A method, apparatus, device, and medium for computing reservoir pore space

Abstract

The application discloses a method, device, equipment and medium for calculating reservoir pore space, which comprises the following steps: acquiring FMI logging images, compensated neutron logging data and density logging data of a current reservoir, and obtaining a pore space proportion of the current reservoir, a first porosity of the current reservoir and a second porosity of the current reservoir; performing correlation analysis on the pore space proportion as a dependent variable and the compensated neutron logging data and the density logging data to obtain an analysis result, so as to determine a first weight of the compensated neutron logging data and a second weight of the density logging data, and taking the weights as constraint conditions to perform nonlinear regression calculation on the pore space proportion, the compensated neutron logging data and the density logging data, and obtain a formation porosity curve. The FMI logging image is data-processed and combined with conventional logging data, so that a more accurate pore space proportion is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of well logging methods, and particularly relates to a method and device for calculating reservoir pore space, equipment and a medium. BACKGROUND

[0002] Well logging, also known as geophysical well logging or field geophysics, is a method for measuring geophysical parameters by using the electrochemical properties, electrical conductivity, acoustic properties, radioactivity and other geophysical properties of rock formations. In short, well logging is to measure the physical parameters of rock formations, just like measuring temperature with a thermometer; rock formations can conduct electricity, and the resistivity is measured by emitting electric current to the formation, and the neutron porosity and density are measured by bombarding the atoms of the formation with high-energy particles. Compensated neutron porosity and density logging generally reflect the total porosity of the formation, but sometimes are limited by the detection radius and the measurement method. For example, when the density logging instrument's pad is close to the well wall near the place with a cave, and within the instrument's detection range, the density value decreases, and vice versa, for example, when the pad is close to the non-cave place, the density logging cannot reflect it.

[0003] The carbonate reservoir has extremely strong heterogeneity, and it is difficult to meet the production requirements by using the conventional logging method. The imaging logging solves the problem of identifying the carbonate reservoir type by using the conventional logging, and can directly show the well wall condition of the reservoir. Since the FMI imaging logging has good identification ability for the carbonate dual-porosity medium reservoir, but it is difficult to effectively evaluate the complex fracture system and the dissolved pore due to the difficulty in picking up by human-computer interaction. SUMMARY

[0004] To overcome the problems in the prior art, the present application provides a method, device, equipment and medium for calculating reservoir pore space.

[0005] To achieve the above object, the embodiments of the present application provide the following technical solutions.

[0006] The first aspect of the embodiments of the present application provides a method for calculating reservoir pore space, which comprises the following steps.

[0007] obtaining the FMI logging image, the compensated neutron logging data and the density logging data of the current reservoir;

[0008] obtaining the pore space proportion of the current reservoir based on the FMI logging image;

[0009] obtaining the first porosity of the current reservoir based on the compensated neutron logging data;

[0010] obtaining the second porosity of the current reservoir based on the density logging data;

[0011] Correlate the porosity space ratio as the dependent variable with the compensated neutron logging data and the density logging data to obtain an analysis result;

[0012] Based on the analysis result, determine a first weight of the compensated neutron logging data and a second weight of the density logging data;

[0013] Take the first weight and the second weight as constraint conditions, and perform nonlinear regression calculation on the porosity space ratio, the compensated neutron logging data and the density logging data to obtain a formation porosity curve.

[0014] Optionally, the porosity space ratio of the current reservoir is obtained based on the FMI logging image, comprising:

[0015] Based on the FMI logging image, an initial porosity space ratio is obtained;

[0016] Natural gamma logging data is obtained;

[0017] Based on the natural gamma logging data, the initial porosity space ratio is corrected for shale content to obtain the porosity space ratio.

[0018] Optionally, the initial porosity space ratio is obtained based on the FMI logging image, comprising:

[0019] The FMI logging image is image-processed to determine the range of target colors and remove preset colors;

[0020] The FMI logging image after image processing is segmented according to a preset size to obtain a plurality of segmented images;

[0021] Based on a plurality of the segmented images, the initial porosity space ratio is obtained.

[0022] Optionally, the initial porosity space ratio is obtained based on a plurality of the segmented images, comprising:

[0023] Each of the segmented images is processed based on a K-means clustering algorithm to obtain a sample set, the sample set comprising a plurality of sample data, the sample data being represented by a hex value;

[0024] Sample data with a hex value greater than a preset value is removed to obtain the initial porosity space ratio.

[0025] Optionally, the preset size is 0.12 meters to 0.13 meters.

[0026] Optionally, the first porosity of the current reservoir is obtained based on the compensated neutron logging data, comprising:

[0027] The compensated neutron logging data is shale corrected to obtain first corrected data.

[0028] The first corrected data is compensated neutron porosity calculated to obtain the first porosity.

[0029] Optionally, the second porosity of the current reservoir is obtained based on the density logging data, and the method comprises:

[0030] The density logging data is shale corrected to obtain second corrected data.

[0031] The second corrected data is density porosity calculated to obtain the second porosity.

[0032] A second aspect of the embodiment of the application provides a device for calculating reservoir porosity space, comprising:

[0033] A logging information acquisition module is configured to acquire FMI logging images, compensated neutron logging data and density logging data of a current reservoir.

[0034] A porosity space proportion acquisition module is configured to acquire a porosity space proportion of the current reservoir based on the FMI logging images.

[0035] A first porosity acquisition module is configured to acquire a first porosity of the current reservoir based on the compensated neutron logging data.

[0036] A second porosity acquisition module is configured to acquire a second porosity of the current reservoir based on the density logging data.

[0037] A correlation analysis module is configured to perform correlation analysis on the porosity space proportion as a dependent variable and the compensated neutron logging data and the density logging data to obtain an analysis result.

[0038] A weight determination module is configured to determine a first weight of the compensated neutron logging data and a second weight of the density logging data based on the analysis result.

[0039] A formation porosity curve calculation module is configured to perform nonlinear regression calculation on the porosity space proportion, the compensated neutron logging data and the density logging data by taking the first weight and the second weight as constraint conditions to obtain a formation porosity curve.

[0040] A third aspect of the embodiment of the application provides a computer device, comprising:

[0041] A processor;

[0042] A memory for storing processor-executable instructions.

[0043] The processor is configured to perform the method for calculating reservoir pore space according to the first aspect.

[0044] The fourth aspect of the embodiments of the present application provides a non-transitory computer readable storage medium, when instructions in the storage medium are executed by a processor, the method for calculating reservoir pore space according to the first aspect is performed.

[0045] The technical solutions provided by the embodiments of the present application can include the following beneficial effects:

[0046] The present application can automatically process FMI images by using image recognition technology, and combine with conventional logging data to extract specific spatial proportion data of different reservoir units in the reservoir, and calculate reservoir porosity by taking density porosity and compensated neutron porosity as constraint conditions, so as to calculate more reliable and more accurate pore space proportion of pore units, greatly improve the effective evaluation of FMI images on complex fracture systems and vugs, save a lot of manpower and time, make FMI imaging logging interpretation more efficient and accurate, and have development potential, and can realize more intelligent, efficient and accurate logging interpretation method by continuously combining with new technologies.

[0047] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings incorporated in the specification and forming a part thereof illustrate embodiments consistent with the present application and together with the description are used to explain the principles of the application.

[0049] Figure 1 It is a schematic diagram of FMI images reflecting resistivity in the embodiments of the present application;

[0050] Figure 2 It is a flowchart of the method for calculating reservoir pore space in the embodiments of the present application;

[0051] Figure 3 It is a flowchart of obtaining the pore space proportion of the current reservoir in the embodiments of the present application;

[0052] Figure 4 It is a schematic diagram of the pore space proportion after shale correction in the embodiments of the present application;

[0053] Figure 5 It is a flowchart of obtaining the pore space proportion of the current reservoir in the embodiments of the present application;

[0054] Figure 6A schematic diagram of FMI logging image in the embodiment of the present application before and after color removal for image processing;

[0055] Figure 7 A slice schematic diagram of FMI logging image in the embodiment of the present application;

[0056] Figure 8 A slice analysis result schematic diagram of FMI logging image in the embodiment of the present application;

[0057] Figure 9 A schematic diagram of density porosity, compensated neutron porosity and HSP porosity curves in the embodiment of the present application;

[0058] Figure 10 A block diagram of a device for calculating reservoir pore space in the embodiment of the present application;

[0059] Figure 11 A schematic diagram of a computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0060] The exemplary embodiments will be described in detail herein with reference to the attached drawings. When the description below refers to the drawings, the same numbers in different drawings refer to the same or similar elements unless otherwise described. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0061] As shown in Figure 1 , FMI (Formation MicroScanner Image) logging image looks like a core profile, and the depth of color represents the size of resistivity, the lower the resistivity, the darker the color, which is suitable for identifying fractures, analyzing thin layers, reservoir evaluation, etc., and has incomparable advantages over conventional logging methods, and plays an important role in the interpretation and evaluation of complex oil and gas reservoirs. However, the evaluation of complex fracture systems and solution pores by FMI logging is difficult to effectively evaluate due to the difficulty of human-computer interaction picking, and the evaluation technology of fracture system mainly includes identifying and determining the occurrence, length, density and other parameter information of various fractures, therefore, we provide a method for calculating reservoir pore space, as shown in Figure 2 , which comprises the following steps:

[0062] S201, obtaining FMI logging image, compensated neutron logging data and density logging data of a current reservoir.

[0063] FMI can be obtained by scanning through resistivity imaging logging instrument in Schlumberger MAXIS 500C imaging logging series. The resistivity imaging logging instrument is composed of four main plates and four negative plates, each plate has two rows of electrodes, each row has 12 electrodes, the distance between the upper and lower rows of electrodes is 0.3 inches, the lateral interval between the electrodes is 0.1 inch, and the vertical distance between the main plate and the auxiliary plate is 5.7 inches. The logging sampling interval is 0.1 inch, and the longitudinal resolution is 0.2 inch. There are a total of 192 measuring button electrodes. The current intensity of each electrode and the applied voltage are directly recorded, and then the instrument coefficient is converted to reflect the microresistivity of the formation around the well wall. The current measured by the FMI sensor has three components, the high-frequency component reflects the microresistivity, the low-frequency component detects the depth and shallow lateral, and the direct current component is filtered out. After data processing and image processing, these microresistivity curves are converted into images, that is, FMI images.

[0064] Neutron logging detects the hydrogen content of the reservoir, and when the formation matrix does not contain hydrogen, it reflects the total porosity of the reservoir.

[0065] Density logging records the Compton scattered gamma rays of the formation, and the detection range of the instrument is a hemisphere with the source distance as the diameter, and the information detected includes matrix pores and secondary pores, which is the response of the total porosity of the reservoir.

[0066] Compensated neutron porosity and density logging generally reflect the total porosity of the formation.

[0067] S202, based on the FMI logging image, obtaining the pore space proportion of the current reservoir.

[0068] Since FMI logging images use different shades of color to represent different resistivity levels, with darker colors indicating lower resistivity, the darker areas can be initially identified as spaces with higher porosity or clay-containing parts of the formation. After processing the FMI logging images, the colors of the uniformly segmented FMI logging images, after removing noise, are further processed using the K-means clustering algorithm. Existing software is used to represent the colors of the uniformly segmented FMI logging images as hex (hexadecimal) values. The hex codes are then used to calculate the K-means clustering algorithm, with the results represented as hex values, forming a sample set. Since hex values ​​represent color depth, and larger hex values ​​indicate lighter colors, data with large hex values ​​are removed to obtain a data set containing only dark-colored portions. This yields the proportion of dark-colored portions in the uniformly segmented FMI logging images with preset measurement intervals after removing noise. Because the formation clay has high water content and low resistivity, the clay portion in the FMI logging images is also dark. Therefore, clay correction is needed to eliminate the interference of clay on the pore space proportion, thus obtaining the pore space proportion of the current reservoir.

[0069] S203, based on compensated neutron logging data, obtains the first porosity of the current reservoir.

[0070] Compensated neutron porosity logging is a logging method that uses an isotopic neutron source and two thermal neutron detectors (far and near) mounted on a slide plate attached to the wellbore wall to measure the formation hydrogen content index by using the count rate ratio of the far and near detectors. The instrument is calibrated in a pure limestone calibration well saturated with fresh water, and the measured hydrogen content index is called compensated neutron porosity.

[0071] S204, based on density logging data, obtains the second porosity of the current reservoir.

[0072] Density logging is an effective logging method for classifying lithology and measuring formation porosity. Density logging data is obtained through active measurement, using rays generated by artificial radioactive materials to detect the bulk density of the formation (i.e., the total density of the rock, including the solid skeleton and fluids in the pores). For sandstone, limestone, and dolomite, whose pores are filled with water, the density logging reading is essentially equal to the true bulk density, and the density porosity can be calculated using the Wylie formula.

[0073] S205 uses the pore space ratio as the dependent variable and performs correlation analysis with compensated neutron logging data and density logging data to obtain the analysis results.

[0074] Using existing software to perform correlation analysis with pore space ratio as the dependent variable and compensated neutron logging data as the independent variable, the results showed a positive correlation between pore space ratio in formation pore units and compensated neutron logging data in the formation. Conversely, using existing software to perform correlation analysis with density logging data, the results showed a negative correlation between pore space ratio in formation pore units and formation density.

[0075] S206. Based on the analysis results, the first weight of the compensated neutron logging data and the second weight of the density logging data were determined.

[0076] Using the pore space ratio as the dependent variable and compensated neutron logging data as the independent variable, a correlation analysis was performed to obtain the first weight of the compensated neutron logging data based on the analysis results. Using the pore space ratio as the dependent variable and density logging data as the independent variable, a correlation analysis was performed to obtain the second weight of the density logging data based on the analysis results.

[0077] S207 uses the first and second weights as constraints to perform nonlinear regression calculations on the pore space ratio, compensated neutron logging data, and density logging data to obtain the formation porosity curve.

[0078] Based on the correlation analysis results, the first and second weights are used as constraints, and nonlinear regression calculations are performed on the pore space ratio of formation pores, density logging data, and compensated neutron logging data according to the well logging interpretation theory to obtain the formation porosity curve based on the pore space ratio of formation pores.

[0079] The method for calculating reservoir porosity provided by this invention utilizes image recognition technology to automatically process FMI logging images and extract the specific spatial proportion data of different reservoir units. It calculates reservoir porosity using density porosity and compensated neutron porosity as constraints, enabling quantitative calculation of reservoir porosity and greatly improving the effectiveness of FMI logging images in evaluating complex fracture systems and dissolution pores.

[0080] As an optional embodiment of the present invention, the pore space ratio of the current reservoir is obtained based on the FMI logging image, such as... Figure 3 As shown, it specifically includes:

[0081] S301, based on FMI logging images, obtain the initial pore space ratio.

[0082] Since FMI logging images use different shades of color to represent different resistivity levels, with darker colors indicating lower resistivity, the darker areas can be initially identified as spaces with higher porosity or clay-containing parts of the formation. After processing the FMI logging image, the color of the uniformly segmented FMI logging image after removing noise is further processed based on the K-means clustering algorithm. This process significantly separates the color of the FMI logging image from other colors, and the pore portion is also effectively segmented. When significant results are achieved, some existing software is used to further process the image with significantly segmented pores. The color of the image with significantly segmented pores is represented by hex values. The distance calculated by the K-means clustering algorithm is calculated using hex codes, and the distance parameter is represented by the hex values ​​calculated using hex codes, forming a sample set. Since hex values ​​can represent color depth, and the larger the hex value, the lighter the color, the data with large hex values ​​in the output data are removed to obtain a data set with only dark proportions. Thus, the dark proportion of the uniformly segmented FMI logging image after removing noise at preset measurement intervals is obtained, which is the initial pore space proportion (Dark Percent, or DP).

[0083] S302, acquire natural gamma logging data.

[0084] Natural gamma logging is a logging method that uses gamma rays to measure the physical properties of formation rocks. It uses a gamma detector to measure the natural gamma radiation within underground rocks and converts it into a corresponding count rate. The count rate helps geologists determine information such as the lithology, thickness, and density of the formation. The count rate refers to the number of gamma ray counts recorded by the measuring instrument within a certain time period; a higher count rate indicates a higher content of radioactive material in the measured formation.

[0085] S303, based on natural gamma logging data, the initial pore space ratio is corrected for clay content to obtain the pore space ratio.

[0086] The initial pore space ratio is corrected for clay content. Because the formation clay has a high water content and low resistivity, the clay part is dark in the FMI logging image. It is necessary to combine natural gamma logging data to correct the obtained data for clay content to eliminate the interference of clay on the pore space ratio.

[0087] The method for calculating clay content is as follows:

[0088]

[0089]

[0090] Where SH is the relative value of natural gamma; GR is the natural gamma value; GR min The natural gamma value of the sandstone layer; GR max V represents the natural gamma value of the mudstone layer; GCUR is the empirical stratigraphic coefficient, with 2 for the new strata and 3 for the old strata; V sh This refers to the mud content of the formation.

[0091] The method for correcting the clay content based on the pore space ratio is as follows:

[0092] HSP = DP - V sh ×DP

[0093] Where HSP is the pore space percentage; DP is the initial pore space percentage.

[0094] like Figure 4 As shown, the pore space percentage after clay correction can accurately characterize the pore space percentage (HSP) in the formation. In wells with depths ranging from 6200m to 6210m, pore space percentage curves with DP and HSP fluctuating in the range of -0.1 to 0.3 were obtained using FMI logging images. The trends of the two are consistent, but the values ​​are different. The HSP has a smaller pore space percentage value fluctuating in the range of -0.1 to 0.3, which is more in line with the actual changes. The two rightmost images are FMI logging images and FMI_DP logging images. FMI_DP (Formation MicroScanner Image_Dark Percent) is the logging image after removing light colors from FMI. The higher the DP and HSP curves, the larger the corresponding dark area of ​​the image.

[0095] Image recognition technology is a technique that uses digital image processing to transform input image information into meaningful numerical or textual information. It primarily relies on computer software and can quickly and accurately identify information contained in countless images. The principle of image recognition technology is based on the shape, size, color, and other features of objects, analyzing and identifying objects in an image based on these features. Specifically, image recognition technology mainly consists of three steps: image acquisition, feature extraction, and recognition. Image acquisition: First, the image data to be recognized is acquired and converted into a digital form that can be processed by a computer. Feature extraction: The acquired image data is analyzed according to different features to extract the main features of the image, such as shape, size, and color. Recognition: Based on the extracted features, the objects in the image are identified and recognized.

[0096] Image recognition technology can be used to automate data processing of FMI images and extract the specific spatial proportions of different reservoir units, which can greatly improve the efficiency and accuracy of FMI image interpretation. Therefore, image recognition technology has significant advantages in the interpretation of FMI imaging logging data, including high efficiency, automation, and data-driven approaches.

[0097] As an optional embodiment of the present invention, the initial pore space ratio is obtained based on the FMI logging image, such as... Figure 5 As shown, it specifically includes:

[0098] S501 performs image processing on the FMI logging image, determines the range of the target color, and removes the preset color.

[0099] For example, image processing is performed on the FMI logging image using some software in the prior art. The color selection tool's color range is set to 10. Since different shades of color in the FMI image represent different resistivity, the darker the color, the lower the resistivity. Thus, the darker parts can be initially identified as spaces with higher porosity or clay-containing parts in the formation. Therefore, the darker colors are the target colors. Similar dark colors are determined as a certain color range. The darker parts are retained, and the lighter colors are removed.

[0100] Reference Figure 6 As shown, Figure 6 The left side (a) is the original image, which specifically reflects the original appearance of the FMI logging image before image processing. The dark areas in the image represent low resistivity. The dark color is set as the target color. Based on the target color, the remaining light colors are removed, resulting in the right side image (b). Image (b) is the desaturated image, which removes the light colors and retains only the dark colors. Therefore, the dark areas in the obtained image (b) represent spaces with high porosity or clay-containing parts in the formation.

[0101] S502, the image-processed FMI logging image is segmented according to a preset size to obtain multiple segmented images.

[0102] Obtain pixelated data of the processed FMI logging image, such as Figure 7 As shown, the FMI logging image after image processing is segmented according to a preset size interval, with the preset size being 0.12 meters to 0.13 meters. Taking 0.125 meters as an example, a well section with a depth of 300 meters is segmented to obtain multiple segmented images. That is, 2400 slices need to be made so that the analyzed data corresponds to conventional logging data.

[0103] Reference Figure 7As shown in the image, the sliced ​​image is divided between 6208.5m and 6208.875m. The darker areas in the image represent spaces with higher porosity or clay-containing portions of the strata. Figure 7 Three segmented images were obtained. From top to bottom, the first segment is a slice image between 6208.5m and 6208.625m, the second segment is a slice image between 6208.625m and 6208.75m, and the third segment is a slice image between 6208.75m and 6208.875m. The dark area in the second segment is larger, indicating that there is a higher porosity space or a larger amount of clay in the strata between 6208.625m and 6208.75m.

[0104] S503, based on multiple segmented images, obtains the initial pore space ratio.

[0105] The pixelated data of multiple segmented images are effectively segmented using the K-means clustering algorithm to obtain the pore portion. Some existing software is used to analyze the data and obtain only the data set of dark percentage, thus obtaining the initial pore space percentage (Dark Percent, or DP) with a preset size as the measurement interval.

[0106] As an optional embodiment of the present invention, the initial pore space ratio is obtained based on multiple segmented images, specifically including:

[0107] Each segmented image is processed using the K-means clustering algorithm to obtain a sample set, which includes multiple sample data, represented by hex values. Sample data with hex values ​​greater than a preset value are removed to obtain the initial pore space ratio.

[0108] With the continuous development of computer technology, image segmentation is being applied in increasingly wider fields. Currently, image segmentation techniques mainly include threshold-based, edge-based, clustering-based, and neural network-based methods. Clustering is one of the most effective methods, including K-means clustering, fuzzy C-means clustering, density-peak clustering, and subtractive clustering. K-means clustering, with its clear semantics, simple structure, and fast computation speed, is the most commonly used clustering algorithm in image segmentation.

[0109] The K-means clustering algorithm divides the original dataset into k disjoint sample data groups. First, k initial cluster centers are randomly selected, and the Euclidean distance from each data group to the initial cluster centers is calculated. Based on the nearest neighbor principle, the data group with the smallest distance is assigned to the data group corresponding to its smallest cluster center. Second, after assignment, each new cluster center is recalculated. Finally, the new Euclidean distance between each cluster center and each data group is calculated, and this iteration is repeated until a predetermined threshold is reached. When segmenting images using the K-means clustering algorithm, clustering is performed based on the features of the image pixels. Let the resolution of an image be x*y, and the image be clustered into k data groups. Let P(x,y) be the input pixel, and C... k The calculation principle for cluster centers is as follows:

[0110] (1) Select k initial cluster centers appropriately;

[0111] (2) Calculate the Euclidean distance d between the image center and each pixel;

[0112] d=||P(x,y)-C k ||

[0113] (3) Assign all pixels to the nearest center according to the distance d;

[0114] (4) After all pixels are assigned, recalculate the new cluster centers;

[0115]

[0116] (5) Repeat the iterative calculation until the determined threshold is met, then stop the calculation;

[0117] (6) Return the image segmentation results.

[0118] The colors in each segmented FMI logging image are further processed using the K-means clustering algorithm. Specifically, some existing software is used to calculate the hex values ​​of the FMI logging images using the K-means clustering algorithm with hex codes. The calculated hex values ​​represent the sample set. In one optional embodiment, the output image width is set to 200, the color recognition type is set to RGB, the number of class centers (K) is set to 2, the maximum number of iterations is set to 50, the convergence count is set to 3, and the maximum number of calculations is set to 50 if the result does not converge. The calculation is terminated after the convergence count is met, and after repeating the calculation twice if it does not converge. The color proportion and the corresponding hex code are output to ensure the accuracy of the calculation results and the efficiency of batch calculation.

[0119] The hex value refers to a hexadecimal number, which is a base-16 system in mathematics. It is generally represented by the numbers 0 to 9 and the letters A to F (or a to f), where A to F represent 10 to 15. Since hex values ​​can represent color depth, and a larger hex value indicates a lighter color, data with large hex values ​​are removed from the output data to obtain a dataset containing only the dark color percentage. This yields dark color percentage data measured at preset intervals of 0.125 meters.

[0120] The K-means clustering algorithm works as follows: Input a set of digitized image samples. Randomly select K=2 cluster centers from the sample set, dividing the sample data into two classes. Then, cluster the remaining data in the set, calculating the distance from each data point to the selected cluster center. Each data point is then grouped into the cluster with its nearest cluster center, forming the clustering result. The cluster centers are calculated, and the mean of the data in each cluster is used as the new cluster center. This iterative clustering and mean calculation process is repeated until the clustering result no longer changes.

[0121] K-means clustering algorithm distance calculation methods include, but are not limited to, the following methods:

[0122] Euclidean distance formula:

[0123]

[0124] Manhattan distance formula:

[0125] d(x,y)=|x1-y1|+|x2-y2|+…+|x n -y n |

[0126] Cosine similarity formula:

[0127]

[0128] The time complexity of the K-means clustering algorithm is O(nmk), where n represents the number of samples, m represents the sample dimension, and k represents the number of classes.

[0129] In an optional embodiment, n is the number of uniformly cut segments of the FMI logging image; the calculated image is a planar graphic, i.e., a two-dimensional sample graphic, where m is 2; and k is the number of categories into which the image is divided.

[0130] Optionally, some existing software can be used to perform batch analysis of the slices based on the K-means clustering algorithm. The analysis parameters are set as follows, and the analysis results are as follows. Figure 8 As shown. See also Figure 8The analysis results after further processing the colors of the sliced ​​image are represented by the contrast of color depth. In the first row, "cluster" represents the cluster center, "pixels" represents the area percentage, "name" is the color description of the cluster center, "HEX" is the hexadecimal value, and "RGB" (Red, Green, Blue, additive color) is the additive color. The second row shows the light-colored portion, occupying 76.45% of the area, with color values ​​of 253, 252, 252, indicating a light color with ΔE = 0.4, HEX #FDFCFC, and RGB 253 252 252. The third row shows the dark-colored portion, occupying 23.55% of the area, with color values ​​of 66, 3, 3, indicating a dark color with ΔE = 2.3, HEX #45080C, and RGB 69 8 12. Here, ΔE represents the threshold of the closest cluster center, i.e., the K-means cluster distance, with a standard of less than or equal to 5.

[0131] The data is analyzed using existing software. The analyzed data is then preliminarily processed. Since the hex value can represent the depth of color, and the larger the hex value, the lighter the color, the data with large hex values ​​are removed from the output data. This yields a data set with only the dark percentage, thus obtaining the dark percentage of the measurement interval with a preset size of 0.125 meters, which is the initial pore space percentage (Dark Percent, or DP).

[0132] By using the K-means clustering algorithm to calculate the segmented FMI logging images, the hex values ​​of two different color categories and the area ratio of each color in the image can be obtained based on preset parameters.

[0133] Using a method that first removes unwanted colors and then performs K-means clustering analysis with slice thicknesses spaced at preset sizes can save a significant amount of computation time and improve the accuracy of the final calculation results.

[0134] As an optional embodiment of the present invention, the preset size is 0.12 meters to 0.13 meters.

[0135] As an optional embodiment of the present invention, obtaining the first porosity of the current reservoir based on compensated neutron logging data specifically includes:

[0136] The compensated neutron logging data was corrected for clay content to obtain the first corrected data; the first corrected data was then used to calculate the compensated neutron porosity to obtain the first porosity.

[0137] The formula for calculating the first porosity is as follows:

[0138] Φ N =(CN-LCOR-0.5×V) sh ×N sh )×0.01

[0139] Where, Φ N The first porosity; CN is the compensated neutron logging value of the target layer, as a percentage; LCOR is the neutron value of the rock skeleton, as a percentage; V sh n represents the clay content of the target layer. sh , where is the neutron value in mudstone, and is a percentage.

[0140] As an optional embodiment of the present invention, obtaining the second porosity of the current reservoir based on density logging data specifically includes:

[0141] Density logging data is corrected for clay content to obtain second corrected data; density porosity is calculated from the second corrected data to obtain second porosity.

[0142] The formula for calculating the second porosity is as follows:

[0143]

[0144] Where, Φ D The second porosity; ρ ma Density of the rock skeleton, in g / cm³ 3 ;ρ f Formation fluid density, in g / cm³ 3 ;ρ b The target layer density is expressed in g / cm³. 3 ;ρ sh Density of mudstone, in g / cm³ 3 V sh The target layer contains clay content.

[0145] As an optional embodiment of the present invention, the proportion of pore space is used as the dependent variable and correlation analysis is performed with compensated neutron logging data and density logging data. The analysis results show that the proportion of reservoir pore space is negatively correlated with formation density and positively correlated with formation compensated neutron value, which is consistent with the actual situation and logging interpretation theory.

[0146] Based on the analysis results, the first weight of the compensated neutron logging data and the second weight of the density logging data were determined, and the first and second weights were used as constraints.

[0147] As shown in Table 1, nonlinear regression calculations were performed on the pore space ratio, compensated neutron logging data, and density logging data to obtain the formation porosity curve.

[0148] Table 1. Nonlinear regression results of reservoir porosity and density logging data and compensated neutron logging data.

[0149]

[0150] In this model, the pore space ratio is used as the dependent variable, and the first porosity and the second porosity are used as independent variables. A nonlinear equation model is set up based on well logging interpretation theory and correlation analysis results:

[0151]

[0152] Where, Φ H Porosity is the proportion of pore space to porosity; Φ N The first porosity; Φ D denoted as the second porosity; a, b, and c are nonlinear regression parameters.

[0153] like Figure 9 As shown, a formation porosity curve based on the proportion of dark areas in the FMI logging image can be obtained through calculation. The leftmost side represents the logging depth, from top to bottom: 6200m, 6210m, 6220m, 6230m, 6240m, 6250m, 6260m, 6270m, 6280m, 6290m, and 6300m. POR_D is the density porosity curve, POR_C is the compensated neutron porosity curve, and POR_H is the HSP porosity curve. From left to right, the second column shows the density porosity curve between 0.0001 and 0.15, the third column shows the compensated neutron porosity curve between 0.0001 and 0.25, and the fourth column shows the HSP porosity curve between 0.0001 and 0.15. The POR_H curve is based on the POR_D density porosity curve. The nonlinear regression analysis using R_D and POR_C is more accurate than POR_D and POR_C, and the logging curves obtained are consistent with the logging interpretation principles and actual conditions.

[0154] This invention also discloses an apparatus for calculating reservoir pore space, such as... Figure 10 As shown, the device includes:

[0155] The well logging information acquisition module 1001 is used to acquire the FMI logging image, compensated neutron logging data and density logging data of the current reservoir.

[0156] The pore space ratio acquisition module 1002 is used to obtain the pore space ratio of the current reservoir based on FMI logging images.

[0157] The first porosity acquisition module 1003 is used to obtain the first porosity of the current reservoir based on compensated neutron logging data.

[0158] The second porosity acquisition module 1004 is used to obtain the second porosity of the current reservoir based on density logging data.

[0159] The correlation analysis module 1005 is used to perform correlation analysis between the pore space ratio as the dependent variable and the compensated neutron logging data and density logging data to obtain the analysis results.

[0160] The weight determination module 1006 is used to determine the first weight of the compensated neutron logging data and the second weight of the density logging data based on the analysis results.

[0161] The formation porosity curve calculation module 1007 is used to perform nonlinear regression calculations on the pore space ratio, compensated neutron logging data and density logging data, using the first weight and the second weight as constraints, to obtain the formation porosity curve.

[0162] The device for calculating reservoir porosity provided by this invention utilizes image recognition technology to automatically process FMI logging images and extract the specific spatial proportion data of different reservoir units in the reservoir. It calculates reservoir porosity using density porosity and compensated neutron porosity as constraints, enabling quantitative calculation of reservoir porosity and greatly improving the effectiveness of FMI logging images in evaluating complex fracture systems and dissolution pores.

[0163] This invention also provides a computer device, such as... Figure 11 As shown, the computer device may include a processor 1101 and a memory 1102, wherein the processor 1101 and the memory 1102 may be connected via a bus or other means. Figure 11 Taking the example of a connection between China and Israel via a bus.

[0164] Processor 1101 may be a central processing unit (CPU). Processor 1101 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.

[0165] The memory 1102, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for calculating reservoir porosity space in the embodiments of the present invention. The processor 1101 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory 1102, thereby implementing the method for calculating reservoir porosity space in the above-described method embodiments.

[0166] The memory 1102 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor 1101, etc. Furthermore, the memory 1102 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1102 may optionally include memory remotely located relative to the processor 1101, and these remote memories may be connected to the processor 1101 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0167] One or more modules are stored in memory 1102, and when executed by processor 1101, they perform actions such as... Figure 2 The method for calculating reservoir porosity space in the illustrated embodiment.

[0168] For specific details regarding the aforementioned computer equipment, please refer to the relevant documentation. Figure 2 The relevant descriptions and effects in the illustrated embodiments are for understanding purposes only and will not be repeated here.

[0169] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0170] It should be noted that the embodiments referred to in the specification, such as "one embodiment," "embodiment," "exemplary embodiment," and "some embodiments," may include specific features, structures, or characteristics, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments, whether explicitly described or not, is within the knowledge scope of those skilled in the art.

[0171] Generally speaking, terms should be understood at least in part by their use in context. For example, at least in part by context, the term "one or more" as used in the text can be used to describe any feature, structure, or characteristic of the singular meaning, or a combination of features, structures, or characteristics of the plural meaning. Similarly, at least in part by context, terms such as "a" or "the" can also be understood to convey either singular or plural usage.

[0172] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for calculating reservoir pore space, characterized in that, The method includes: Acquire FMI logging images, compensated neutron logging data, and density logging data for the current reservoir; Based on the FMI logging image, the porosity of the current reservoir is obtained; Based on the compensated neutron logging data, the first porosity of the current reservoir is obtained; Based on the density logging data, the second porosity of the current reservoir is obtained; The porosity ratio was used as the dependent variable to perform correlation analysis with the compensated neutron logging data and the density logging data to obtain the analysis results. Based on the analysis results, the first weight of the compensated neutron logging data and the second weight of the density logging data are determined. Using the first weight and the second weight as constraints, nonlinear regression calculations are performed on the pore space ratio, the compensated neutron logging data, and the density logging data to obtain the formation porosity curve.

2. The method for calculating reservoir pore space as described in claim 1, characterized in that, The step of obtaining the porosity of the current reservoir based on the FMI logging image includes: Based on the FMI logging images, the initial pore space ratio is obtained; Acquire natural gamma logging data; Based on the natural gamma logging data, the initial pore space ratio is corrected for clay content to obtain the pore space ratio.

3. The method for calculating reservoir pore space as described in claim 2, characterized in that, The step of obtaining the initial pore space ratio based on the FMI logging image includes: The FMI logging image is processed to determine the range of the target color and remove preset colors; The FMI logging image after image processing is segmented according to a preset size to obtain multiple segmented images; The initial pore space ratio is obtained based on multiple segmented images.

4. The method for calculating reservoir pore space as described in claim 3, characterized in that, The step of obtaining the initial pore space ratio based on multiple segmented images includes: Each segmented image is processed using the K-means clustering algorithm to obtain a sample set, which includes multiple sample data, and the sample data is represented by hex values. Remove sample data with hex values ​​greater than a preset value to obtain the initial pore space ratio.

5. The method for calculating reservoir pore space as described in claim 3, characterized in that, The preset size is 0.12 meters to 0.13 meters.

6. The method for calculating reservoir porosity space as described in any one of claims 1 to 5, characterized in that, The step of obtaining the first porosity of the current reservoir based on the compensated neutron logging data includes: The compensated neutron logging data is corrected for clay content to obtain the first corrected data; The first porosity is obtained by calculating the compensated neutron porosity based on the first corrected data.

7. The method for calculating reservoir porosity space as described in any one of claims 1 to 5, characterized in that, The process of obtaining the second porosity of the current reservoir based on the density logging data includes: The density logging data is corrected for clay content to obtain second corrected data; The second porosity is obtained by calculating the density and porosity of the second corrected data.

8. An apparatus for calculating reservoir pore space, characterized in that, include: The well logging information acquisition module is used to acquire the FMI logging images, compensated neutron logging data and density logging data of the current reservoir; The pore space ratio acquisition module is used to obtain the pore space ratio of the current reservoir based on the FMI logging image; The first porosity acquisition module is used to obtain the first porosity of the current reservoir based on the compensated neutron logging data. The second porosity acquisition module is used to obtain the second porosity of the current reservoir based on the density logging data. The correlation analysis module is used to perform correlation analysis between the pore space ratio as the dependent variable and the compensated neutron logging data and the density logging data to obtain the analysis results. The weight determination module is used to determine the first weight of the compensated neutron logging data and the second weight of the density logging data based on the analysis results. The formation porosity curve calculation module is used to perform nonlinear regression calculations on the pore space ratio, the compensated neutron logging data, and the density logging data, using the first weight and the second weight as constraints, to obtain the formation porosity curve.

9. A computer device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to perform the method for calculating reservoir porosity space as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by a processor, they cause the processor to perform the method for calculating reservoir porosity space as described in any one of claims 1 to 7.

Images