces, cross-bedding, parallel bedding, etc.), a quantitative classification standard for lithology-facies suitable for the target area is established (e.g., coarse sandstone facies, fine sandstone facies, and fine sandstone facies of estuary bars / sand flats, etc.), clarifying the sedimentary environment and physical basis of different lithology-facies. By comprehensively analyzing the characteristics of conventional logging curves, X-ray diffraction logging mineral content information, gas logging anomaly characteristics, and imaging logging sedimentary structural characteristics, lithology-facies sensitive logging parameters are extracted, and a lithology-facies logging identification model is constructed to achieve continuous vertical division of the target reservoir's lithology-facies in a single well, clarifying the sedimentary basis favorable for diagenetic facies development.

[0074] S920. Determine the diagenetic-related logging characteristics corresponding to the diagenetic facies, and construct a diagenetic facies identification model based on the diagenetic-related logging characteristics and the diagenetic facies classification criteria.

[0075] The diagenetic facies identification model is a trained neural network model. It is a multi-layer feedforward neural network. The input parameters are natural gamma ray logging curves, density logging curves, compensated neutron logging curves, sonic transit time logging curves, and resistivity logging curves. The output is the diagenetic facies type. Diagenetic-related logging features are logging curve parameters that change due to diagenetic processes such as compaction, cementation, and dissolution. The multi-layer feedforward neural network is a machine learning network composed of multiple interconnected neurons. Natural gamma ray logging, density logging, compensated neutron logging, sonic transit time logging, and resistivity logging are the five basic logging curves characterizing reservoir diagenetic changes. The diagenetic facies type is a reservoir diagenetic category classified according to the intensity of diagenetic alteration.

[0076] Specifically, by combining thin-section diagenetic test data, the response patterns of five types of conventional logging curves with changes in compaction, cementation, and dissolution were analyzed. Five logging parameters were determined as diagenetic-related logging features, and five logging data were used as input layer parameters for a neural network. The diagenetic facies type labeled according to the diagenetic facies classification criteria was used as the model output. A multi-layer feedforward neural network-based diagenetic facies identification model was constructed. It should be noted that during the model training process, core well data within the target reservoir were divided into training and validation samples. The backpropagation algorithm was used to iteratively optimize the network weights, continuously reducing the error between the predicted and measured diagenetic facies. When the recognition accuracy of the validation set reached the preset standard, the model was finalized. The finalized neural network can input continuous logging data from any well and automatically output the diagenetic facies classification results at each depth.

[0077] For example, based on thin section analysis, scanning electron microscopy, and diagenetic parameter testing data, the diagenetic characteristics of the target reservoir, such as compaction, cementation, and dissolution, were analyzed. Using compaction rate, cementation rate, and dissolution porosity as core parameters, a quantitative classification standard for diagenetic facies was established, dividing the reservoir into compacted tight facies, carbonate cemented facies, clay mineral-filled facies, unstable component dissolution facies, and residual intergranular porosity + weakly dissolution facies, clarifying the controlling role of different diagenetic facies on reservoir properties. A total of five diagenetic facies were classified. Based on the classification, combined with the logging response characteristics of different diagenetic facies, logging curves sensitive to diagenesis are selected, a logging interpretation model for diagenetic parameters is constructed, and a logging identification method for diagenetic facies is established based on the calculation results of diagenetic parameters and the classification standards of diagenetic facies, so as to realize the continuous vertical identification of the diagenetic facies type of the target reservoir in a single well.

[0078] Well logging response characteristic analysis: The well logging response patterns of different diagenetic facies were clarified. For example, residual intergranular pores + weak dissolution facies are characterized by low GR, low CNL, low DEN, and obvious differentiation of neutron-density curves; carbonate cemented facies are characterized by low GR, low CNL, high DEN, and high RT. Based on the BP neural network algorithm, with GR, DEN, CNL, DTC, and RT as input parameters and diagenetic facies type as output parameter, a diagenetic facies well logging identification model was established to achieve continuous vertical identification of single wells.

[0079] S930. Determine the response relationship between logging parameters and pore structure characteristic parameters in the target reservoir data, and construct a pore structure identification model based on the response relationship and pore structure classification criteria.

[0080] The response relationship can be understood as the corresponding variation law of logging parameters with pore throat size and bound water. The pore structure identification model can be a quantitative calculation model that uses logging data to invert pore throat type.

[0081] Specifically, based on pore structure characteristic data measured by high-pressure mercury injection and nuclear magnetic resonance, matching well logging data at the same depth is used to statistically analyze the variation law of well logging values ​​corresponding to different pore throat types, quantify the intrinsic response relationship between well logging parameters and characteristic parameters such as maximum pore throat radius and displacement pressure, and build a pore structure identification model based on the quantified response relationship and the classification threshold of various pore throats in the pore structure classification criteria. Then, the model parameters are calibrated using the measured pore throat data from core wells. After calibration, the pore structure characteristic parameters can be inverted at each depth and the pore structure type can be automatically determined.

[0082] For example, based on high-pressure mercury injection and nuclear magnetic resonance (NMR) experimental data, the pore-throat structure characteristics of the target reservoir and their relationship with reservoir properties are analyzed. Parameters such as maximum pore-throat radius, displacement pressure, T2 geometric mean, and bound water saturation are selected to establish a quantitative classification standard for pore structure, clarifying the differences in storage and permeability corresponding to different pore structure types. Based on this, a well logging calculation model for pore structure parameters is constructed by combining the response relationship between well logging parameters and pore structure characteristic parameters, enabling quantitative calculation of pore structure characteristic parameters. Furthermore, based on the pore structure classification standard, a quantitative identification method for pore structure well logging is established to achieve continuous identification of the pore structure type of the target reservoir.

[0083] S940. The target classification and identification model is obtained by combining the lithology and lithofacies identification model, the diagenetic facies identification model and the pore structure identification model.

[0084] Specifically, in terms of computation timing, the lithology and lithofacies identification model is first called to complete the lithofacies division of the entire well. The lithofacies identification results are used as auxiliary constraints for the diagenetic facies model. Then, the diagenetic facies identification model is run. Finally, the diagenetic facies output results are brought into the pore structure identification model to achieve linkage constraints of the three types of results.

[0085] This invention constructs a three-phase synergistic coupling evaluation system of lithology-lithofacies, diagenetic facies, and pore structure, improving the systematicness and completeness of reservoir evaluation. Existing technologies mostly focus on single aspects of lithology identification, diagenetic facies classification, or pore structure analysis, lacking a systematic characterization of the intrinsic control relationship between sedimentation, diagenesis, and pore throat structure. Based on the geological mechanism that "lithology-lithofacies control diagenetic facies development, diagenetic facies shape pore structure, and pore structure determines reservoir properties," this invention establishes a three-phase synergistic control relationship and a quantitative evaluation model, thereby overcoming the limitations of single-factor analysis in existing technologies and improving the systematicness and reliability of reservoir evaluation results.

[0086] This invention enables continuous identification and quantitative classification of key reservoir attributes, improving the continuity, standardization, and repeatability of evaluation results. Traditional methods rely heavily on core, thin section, and experimental data, and are limited by the number of core samples, sampling density, and testing costs, making it difficult to achieve continuous evaluation across the entire well section. Furthermore, diagenetic facies classification and pore structure evaluation often depend on empirical judgment, resulting in insufficient interpretive consistency. This invention establishes a well logging quantitative identification model for lithology-lithofacies, diagenetic facies, and pore structure, extending the understanding of discrete samples to uncored sections and wells. It also establishes quantitative classification standards for diagenetic facies and pore structure, thereby achieving continuous vertical identification of key reservoir attributes, reducing evaluation subjectivity, and improving the standardization and repeatability of results.

[0087] This invention improves the targeting of favorable reservoir prediction and has good engineering application value. Based on the continuous identification of three phases, this invention constructs reservoir classification and evaluation parameters (RPF) and combines them with actual production test data to achieve reservoir quality grading. This helps to identify the combination of constructive diagenetic facies, favorable porosity structure, and high-quality sedimentary facies, thereby improving the reliability of favorable reservoir and "sweet spot" reservoir prediction. Simultaneously, this invention comprehensively utilizes logging data and rock physics experimental data to form a complete technical process from data preprocessing, parameter optimization, model construction to comprehensive evaluation. It can be used for the fine exploration and development evaluation of deep, low-porosity and permeability reservoirs, and has good application prospects.

[0088] Figure 10 This is a schematic diagram of a device for determining sweet spots in a multiphase coupled reservoir, provided in an embodiment of the present invention. Figure 10 As shown, the device includes: a reservoir data processing module 1010, a classification basis determination module 1020, a classification identification model construction module 1030, and a reservoir prediction module 1040.

[0089] The reservoir data processing module 1010 is used to acquire the original reservoir data corresponding to the target research reservoir and determine the target reservoir data based on the original reservoir data.

[0090] The classification criteria determination module 1020 is used to determine the reservoir classification criteria corresponding to the target research reservoir based on the target reservoir data. The reservoir classification criteria include lithological and lithofacies classification criteria, diagenetic facies classification criteria, and pore structure classification criteria.

[0091] The classification and identification model construction module 1030 is used to establish a target classification and identification model corresponding to the reservoir classification criteria based on the target reservoir data.

[0092] The reservoir prediction module 1040 is used to process the logging data of the target well based on the target classification and recognition model to obtain the reservoir sweet spot prediction result corresponding to the target well.

[0093] Based on the above technical solution, the classification basis determination module is used to extract lithological and lithofacies characteristics corresponding to the target reservoir from the target reservoir data, and determine the lithological and lithofacies classification basis based on the lithological and lithofacies characteristics; extract diagenetic facies characteristics corresponding to the target reservoir from the target reservoir data, and determine the diagenetic facies classification basis based on the diagenetic facies characteristics; and extract pore structure characteristics corresponding to the target reservoir from the target reservoir data, and determine the pore structure classification basis based on the pore structure characteristics.

[0094] Based on the above technical solution, a classification and identification model construction module is used to determine the sensitive logging parameters corresponding to lithology and lithofacies, and to construct a lithology and lithofacies identification model based on the sensitive logging parameters and lithology and lithofacies classification criteria; to determine the diagenetic related logging features corresponding to diagenetic facies, and to construct a diagenetic facies identification model based on the diagenetic related logging features and diagenetic facies classification criteria, wherein the diagenetic facies identification model is a trained neural network model; to determine the response relationship between logging parameters and pore structure feature parameters in the target reservoir data, and to construct a pore structure identification model based on the response relationship and pore structure classification criteria; and to combine the lithology and lithofacies identification model, the diagenetic facies identification model, and the pore structure identification model to obtain the target classification and identification model.

[0095] Based on the above technical solution, the diagenetic facies identification model is a multilayer feedforward neural network; the input parameters of the diagenetic facies identification model are natural gamma logging curves, density logging curves, compensated neutron logging curves, sonic transit time logging curves, and resistivity logging curves; the output of the diagenetic facies identification model is the diagenetic facies type.

[0096] Based on the above technical solution, the reservoir prediction module is used to acquire logging data corresponding to the target well and input the logging data into the target classification and recognition model; acquire the single recognition result corresponding to the target well output by the target classification and recognition model; and determine the reservoir sweet spot prediction result corresponding to the target well based on the single recognition result.

[0097] Based on the above technical solution, the reservoir prediction module is used to determine the physical property coefficients corresponding to each individual identification result and obtain the weight values ​​corresponding to each individual identification result; the comprehensive evaluation result is determined based on the weight values ​​and physical property coefficients, and the reservoir sweet spot prediction result corresponding to the target well is determined according to the comprehensive evaluation result and the preset classification standard.

[0098] Based on the above technical solution, the reservoir data processing module is used to standardize the original reservoir data to obtain the target reservoir data. The original reservoir data includes conventional logging, imaging logging, X-ray diffraction logging, core thin section and high pressure physical property test data. The standardization process includes depth correction, outlier removal and dimensional normalization.

[0099] The technical solution of this invention involves acquiring original reservoir data corresponding to the target reservoir, determining the target reservoir data based on the original reservoir data, determining the reservoir classification criteria corresponding to the target reservoir based on the target reservoir data, establishing a target classification identification model corresponding to the reservoir classification criteria based on the target reservoir data, and processing the logging data of the target well based on the target classification identification model to obtain the reservoir sweet spot prediction result corresponding to the target well. Based on the above technical solution, by fusing logging data and well logging data to establish a multi-classification target classification identification model, and determining the reservoir sweet spot prediction result of the target well based on the target classification identification model, continuous identification of diagenetic facies of low-porosity and permeability reservoirs, reservoir classification evaluation, and accurate prediction of favorable reservoir sweet spots are achieved, providing reliable technical support for the exploration and development of low-porosity and permeability oil and gas reservoirs.

[0100] The apparatus for determining the sweet spot of a multiphase coupled reservoir provided in this embodiment of the invention can execute the method for determining the sweet spot of a multiphase coupled reservoir provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0101] Figure 11 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0102] like Figure 11 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0103] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0104] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining sweet spots in multiphase coupled reservoirs.

[0105] In some embodiments, the method for determining multiphase-coupled reservoir sweet spots may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining multiphase-coupled reservoir sweet spots described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining multiphase-coupled reservoir sweet spots by any other suitable means (e.g., by means of firmware).

[0106] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0107] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0108] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0109] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0110] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0111] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0112] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0113] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining sweet spots in multiphase coupled reservoirs, characterized in that, include: Obtain the original reservoir data corresponding to the target reservoir, and determine the target reservoir data based on the original reservoir data; Based on the target reservoir data, the reservoir classification criteria corresponding to the target research reservoir are determined, wherein the reservoir classification criteria include lithological and lithofacies classification criteria, diagenetic facies classification criteria, and pore structure classification criteria; Based on the target reservoir data, establish a target classification and identification model corresponding to the reservoir classification criteria; Based on the target classification and recognition model, the logging data of the target well is processed to obtain the reservoir sweet spot prediction result corresponding to the target well.

2. The method according to claim 1, characterized in that, The determination of reservoir classification criteria corresponding to the target research reservoir based on the target reservoir data includes: Extract lithological and lithofacies characteristics corresponding to the target reservoir from the target reservoir data, and determine the lithological and lithofacies classification criteria based on the lithological and lithofacies characteristics; Extract diagenetic facies features corresponding to the target reservoir from the target reservoir data, and determine the diagenetic facies classification criteria based on the diagenetic facies features; Pore ​​structure features corresponding to the target reservoir are extracted from the target reservoir data, and the pore structure classification criteria are determined based on the pore structure features.

3. The method according to claim 2, characterized in that, Based on the target reservoir data, a target classification and identification model corresponding to the reservoir classification criteria is established, including: Determine the sensitive logging parameters corresponding to the lithology and lithofacies, and construct a lithology and lithofacies identification model based on the sensitive logging parameters and the lithology and lithofacies classification criteria; Determine the diagenetic-related logging features corresponding to the diagenetic facies, and construct a diagenetic facies identification model based on the diagenetic-related logging features and the diagenetic facies classification criteria, wherein the diagenetic facies identification model is a trained neural network model; Determine the response relationship between logging parameters and pore structure characteristic parameters in the target reservoir data, and construct a pore structure identification model based on the response relationship and the pore structure classification criteria. The target classification and identification model is obtained by combining the lithology and lithofacies identification model, the diagenetic facies identification model, and the pore structure identification model.

4. The method according to claim 3, characterized in that, The diagenetic facies identification model is a multilayer feedforward neural network; the input parameters of the diagenetic facies identification model are natural gamma logging curves, density logging curves, compensated neutron logging curves, sonic transit time logging curves, and resistivity logging curves; the output of the diagenetic facies identification model is the diagenetic facies type.

5. The method according to claim 1, characterized in that, The process of processing the logging data of the target well based on the target classification and recognition model to obtain the reservoir sweet spot prediction result corresponding to the target well includes: Obtain logging data corresponding to the target well, and input the logging data into the target classification and recognition model; Obtain the single-item recognition result corresponding to the target well output by the target classification and recognition model; Based on the individual identification results, the reservoir sweet spot prediction result corresponding to the target well is determined.

6. The method according to claim 5, characterized in that, The step of determining the reservoir sweet spot prediction result corresponding to the target well based on the single identification result includes: Determine the physical property coefficient corresponding to each individual identification result, and obtain the weight value corresponding to each individual identification result; The comprehensive evaluation result is determined based on the weight value and the physical property coefficient, and the reservoir sweet spot prediction result corresponding to the target well is determined based on the comprehensive evaluation result and the preset division standard.

7. The method according to claim 1, characterized in that, The step of determining the target reservoir data based on the original reservoir data includes: The target reservoir data is obtained by standardizing the original reservoir data, wherein the original reservoir data includes conventional logging, imaging logging, X-ray diffraction logging, core thin section and high pressure physical property test data; the standardization process includes depth correction, outlier removal and dimensional normalization.

8. A device for determining sweet spots in multiphase coupled reservoirs, characterized in that, include: The reservoir data processing module is used to acquire raw reservoir data corresponding to the target reservoir under study, and to determine the target reservoir data based on the raw reservoir data. The classification criteria determination module is used to determine the reservoir classification criteria corresponding to the target research reservoir based on the target reservoir data. The reservoir classification criteria include lithological and lithofacies classification criteria, diagenetic facies classification criteria, and pore structure classification criteria. The classification and identification model construction module is used to establish a target classification and identification model corresponding to the reservoir classification criteria based on the target reservoir data. The reservoir prediction module is used to process the logging data of the target well based on the target classification and recognition model to obtain the reservoir sweet spot prediction result corresponding to the target well.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the method for determining the sweet spot of a multiphase coupled reservoir as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the sweet spot of a multiphase coupled reservoir as described in any one of claims 1-7.

Images