A method, device, electronic device and medium for predicting the permeability of reservoir space

Abstract

The embodiments of the present invention disclose a method, device, electronic device, and medium for predicting reservoir space permeability. The method comprises: classifying pore structures based on the first flow unit index of the mercury injection sample and determining the range of flow unit indices corresponding to different pore structures; constructing a permeability calculation model corresponding to different pore structures based on the first flow unit index and the second flow unit index of the target core sample; determining the third flow unit index of the uncored sample based on the relationship between the second flow unit index and the well logging curve; inferring the fourth flow unit index of the unsampled reservoir near the well based on the relationship between the third flow unit index and the wellside seismic parameters and constructing a three-dimensional space flow unit index prediction model; constructing a three-dimensional space permeability model based on the three-dimensional space flow unit index prediction model, and predicting the reservoir space permeability. This solution enables quantitative characterization of the permeability of offshore low-permeability and ultra-low-permeability reservoirs from single wells to three-dimensional space.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of reservoir exploration technology, and in particular to a reservoir space permeability prediction method, device, electronic equipment and medium. Background Art

[0002] Low- and ultra-low-permeability reservoirs have complex pore structures, often exhibiting permeability variations spanning two orders of magnitude at the same porosity. Traditional porosity-permeability statistical regression methods and conventional well logging interpretation methods have yielded low permeability calculation accuracy for these reservoirs. Previous researchers have explored methods for establishing porosity-permeability relationships corresponding to different pore structures, significantly improving the accuracy of single-well permeability calculations.

[0003] However, the accuracy of spatial permeability prediction is even more crucial for improving the drilling rate of "sweet spots" with high relative permeability and unlocking the productivity of low- and ultra-low-permeability gas reservoirs. Currently, spatial permeability predictions are mostly based on directly converting spatial porosity into a permeability field under the permeability constraints of a single well. In offshore scenarios with few wells or large well spacing, this approach cannot accurately characterize permeability variations between wells, resulting in large errors in spatial permeability predictions.

[0004] Therefore, how to improve the prediction accuracy of spatial permeability of offshore low-permeability and ultra-low-permeability reservoirs is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] Embodiments of the present invention provide a reservoir space permeability prediction method, device, electronic equipment, and medium to achieve quantitative characterization of offshore low-permeability and ultra-low-permeability reservoir permeability from a single well to three-dimensional space, improve the prediction accuracy of three-dimensional space permeability under offshore conditions with few wells, and provide guidance for pre-drilling trajectory optimization and production capacity prediction.

[0006] In a first aspect, an embodiment of the present invention provides a reservoir spatial permeability prediction method, comprising:

[0007] Determining a first flow unit index and a pore structure type of the mercury injection sample based on a core mercury injection test curve, and determining a range of flow unit indices corresponding to different types of pore structures based on the first flow unit index; wherein reservoirs with different types of pore structures represent different flow units;

[0008] Determining a second flow unit index of the target core sample based on the permeability and porosity of the target core sample, and determining a target pore structure type corresponding to the target core sample based on the second flow unit index; wherein the target core sample has not been subjected to a mercury injection test;

[0009] Determining a first correspondence between permeability and porosity corresponding to different types of pore structures, and constructing a permeability calculation model corresponding to different types of pore structures based on the first correspondence;

[0010] determining a second corresponding relationship between the second flow unit index and the logging curve in the vertical direction, and determining a third flow unit index of the uncored sample based on the second corresponding relationship;

[0011] Constructing a third correspondence between the third flow unit index and the seismic parameters near the well, inferring the fourth flow unit index of the unsampled reservoir near the well based on the third correspondence, and constructing a three-dimensional flow unit index prediction model;

[0012] A three-dimensional space permeability model is constructed based on the three-dimensional space flow unit index prediction model and the permeability calculation model, and the three-dimensional space permeability model is used to predict the reservoir space permeability.

[0013] In a second aspect, an embodiment of the present invention further provides a reservoir space permeability prediction device, comprising:

[0014] a mercury injection sample information determination module, which determines a first flow unit index and a pore structure type of the mercury injection sample based on a core mercury injection test curve, and determines a range of flow unit indices corresponding to different types of pore structures based on the first flow unit index; wherein reservoirs with different types of pore structures represent different flow units;

[0015] a target core sample information determination module, configured to determine a second flow unit index of the target core sample based on the permeability and porosity of the target core sample, and to determine a target pore structure type corresponding to the target core sample based on the second flow unit index; wherein the target core sample has not undergone mercury injection testing;

[0016] a permeability calculation model determination module, configured to determine a first correspondence between permeability and porosity corresponding to different types of pore structures, and construct permeability calculation models corresponding to different types of pore structures based on the first correspondence;

[0017] an uncored sample information determination module, configured to determine a second vertical correspondence between a second flow unit index and a well logging curve, and determine a third flow unit index of the uncored sample based on the second correspondence;

[0018] A three-dimensional flow unit index prediction model construction module is used to construct a third corresponding relationship between the third flow unit index and the wellbore seismic parameters, reversely infer the fourth flow unit index of the unsampled reservoir near the wellbore based on the third corresponding relationship, and construct a three-dimensional flow unit index prediction model;

[0019] The three-dimensional space permeability model construction module is used to construct a three-dimensional space permeability model based on the three-dimensional space flow unit index prediction model and the permeability calculation model, and use the three-dimensional space permeability model to predict the reservoir space permeability.

[0020] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0021] one or more processors;

[0022] a storage device for storing one or more programs;

[0023] When the one or more programs are executed by the one or more processors, the one or more processors implement the reservoir space permeability prediction method described in any embodiment of the present invention.

[0024] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the reservoir space permeability prediction method described in any embodiment of the present invention.

[0025] In a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the reservoir space permeability prediction method as described in any embodiment of the present invention.

[0026] Embodiments of the present invention provide a reservoir space permeability prediction method, device, electronic device and storage medium. The method classifies pore structures by determining a first flow unit index of a mercury injection sample subjected to a mercury injection experiment, and determines the range of flow unit indices corresponding to different types of pore structures. Based on the first flow unit index and the second flow unit index of a target core sample, a permeability calculation model corresponding to different types of pore structures is constructed. A second vertical correspondence between the second flow unit index and a logging curve is determined to determine a third flow unit index of an uncored sample. Based on a third correspondence between the third flow unit index and a near-well seismic parameter, a fourth flow unit index of an unsampled reservoir near the well is inferred and a three-dimensional space flow unit index prediction model is constructed. A three-dimensional space permeability model is constructed based on the three-dimensional space flow unit index prediction model and the permeability calculation model, and the three-dimensional space permeability model is used to predict the reservoir space permeability. By adopting the technical solution of the embodiment of the present invention, the pore structure, a key factor affecting permeability, is reflected in the prediction of spatial permeability, and quantitative characterization of the permeability of offshore low-permeability and ultra-low-permeability reservoirs from a single well to three-dimensional space is achieved. The prediction accuracy of three-dimensional spatial permeability under offshore conditions with few wells is improved, and guidance can be provided for pre-drilling trajectory optimization and production capacity prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Other features, objects, and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered as limiting the present invention. Like reference characters are used throughout the drawings to denote like parts. In the drawings:

[0028] Figure 1 This is a flow chart of a reservoir space permeability prediction method provided in Example 1 of the present invention;

[0029] Figure 2 This is a flow chart of a reservoir space permeability prediction method provided by the second embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of a permeability model based on flow unit index classification provided by the second embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of a probabilistic neural network prediction principle provided by the second embodiment of the present invention;

[0032] Figure 5 This is a schematic diagram of the correspondence between a target curve and seismic parameters provided by the second embodiment of the present invention;

[0033] Figure 6 This is a schematic diagram of operator length sensitivity analysis provided by the second embodiment of the present invention;

[0034] Figure 7 This is a schematic diagram of average error and number of attributes provided by the second embodiment of the present invention;

[0035] Figure 8 This is a schematic diagram comparing a probabilistic neural network prediction curve and an actual curve provided by the second embodiment of the present invention;

[0036] Figure 9 This is a schematic diagram of the intersection of a probabilistic neural network prediction curve and an actual curve provided by the second embodiment of the present invention;

[0037] Figure 10 This is a schematic diagram of a three-dimensional spatial flow unit index prediction model provided by the second embodiment of the present invention;

[0038] Figure 11 This is a schematic diagram of a three-dimensional permeability model of a target area established using a traditional method according to the second embodiment of the present invention;

[0039] Figure 12 This is a schematic diagram of a three-dimensional spatial permeability model provided by the second embodiment of the present invention;

[0040] Figure 131 is a schematic structural diagram of a reservoir space permeability prediction device provided in an embodiment of the present invention;

[0041] Figure 14 It is a structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0043] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the various operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0044] Among them, the acquisition, storage, use and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0045] Example 1

[0046] Figure 1 This is a flow chart of a reservoir permeability prediction method provided in an embodiment of the present invention. This embodiment is applicable to permeability prediction of reservoir spaces in low-permeability and ultra-low-permeability environments. The method of this embodiment can be executed by a reservoir permeability prediction device, which can be implemented using hardware and / or software. The device can be configured in a server for reservoir permeability prediction. The method specifically includes the following steps:

[0047] S110 , determining a first flow unit index and a pore structure type of the mercury injection sample according to a core mercury injection test curve, and determining flow unit index ranges corresponding to different types of pore structures according to the first flow unit index.

[0048] Among them, the core mercury injection experiment is an important experimental method for studying the pore structure of rocks, especially suitable for the study of low-permeability rocks. It can help researchers understand key parameters such as the pore size, distribution, and starting pressure of rocks, and then evaluate the permeability and production potential of the reservoir.

[0049] Pore structure refers to the geometry, size, distribution, interconnectivity, and configuration of pores and throats within a rock. Pore structure reflects the combination of various pore types and the connecting throats within a reservoir, providing an overall picture of pore and throat development.

[0050] The flow zone indicator (FZI) is a parameter used to describe regions with similar fluid flow characteristics in reservoir rocks and is widely used to quantitatively identify and divide flow units.

[0051] In an embodiment of the present invention, the first flow unit index of different mercury injection samples is determined based on the core mercury injection test curve, and the pore structure is classified according to the first flow unit index; the first flow unit index of different pore structures is matched, and the flow unit index range corresponding to different types of pore structures is determined; wherein, reservoirs with different types of pore structures represent different flow units.

[0052] S120: Determine a second flow unit index of the target core sample based on the permeability and porosity of the target core sample, and determine a target pore structure type corresponding to the target core sample based on the second flow unit index.

[0053] The target core sample has not undergone mercury injection testing. The permeability and porosity of the target core sample are determined, and a second flow unit index of the target core sample is determined based on the permeability and porosity. The second flow unit index is compared with the first flow unit index to determine the target pore structure type corresponding to the target core sample. In an embodiment of the present invention, the second flow unit index of the target core sample is determined based on the permeability and porosity. The target core sample may be obtained from a low-permeability or ultra-low-permeability reservoir. The second flow unit index is compared with the first flow unit index to determine the target pore structure type corresponding to the target core sample.

[0054] It can be understood that the first flow unit index can be a proxy to distinguish different flow unit indices that appear before and after in the embodiment to execute corresponding logic. Any flow unit index selected from the flow unit index can be used to explain the execution logic from the selected flow unit index. Therefore, the flow unit index that appears for the first time in this article is called the first flow unit index, and other flow unit indices that appear subsequently and are different from the first flow unit index are called second flow unit indices, which will not be repeated later.

[0055] S130 , determining a first corresponding relationship between permeability and porosity corresponding to different types of pore structures, and constructing a permeability calculation model corresponding to different types of pore structures based on the first corresponding relationship.

[0056] Permeability is a parameter that characterizes the ability of rock to allow fluid to pass through. It is the physical basis of oil (gas) reservoir rocks and has a significant impact on oil and gas migration and seepage mechanics. The numerical value of permeability can indicate the quality of rock permeability.

[0057] The core sample includes a target core sample and a mercury injection sample for a core mercury injection experiment. The present invention constructs a first correspondence between the permeability and porosity of the core sample based on the relationship between the permeability and porosity of the target core sample and the relationship between the permeability and porosity of the mercury injection sample. Because the porosity and permeability of low-permeability and ultra-low-permeability reservoirs have a poor correlation, the porosity and permeability analyzed by the core mercury injection experiment for different flow units are intersected to obtain permeability calculation models for different flow units, that is, permeability calculation models for different types of pore structures.

[0058] S140: Determine a second corresponding relationship between the second flow unit index and the logging curve in the vertical direction, and determine a third flow unit index of the uncored sample based on the second corresponding relationship.

[0059] Well logs are curves of changes in formation rock physical properties measured and plotted using well logging technology during petroleum geological exploration. These curves reflect various physical properties of underground rock formations and fluids, and can indirectly reveal the pore structure of low- and ultra-low-permeability reservoirs. These well logs include, but are not limited to, natural gamma ray logs, neutron logs, density logs, sonic transit time logs, and resistivity logs.

[0060] In this embodiment of the present invention, after determining the second flow unit index of the target core sample and the target pore structure type, a relationship between the flow unit index FZI of all core analysis and testing samples and the corresponding depth point logging curve is constructed according to a machine learning algorithm (K-Nearest Neighbor, KNN), thereby obtaining the third flow unit index of the non-coring sample.

[0061] S150, constructing a third corresponding relationship between the third flow unit index and the wellbore seismic parameter, inferring the fourth flow unit index of the unsampled reservoir near the wellbore based on the third corresponding relationship, and constructing a three-dimensional space flow unit index prediction model.

[0062] Seismic parameters may refer to quantitative descriptions of earthquake source characteristics based on seismic data analysis, including basic earthquake parameters, seismic mechanism solutions, and source dynamic parameters. These seismic parameters include, but are not limited to, density, P-wave and S-wave velocities, frequency, P-wave impedance, Poisson's ratio, S-wave impedance, and P-wave and S-wave velocity ratios. Near-well seismic parameters may refer to seismic parameters of the reservoir between the target well and adjacent wells. In this embodiment of the present invention, the target well may refer to the well from which the target core sample was taken.

[0063] In an embodiment of the present invention, a corresponding third flow unit index is determined based on the wellside seismic parameters, and a third corresponding relationship between the third flow unit index and the wellside seismic parameters is constructed. The fourth flow unit index on other reservoirs is inferred based on the third corresponding relationship; a three-dimensional space flow unit index prediction model is constructed to predict the flow unit index of other unsampled wells or inter-well reservoirs in three-dimensional space.

[0064] S160: Construct a three-dimensional permeability model based on the three-dimensional flow unit index prediction model and the permeability calculation model, and use the three-dimensional permeability model to predict the reservoir space permeability.

[0065] According to the relationship between the flow unit index and the permeability, a three-dimensional space permeability model is constructed on the basis of the three-dimensional space flow unit index prediction model; and the three-dimensional space permeability model is used to predict the reservoir space permeability.

[0066] An embodiment of the present invention provides a method for predicting reservoir spatial permeability. The method comprises determining a first flow unit index and a pore structure type of a mercury injection sample based on a core mercury injection test curve, and determining a range of flow unit indices corresponding to different types of pore structures based on the first flow unit index; determining a second flow unit index of a target core sample based on the permeability and porosity of the target core sample, and determining a target pore structure type corresponding to the target core sample based on the second flow unit index; determining a first correspondence between permeability and porosity corresponding to different types of pore structures, and constructing a permeability calculation model corresponding to different types of pore structures based on the first correspondence; determining a second correspondence between the second flow unit index and a well logging curve in the vertical direction, and determining a third flow unit index of an uncored sample based on the second correspondence; constructing a third correspondence between the third flow unit index and a near-well seismic parameter, and inferring a fourth flow unit index of an unsampled reservoir near the well based on the third correspondence, and constructing a three-dimensional flow unit index prediction model; constructing a three-dimensional permeability model based on the three-dimensional flow unit index prediction model and the permeability calculation model, and using the three-dimensional permeability model to predict reservoir spatial permeability. By adopting the technical solution of the embodiment of the present invention, the pore structure, a key factor affecting permeability, is reflected in the prediction of spatial permeability, and quantitative characterization of the permeability of offshore low-permeability and ultra-low-permeability reservoirs from a single well to three-dimensional space is achieved. The prediction accuracy of three-dimensional spatial permeability under offshore conditions with few wells is improved, and guidance can be provided for pre-drilling trajectory optimization and production capacity prediction.

[0067] Example 2

[0068] Figure 2This is a flow chart of a reservoir space permeability prediction method provided in an embodiment of the present invention. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment. The embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the reservoir space permeability prediction method provided in the embodiment of the present invention may include the following steps:

[0069] S210 , determining a first flow unit index and a pore structure type of the mercury injection sample according to a core mercury injection test curve, and determining flow unit index ranges corresponding to different types of pore structures according to the first flow unit index.

[0070] Based on the results of mercury injection experiments on low- and ultra-low-permeability reservoir cores in the target area, the pore structures were classified according to the morphological characteristics of the mercury injection curves, and the flow unit index ranges corresponding to different types of pore structures were determined. Using the porosity and permeability data from core analysis, the first flow unit index corresponding to different types of pore structures was calculated according to the Kozeny-Carman equation; the Kozeny-Carman equation is a formula that describes the relationship between rock permeability, porosity, and rock specific surface area, and can be expressed as:

[0071]

[0072] Where K represents permeability, mD; φ represents effective porosity; H c Represents the structural performance constant, dimensionless.

[0073] Due to the influence of sediment heterogeneity, the pore tortuosity and shape coefficient vary greatly. Also due to the influence of cementation, pore roughness and other factors, H c There have been big changes.

[0074]

[0075] The reservoir quality index (RQI) is defined and can be expressed as:

[0076]

[0077] Define the ratio of pore volume to particle volume (φ z ), which can be expressed as:

[0078]

[0079] The flow unit index is expressed as:

[0080] FZI=RQI / φ z

[0081] Taking the logarithm on both sides, it can be expressed as:

[0082] lgRQI = lgFZI + lgφ x

[0083] It can be seen from this that under logarithmic coordinates, RQI and φ z have a linear correlation. The flow unit index FZI corresponding to different pore structure types corresponds to different ranges between 0 and 1.

[0084] In the embodiments of the present invention, the pore structures are divided into six categories, and the ranges of the flow unit indices corresponding to the different types of pore structures are respectively: for type I, FZI > 0.5; for type II, 0.3 < FZI ≤ 0.5; for type III, 0.15 < FZI ≤ 0.3; for type IV, 0.1 < FZI ≤ 0.15; for type V, 0.05 < FZI ≤ 0.1; for type VI, FZI ≤ 0.05.

[0085] S220. Determine the second flow unit index of the target core sample according to the permeability and porosity of the target core sample, and determine the target pore structure type corresponding to the target core sample according to the second flow unit index.

[0086] Among them, based on the calculation method of the first flow unit index FZI in step A1, calculate the second flow unit index of the target core sample without performing the core mercury injection experiment, and classify the target core sample into the corresponding pore structure classification according to the second flow unit index.

[0087] As an optional but non-limiting implementation manner, the determining the second flow unit index of the target core sample according to the permeability and porosity of the target core sample, and determining the target pore structure type corresponding to the target core sample according to the second flow unit index includes, but is not limited to, steps A1 - A2:

[0088] Step A1: Determine the permeability and porosity of the target core sample, and determine the second flow unit index of the target core sample according to the permeability and porosity.

[0089] Step A2: Correlate the second flow unit index with the first flow unit index to determine the target pore structure type corresponding to the target core sample.

[0090] Since data from mercury injection core injection analysis is relatively limited, to improve the accuracy of the permeability calculation model, the porosity and permeability of the target core sample, which has not undergone mercury injection core injection analysis, are determined using well logging curves to determine the second flow unit index of the target core sample. Specifically, based on the calculation method for the first flow unit index FZI in step A1, the permeability and porosity of the target core sample are determined based on well logging curves, and the second flow unit index of the target core sample, which has not undergone mercury injection core injection, is calculated. The second flow unit index is compared with the first flow unit index to determine the target pore structure type corresponding to the target core sample.

[0091] S230: Determine a first corresponding relationship between permeability and porosity corresponding to different types of pore structures, and construct a permeability calculation model corresponding to different types of pore structures based on the first corresponding relationship.

[0092] Among them, the embodiment of the present invention constructs a first corresponding relationship between the permeability and porosity of the core sample based on the relationship between the permeability and porosity of the target core sample, and the relationship between the permeability and porosity of the mercury injection sample; and constructs a permeability calculation model corresponding to different types of pore structures based on the first corresponding relationship.

[0093] As an optional but non-limiting implementation, determining the first correspondence between the permeability and porosity corresponding to different types of pore structures, and constructing the permeability calculation model corresponding to different types of pore structures based on the first correspondence, includes but is not limited to steps B1-B2:

[0094] Step B1: Determine a first correspondence between the permeability and porosity of the core sample based on a first flow unit index of the mercury injection sample and a second flow unit index of the target core sample; the core sample includes the target core sample and the mercury injection sample for the core mercury injection experiment.

[0095] Step B2: Constructing permeability calculation models corresponding to different types of pore structures based on the first corresponding relationship.

[0096] Different pore structure types correspond to different flow unit index ranges. The corresponding relationship between permeability and porosity corresponding to different flow unit index ranges is determined to construct permeability calculation models corresponding to different pore structure types. Specifically, the different pore structure types of the core sample are determined by determining a first flow unit index and a second flow unit index. The first and second flow unit indices are determined based on the permeability and porosity of the mercury injection sample and the permeability and porosity of the target core sample. Therefore, based on the first and second flow unit indices, a first corresponding relationship between the permeability and porosity of the core sample is determined; and based on this first corresponding relationship, a permeability calculation model corresponding to different pore structure types is constructed.

[0097] Optionally, the porosity and permeability of six types of flow units in low-permeability and ultra-low-permeability reservoirs in different target areas are intersected separately to obtain the permeability calculation models of six different flow units. Figure 3 , the correlation between porosity and permeability increased to more than 90%.

[0098] S240: Determine a second corresponding relationship between the second flow unit index and the logging curve in the vertical direction, and determine a third flow unit index of the uncored sample based on the second corresponding relationship.

[0099] Optionally, the uncored samples may belong to different types of pore structures in the vertical direction. The corresponding type of pore structure is determined based on the third flow unit index of the uncored samples; the corresponding permeability calculation model is determined based on the pore structure, and the permeability of the uncored samples belonging to different types of pore structures is determined based on the corresponding permeability calculation model.

[0100] In the embodiment of the present invention, the permeabilities of uncored samples with different types of pore structures in the vertical direction are determined so as to calibrate the permeability predicted by the constructed three-dimensional spatial permeability model.

[0101] S250: Construct a third corresponding relationship between the third flow unit index and the seismic parameters of the wellbore, and determine a fourth flow unit index of the unsampled reservoir beside the wellbore based on the third corresponding relationship and the seismic parameters of the unsampled reservoir beside the wellbore.

[0102] In this embodiment of the present invention, a third correspondence is established between a third flow unit index calculated from well logging curves and near-well seismic parameters. This correspondence is used to infer a fourth flow unit index for unsampled reservoirs near the well. The near-well seismic parameters include density, P-wave and S-wave velocities, frequency, P-wave impedance, Poisson's ratio, S-wave impedance, and P-wave and S-wave velocity ratio. The third correspondence can be a linear or nonlinear relationship.

[0103] S260: Construct a reservoir flow unit index curve according to the second flow unit index and the fourth flow unit index.

[0104] Wherein, a reservoir flow unit index curve is constructed in the vertical direction according to the second flow unit index and the fourth flow unit index.

[0105] S270: Using the flow unit index curve and wellbore seismic parameters as training samples, a three-dimensional flow unit index prediction model is constructed.

[0106] The corresponding relationship between the flow unit index and the wellbore seismic parameters can be linear or nonlinear. If a linear relationship exists between the flow unit index and the wellbore seismic parameters, the correlation coefficient can be derived using the wellbore and wellbore seismic parameters within a certain time window. If a nonlinear relationship exists between the flow unit index and the wellbore seismic parameters, the wellbore and wellbore seismic parameters within a certain time window can be used as training samples to derive the implicit relationship using a neural network.

[0107] Among them, multiple types of seismic data bodies can be used simultaneously in the prediction process, such as AVO attribute bodies and conventional acoustic impedance inversion bodies, and multiple characteristic parameter bodies (such as instantaneous frequency) can be derived from each data body. Among the many parameters, the EMERGE module of HRS can automatically find a set of seismic parameters that best matches the target curve under a given mode to participate in the prediction. Among them, the EMERGE module of HRS is a powerful software tool that focuses on analyzing well logging curves and seismic data for multi-attribute analysis and prediction; the target curve refers to the flow unit index curve. This algorithm is actually a process of interpolating known well point information in a multi-dimensional seismic characteristic parameter space. Since it does not require a fixed mathematical model, it can better adapt to local data and can provide inversion results with a high consistency rate with known well points. Its disadvantage is that the lateral stability of the inversion results is difficult to control, so repeated parameter experiments are required.

[0108] The most distinctive feature of this method is its ability to use multiple different seismic data bodies simultaneously and combine them with AVO processing results, which is equivalent to introducing pre-stack seismic information into the inversion, providing a more sufficient basis for inverting other rock physical parameters besides acoustic impedance.

[0109] In the linear relationship model, it is assumed that the corresponding relationship between the flow unit index and the wellbore seismic parameters can be expressed by the following linear equation:

[0110] M=a11S 11 +a12S 12 +…+a1mS 1m +a21S 21 +a22S 22 +…+a2mS2

[0111] +an1S n1 +an2S n2 +…+anmS nm

[0112] Among them, S ij is the jth sample point of the i-th seismic parameter curve; a is a constant coefficient, determined by optimally matching the target parameter curve M; and n is the number of seismic parameter types used, determined by minimizing the cross-validation error. The so-called cross-validation error is the average of the differences between the two for all known well points, after removing one known well. The minimum cross-validation error criterion is the core of almost all EMERGE modules. Seismic parameters are selected using a single-step incremental approach. First, the seismic parameter that best matches the well point is selected. The remaining parameters are tested one by one, and the second parameter that best matches the well point under the given regression model is selected. The remaining seismic parameters are selected in this manner.

[0113] After constructing a linear relationship between the third flow unit index and the wellbore seismic parameters, the fourth flow unit index of the unsampled reservoir near the wellbore is inferred based on the linear relationship and a three-dimensional flow unit index prediction model is constructed.

[0114] As an optional but non-limiting implementation, when there is a nonlinear relationship between the third flow unit index and the wellbore seismic parameters, the flow unit index curve and the wellbore seismic parameters are used as training samples to construct a three-dimensional flow unit index prediction model, including but not limited to steps C1-C3:

[0115] Step C1: Using a cross-check error algorithm, a target seismic parameter that matches the flow unit index curve under a preset regression mode is determined from the wellbore seismic parameters.

[0116] Step C2: Using the target earthquake parameters and the flow unit index curve as training samples, a probabilistic neural network is used to train a three-dimensional flow unit index prediction model to obtain a first three-dimensional flow unit index prediction model.

[0117] Step C3: using the seismic parameters of the sampled adjacent wells to verify the first three-dimensional spatial flow unit index prediction model and adjust the parameters to determine the second three-dimensional spatial flow unit index prediction model.

[0118] Among them, the embodiment of the present invention uses the target seismic parameters and the flow unit index curve as training samples, and the prediction result consistency rate through the probabilistic neural network (PNN) will be greatly improved. The relevant model is predicted using the (PNN) method, that is, the well and seismic data within a certain time window range are used as training samples, and the implicit relationship is derived using the neural network. The target seismic parameters are consistent with the method of determining seismic parameters in the linear relationship. In the prediction process, multiple types of seismic data bodies can be used simultaneously, such as AVO attribute bodies, conventional acoustic impedance inversion bodies, etc., and each data body can derive multiple characteristic parameter bodies (such as instantaneous frequency) from them. Among the numerous parameters, a set of target seismic parameters that best match the target curve under a given mode is found to participate in the prediction.

[0119] See also Figure 4 What distinguishes probabilistic neural networks from the commonly used BP neural network is its boundary stability, which often results in more stable predictions for regions far from the sample space. Another significant difference is that PNNs abandon the "black box" nature of BP in favor of a clear mathematical model. This allows for a rough estimate of their predictive performance in advance, and allows for the appropriate adjustment of trained network parameters to achieve optimal predictions.

[0120] Optionally, given a set of training samples: {x i1 , x i2 ,…,x i2 , L i}, the PNN network output value L at a point x in the earthquake parameter space is given by the following formula:

[0121]

[0122] in: represents the n-dimensional spatial distance between the earthquake parameter space point x and the i-th training sample; the weighting coefficient r is an undetermined network parameter used to control the sensitivity of different types of earthquake parameters to the prediction results; n represents the number of earthquake parameter types involved in the training, m represents the number of samples, and L can refer to the objective function value.

[0123] It can be seen that the PNN network prediction process is actually an interpolation process of well point information in the seismic parameter space. The determination of the network parameter r is based on the criterion of minimizing the cross-check error of each well. At the same time, it can also be combined with the geological understanding of the local area and artificially adjusted through repeated trial calculations of several key lines. The smaller the value of r, the closer the prediction result is to the known well point.

[0124] Based on the predictions of single-well training simulations using a probabilistic neural network (PNN), this nonlinear relationship is applied to the entire seismic data volume, enabling seismic prediction of the entire FZI data volume. Based on the FZI data volume predicted by the probabilistic neural network (PNN) method, a sequential Gaussian simulation method is used to establish a three-dimensional flow unit index prediction model for the target area using trend-constrained co-simulation, based on the results of variogram analysis (primary and secondary ranges and provenance direction).

[0125] In an alternative embodiment of the present invention, see Figure 5 , using the probabilistic neural network (PNN) method to predict, that is, the FZI data and seismic data of the well within a certain time window range are used as training samples, and the neural network is used to derive the implicit relationship. Through the analysis of the flow unit index curve (FZI curve) and seismic related multi-attribute analysis, it is found that Figure 6 as well as Figure 7 When the operator length is 5 and the number of attributes is 7, the average root mean square error between the predicted result and the actual FZI curve is the smallest. The operator length is the number of seismic sampling points symmetrically distributed around the seismic sampling point corresponding to the target curve sample point, and the seismic multi-attribute values at multiple points are convolved to represent the value at a sample point of the target curve. Preferred seismic parameters include but are not limited to average frequency, inverse Poisson's ratio, instantaneous phase cosine, seismic bandpass filtering, shear wave impedance squared, longitudinal wave impedance squared, and longitudinal-to-straight wave velocity ratio squared.

[0126] Based on the earthquake multi-attribute analysis and prediction results, the probabilistic neural network (PNN) is used for continuous iterative training and learning, which significantly improves the prediction accuracy and reduces the prediction error. Figure 8 as well as Figure 9 ,From the comparison and intersection of the PNN prediction and ,actual curves, it can be seen that the two curves of the four ,wells have consistent trends in the vertical direction, the ,curve change positions are unified, and the correlation coefficient is increased to 76.7%.

[0127] Based on the probabilistic neural network (PNN) single well training simulation prediction, this nonlinear relationship is applied to the entire seismic data volume to achieve seismic prediction of the entire FZI curve. Figure 10 Based on the FZI data body predicted by the probabilistic neural network (PNN) method, according to the variogram analysis results (primary and secondary variation ranges and material source direction), the sequential Gaussian simulation method is used to establish a three-dimensional spatial flow unit index prediction model for the target area with trend constraint co-simulation.

[0128] S280: Construct a three-dimensional space permeability model based on the three-dimensional space flow unit index prediction model and the permeability calculation model, and use the three-dimensional space permeability model to predict the reservoir space permeability.

[0129] Wherein, a three-dimensional spatial permeability model is constructed based on the three-dimensional spatial flow unit index prediction model, and the three-dimensional spatial permeability model is used to predict the reservoir spatial permeability.

[0130] As an optional but non-limiting implementation, the three-dimensional permeability model is constructed based on the three-dimensional flow unit index prediction model and the permeability calculation model, and the reservoir spatial permeability is predicted using the three-dimensional permeability model, including but not limited to steps D1-D3:

[0131] Step D1: Determine the corresponding relationship between the flow unit index and the permeability calculation model based on the second flow unit index of the target core sample and the target permeability calculation model.

[0132] Step D2: Based on the corresponding relationship, a three-dimensional space permeability model is constructed on the basis of the three-dimensional space flow unit index prediction model.

[0133] Step D3: using the three-dimensional spatial permeability model to predict the reservoir spatial permeability.

[0134] Among them, according to the relationship between the flow unit index and permeability, the corresponding relationship between the flow unit index and the permeability calculation model is determined; based on the three-dimensional space flow unit index prediction model, a three-dimensional space permeability model is constructed, and the three-dimensional space permeability model is used to predict the reservoir space permeability.

[0135] Alternatively, the prediction of 3D spatial permeability of low-permeability and ultra-low-permeability reservoirs can be achieved by first establishing a target area porosity model based on the porosity inversion prediction results, using the variogram analysis parameters (primary and secondary ranges and provenance direction) and lithofacies control using the sequential Gaussian simulation method with trend constraints. Based on the corresponding porosity-permeability relationship prediction results for different FZI values, a trend-constrained co-simulation is then performed to establish a 3D permeability attribute model for the target area. See [1]. Figure 11 as well as Figure 12 The results show that the permeability plane characteristics of the target area are quite different from the original permeability model calculated directly using the porosity model according to a single porosity-permeability relationship. The heterogeneity of low permeability and ultra-low permeability is more refined: the permeability around Well 4 and the northwest area of the anticline is higher, but the heterogeneity around the well is stronger.

[0136] In an optional solution of an embodiment of the present invention, the permeability predicted by the three-dimensional permeability model can be calibrated based on the permeability of uncored samples, and the three-dimensional permeability model can be optimized. For example, a first permeability of uncored sample A is determined, and a second permeability of sample A is determined using the three-dimensional permeability model. The first and second permeabilities are compared, and if the difference exceeds a preset threshold, the parameters of the three-dimensional permeability model are adjusted to calibrate and optimize the three-dimensional permeability model.

[0137] An embodiment of the present invention provides a method for predicting reservoir spatial permeability. Based on core mercury injection experimental data, low-permeability and ultra-low-permeability reservoirs are classified according to pore structure type, and a first flow unit index reflecting the quality of each type of pore structure reservoir is constructed to obtain the flow unit index range for different types of reservoirs. Then, a relationship between the second flow unit index of the target core sample and the well logging curve is established, and the third flow unit index value of the uncored layer is calculated. Based on the classification, a permeability calculation model for different types of reservoirs is established. Probabilistic neural network (PNN) prediction is performed by combining original seismic data, prestack inversion results, and seismic internal operation attributes to invert the spatial reservoir flow zone index (FZI) data volume. A sequential Gaussian simulation method is used to establish a three-dimensional spatial flow unit index prediction model through trend-constrained co-simulation. Permeability is predicted based on the pore-permeability relationship corresponding to different FZI values. On this basis, trend-constrained co-simulation is performed to establish a three-dimensional spatial permeability model for the target area. Compared with the traditional direct conversion of spatial porosity field into permeability field under the permeability constraint of a single well, the present invention better overcomes the problem of poor correlation between porosity and permeability of low-permeability and extra-low-permeability reservoirs. The pore structure, a key factor affecting the permeability of such reservoirs, can be reflected in the prediction of three-dimensional spatial permeability, thereby realizing quantitative characterization of the permeability of offshore low-permeability and extra-low-permeability reservoirs from a single well to three-dimensional space. This makes the prediction of spatial permeability under the constraint of few offshore wells more reasonable and more accurate, improves the prediction accuracy of three-dimensional spatial permeability under the condition of few offshore wells, and provides guidance for pre-drilling trajectory optimization and production capacity prediction.

[0138] Example 3

[0139] Figure 13 This is a schematic diagram of the structure of a reservoir space permeability prediction device provided in an embodiment of the present invention. The technical solution of this embodiment is applicable to the case of reservoir space permeability prediction. The device can be implemented by software and / or hardware and is generally integrated into any electronic device with network communication function, including but not limited to: servers, computers, personal digital assistants and other devices. Figure 4As shown, the reservoir space permeability prediction device provided in this embodiment may include: a mercury injection sample information determination module 1310, a target core sample information determination module 1320, a permeability calculation model determination module 1330, an uncored sample information determination module 1340, a three-dimensional space flow unit index prediction model construction module 1350, and a three-dimensional space permeability model construction module 1360; wherein,

[0140] The mercury injection sample information determination module 1310 determines a first flow unit index and a pore structure type of the mercury injection sample based on the core mercury injection test curve, and determines a range of flow unit indices corresponding to different types of pore structures based on the first flow unit index; wherein reservoirs with different types of pore structures represent different flow units;

[0141] The target core sample information determination module 1320 is configured to determine a second flow unit index of the target core sample based on the permeability and porosity of the target core sample, and determine a target pore structure type corresponding to the target core sample based on the second flow unit index; wherein the target core sample has not undergone mercury injection testing;

[0142] A permeability calculation model determination module 1330 is configured to determine a first correspondence between permeability and porosity of a core sample, and construct permeability calculation models corresponding to different types of pore structures based on the first correspondence; the core sample includes a target core sample and a mercury injection sample for a core mercury injection experiment;

[0143] The uncored sample information determination module 1340 is configured to determine a second vertical correspondence between the second flow unit index and the well logging curve, and determine a third flow unit index of the uncored sample based on the second correspondence.

[0144] A three-dimensional flow unit index prediction model construction module 1350 is used to construct a third correspondence between the third flow unit index and the wellbore seismic parameters, reversely infer the fourth flow unit index of the unsampled reservoir near the wellbore based on the third correspondence, and construct a three-dimensional flow unit index prediction model;

[0145] The three-dimensional permeability model construction module 1360 is used to construct a three-dimensional permeability model based on the three-dimensional flow unit index prediction model and the permeability calculation model, and use the three-dimensional permeability model to predict the reservoir space permeability.

[0146] Based on the above embodiment, optionally, the target core sample information determination module is specifically configured to:

[0147] determining the permeability and porosity of the target core sample, and determining a second flow unit index of the target core sample based on the permeability and porosity;

[0148] The second flow unit index is matched with the first flow unit index to determine the target pore structure type corresponding to the target core sample.

[0149] Based on the above embodiment, optionally, the permeability calculation model determination module is specifically configured to:

[0150] Determining a first corresponding relationship between the permeability and porosity of the core sample based on a first flow unit index of the mercury injection sample and a second flow unit index of the target core sample; the core sample includes the target core sample and the mercury injection sample for the core mercury injection experiment;

[0151] Based on the first corresponding relationship, a permeability calculation model corresponding to different types of pore structures is constructed.

[0152] Based on the above embodiment, optionally, the three-dimensional space flow unit index prediction model construction module is specifically used to:

[0153] Establishing a third correspondence between the third flow unit index and the wellbore seismic parameters, and determining a fourth flow unit index of the unsampled reservoir near the wellbore based on the third correspondence and the seismic parameters of the unsampled reservoir near the wellbore; wherein the wellbore seismic parameters include density, P-wave velocity, S-wave velocity, frequency, P-wave impedance, Poisson's ratio, S-wave impedance, and P-wave velocity ratio; and the correspondence includes a linear relationship or a nonlinear relationship;

[0154] constructing a reservoir flow unit index curve according to the second flow unit index and the fourth flow unit index;

[0155] The flow unit index curve and wellside seismic parameters are used as training samples to construct a three-dimensional flow unit index prediction model.

[0156] Based on the above embodiment, optionally, when there is a nonlinear relationship between the third flow unit index and the wellbore seismic parameter, the three-dimensional space flow unit index prediction model construction module is further specifically used to:

[0157] A cross-check error algorithm is used to determine target seismic parameters that match the flow unit index curve under a preset regression model from the wellbore seismic parameters;

[0158] The target earthquake parameters and the flow unit index curve are used as training samples, and a probabilistic neural network is used to train a three-dimensional flow unit index prediction model to obtain a first three-dimensional flow unit index prediction model;

[0159] The seismic parameters of the sampled adjacent wells are used to verify the first three-dimensional spatial flow unit index prediction model and adjust the parameters to determine the second three-dimensional spatial flow unit index prediction model.

[0160] Based on the above embodiment, optionally, the three-dimensional space permeability model construction module is specifically used to:

[0161] According to the second flow unit index of the target core sample and the target permeability calculation model, the corresponding relationship between the flow unit index and the permeability calculation model is determined;

[0162] According to the corresponding relationship, a three-dimensional space permeability model is constructed based on the three-dimensional space flow unit index prediction model;

[0163] The three-dimensional spatial permeability model is used to predict the reservoir spatial permeability.

[0164] The reservoir space permeability prediction device provided in the embodiment of the present invention can execute the reservoir space permeability prediction method provided in any embodiment of the present invention mentioned above, and has the corresponding functions and beneficial effects of executing the reservoir space permeability prediction method. For detailed process, please refer to the relevant operations of the reservoir space permeability prediction method in the above embodiment.

[0165] Example 4

[0166] Figure 14 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 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 processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0167] like Figure 14As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0168] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0169] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the reservoir space permeability prediction method.

[0170] In some embodiments, the reservoir space permeability prediction method can 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 can be loaded and / or installed 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 reservoir space permeability prediction method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the reservoir space permeability prediction method in any other appropriate manner (e.g., by means of firmware).

[0171] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0172] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0173] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0174] 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 can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0175] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0176] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0177] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0178] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

[0179] Example 5

[0180] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the reservoir space permeability prediction method provided in any embodiment of the present application.

[0181] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

Claims

1. A reservoir space permeability prediction method, characterized in that: The method comprises: Determining a first flow unit index and a pore structure type of the mercury injection sample based on a core mercury injection test curve, and determining a range of flow unit indices corresponding to different types of pore structures based on the first flow unit index; wherein reservoirs with different types of pore structures represent different flow units; Determining a second flow unit index of the target core sample based on the permeability and porosity of the target core sample, and determining a target pore structure type corresponding to the target core sample based on the second flow unit index; wherein the target core sample has not been subjected to a mercury injection test; Determining a first correspondence between permeability and porosity corresponding to different types of pore structures, and constructing a permeability calculation model corresponding to different types of pore structures based on the first correspondence; determining a second corresponding relationship between the second flow unit index and the logging curve in the vertical direction, and determining a third flow unit index of the uncored sample based on the second corresponding relationship; Constructing a third correspondence between the third flow unit index and the seismic parameters near the well, inferring the fourth flow unit index of the unsampled reservoir near the well based on the third correspondence, and constructing a three-dimensional flow unit index prediction model; Constructing a three-dimensional space permeability model based on the three-dimensional space flow unit index prediction model and the permeability calculation model, and using the three-dimensional space permeability model to predict the reservoir space permeability; The method of constructing a third correspondence between the third flow unit index and the wellbore seismic parameter, inferring the fourth flow unit index of the unsampled reservoir near the wellbore based on the third correspondence, and constructing a three-dimensional flow unit index prediction model includes: Establishing a third correspondence between the third flow unit index and near-well seismic parameters, and determining a fourth flow unit index of the unsampled reservoir near the well based on the third correspondence and the seismic parameters of the unsampled reservoir near the well; wherein the near-well seismic parameters include density, P-wave velocity, S-wave velocity, frequency, P-wave impedance, Poisson's ratio, S-wave impedance, and P-wave velocity ratio, and the correspondence includes a linear relationship or a nonlinear relationship; constructing a reservoir flow unit index curve in the vertical direction based on the second flow unit index and the fourth flow unit index; and constructing a three-dimensional flow unit index prediction model using the flow unit index curve and the near-well seismic parameters as training samples; When a nonlinear relationship exists between the third flow unit index and the wellbore seismic parameters, the flow unit index curve and the wellbore seismic parameters are used as training samples to construct a three-dimensional flow unit index prediction model, including: A cross-check error algorithm is used to determine target seismic parameters that match the flow unit index curve under a preset regression mode from the seismic parameters near the well; the target seismic parameters and the flow unit index curve are used as training samples, and a probabilistic neural network is used to train a three-dimensional flow unit index prediction model to obtain a first three-dimensional flow unit index prediction model; the seismic parameters of the sampled adjacent wells are used to verify the first three-dimensional flow unit index prediction model and adjust the parameters to determine a second three-dimensional flow unit index prediction model.

2. The method according to claim 1, characterized in that Determining a second flow unit index of the target core sample based on the permeability and porosity of the target core sample, and determining a target pore structure type corresponding to the target core sample based on the second flow unit index, includes: determining the permeability and porosity of the target core sample, and determining a second flow unit index of the target core sample based on the permeability and porosity; The second flow unit index is matched with the first flow unit index to determine the target pore structure type corresponding to the target core sample.

3. The method according to claim 1, characterized in that The determining of a first correspondence between permeability and porosity corresponding to different types of pore structures, and constructing a permeability calculation model corresponding to different types of pore structures based on the first correspondence, includes: Determining a first corresponding relationship between the permeability and porosity of the core sample based on a first flow unit index of the mercury injection sample and a second flow unit index of the target core sample; the core sample includes the target core sample and the mercury injection sample for the core mercury injection experiment; Based on the first corresponding relationship, a permeability calculation model corresponding to different types of pore structures is constructed.

4. The method according to claim 1, wherein The method of constructing a three-dimensional permeability model based on the three-dimensional flow unit index prediction model and the permeability calculation model, and using the three-dimensional permeability model to predict the reservoir space permeability, includes: According to the second flow unit index of the target core sample and the target permeability calculation model, the corresponding relationship between the flow unit index and the permeability calculation model is determined; According to the corresponding relationship, a three-dimensional space permeability model is constructed based on the three-dimensional space flow unit index prediction model; The three-dimensional spatial permeability model is used to predict the reservoir spatial permeability.

5. A reservoir space permeability prediction device, characterized in that: The device comprises: a mercury injection sample information determination module, which determines a first flow unit index and a pore structure type of the mercury injection sample based on a core mercury injection test curve, and determines a range of flow unit indices corresponding to different types of pore structures based on the first flow unit index; wherein reservoirs with different types of pore structures represent different flow units; a target core sample information determination module, configured to determine a second flow unit index of the target core sample based on the permeability and porosity of the target core sample, and to determine a target pore structure type corresponding to the target core sample based on the second flow unit index; wherein the target core sample has not undergone mercury injection testing; a permeability calculation model determination module, configured to determine a first correspondence between permeability and porosity corresponding to different types of pore structures, and construct permeability calculation models corresponding to different types of pore structures based on the first correspondence; an uncored sample information determination module, configured to determine a second vertical correspondence between a second flow unit index and a well logging curve, and determine a third flow unit index of the uncored sample based on the second correspondence; A three-dimensional flow unit index prediction model construction module is used to construct a third corresponding relationship between the third flow unit index and the wellbore seismic parameters, reversely infer the fourth flow unit index of the unsampled reservoir near the wellbore based on the third corresponding relationship, and construct a three-dimensional flow unit index prediction model; A three-dimensional permeability model construction module is used to construct a three-dimensional permeability model based on the three-dimensional flow unit index prediction model and the permeability calculation model, and use the three-dimensional permeability model to predict the reservoir space permeability; The three-dimensional flow unit index prediction model construction module is specifically used to: construct a third corresponding relationship between the third flow unit index and the wellbore seismic parameters, and determine the fourth flow unit index of the unsampled reservoir near the well based on the third corresponding relationship and the seismic parameters of the unsampled reservoir near the well; wherein the wellbore seismic parameters include density, P-wave velocity, S-wave velocity, frequency, P-wave impedance, Poisson's ratio, S-wave impedance, and P-wave velocity ratio, and the corresponding relationship includes a linear relationship or a nonlinear relationship; construct a reservoir flow unit index curve based on the second flow unit index and the fourth flow unit index; and use the flow unit index curve and the wellbore seismic parameters as training samples to construct a three-dimensional flow unit index prediction model; Wherein, when there is a nonlinear relationship between the third flow unit index and the wellbore seismic parameter, the three-dimensional space flow unit index prediction model construction module is further specifically used to: A cross-check error algorithm is used to determine target seismic parameters that match the flow unit index curve under a preset regression mode from the seismic parameters near the well; the target seismic parameters and the flow unit index curve are used as training samples, and a probabilistic neural network is used to train a three-dimensional flow unit index prediction model to obtain a first three-dimensional flow unit index prediction model; the seismic parameters of the sampled adjacent wells are used to verify the first three-dimensional flow unit index prediction model and adjust the parameters to determine a second three-dimensional flow unit index prediction model.

6. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the reservoir space permeability prediction method according to any one of claims 1 to 4.

7. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the reservoir space permeability prediction method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the reservoir space permeability prediction method according to any one of claims 1 to 4.

Images