A method and device for determining porosity using well logging interpretation and image recognition

Abstract

The present invention provides a method and device for determining porosity by using logging interpretation and image recognition, which relates to the technical field of petroleum exploration and development, including: obtaining structural parameters of shale samples by using logging interpretation and image recognition respectively; the structural parameters include TOC content, mineral content and porosity data; determining a first linear relationship based on the first type of structural parameters obtained by logging interpretation, and determining a second linear relationship based on the second type of structural parameters obtained by image recognition; the first linear relationship and the second linear relationship respectively characterize the mapping relationship between the porosity data and TOC content and mineral content at the macro level and the micro level; combining the first linear relationship and the second linear relationship by using Bayesian theorem to obtain the target linear relationship corresponding to the porosity data. By obtaining logging data and scanning electron microscope images, the pore characteristics of shale are comprehensively analyzed from both macro and micro levels, thereby improving the accuracy and comprehensiveness of porosity calculation.

Description

Technical Field

[0001] The present invention relates to the technical field of petroleum exploration and development, and in particular to a method and device for determining porosity by utilizing well logging interpretation and image recognition. Background Art

[0002] The calculation of shale porosity is of great significance in oil exploration and development, because the reservoir evaluation and development design of shale oil and gas reservoirs rely heavily on accurate porosity measurement. Shale porosity is usually obtained by laboratory methods, and its main methods include: helium determination method, which uses the strong permeability of helium to measure the volume of rock skeleton to calculate porosity; mercury injection method, which presses mercury into pores under high pressure to obtain pore size distribution and total porosity; gas adsorption method, such as nitrogen adsorption (BET method) and carbon dioxide adsorption, to determine the specific surface area and pore size distribution of micropores and mesopores; nuclear magnetic resonance (NMR) determination method, based on the nuclear magnetic resonance signal of hydrogen atoms, provides porosity and pore size distribution information; scanning electron microscopy (SEM), directly observes the morphology, size and distribution of pores; small angle neutron scattering (SANS) and small angle X-ray Scattering (SAXS), analyzes nanoscale pore structure; X-ray computed tomography (CT), obtains the three-dimensional structure of the rock, calculates porosity and connectivity; liquid saturation method, calculates pore volume by measuring the mass change before and after rock saturation; density method, measures dry density and particle density, and uses formula to calculate porosity; digital image analysis method, microscopic imaging and image processing of rock slices; ultrasonic measurement method, indirect calculation using the relationship between ultrasonic propagation velocity and porosity; low-temperature liquid nitrogen adsorption-desorption method, measures nitrogen adsorption-desorption isotherms; saturated brine method, calculates porosity by the mass difference before and after rock saturated with brine. However, due to the complex pore structure of shale and the complex mineral composition of the internal reservoir, current measurement methods are usually difficult to accurately estimate. Summary of the invention

[0003] The purpose of the present invention is to solve the problem that the current shale pore structure is complex and the internal reservoir mineral composition is complicated, which makes it difficult to accurately estimate its porosity. The present invention provides a method and device for determining porosity by using logging interpretation and image recognition.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] A first aspect of an embodiment of the present application provides a method for determining porosity by using well logging interpretation and image recognition, comprising:

[0006] The structural parameters of the shale samples are obtained by using logging interpretation and image recognition respectively; the structural parameters include TOC content, mineral content and porosity data;

[0007] A first linear relationship is determined based on a first type of structural parameter obtained by logging interpretation, and a second linear relationship is determined based on a second type of structural parameter obtained by image recognition; the first linear relationship and the second linear relationship respectively characterize the mapping relationship between the porosity data and the TOC content and the mineral content at the macro level and the micro level;

[0008] The first linear relationship and the second linear relationship are combined using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data.

[0009] Optionally, the obtaining of structural parameters of shale samples by respectively using well logging interpretation and image recognition includes:

[0010] The TOC content of the shale sample core is obtained by using the core experimental test method and the ΔLogR method.

[0011] Optionally, the obtaining of structural parameters of shale samples by respectively using well logging interpretation and image recognition includes:

[0012] The mineral content of the shale sample is obtained by X-ray diffraction (XRD) testing and BP neural network calculation.

[0013] Optionally, the obtaining of structural parameters of shale samples by respectively using well logging interpretation and image recognition includes:

[0014] The porosity data of shale samples are obtained by using the gravity method, and the porosity data of shale samples are obtained by combining density logging and neutron logging data.

[0015] Optionally, the determining of the first linear relationship based on the first type of structural parameters obtained by logging interpretation, and the determining of the second linear relationship based on the second type of structural parameters obtained by image recognition, comprises:

[0016] The first type of structural parameters obtained by logging interpretation are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain multiple shale lithofacies categories;

[0017] Based on the first type of structural data corresponding to each of the shale lithofacies categories, a first linear relationship under each of the shale lithofacies categories is determined.

[0018] Optionally, the determining of the first linear relationship based on the first type of structural parameters obtained by logging interpretation, and the determining of the second linear relationship based on the second type of structural parameters obtained by image recognition, comprises:

[0019] The second type of structural parameters obtained by image recognition are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain a plurality of shale lithofacies categories;

[0020] Based on the second type of structural data corresponding to each of the shale lithofacies categories, a second linear relationship under each of the shale lithofacies categories is determined.

[0021] Optionally, the combining the first linear relationship and the second linear relationship by using Bayes' theorem to obtain a target linear relationship corresponding to the porosity data includes:

[0022] Determine a priori probability distribution at the macro level and the micro level based on the structural parameters;

[0023] Using the first linear relationship and the second linear relationship to construct a macro likelihood function and a micro likelihood function respectively, and combining the macro likelihood function and the micro likelihood function to obtain a joint likelihood function;

[0024] The prior probability distribution and the joint likelihood function are combined using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data.

[0025] The second aspect of the embodiment of the present application provides a device for determining porosity by using well logging interpretation and image recognition, comprising: an acquisition module, a determination module and a combination module; wherein:

[0026] The acquisition module is configured to acquire structural parameters of shale samples by using logging interpretation and image recognition respectively; the structural parameters include TOC content, mineral content and porosity data;

[0027] The determination module is configured to determine a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and to determine a second linear relationship based on a second type of structural parameter obtained by image recognition; the first linear relationship and the second linear relationship respectively characterize a mapping relationship between the porosity data at a macro level and a micro level and the TOC content and the mineral content;

[0028] The combining module is configured to combine the first linear relationship and the second linear relationship using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data.

[0029] A third aspect of an embodiment of the present application provides an electronic device, comprising a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the method for determining porosity by using well logging interpretation and image recognition as described in the first aspect.

[0030] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0031] Compared with the prior art, the technical solution provided by this application has the following beneficial effects:

[0032] The present invention provides a method and device for determining porosity by using logging interpretation and image recognition, by respectively using logging interpretation and image recognition to obtain structural parameters of shale samples, determining a first linear relationship based on the first type of structural parameters obtained by logging interpretation, and determining a second linear relationship based on the second type of structural parameters obtained by image recognition, and combining the first linear relationship and the second linear relationship using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data. By obtaining logging data and scanning electron microscope images, the pore characteristics of shale are comprehensively analyzed from both macroscopic and microscopic levels, and information from different data sources is effectively combined, thereby reducing errors that may be caused by a single data source and improving the accuracy and comprehensiveness of porosity calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic flow chart of a method for determining porosity by using well logging interpretation and image recognition provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of the effect of the ΔLogR method provided in this embodiment on predicting TOC content;

[0035] Figure 3 A schematic diagram of using an artificial neural network to predict mineral content provided in this embodiment;

[0036] Figure 4 A schematic diagram of identifying pores using a scanning electron microscope provided in this embodiment;

[0037] Figure 5 A schematic diagram of shale lithofacies division provided for this embodiment;

[0038] Figure 6 A schematic diagram of the structure of a device for determining porosity by using well logging interpretation and image recognition provided in an embodiment of the present application;

[0039] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] Below, embodiments of the present application will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present application. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present application. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present application.

[0041] The terms used herein are only for describing specific embodiments and are not intended to limit the present application. The terms "include", "comprising", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0042] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0043] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some blocks or combinations thereof in the block diagrams and / or flow charts may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that these instructions, when executed by the processor, may create a device for implementing the functions / operations described in these block diagrams and / or flow charts.

[0044] In some embodiments, see Figure 1 , Figure 1 A flow chart of a method for determining porosity by using well logging interpretation and image recognition provided in an embodiment of the present application; The method for determining porosity by using well logging interpretation and image recognition provided in an embodiment of the present application includes:

[0045] S110, using logging interpretation and image recognition to obtain structural parameters of shale samples; the structural parameters include TOC content, mineral content and porosity data.

[0046] Well logging, also known as geophysical logging, is a method of measuring geophysical parameters by using the geophysical properties of rock formations, such as electrochemical properties, electrical conductivity, acoustic properties, and radioactivity. Well logging interpretation is to analyze and interpret the data obtained from these measurements to understand the underground geological conditions, such as lithology, reservoir characteristics, and fluid properties. It should be noted that the image source for image recognition can be a scanning electron microscope (SEM) or other equipment with shooting function.

[0047] In some embodiments, S110, obtaining structural parameters of shale samples by using well logging interpretation and image recognition respectively includes:

[0048] The TOC content of shale sample cores was obtained using the core experimental test method and the ΔLogR method.

[0049] In this example, the total organic carbon (TOC) content of the shale sample is obtained by well logging interpretation. Figure 2, Figure 2 A schematic diagram of the effect of the ΔLogR method provided in this embodiment on predicting TOC content; a portion of the TOC content can be measured using the core test method, that is, obtained through organic geochemical analysis. The TOC content data obtained from the core test is highly accurate, but its representative range is small, the coring and experimental process is time-consuming and costly, and it is difficult to accurately and effectively evaluate the TOC content in a large area. Therefore, in order to obtain sufficient data, the ΔLogR method can also be used. The ΔLogR method uses the difference between the measurement curve and the baseline curve to calculate the total organic carbon. TOC is calculated using the acoustic time difference (AC) and deep lateral resistivity (LLD) curves. It should be noted that the shale samples can be multiple samples randomly sampled from the shale to be tested.

[0050] In an optional embodiment, the total organic carbon (TOC) content of the shale sample is obtained by image recognition. Based on computer vision (CV), the identification of TOC content from the scanning electron microscope (SEM) photos of shale can be to automatically identify the organic matter area through image segmentation and classification algorithms. First, the SEM image is preprocessed, such as noise reduction and contrast enhancement, and then the convolutional neural network (CNN) model is used to extract features and classify the image to distinguish organic matter from minerals. By calculating the pixel ratio of the organic matter area and combining the TOC content model of the known sample, the TOC percentage in the image is inferred.

[0051] In some embodiments, S110, obtaining structural parameters of shale samples by using well logging interpretation and image recognition respectively includes:

[0052] The mineral content of shale samples was obtained by X-ray diffraction (XRD) testing and BP neural network calculation.

[0053] In this embodiment, the mineral content of the shale sample is obtained by logging interpretation. Part of the mineral content can be obtained by X-ray diffraction (XRD) testing. The structure of the mineral crystal will cause the X-rays to diffract at a specific angle. The diffraction angle and intensity are recorded by the detector to obtain a diffraction spectrum. Each mineral has a unique diffraction peak position and intensity characteristics, and this information can be used to identify the type of mineral in the sample. This method can accurately identify the mineral composition in complex samples and provide reliable data support for geological research. Similarly, this method represents a small range, the experimental process is time-consuming and costly, and it is difficult to accurately and effectively evaluate the mineral content in a large area.

[0054] In an example, see Figure 3 , Figure 3A schematic diagram of using artificial neural network to predict mineral content provided in this embodiment; in order to obtain sufficient data, the mineral content can also be calculated by BP neural network. The GR, LOGLLD, AC, NPHI, RHOB curve data in the basic logging data and the mineral content data measured by XRD method are used as training data. After the model is trained, the GR, LOGLLD, AC, NPHI, RHOB curve data of the well without measured mineral content data are used as input, and the clay mineral content, felsic mineral content, and carbonate mineral content are used as output, thereby obtaining the final result.

[0055] In an optional embodiment, image recognition is used to obtain the mineral content of shale samples. Mineral types can be divided into carbonate minerals, quartz minerals, and clay minerals. Based on the fractal method, the identification of mineral content from the scanning electron microscope (SEM) photos of shale utilizes the fractal characteristics of mineral particles at different scales. First, the edges and morphologies of mineral particles are extracted through image processing, and their fractal dimensions at different scales are calculated. Since the fractal dimensions of different minerals have characteristic differences, the morphological complexity and distribution law of mineral particles can be analyzed by fractal dimensions. Then, based on the fractal characteristics and combined with the known mineral model, the content of the three minerals in the image can be estimated.

[0056] In some embodiments, S110, obtaining structural parameters of shale samples by using well logging interpretation and image recognition respectively includes:

[0057] The porosity data of shale samples are obtained by using the gravity method, and the porosity data of shale samples are obtained by combining density logging and neutron logging data.

[0058] In this embodiment, the porosity data of the shale sample is obtained by logging interpretation. The porosity data can be measured by gravity method. The core sample is dried to constant weight and the dry mass is weighed. Then, the sample is immersed in a liquid so that its pores are filled with liquid, and the wet mass after saturation is weighed. Next, the volume of the sample is measured by the drainage method, that is, the sample is completely immersed in the liquid and the volume of the discharged liquid is recorded. The pore volume is calculated by the dry mass, wet mass and volume, and the porosity is finally obtained. Similarly, this method represents a small range, the experimental process is time-consuming and costly, and it is difficult to accurately and effectively evaluate the porosity of a large area. Therefore, in order to obtain sufficient data, density logging and neutron logging data can also be combined to form a cross plot. The cross plot of density and neutron logging can help distinguish the effects of gas, water and oil, and the measured total porosity value is more accurate.

[0059] In an optional embodiment, image recognition is used to obtain porosity data of shale samples. Figure 4 , Figure 4 A schematic diagram of using a scanning electron microscope to identify pores is provided for this embodiment; specifically, based on computer vision (CV), the identification of total porosity from a scanning electron microscope (SEM) photograph of shale utilizes image segmentation and analysis to identify and quantify the pore area. First, the SEM image is preprocessed, such as denoising and contrast enhancement, to more clearly display the pores. Next, a convolutional neural network (CNN) is used to classify the pores and solid parts in the image. Finally, the total porosity in the image is quantified by calculating the proportion of the pore area to the total image.

[0060] S120, determining a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and determining a second linear relationship based on a second type of structural parameter obtained by image recognition; the first linear relationship and the second linear relationship respectively characterize the mapping relationship between porosity data and TOC content and mineral content at the macro level and micro level.

[0061] In this embodiment, the TOC, mineral content and porosity data obtained by well logging interpretation and image recognition are classified, and the data from different sources are divided into two categories: the data obtained from well logging interpretation is at the macro level, and the data obtained from image recognition is at the micro level.

[0062] The formula for porosity in relation to TOC and mineral content is:

[0063] ;

[0064] in, is the porosity, Clay mineral content, The content of felsic minerals, is the carbonate mineral content, a, b, c, d are constants.

[0065] Understandably, there are differences in the numerical values ​​of constants at the macro and micro levels.

[0066] In some embodiments, S120, determining a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and determining a second linear relationship based on a second type of structural parameter obtained by image recognition, includes:

[0067] The first type of structural parameters obtained by logging interpretation are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain multiple shale lithofacies categories;

[0068] Based on the first type of structural data corresponding to each shale lithofacies category, a first linear relationship under each shale lithofacies category is determined.

[0069] In an alternative embodiment, refer to Figure 5 , Figure 5 which is a schematic diagram of shale lithofacies division provided in this embodiment; for the first type of structural parameters obtained from well logging interpretation, according to the level of organic carbon content, shale can be divided into three categories: high TOC shale, medium TOC shale, and low TOC shale; according to the data of the contents of three minerals, shale can be divided into four categories: felsic shale, clay shale, calcareous shale, and mixed sedimentary shale. In summary, this method can divide shale into a total of 12 types: low TOC felsic shale, medium TOC felsic shale, high TOC felsic shale, low TOC clay shale, medium TOC clay shale, high TOC clay shale, low TOC calcareous shale, medium TOC calcareous shale, high TOC calcareous shale, low TOC mixed sedimentary shale, medium TOC mixed sedimentary shale, and high TOC mixed sedimentary shale.

[0070] Specifically, the classification basis with TOC content as the judgment standard is: if TOC > 3, it is high TOC shale; if 2 < TOC < 3, it is medium TOC shale; if TOC < 2, it is low TOC shale. Specifically, the classification basis with mineral content as the judgment standard is: if the felsic mineral content exceeds 50%, it is felsic shale; if the carbonate mineral content exceeds 50%, it is calcareous shale; if the clay mineral content exceeds 50%, it is clay shale; if the contents of all three minerals are less than 50%, it is mixed sedimentary shale. Low TOC felsic shale refers to shale with a TOC content less than 2 and a felsic mineral content exceeding 50%; medium TOC felsic shale refers to shale with a TOC content between 2 and 3 and a felsic mineral content exceeding 50%; high TOC felsic shale refers to shale with a TOC content greater than 3 and a felsic mineral content exceeding 50%.

[0071] Low TOC clay shale refers to shale with a TOC content less than 2 and a clay mineral content exceeding 50%; medium TOC clay shale refers to shale with a TOC content between 2 and 3 and a clay mineral content exceeding 50%; high TOC clay shale refers to shale with a TOC content greater than 3 and a clay mineral content exceeding 50%.

[0072] Low TOC calcareous shale refers to shale with a TOC content less than 2 and a carbonate mineral content exceeding 50%; medium TOC calcareous shale refers to shale with a TOC content between 2 and 3 and a carbonate mineral content exceeding 50%; high TOC calcareous shale refers to shale with a TOC content greater than 3 and a carbonate mineral content exceeding 50%.

[0073] Low-TOC mixed shale refers to shale with a TOC content of less than 2, and the contents of felsic, clay, and carbonate minerals are all less than 50%; medium-TOC mixed shale refers to shale with a TOC content between 2 and 3, and the contents of these three minerals are all less than 50%; high-TOC mixed shale refers to shale with a TOC content greater than 3, and the contents of these three minerals are all less than 50%.

[0074] In some embodiments, S120, determining a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and determining a second linear relationship based on a second type of structural parameter obtained by image recognition, includes:

[0075] The second type of structural parameters obtained by image recognition are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain a plurality of shale lithofacies categories;

[0076] Based on the second type of structural data corresponding to each shale lithofacies category, a second linear relationship under each shale lithofacies category is determined.

[0077] Similar to the previous embodiment, here, for the second type of structural parameters obtained by image recognition, shale can be divided into three categories according to the organic carbon content: high TOC shale, medium TOC shale and low TOC shale; according to the three mineral content data, shale can be divided into four categories: felsic shale, clay shale, calcareous shale, and mixed shale. In total, shale can be divided into 12 types.

[0078] S130, combining the first linear relationship and the second linear relationship using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data.

[0079] Bayes' theorem describes the probability of an event occurring under certain known conditions (i.e., conditional probability). Here, the first linear relationship and the second linear relationship are combined through Bayes' theorem to ensure the applicability of the target linear relationship.

[0080] In some embodiments, S130, combining the first linear relationship and the second linear relationship using the Bayesian theorem to obtain a target linear relationship corresponding to the porosity data includes:

[0081] Determine the prior probability distribution at the macro and micro levels based on the structural parameters;

[0082] The macro likelihood function and the micro likelihood function are constructed respectively by using the first linear relationship and the second linear relationship, and the macro likelihood function and the micro likelihood function are combined to obtain a joint likelihood function;

[0083] The Bayesian theorem is used to combine the prior probability distribution and the joint likelihood function to obtain the target linear relationship corresponding to the porosity data.

[0084] In this example, the consistency and integrity of the macro data obtained from logging interpretation and the micro data obtained from SEM image recognition must be ensured. The macro data contains information such as total organic carbon (TOC) content, mineral content, and porosity, while the micro data also covers the corresponding TOC, mineral content, and porosity. In order to effectively integrate these data, it is necessary to ensure that the units, formats, and measurement conditions of all data are the same to ensure reliability in subsequent analysis.

[0085] Next, based on existing geological knowledge and historical research data, set prior probability distributions for macro and micro data. This prior distribution reflects your expectations and uncertainties about the characteristics of the data. For example, a normal distribution can be used to represent the range of variation of TOC and mineral content, and the prior probability can be used to reflect the distribution characteristics of TOC and mineral components that may appear under different geological conditions. This step lays the foundation for subsequent Bayesian inference, allowing the model to learn effectively based on existing knowledge. Further, construct a likelihood function, which can be regarded as a quantification of the relationship between macro and micro data. For macro data, we first establish a function that describes the relationship between porosity and these factors based on TOC and mineral content. This function will reflect how TOC and mineral content affect the change in porosity, taking into account the degree of influence of different minerals on porosity. In addition, it is necessary to take into account the possible errors and uncertainties in the data, which will be represented by the error term. Similarly, for micro data, a similar function needs to be constructed to describe the influence of TOC and mineral content on porosity at the micro scale. These two functions will come from macro and micro data respectively, but their purpose is to reveal the same geological phenomenon through data of different scales. After completing the construction of the likelihood function, the likelihood functions of the macro and micro data are combined to form a comprehensive joint likelihood function. Through this joint function, the two sets of data can be effectively integrated to reflect their joint role in porosity calculation, thus providing a basis for subsequent Bayesian inference. The Bayesian theorem is applied to combine the prior probability with the joint likelihood function to calculate the posterior probability distribution. This posterior distribution will combine the existing macro and micro data to obtain a more accurate estimate of the relationship between TOC, mineral content and porosity. Through this process, a comprehensive model containing macro and micro information can be obtained, which helps to reveal how TOC and mineral content affect porosity under different geological conditions.

[0086] The embodiment of the present invention obtains the structural parameters of the shale sample by using logging interpretation and image recognition respectively, determines the first linear relationship based on the first type of structural parameters obtained by logging interpretation, and determines the second linear relationship based on the second type of structural parameters obtained by image recognition, and combines the first linear relationship and the second linear relationship using Bayesian theorem to obtain the target linear relationship corresponding to the porosity data. By obtaining logging data and scanning electron microscope images, the pore characteristics of shale are comprehensively analyzed from both macroscopic and microscopic levels, and the information of different data sources is effectively combined, which reduces the errors that may be caused by a single data source and improves the accuracy and comprehensiveness of porosity calculation.

[0087] In some embodiments, see Figure 6 , Figure 6 A schematic diagram of a structure of a device for determining porosity by using well logging interpretation and image recognition provided in an embodiment of the present application; an embodiment of the present application provides a device 700 for determining porosity by using well logging interpretation and image recognition, including: an acquisition module 710, a determination module 720 and a combination module 730; wherein,

[0088] An acquisition module 710 is configured to acquire structural parameters of shale samples using logging interpretation and image recognition respectively; the structural parameters include TOC content, mineral content and porosity data;

[0089] The determination module 720 is configured to determine a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and to determine a second linear relationship based on a second type of structural parameter obtained by image recognition; the first linear relationship and the second linear relationship respectively represent a mapping relationship between porosity data and TOC content and mineral content at a macro level and a micro level;

[0090] The combining module 730 is configured to combine the first linear relationship and the second linear relationship using the Bayesian theorem to obtain a target linear relationship corresponding to the porosity data.

[0091] In some embodiments, the acquisition module 710 is specifically configured as follows:

[0092] The TOC content of shale sample cores was obtained using the core experimental test method and the ΔLogR method.

[0093] In some embodiments, the acquisition module 710 is specifically configured as follows:

[0094] The mineral content of the shale sample is obtained by X-ray diffraction (XRD) testing and BP neural network calculation.

[0095] In some embodiments, the acquisition module 710 is specifically configured as follows:

[0096] The porosity data of shale samples are obtained by using the gravity method, and the porosity data of shale samples are obtained by combining density logging and neutron logging data.

[0097] In some embodiments, the determination module 720 is specifically configured to:

[0098] The first type of structural parameters obtained by logging interpretation are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain multiple shale lithofacies categories;

[0099] Based on the first type of structural data corresponding to each shale lithofacies category, a first linear relationship under each shale lithofacies category is determined.

[0100] In some embodiments, the determination module 720 is specifically configured to:

[0101] The second type of structural parameters obtained by image recognition are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain a plurality of shale lithofacies categories;

[0102] Based on the second type of structural data corresponding to each shale lithofacies category, a second linear relationship under each shale lithofacies category is determined.

[0103] In some embodiments, the combining module 730 is specifically configured as follows:

[0104] Determine the prior probability distribution at the macro and micro levels based on the structural parameters;

[0105] The macro likelihood function and the micro likelihood function are constructed respectively by using the first linear relationship and the second linear relationship, and the macro likelihood function and the micro likelihood function are combined to obtain a joint likelihood function;

[0106] The Bayesian theorem is used to combine the prior probability distribution and the joint likelihood function to obtain the target linear relationship corresponding to the porosity data.

[0107] The device for determining porosity by using well logging interpretation and image recognition provided in the embodiment of the present application can realize each process in the embodiment corresponding to the method for determining porosity by using well logging interpretation and image recognition described above, and will not be described again here to avoid repetition.

[0108] It should be noted that the device for determining porosity using well logging interpretation and image recognition provided in the embodiment of the present application and the method for determining porosity using well logging interpretation and image recognition provided in the embodiment of the present application are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned method for determining porosity using well logging interpretation and image recognition, and the repeated parts will not be repeated.

[0109] In some embodiments, see Figure 7 , Figure 7A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. An electronic device 800 provided in an embodiment of the present application includes a processor 810 and a memory 820; the memory 820 stores a computer program, wherein the computer program implements the above-mentioned method for determining porosity by using well logging interpretation and image recognition when executed by the processor.

[0110] Specifically, the processor 810 may include, for example, a general-purpose microprocessor, an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 810 may also include an onboard memory for cache purposes. The processor 810 may be a single processing unit or multiple processing units for executing different actions of the method flow according to an embodiment of the present application.

[0111] The memory 820 may be any medium capable of containing, storing, conveying, propagating or transmitting instructions. For example, the memory 820 may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device, component or propagation medium. Specific examples of the memory 820 include: a magnetic storage device, such as a magnetic tape or a hard disk (HDD); an optical storage device, such as a compact disk (CD-ROM); a random access memory (RAM) or flash memory; and / or a wired / wireless communication link.

[0112] The present application also provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method for determining porosity by using logging interpretation and image recognition is implemented. The computer-readable medium may be included in the device / apparatus / system described in the above embodiment; or it may exist independently without being assembled into the device / apparatus / system. The above computer-readable medium carries one or more programs. When the above one or more programs are executed, the method according to the embodiment of the present application is implemented.

[0113] According to an embodiment of the present application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, optical cable, radio frequency signal, etc., or any suitable combination of the above.

[0114] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims of the present application may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present application. In particular, without departing from the spirit and teachings of the present application, the features described in the various embodiments and / or claims of the present application may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present application. Therefore, the scope of the present application should not be limited to the above-described embodiments, but should be determined not only by the appended claims, but also by the equivalents of the appended claims.

Claims

1. A method for determining porosity using well logging interpretation and image recognition, characterized in that: include: The structural parameters of the shale samples are obtained by using logging interpretation and image recognition respectively; the structural parameters include TOC content, mineral content and porosity data; A first linear relationship is determined based on a first type of structural parameter obtained by logging interpretation, and a second linear relationship is determined based on a second type of structural parameter obtained by image recognition; the first linear relationship and the second linear relationship respectively characterize the mapping relationship between the porosity data and the TOC content and the mineral content at the macro level and the micro level; Combining the first linear relationship and the second linear relationship using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data includes: Determine a priori probability distribution at the macro level and the micro level based on the structural parameters; Using the first linear relationship and the second linear relationship to construct a macro likelihood function and a micro likelihood function respectively, and combining the macro likelihood function and the micro likelihood function to obtain a joint likelihood function; The prior probability distribution and the joint likelihood function are combined using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data.

2. The method for determining porosity by using well logging interpretation and image recognition according to claim 1, characterized in that: The method of obtaining the structural parameters of the shale sample by respectively using well logging interpretation and image recognition includes: The TOC content of the shale sample core is obtained by using the core experimental test method and the ΔLogR method.

3. The method for determining porosity by using well logging interpretation and image recognition according to claim 1, characterized in that: The method of obtaining the structural parameters of the shale sample by respectively using well logging interpretation and image recognition includes: The mineral content of the shale sample is obtained by X-ray diffraction (XRD) testing and BP neural network calculation.

4. The method for determining porosity by using well logging interpretation and image recognition according to claim 1, characterized in that: The method of obtaining the structural parameters of the shale sample by respectively using well logging interpretation and image recognition includes: The porosity data of shale samples are obtained by using the gravity method, and the porosity data of shale samples are obtained by combining density logging and neutron logging data.

5. The method for determining porosity by using well logging interpretation and image recognition according to claim 1, characterized in that: The method of determining a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and determining a second linear relationship based on a second type of structural parameter obtained by image recognition, comprises: The first type of structural parameters obtained by logging interpretation are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain multiple shale lithofacies categories; Based on the first type of structural parameters corresponding to each of the shale lithofacies categories, a first linear relationship under each of the shale lithofacies categories is determined.

6. The method for determining porosity by using well logging interpretation and image recognition according to claim 1, characterized in that: The method of determining a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and determining a second linear relationship based on a second type of structural parameter obtained by image recognition, comprises: The second type of structural parameters obtained by image recognition are divided using at least one set of TOC content thresholds and at least one set of mineral content thresholds to obtain a plurality of shale lithofacies categories; Based on the second type of structural parameters corresponding to each of the shale lithofacies categories, a second linear relationship under each of the shale lithofacies categories is determined.

7. A device for determining porosity using well logging interpretation and image recognition, characterized in that: include: Acquisition module, determination module and combination module; wherein, The acquisition module is configured to acquire structural parameters of shale samples by using logging interpretation and image recognition respectively; the structural parameters include TOC content, mineral content and porosity data; The determination module is configured to determine a first linear relationship based on a first type of structural parameter obtained by logging interpretation, and to determine a second linear relationship based on a second type of structural parameter obtained by image recognition; the first linear relationship and the second linear relationship respectively characterize a mapping relationship between the porosity data at a macro level and a micro level and the TOC content and the mineral content; The combining module is configured to combine the first linear relationship and the second linear relationship using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data, including: Determine a priori probability distribution at the macro level and the micro level based on the structural parameters; Using the first linear relationship and the second linear relationship to construct a macro likelihood function and a micro likelihood function respectively, and combining the macro likelihood function and the micro likelihood function to obtain a joint likelihood function; The prior probability distribution and the joint likelihood function are combined using Bayesian theorem to obtain a target linear relationship corresponding to the porosity data.

8. An electronic device comprising a processor and a memory; the memory stores a computer program, wherein: When the computer program is executed by the processor, the method for determining porosity by using well logging interpretation and image recognition according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images