Reservoir asphalt content acquisition method and apparatus, electronic device, and readable storage medium

Abstract

A reservoir asphalt content acquisition method, comprising: on the basis of an interactive analysis of a well logging curve and mud logging data, acquiring a corrected well logging curve (S101); on the basis of the correlation between the reconstructed natural gamma curve, an actually measured rock core gamma curve, and the corrected well logging curve, acquiring the reconstructed natural gamma curve (S102); acquiring a resistivity difference curve on the basis of a resistivity difference between a deep resistivity curve and a shallow resistivity curve (S103); on the basis of the correlation between the asphalt content, the corrected well logging curve, the reconstructed natural gamma curve, and the resistivity difference curve, acquiring an asphalt content prediction model (S104); and using the asphalt content prediction model to calculate the asphalt content in an asphalt-containing reservoir (S105). Further provided is a reservoir asphalt content acquisition apparatus. The assessment efficiency and accuracy of the asphalt-containing reservoir of the whole-segment reservoir can be improved.

Description

Method, device, electronic device and readable storage medium for obtaining reservoir asphalt content Technical Field

[0001] The present invention relates to the field of oil and gas exploration technology, and in particular to a method for obtaining reservoir asphalt content, a device for obtaining reservoir asphalt content, an electronic device, and a computer-readable storage medium. Background Art

[0002] Asphalt-bearing reservoirs are a common occurrence in oil and gas exploration and development. Asphalt content is a major factor affecting reservoir quality. Excessive asphalt content can even block the reservoir, acting as a lateral barrier to oil and gas flow. Accurately determining asphalt content also plays a crucial role in estimating remaining oil and gas resources. Therefore, accurate calculation and efficient acquisition of asphalt content are crucial for oil and gas reservoir evaluation and fluid identification.

[0003] In the prior art, there are three main methods for obtaining the asphalt content in reservoirs in the field of oil and gas exploration: (1) obtaining the asphalt content by grinding fluorescent thin slices and observing the fluorescence characteristics of asphalt under a fluorescence microscope. This method is the most commonly used method, but it is mainly based on naked eye estimation and cannot accurately calculate the asphalt content; (2) calculating the reservoir asphalt content by nuclear magnetic resonance technology. Although this method can quantitatively obtain the asphalt content, it cannot accurately calculate the asphalt content because the nuclear magnetic resonance signal of asphalt and the nuclear magnetic resonance signal of mud bound water are similar, and the accuracy is low; (3) using nuclear magnetic resonance technology to establish a model of mud content and asphalt nuclear magnetic signal amplitude, and calculating the asphalt content based on the model. Although this method replaces the process of directly calculating the reservoir asphalt content by nuclear magnetic resonance technology, it still needs to use nuclear magnetic resonance technology when coring, which has a long experimental time, low efficiency, high cost, and limited representativeness.

[0004] Although the above three methods can all achieve the acquisition of reservoir asphalt content and play an important role in the oil and gas exploration process, they still have great limitations: (1) All three methods can only calculate the asphalt content of the cored section, but are helpless in obtaining the asphalt content of the uncored section. In exploration practice, drilling and coring ultra-deep oil and gas layers is difficult and costly, and the coring length of a single well only accounts for 2% to 15% of the reservoir section, making it impossible to calculate the asphalt content of the entire asphalt-bearing reservoir section; (2) The samples of the three methods are all small, all at the centimeter level, and the fluorescent thin section method is generally less than 1 cm. Due to the strong heterogeneity of asphalt, the sample representativeness is limited, which leads to limitations in the asphalt content value obtained through the sample; (3) All three methods require the preparation of thin sections or plunger samples required for nuclear magnetic resonance, which has a long experimental cycle and low efficiency. They cannot obtain asphalt content quickly and efficiently, and cannot meet the accuracy and timeliness requirements of oil and gas exploration.

[0005] In summary, it is necessary to provide a method for obtaining reservoir asphalt content to solve at least one of the above problems.

[0006] Summary of the Invention

[0007] The purpose of the embodiment of the present invention is to provide a method for obtaining reservoir asphalt content, which is at least used to solve the problems existing in the existing asphalt content acquisition method, such as limited sample representativeness, inability to accurately calculate the asphalt content of the entire layer of the asphalt-containing reservoir, and long experimental cycle.

[0008] In order to achieve the above-mentioned objectives, the first aspect of the present invention provides a method for obtaining reservoir asphalt content, which includes the following steps: obtaining a corrected logging curve based on the interactive analysis of logging curves and logging data; obtaining a reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve; obtaining a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve; obtaining an asphalt content prediction model based on the correlation between the asphalt content, the corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve; and using the asphalt content prediction model to calculate and obtain the asphalt content in the asphalt-containing reservoir.

[0009] In an exemplary embodiment of the present invention, the well logging curve may be at least one of a density curve, an acoustic wave curve, a resistivity curve, a neutron curve, a caliper curve, and a spontaneous potential curve.

[0010] In an exemplary embodiment of the present invention, the acquisition of the reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated well logging curve may include: determining the first weight of each calibrated well logging curve by multivariate regression fitting based on the measured core gamma curve and at least one calibrated well logging curve; constructing a reconstructed gamma value prediction model based on the first weight of each calibrated well logging curve; acquiring the reconstructed natural gamma curve based on the reconstructed gamma value prediction model; the reconstructed gamma value prediction model is: GR new =GR+a1X1+a2X2……+a n X n ,

[0011] Among them, GR new To reconstruct the natural gamma value, GR is the natural gamma value of the well logging corresponding to the measured core gamma curve, X1, X2...X n are the corrected logging values ​​corresponding to each corrected logging curve, a1, a2...a n are the first weights of each corrected logging curve.

[0012] In another exemplary embodiment of the present invention, the obtaining of the reconstructed natural gamma curve based on the correlation among the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve may include: inputting a first training data set into a neural network, determining the correlation among the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve through the neural network, and obtaining a trained reconstructed gamma value prediction model; inputting the measured core gamma curve and at least one corrected logging curve into the trained reconstructed gamma value prediction model to obtain the reconstructed natural gamma curve; wherein the first training data set includes: sample data of the reconstructed natural gamma value, sample data of the logging natural gamma value and sample data of at least one corrected logging value.

[0013] In an exemplary embodiment of the present invention, the obtaining of the reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve may also include: performing correlation analysis on the reconstructed natural gamma curve and the measured core gamma curve to obtain a first correlation between the reconstructed natural gamma curve and the measured core gamma curve; judging whether the first correlation is less than a first preset value; if it is determined that the first correlation is less than the first preset value, re-obtaining the reconstructed natural gamma curve; if it is determined that the first correlation is greater than or equal to the first preset value, outputting the reconstructed natural gamma curve.

[0014] In an exemplary embodiment of the present invention, obtaining a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve may include: taking logarithms of the deep resistivity curve and the shallow resistivity curve, respectively, to obtain a logarithmic value of the deep resistivity curve and a logarithmic value of the shallow resistivity curve; subtracting the logarithmic value of the deep resistivity curve from the logarithmic value of the shallow resistivity curve to obtain a resistivity logarithmic difference; taking the absolute value of the resistivity logarithmic difference to obtain a resistivity difference; and obtaining a resistivity difference curve based on the resistivity difference.

[0015] In an exemplary embodiment of the present invention, the method of obtaining an asphalt content prediction model based on the correlation between asphalt content, a calibrated well logging curve, a reconstructed natural gamma curve, and a resistivity difference curve may include: determining a second weight of each calibrated well logging curve by multivariate regression fitting based on at least one calibrated well logging curve, a reconstructed natural gamma curve, and a resistivity difference curve; and constructing an asphalt content prediction model based on the second weight of each calibrated well logging curve; the asphalt content prediction model is: BC = GR new +Re+b1X1+b2X2……+b n X n ;

[0016] Among them, BC is the predicted asphalt content value, GR newis the reconstructed natural gamma value corresponding to the reconstructed natural gamma curve, Re is the resistivity difference corresponding to the resistivity difference curve, X1, X2...X n are the corrected logging values ​​corresponding to each corrected logging curve, b1, b2...b n are the second weights of each corrected logging curve.

[0017] In another exemplary embodiment of the present invention, the method of obtaining the asphalt content prediction model based on the correlation between the asphalt content, the corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve may include: inputting a second training data set into a neural network, determining the correlation between the asphalt content, the corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve through the neural network, and obtaining a trained asphalt content prediction model; wherein the second training data set includes: sample data of asphalt content values, sample data of reconstructed natural gamma values, sample data of logging natural gamma values ​​and sample data of at least one corrected logging value.

[0018] In an exemplary embodiment of the present invention, the use of an asphalt content prediction model to calculate and obtain the asphalt content in an asphalt-containing reservoir may include: using the asphalt content prediction model to calculate and obtain a model-predicted asphalt content value; performing a correlation analysis between the model-predicted asphalt content value and the core-measured asphalt content value to obtain a second correlation between the model-predicted asphalt content value and the core-measured asphalt content value; determining whether the second correlation is less than a second preset value; if it is determined that the second correlation is less than the second preset value, re-acquiring the asphalt content prediction model; if it is determined that the second correlation is greater than or equal to the second preset value, determining the model-predicted asphalt content value as the asphalt content in the asphalt-containing reservoir.

[0019] A second aspect of the present invention provides a reservoir asphalt content acquisition device, which includes: a correction module, a natural gamma ray reconstruction module, a resistivity difference acquisition module, an asphalt content prediction model acquisition module and an asphalt content calculation module; the correction module is used to obtain a corrected logging curve based on the interactive analysis of the logging curve and the logging data; the natural gamma ray reconstruction module is used to obtain a reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve; the resistivity difference acquisition module is used to obtain a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve; the asphalt content prediction model acquisition module is used to obtain an asphalt content prediction model based on the correlation between the asphalt content, the corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve; the asphalt content calculation module is used to calculate the asphalt content in the asphalt-containing reservoir using the asphalt content prediction model.

[0020] The third aspect of the present invention provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by one or more of the above-mentioned processors to enable the processor to execute the above-mentioned reservoir asphalt content acquisition method.

[0021] A fourth aspect of the present invention provides a computer-readable storage medium storing at least one program code, wherein the program code is loaded and executed by a processor to enable a computer to execute the above-mentioned method for obtaining reservoir asphalt content.

[0022] Through the above technical solution, the beneficial effects of the present invention are as follows:

[0023] (1) The asphalt content acquisition method provided by the present invention effectively solves the problem of inaccurate prediction in existing asphalt content acquisition methods. This method fully considers the factors affecting the asphalt content, reconstructs the natural gamma curve of the well logging based on the correlation between the measured core gamma curve and the calibrated well logging curve, and constructs an asphalt content prediction model based on the correlation between the calibrated well logging curve, the reconstructed natural gamma curve and the resistivity difference curve, thereby accurately obtaining the asphalt content of the entire layer in the asphalt-bearing reservoir, and the predicted asphalt content value has a high correlation with the measured core value;

[0024] (2) The asphalt content acquisition method provided by the present invention effectively solves the problem of difficulty in acquiring asphalt content in non-coring sections. In exploration practice, especially in ultra-deep exploration, the high cost of coring leads to extremely limited coring data. In the past, there was no way to acquire asphalt content in non-coring sections. Asphalt effects were not or were difficult to consider in reservoir evaluation, resulting in inaccurate reservoir evaluation. The asphalt content acquisition method of the present invention effectively solves this problem by making full use of well logging data. It not only provides a basis for continuous and accurate reservoir evaluation of the entire well section, but also improves the efficiency and accuracy of reservoir evaluation of the entire section of the asphalt-containing reservoir.

[0025] (3) The asphalt content acquisition method provided by the present invention effectively solves the problem of insufficient timeliness in obtaining asphalt content. The existing methods of obtaining asphalt content by grinding fluorescent thin slices and nuclear magnetic resonance require at least three working days for the entire process from sampling, sample delivery, sample preparation to analysis, provided that local experimental conditions are available and long-distance transportation is not required. However, the asphalt content acquisition method of the present invention can achieve the purpose of predicting asphalt content in only four hours at most, thus having a high timeliness.

[0026] (4) The asphalt content acquisition method provided by the present invention effectively solves the problem of asphalt content limitations caused by poor sample representativeness. The sample particle size used in the existing asphalt content acquisition method is basically at the centimeter level. However, the asphalt content in the actual reservoir is highly heterogeneous. The sample sampling method in the existing technology may not fully represent the spatial variation of the asphalt content in the actual reservoir, which may lead to certain limitations in the evaluation and analysis of sample properties. The asphalt content acquisition method of the present invention can better circumvent the problem of sampling limitations and fully utilize the advantages of high vertical resolution and longitudinal continuity of logging data. A data point is selected at a certain interval (such as 0.125m), thereby maximally meeting the asphalt content acquisition requirements for the diversity of sample data points;

[0027] (5) The asphalt content acquisition method provided by the present invention can greatly save exploration and development costs. For example, the method of obtaining asphalt content by grinding fluorescent thin slices costs about 200 yuan per sample, while the method of obtaining asphalt content by nuclear magnetic resonance technology costs about 1,000 yuan per use of nuclear magnetic resonance technology. Compared with the above methods, the asphalt content acquisition method of the present invention does not require special sample preparation or the use of nuclear magnetic resonance technology. It only needs to fully analyze the existing logging data to achieve the purpose of predicting asphalt content. While improving timeliness, it also greatly saves research costs.

[0028] (6) The asphalt content results obtained by the asphalt content acquisition method provided by the present invention are highly accurate and helpful in expanding the scope of exploration and development. On the one hand, based on the quantitative results, it can be determined whether there are oil and gas reservoirs with asphalt lateral blockage in the basin. On the other hand, since the asphalt content has a strong correlation with the oil and gas layer, it is also helpful to avoid the possibility of leakage of the oil and gas layer due to mud contamination of the reservoir. In addition, the quantitative acquisition of asphalt content by a large number of wells drilled in the basin helps to determine the amount of oil and gas resources destroyed in the geological period, which in turn helps to understand the basin's reservoir formation laws and promote the basin's exploration and development process.

[0029] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0031] FIG1 is a technical roadmap of a method for obtaining reservoir asphalt content provided by an embodiment of the present invention;

[0032] FIG2 is a schematic flow chart of a method for obtaining reservoir asphalt content according to an embodiment of the present invention;

[0033] FIG3 is a correlation diagram of the reconstructed gamma and measured core of Well XX provided by an embodiment of the present invention;

[0034] FIG4 is a comprehensive histogram of asphalt content prediction of Well XX provided by an embodiment of the present invention;

[0035] FIG5 is a correlation diagram of the predicted asphalt content and the measured value of the XX well provided by an embodiment of the present invention;

[0036] FIG6 is a schematic structural diagram of a device for obtaining reservoir asphalt content according to an embodiment of the present invention;

[0037] FIG7 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0038] Description of Reference Numerals

[0039] 101 - correction module, 102 - natural gamma reconstruction module, 103 - resistivity difference acquisition module, 104 - asphalt content prediction model acquisition module, 105 - asphalt content calculation module, 201 - processor, 202 - memory. DETAILED DESCRIPTION

[0040] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0041] In the present invention, unless otherwise indicated, directional terms such as "upper, lower, top, and bottom" are generally used to describe the relative positions of components relative to the directions shown in the drawings, or relative to the vertical, perpendicular, or gravitational directions. "First," "second," etc. are merely for convenience of description and distinction and should not be construed as indicating or implying relative importance.

[0042] It should also be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "installation" and "connection" should be understood in a broad sense. For example, they may refer to fixed connection, detachable connection, or integrated connection; direct connection, indirect connection, wired connection, or wireless connection. Those skilled in the art will understand the specific meanings of the above terms in the present invention depending on the specific circumstances.

[0043] Existing techniques can measure the asphalt content of asphalt-bearing reservoirs by observing the fluorescence characteristics of ground fluorescent thin sections and using nuclear magnetic resonance (NMR) technology. While these methods can quantitatively determine asphalt content, the core samples used are typically at the centimeter level. Asphalt in reservoirs is highly heterogeneous, asphalt content values ​​obtained from centimeter-level core samples alone have certain limitations and cannot fully characterize the asphalt content of the entire asphalt reservoir. Furthermore, asphalt content often varies significantly between reservoir sections. To accurately determine the asphalt content of the entire asphalt reservoir, it is necessary to obtain core samples from different reservoir sections and calculate the asphalt content of each section. However, in exploration practice, especially in ultra-deep exploration, coring ultra-deep oil and gas reservoirs is difficult and costly, and the core length of a single well only accounts for 2% to 15% of the reservoir section, making it impossible to calculate the asphalt content of the entire asphalt reservoir section.

[0044] Considering the problem of inaccurate asphalt content results obtained in the entire layer of an asphalt-bearing reservoir in the prior art, the present invention proposes a method for obtaining reservoir asphalt content. As shown in Figure 1, this method first performs data normalization, correction, and outlier removal on the logging curve values ​​to obtain a corrected logging curve. Then, by fully considering the factors affecting the asphalt content, the natural gamma is reconstructed based on the corrected logging curve to obtain a reconstructed natural gamma curve, and the resistivity is reconstructed to obtain a resistivity difference curve. Finally, a multivariate fitting is performed on the reconstructed natural gamma curve, the resistivity difference curve, and the corrected logging curve to establish an asphalt content prediction model, thereby obtaining the predicted asphalt content value. In this method, neither the preparation of core samples nor the introduction of nuclear magnetic resonance technology is required. The reservoir asphalt content can be obtained based solely on existing logging data. Compared with the asphalt content acquisition methods in the prior art, the accuracy of asphalt content prediction can be improved. In specific implementation, the above method can be executed by an electronic device, which can be a server, terminal, or other device with processing capabilities.

[0045] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0046] As shown in FIG2 , an embodiment of the present invention provides a method for obtaining reservoir asphalt content, the method comprising the following steps:

[0047] Step S101: obtaining a corrected logging curve based on interactive analysis of the logging curve and the logging data.

[0048] Step S102: Based on the correlation between the reconstructed natural gamma ray curve, the measured core gamma ray curve and the calibrated well logging curve, a reconstructed natural gamma ray curve is obtained.

[0049] Step S103: obtaining a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve.

[0050] Step S104: obtaining an asphalt content prediction model based on the asphalt content, the calibrated logging curve, the correlation between the reconstructed natural gamma ray curve and the resistivity difference curve.

[0051] Step S105: using the asphalt content prediction model to calculate and obtain the asphalt content in the asphalt-containing reservoir.

[0052] Furthermore, in a possible embodiment, in step S101, the process of obtaining a corrected logging curve based on the interactive analysis of the logging curve and the logging data may include: combining the drilling information, interactively analyzing the logging curve and the logging data, and performing data normalization, correction, and elimination on the logging curve values, including information such as the logging depth and / or the logging lithology value, so that the logging curve values ​​match the values ​​corresponding to the logging data (such as depth, lithology, etc.) to obtain a corrected logging curve.

[0053] Among them, when the lithologic information provided by the logging curve has obvious deviations compared with the lithologic information during drilling, the lithologic information provided by the logging curve is normalized, corrected and eliminated based on the drilling information to obtain a corrected logging curve. The accuracy of the corrected logging curve should be higher than that of the original logging curve.

[0054] A well log curve is a curve generated during well logging that reflects the characteristics of different lithologies and horizons. By determining specific lithologies and horizons based on the well log curve and correcting it based on logging data and drilling conditions, the accuracy of the well log curve can be improved, providing strong support for ultimately determining bitumen content.

[0055] Furthermore, in one possible embodiment, the well logging curves may include at least one of a density curve, an acoustic wave curve, a resistivity curve, a neutron curve, a caliper curve, and a spontaneous potential curve. Well logging curves are downhole measurement data. After logging is completed, the well logging curves are stored in a database for subsequent retrieval and use. Different well logging curves are selected for different well conditions and can be determined based on actual conditions.

[0056] In addition, it should be noted that the logging curves described in the embodiments of the present invention may include but are not limited to the above-mentioned curves. In the asphalt content acquisition method provided in the embodiments of the present invention, the logging curve selected may be determined according to actual conditions, and may be one of them or any combination.

[0057] Furthermore, in a possible embodiment, in step S102, based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated logging curve, the process of obtaining the reconstructed natural gamma curve may include but is not limited to the following sub-steps S1021 to S1023.

[0058] Sub-step S1021: Based on the measured core gamma curve and at least one corrected well logging curve, determine the first weight of each corrected well logging curve through multivariate regression fitting.

[0059] Sub-step S1022: constructing a reconstructed gamma value prediction model based on the first weight of each corrected logging curve.

[0060] Here, the reconstructed gamma value prediction model is: GR new =GR+a1X1+a2X2……+a n X n (1)

[0061] In formula (1), GR new To reconstruct the natural gamma value, GR is the corresponding logging natural gamma value in the measured core gamma curve, X1, X2...X n are the corrected logging values ​​corresponding to each corrected logging curve, a1, a2...a n are the first weights of each corrected logging curve.

[0062] Sub-step S1023: obtaining a reconstructed natural gamma curve based on the reconstructed gamma value prediction model.

[0063] By performing a multivariate fit between the measured core gamma curve and the calibrated logging curve, we can determine the first weights for each calibrated logging curve and reconstruct the natural gamma curve. The reconstructed natural gamma curve serves as a correction curve for the measured natural gamma, improving work efficiency and providing support for subsequent work.

[0064] For example, assuming that the density curve is selected as the logging curve required for subsequent calculations, the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve is: GR new -GR-a1×X1=0, then the specific process of obtaining the reconstructed natural gamma curve based on the logging curve is as follows: first, select several groups (for example, group i) of logging gamma values ​​from the measured core gamma curve, namely GR1, GR2...GR i At the same time, select several groups (such as group i) of correction density values ​​in the correction density curve, which are X 11 、X 12 ...X 1i; Then, the above-mentioned several groups of logging gamma values ​​and several groups of corrected density values ​​are used as fitting data, and the first weight value a1 of the corrected density curve is determined by multivariate regression fitting, so as to construct a reconstructed gamma value prediction model; finally, the reconstructed gamma value is calculated according to the constructed reconstructed gamma value prediction model and the curve is drawn to obtain the reconstructed natural gamma curve.

[0065] For another example, assuming that the density curve and the acoustic wave curve are selected as the logging curves required for subsequent calculations, the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve is: GR new -GR-a1×X1-a2×X2=0, then the specific process of obtaining the reconstructed natural gamma curve based on the logging curve is: first select several groups (for example, group j) of logging gamma values ​​in the measured core gamma curve, namely GR1, GR2...GR j At the same time, select several groups (such as j groups) of correction density values ​​in the correction density curve, which are X 11 、X 12 ...X 1j , and select several groups (for example, j groups) of corrected sound wave values ​​in the corrected sound wave curve, which are X 21 、X 22 ...X 2j ; Then, the above-mentioned several groups of logging gamma values, several groups of corrected density values ​​and several groups of corrected acoustic wave values ​​are used as fitting data, and the first weight value a1 of the corrected density curve and the first weight value a2 of the corrected acoustic wave curve are determined respectively through multivariate regression fitting, so as to construct a reconstructed gamma value prediction model; finally, the reconstructed gamma value is calculated according to the constructed reconstructed gamma value prediction model and the curve is drawn to obtain the reconstructed natural gamma curve.

[0066] It should be noted that the present invention is not limited to this. In another possible implementation, in step S102, based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated logging curve, the process of obtaining the reconstructed natural gamma curve may also include but is not limited to the following sub-steps S1021' to S1023'.

[0067] Sub-step S1021 ′: obtaining a first training data set, the first training data set including: sample data of reconstructed natural gamma values, sample data of well logging natural gamma values, and sample data of at least one type of corrected well logging value.

[0068] Sub-step S1022': input the first training data set into the neural network, determine the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated logging curve through the neural network, and obtain a trained reconstructed gamma value prediction model.

[0069] Sub-step S1023 ′: inputting the measured core gamma curve and at least one calibrated logging curve as a first test data set into the trained reconstructed gamma value prediction model to obtain a prediction result of the reconstructed natural gamma curve.

[0070] For example, the reconstructed natural gamma curve, the measured core gamma curve and the calibrated logging curve in the test well of the completed reservoir asphalt content in the target block can be selected as the first training data set, and the neural network can be trained with the first training data set to obtain a trained reconstructed gamma value prediction model; then the measured core gamma curve and the calibrated logging curve in the target well to be tested in the target block are input into the trained reconstructed gamma value prediction model, and the accurate prediction of the reconstructed natural gamma curve of the target well can be achieved.

[0071] Of course, the present invention is not limited to this. Other machine learning models such as support vector regression model, linear regression model, ridge regression model or Lasso regression model can also be used to train the reconstructed gamma value prediction model of the present invention, as long as the machine learning model can satisfy the requirements of determining the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve, and obtain the prediction result of the reconstructed natural gamma curve.

[0072] Furthermore, in a possible implementation, in step S102, based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated logging curve, the process of obtaining the reconstructed natural gamma curve may further include sub-steps S1024 to S1027.

[0073] Sub-step S1024: performing a correlation analysis on the reconstructed natural gamma curve and the measured core gamma curve to obtain a first correlation between the reconstructed natural gamma curve and the measured core gamma curve.

[0074] Sub-step S1025: Determine whether the first correlation is less than a first preset value.

[0075] Sub-step S1026: when it is determined that the first correlation is less than the first preset value, re-obtaining the reconstructed natural gamma curve.

[0076] Sub-step S1027: when it is determined that the first correlation is greater than or equal to the first preset value, output the reconstructed natural gamma curve.

[0077] Correlation analysis can be used to verify whether the data for reconstructing the natural gamma curve is available. Through repeated steps, the accuracy of the data and outliers can be manually checked to improve the accuracy of the results.

[0078] For example, the first preset value can be set to 80%. After obtaining the reconstructed natural gamma curve, the reconstructed natural gamma curve and the measured core gamma curve can be subjected to correlation analysis. When the correlation between the reconstructed natural gamma curve and the measured core gamma curve of the coring section is less than 80%, steps S101 to S102 are repeated for manual verification to eliminate manual errors until the correlation between the reconstructed natural gamma curve and the measured core gamma curve is greater than 80%.

[0079] The measured core gamma curve is the measured gamma value of the core taken out from the well, measured on the ground by a gamma meter. Since the coring section is only the core of a specific layer depth and cannot represent the core data of the entire formation, the embodiment of the present invention combines the measured core gamma curve with the corresponding part of the core in the reconstructed natural gamma curve through the above steps to perform correlation analysis, so as to determine whether the reconstructed natural gamma curve meets the requirements.

[0080] Furthermore, in a possible implementation, in step S103 , the process of obtaining the resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve may include but is not limited to the following sub-steps S1031 to S1034 .

[0081] Sub-step S1031: taking logarithms of the deep resistivity curve and the shallow resistivity curve respectively to obtain the logarithmic value of the deep resistivity curve and the logarithmic value of the shallow resistivity curve.

[0082] Sub-step S1032: Subtract the logarithmic value of the deep resistivity curve from the logarithmic value of the shallow resistivity curve to obtain a resistivity logarithmic difference.

[0083] Sub-step S1033: taking the absolute value of the resistivity logarithmic difference to obtain the resistivity difference.

[0084] Sub-step S1034: obtaining a resistivity difference curve based on the resistivity difference.

[0085] During the drilling process, the pressure of the mud column in the wellbore is greater than the formation pressure. The pressure difference causes the mud to penetrate into the formation and even replace the fluid in the pores of the original permeable layer, which is a phenomenon called mud intrusion. Resistivity logging is a method of distinguishing the rock properties on the drilling profile based on the fact that different rock types and minerals in nature have different conductor capacities. The resistivity curve obtained by logging can reflect lithological information, and there are usually two types: deep resistivity curve and shallow resistivity curve. Due to the different residence time of mud at different depths, the impact on resistivity is relatively large. Combined with other influencing factors, the final prediction result has a large deviation. When the difference between deep and shallow resistivities is relatively small, the resistivity curve has a poor relationship with the lithology. The embodiment of the present invention takes the logarithm of the difference between the deep resistivity curve and the shallow resistivity curve, and then takes the absolute value of the difference, thereby weakening or eliminating the influence of influencing factors on the resistivity curve, and obtaining a corrected resistivity difference curve.

[0086] Furthermore, in a possible embodiment, in step S104, the process of obtaining the asphalt content prediction model based on the correlation between the asphalt content, the corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve may include but is not limited to the following sub-steps S1041 to S1042.

[0087] Sub-step S1041: Based on at least one corrected logging curve, the reconstructed natural gamma ray curve and the resistivity difference curve, determine the second weight of each corrected logging curve through multivariate regression fitting.

[0088] Sub-step S1042: constructing an asphalt content prediction model based on the second weight of each corrected well logging curve.

[0089] Here, the asphalt content prediction model is: BC=GR new +Re+b1X1+b2X2……+b n X n (2)

[0090] In formula (2), BC is the predicted asphalt content value, GR new To reconstruct the natural gamma value, Re is the resistivity difference, X1, X2...X n are the logging values ​​corresponding to each corrected logging curve, b1, b2...b n are the second weights of each corrected logging curve.

[0091] By performing multivariate fitting of the calibrated well log curves, reconstructed natural gamma ray curves, and resistivity difference curves, we can determine the secondary weights of each calibrated well log curve, thereby constructing a bitumen content prediction model. This prediction model can be used to quickly determine the bitumen content of the entire interval of an asphalt-bearing reservoir, meeting the requirements of accuracy and timeliness in oil and gas exploration.

[0092] For example, assuming that the density curve is selected as the logging curve required for subsequent calculations, the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve is: BC-GR new -Re-b1×X1=0, then the specific process of constructing the asphalt content prediction model based on the logging curve is: first select several groups (for example, group i) of calibrated density values ​​in the calibrated density curve, which are X 11 、X 12 ...X 1i At the same time, several groups (for example, group i) are selected from the reconstructed natural gamma curve to reconstruct the gamma values, namely GRnew1, GRnew2...GRnew i , select several groups (for example, group i) of resistivity differences in the resistivity difference curve, namely Re1, Re2...Re i Then, the above-mentioned several groups of reconstructed gamma values, several groups of resistivity difference values ​​and several groups of corrected density values ​​are used as fitting data, and the second weight value b1 of the corrected density curve is determined by multivariate regression fitting, thereby constructing an asphalt content prediction model.

[0093] For another example, assuming that the density curve and the acoustic wave curve are selected as the logging curves required for subsequent calculations, the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve is: BC-GR new =Re-b1×X1-b2×X2=0, then the specific process of constructing the asphalt content prediction model based on the logging curve is: first select several groups (for example, group j) of calibrated density values ​​in the calibrated density curve, which are X 11 、X 12 ...X 1j , and select several groups (for example, j groups) of corrected sound wave values ​​in the corrected sound wave curve, which are X 21 、X 22 ...X 2j ; At the same time, select several groups (for example, j groups) of reconstructed gamma values ​​in the reconstructed natural gamma curve, namely GRnew1, GRnew2...GRnew j , select several groups (for example, group j) of resistivity differences in the resistivity difference curve, namely Re1, Re2...Re jThen, the above-mentioned several groups of reconstructed gamma values, several groups of resistivity difference values, several groups of corrected density values ​​and several groups of corrected acoustic wave values ​​are used as fitting data, and the second weight value b1 of the corrected density curve and the second weight value b2 of the corrected acoustic wave curve are determined respectively through multivariate regression fitting, thereby constructing an asphalt content prediction model.

[0094] It should be noted that the present invention is not limited to this. In another possible implementation, in step S104, the process of obtaining the asphalt content prediction model based on the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve may also include but is not limited to the following sub-steps S1041' to S1042'.

[0095] Sub-step S1041 ′: obtaining a second training data set, the second training data set including: sample data of asphalt content values, sample data of reconstructed natural gamma values, sample data of well logging natural gamma values, and sample data of at least one corrected well logging value.

[0096] Sub-step S1042': input the second training data set into the neural network, determine the asphalt content, correct the well logging curve, reconstruct the correlation between the natural gamma ray curve and the resistivity difference curve through the neural network, and obtain a trained asphalt content prediction model.

[0097] For example, the asphalt content, reconstructed natural gamma curve, resistivity difference curve and corrected logging curve of the cored section of the target well can be selected as the second training data set, and the neural network can be trained using the second training data set to obtain a trained asphalt content prediction model; then the reconstructed natural gamma curve, resistivity difference curve and corrected logging curve of the uncored section of the target well are input into the trained asphalt content prediction model, and the asphalt content value of the uncored section of the target well can be accurately predicted.

[0098] Of course, the present invention is not limited to this. Other machine learning models such as support vector regression model, linear regression model, ridge regression model or Lasso regression model are also suitable for training the asphalt content prediction model of the present invention, as long as the machine learning model can meet the requirements of determining the asphalt content, correcting the logging curve, reconstructing the correlation between the natural gamma curve and the resistivity difference curve, and obtaining the prediction results of the asphalt content prediction model.

[0099] Furthermore, in a possible implementation, in step S105, the process of using the asphalt content prediction model to calculate and obtain the asphalt content in the asphalt-containing reservoir may include but is not limited to the following sub-steps S1051 to S1055.

[0100] Sub-step S1051: using the asphalt content prediction model to calculate and obtain the asphalt content value predicted by the model.

[0101] Sub-step S1052: performing a correlation analysis on the asphalt content value predicted by the model and the asphalt content value actually measured in the core, and obtaining a second correlation between the asphalt content value predicted by the model and the asphalt content value actually measured in the core.

[0102] Sub-step S1053: Determine whether the second correlation is less than a second preset value.

[0103] Sub-step S1054: when it is determined that the second correlation is less than the second preset value, re-acquire the asphalt content prediction model.

[0104] Sub-step S1055: When it is determined that the second correlation is greater than or equal to the second preset value, the asphalt content value predicted by the model is determined as the asphalt content in the asphalt-containing reservoir.

[0105] Correlation analysis can verify the usability of the predicted data from the asphalt content prediction model, thereby improving the accuracy of the results. For example, the second preset value can be set to 80%. After obtaining the asphalt content prediction model, a correlation analysis can be performed between the asphalt content values ​​predicted by the model and the asphalt content values ​​measured in the core. If the correlation between the asphalt content values ​​predicted by the model and the asphalt content values ​​measured in the core is less than 80%, steps S101 to S104 are repeated to eliminate some deviations that may exist during manual operation, thereby reconstructing the asphalt content prediction model until the correlation between the asphalt content values ​​predicted by the model and the asphalt content values ​​measured in the core is greater than 80%.

[0106] In order to verify the effectiveness and practicality of the reservoir asphalt content acquisition method of the present invention, taking the XX well in the Tarim Oilfield as an example, the reservoir asphalt content acquisition method of the embodiment of the present invention is implemented for the well to obtain the asphalt content. The Silurian System in the Tarim Basin is one of the areas with the most developed asphalt reservoirs in my country. The asphalt reservoirs are distributed over an area of ​​about 59,200 square kilometers with a maximum thickness of 158 meters. They are mainly distributed in Gudong, Badong, Tabei-Tazhong and other areas. Accurate and efficient acquisition of asphalt content has always been one of the problems restricting exploration and development in this field. Accurate and rapid determination of asphalt content directly affects the efficiency and accuracy of reservoir evaluation. Asphalt reservoirs are developed over a large area in the Tazhong area, covering an area of ​​42,000 square kilometers. However, relying solely on existing methods, it is impossible to accurately and quickly determine the asphalt content, especially the asphalt content in non-coring sections.

[0107] To address this challenge and promote exploration and development in the region, a method for obtaining asphalt content, provided by an embodiment of the present invention, was used to quickly and efficiently determine the asphalt content of the entire well section within the asphalt-bearing reservoir of the Silurian Kepingtag Formation in the Tazhong area. Figure 3 shows a correlation plot between the reconstructed gamma ray and the measured core data for Well XX after implementing the asphalt content acquisition method of the present invention; Figure 4 shows a comprehensive histogram of the predicted asphalt content for Well XX after implementing the asphalt content acquisition method of the present invention; and Figure 5 shows a correlation plot between the predicted asphalt content and the measured values ​​for Well XX after implementing the asphalt content acquisition method of the present invention. As shown in Figure 3, after reconstructing the natural gamma ray curve for Well XX, a correlation analysis was performed between the reconstructed natural gamma ray curve and the measured core gamma ray curve. The first correlation reached 88.82%, exceeding the first preset value of 80%, indicating the high accuracy of the reconstructed natural gamma ray curve. As shown in Figure 4, the asphalt content results for Well XX calculated using the asphalt content prediction model show that the asphalt content for the fine sandstone reservoir is primarily between 7.0% and 15.9%, and for the siltstone reservoir, the asphalt content is primarily between 0.1% and 7.0%. As shown in Figure 5, after calculating the XX well using the asphalt content prediction model and obtaining the asphalt content value predicted by the model, a correlation analysis was performed between the asphalt content value predicted by the above model and the asphalt content value measured in the core. The second correlation reached 90.66%, indicating that the accuracy of the asphalt content in the asphalt-containing reservoir is relatively high.

[0108] In addition, the implementation environment of this embodiment includes at least one terminal and a server, and the method is executed on the terminal or the server respectively. The terminal and the server can be connected in communication to realize the interactive transmission of information.

[0109] Among them, the terminal can be any electronic product that can interact with the user through one or more methods such as keyboard, touchpad, touch screen, voice interaction, etc., such as PC (Personal Computer), PPC (Pocket Personal Computer), tablet computer, etc.

[0110] A server can be a single server or a server cluster consisting of multiple servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0111] As shown in FIG6 , an embodiment of the present invention further provides a reservoir asphalt content acquisition device, which includes: a correction module 101 , a natural gamma ray reconstruction module 102 , a resistivity difference acquisition module 103 , an asphalt content prediction model acquisition module 104 and an asphalt content calculation module 105 .

[0112] The correction module 101 is used to obtain a corrected logging curve based on interactive analysis of the logging curve and the logging data.

[0113] The natural gamma ray reconstruction module 102 is configured to obtain a reconstructed natural gamma ray curve based on the correlation between the reconstructed natural gamma ray curve, the measured core gamma ray curve, and the calibrated well logging curve.

[0114] The resistivity difference acquisition module 103 is configured to acquire a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve.

[0115] The asphalt content prediction model acquisition module 104 is used to acquire the asphalt content prediction model based on the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma ray curve and the resistivity difference curve.

[0116] The asphalt content calculation module 105 is used to calculate the asphalt content in the asphalt-containing reservoir using an asphalt content prediction model.

[0117] Furthermore, in a possible implementation, the natural gamma reconstruction module 102 may include: a first fitting submodule, a multivariate function model construction submodule, and a gamma curve reconstruction submodule.

[0118] The first fitting submodule is configured to determine a first weight of each corrected logging curve by multivariate regression fitting based on a measured core gamma curve and at least one corrected logging curve.

[0119] The multivariate function model construction submodule is used to construct a reconstructed gamma value prediction model based on the first weight of each corrected logging curve.

[0120] The gamma curve reconstruction submodule is used to obtain a reconstructed natural gamma curve based on a reconstructed gamma value prediction model.

[0121] Furthermore, in a possible implementation, the natural gamma reconstruction module 102 may further include: a first correlation analysis submodule, a first judgment submodule, a first update submodule, and a first output submodule.

[0122] The first correlation analysis submodule is used to perform correlation analysis on the reconstructed natural gamma curve and the measured core gamma curve to obtain a first correlation between the reconstructed natural gamma curve and the measured core gamma curve.

[0123] The first judgment submodule is configured to judge whether the first correlation is less than a first preset value.

[0124] The first updating submodule is configured to re-acquire and reconstruct the natural gamma curve when it is determined that the first correlation is less than the first preset value.

[0125] The first output submodule is configured to output a reconstructed natural gamma curve when it is determined that the first correlation is greater than or equal to the first preset value.

[0126] Furthermore, in a possible implementation, the resistivity difference acquisition module 103 may include: a logarithmic acquisition submodule, a difference submodule, an absolute value acquisition submodule, and a resistivity difference curve determination submodule.

[0127] The logarithm acquisition submodule is used to obtain the logarithms of the deep resistivity curve and the shallow resistivity curve respectively, to obtain the logarithm value of the deep resistivity curve and the logarithm value of the shallow resistivity curve.

[0128] The difference submodule is used to make a difference between the logarithmic value of the deep resistivity curve and the logarithmic value of the shallow resistivity curve to obtain a resistivity logarithmic difference.

[0129] The absolute value acquisition submodule is used to take the absolute value of the resistivity logarithmic difference to obtain the resistivity difference.

[0130] The resistivity difference curve determination submodule is configured to obtain a resistivity difference curve based on the resistivity difference.

[0131] Furthermore, in a possible implementation, the asphalt content prediction model acquisition module 104 may include: a second fitting submodule and a prediction module construction submodule.

[0132] The second fitting submodule is configured to determine a second weight of each corrected logging curve by multivariate regression fitting based on at least one corrected logging curve, a reconstructed natural gamma ray curve, and a resistivity difference curve.

[0133] The prediction module constructs a submodule for constructing an asphalt content prediction model based on the second weight of each corrected well logging curve.

[0134] Furthermore, in a possible implementation, the asphalt content calculation module 105 may include: a predicted value calculation submodule, a second correlation analysis submodule, a second judgment submodule, a second update submodule, and a second output submodule.

[0135] The predicted value calculation submodule is used to use the asphalt content prediction model to calculate and obtain the asphalt content value predicted by the model.

[0136] The second correlation analysis submodule is used to perform a correlation analysis on the asphalt content value predicted by the model and the asphalt content value actually measured in the core, and obtain a second correlation between the asphalt content value predicted by the model and the asphalt content value actually measured in the core.

[0137] The second judgment submodule is configured to judge whether the second correlation is less than a second preset value.

[0138] The second updating submodule is used to re-acquire the asphalt content prediction model when it is determined that the second correlation is less than the second preset value.

[0139] The second output submodule is configured to determine the asphalt content value predicted by the model as the asphalt content in the asphalt-containing reservoir when it is determined that the second correlation is greater than or equal to the second preset value.

[0140] It should be noted that the above-mentioned device only uses the division of the above-mentioned functional modules as an example to illustrate its functions. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device provided in the above embodiment and the method provided in the above embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0141] As shown in Figure 7, an embodiment of the present invention also provides an electronic device, which includes a processor 201 and a memory 202, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by one or more of the above-mentioned processors to enable the processor to implement the reservoir asphalt content acquisition method in the above-mentioned embodiment.

[0142] Of course, the electronic device may also have components such as a wired or wireless network interface, a keyboard, and an input / output interface for input and output. The electronic device may also include other components for realizing various functions of the device, which will not be described in detail here.

[0143] An embodiment of the present invention further provides a computer-readable storage medium, in which at least one program code is stored. The program code is loaded and executed by a processor to enable a computer to implement the reservoir asphalt content acquisition method in the above embodiment.

[0144] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, or an optical disc data storage device. Those skilled in the art will appreciate that all or part of the steps in the above-mentioned embodiment method can be accomplished by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for causing a single-chip microcomputer, a chip, or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc.

[0145] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various simple modifications can be made to the technical solution of the present invention, and these simple modifications all fall within the scope of protection of the present invention.

[0146] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

[0147] In addition, the various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the spirit of the present invention, they should also be regarded as the contents disclosed by the present invention. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific embodiments of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for obtaining reservoir asphalt content, characterized in that: The method comprises: Based on the interactive analysis of well logging curves and logging data, the corrected well logging curves are obtained; Based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve, a reconstructed natural gamma curve is obtained; Obtaining a resistivity difference curve based on a resistivity difference between a deep resistivity curve and a shallow resistivity curve; Based on the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve, the asphalt content prediction model is obtained; The asphalt content prediction model is used to calculate the asphalt content in the asphalt-containing reservoir.

2. The method for obtaining reservoir asphalt content according to claim 1, characterized in that: The logging curve is at least one of a density curve, an acoustic wave curve, a resistivity curve, a neutron curve, a caliper curve and a natural potential curve.

3. The method for obtaining reservoir asphalt content according to claim 1, characterized in that: The method of obtaining the reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve includes: Based on the measured core gamma curve and at least one corrected logging curve, determining a first weight of each corrected logging curve by multivariate regression fitting; Based on the first weight of each corrected logging curve, a reconstructed gamma value prediction model is constructed; Based on the reconstructed gamma value prediction model, a reconstructed natural gamma curve is obtained; The reconstructed gamma value prediction model is: GR new =GR+a1X1+a2X2……+a n X n , Among them, GR new To reconstruct the natural gamma value, GR is the well logging natural gamma value corresponding to the measured core gamma curve, X1, X2...X n are the corrected logging values ​​corresponding to each corrected logging curve, a1, a2, ..., a n are the first weights of each corrected logging curve.

4. The method for obtaining reservoir asphalt content according to claim 1, characterized in that: The method of obtaining the reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve includes: Inputting the first training data set into the neural network, determining the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated logging curve through the neural network, and obtaining a trained reconstructed gamma value prediction model; Inputting the measured core gamma curve and at least one corrected logging curve into a trained reconstructed gamma value prediction model to obtain a reconstructed natural gamma curve; The first training data set includes: sample data of reconstructed natural gamma values, sample data of well logging natural gamma values, and sample data of at least one corrected well logging value.

5. The method for obtaining reservoir asphalt content according to claim 3 or 4, characterized in that: The method of obtaining the reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve also includes: Performing correlation analysis on the reconstructed natural gamma curve and the measured core gamma curve to obtain a first correlation between the reconstructed natural gamma curve and the measured core gamma curve; Determining whether the first correlation is less than a first preset value; When it is determined that the first correlation is less than the first preset value, re-obtaining a reconstructed natural gamma curve; When it is determined that the first correlation is greater than or equal to the first preset value, a reconstructed natural gamma curve is output.

6. The method for obtaining reservoir asphalt content according to claim 1, characterized in that: The step of obtaining a resistivity difference curve based on a resistivity difference between a deep resistivity curve and a shallow resistivity curve comprises: Taking logarithms of the deep resistivity curve and the shallow resistivity curve respectively, obtaining the logarithmic value of the deep resistivity curve and the logarithmic value of the shallow resistivity curve; Subtracting the logarithmic value of the deep resistivity curve from the logarithmic value of the shallow resistivity curve to obtain a resistivity logarithmic difference; Taking the absolute value of the resistivity logarithmic difference to obtain the resistivity difference; Based on the resistivity difference, a resistivity difference curve is obtained.

7. The method for obtaining reservoir asphalt content according to claim 1, characterized in that: The asphalt content prediction model is obtained based on the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve, including: Based on at least one corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve, determining a second weight of each corrected logging curve by multivariate regression fitting; Based on the second weight of each corrected well logging curve, a bitumen content prediction model is constructed; The asphalt content prediction model is: BC = GR new +Re+b1X1+b2X2……+b n X n ; Among them, BC is the predicted asphalt content value, GR new is the reconstructed natural gamma value corresponding to the reconstructed natural gamma curve, Re is the resistivity difference corresponding to the resistivity difference curve, X1, X2…X n are the corrected logging values ​​corresponding to each corrected logging curve, b1, b2, ... n are the second weights of each corrected logging curve.

8. The method for obtaining reservoir asphalt content according to claim 1, characterized in that: The asphalt content prediction model is obtained based on the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve, including: Inputting the second training data set into the neural network, determining the asphalt content, correcting the well logging curve, reconstructing the correlation between the natural gamma curve and the resistivity difference curve through the neural network, and obtaining a trained asphalt content prediction model; The second training data set includes: sample data of asphalt content values, sample data of reconstructed natural gamma values, sample data of well logging natural gamma values, and sample data of at least one corrected well logging value.

9. The method for obtaining reservoir asphalt content according to claim 1, characterized in that: The method of using the asphalt content prediction model to calculate and obtain the asphalt content in the asphalt-containing reservoir includes: The asphalt content prediction model is used to calculate and obtain the asphalt content value predicted by the model; Performing a correlation analysis on the asphalt content value predicted by the model and the asphalt content value actually measured by the core, to obtain a second correlation between the asphalt content value predicted by the model and the asphalt content value actually measured by the core; Determining whether the second correlation is less than a second preset value; When it is determined that the second correlation is less than the second preset value, re-acquiring the asphalt content prediction model; When it is determined that the second correlation is greater than or equal to the second preset value, the asphalt content value predicted by the model is determined as the asphalt content in the asphalt-containing reservoir.

10. A reservoir asphalt content acquisition device, characterized in that: The device comprises: The correction module is used to obtain the corrected logging curve based on the interactive analysis of the logging curve and the logging data; A natural gamma reconstruction module is used to obtain a reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated logging curve; A resistivity difference acquisition module is used to acquire a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve; An asphalt content prediction model acquisition module is used to acquire an asphalt content prediction model based on the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve; The asphalt content calculation module is used to calculate the asphalt content in the asphalt-containing reservoir using an asphalt content prediction model.

11. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by one or more of the processors so that the processor executes the reservoir asphalt content acquisition method described in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one program code, and the program code is loaded and executed by a processor to enable a computer to execute the reservoir asphalt content acquisition method according to any one of claims 1 to 10.

Images