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

Abstract

The invention provides a reservoir asphalt content obtaining method and device, electronic equipment and a readable storage medium, and belongs to the field of oil-gas exploration. The method comprises the steps that a corrected logging curve is obtained based on interaction analysis of the logging curve and logging data; obtaining a reconstructed natural gamma curve based on the relevance among the reconstructed natural gamma curve, the actually measured rock core gamma curve and the corrected logging curve; acquiring a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve; based on the asphalt content, the correction logging curve, and the relevance between the reconstructed natural gamma curve and the resistivity difference curve, obtaining an asphalt content prediction model; and calculating the asphalt content in the asphalt-containing reservoir by adopting the asphalt content prediction model. Through the method provided by the invention, the asphalt content in the asphalt-containing reservoir can be efficiently, quickly and accurately obtained, and the evaluation efficiency and accuracy of the full-interval reservoir of the asphalt-containing reservoir are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas exploration. Specifically, it relates 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] In oil and gas exploration and development, it often occurs that asphalt-bearing reservoirs are drilled. The asphalt content is one of the main factors affecting the reservoir quality. When the reservoir asphalt content is too high, it may even block the reservoir and act as a lateral seal for oil and gas. At the same time, accurately obtaining the asphalt content also has a certain effect on estimating the remaining oil and gas resources. Therefore, the accurate calculation and efficient acquisition of asphalt content are very crucial for oil and gas reservoir evaluation and fluid identification.

[0003] In the prior art, there are mainly the following three 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 sections and observing the fluorescence characteristics of asphalt under a fluorescence microscope. This is the most commonly used method, but it mainly relies on visual estimation and cannot accurately calculate the asphalt content; (2) Calculating the reservoir asphalt content through nuclear magnetic resonance technology. Although this method can quantitatively obtain the asphalt content, due to the similarity between the nuclear magnetic resonance signals of asphalt and the nuclear magnetic resonance signals of clay-bound water, it is impossible to accurately calculate the asphalt content, and the accuracy is relatively low; (3) Establishing a model of clay content and the amplitude of the nuclear magnetic resonance signal of asphalt using nuclear magnetic resonance technology and calculating the asphalt content based on this model. Although this method replaces the process of directly calculating the reservoir asphalt content through nuclear magnetic resonance technology, it still requires the use of nuclear magnetic resonance technology under the condition of coring, with 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 process of oil and gas exploration, there are still relatively large 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, it is difficult and costly to drill cores in ultra-deep hydrocarbon-bearing formations. The single-well core length only accounts for 2%-15% of the reservoir section, and it is impossible to carry out the calculation of the asphalt content of the entire section of the asphalt-bearing reservoir; (2) The samples of the three methods are all small, in the centimeter level. The method of fluorescent thin sections is even generally less than 1 centimeter. Due to the strong non-uniformity of asphalt, the sample representativeness is limited, and thus the asphalt content value obtained through this sample has limitations; (3) All three methods require the preparation of thin sections or plug samples required for nuclear magnetic resonance. The experimental period is long, the efficiency is low, and the asphalt content cannot be obtained quickly and efficiently, which cannot meet the requirements of accuracy and timeliness in 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. Summary of the Invention

[0006] In view of the technical problems existing in the method for obtaining asphalt content in the prior art, such as limited representativeness of samples, inability to accurately calculate the asphalt content of the entire layer section of the asphalt-bearing reservoir, and long experimental period, the present invention provides a method for obtaining reservoir asphalt content. Using this method, the asphalt content in the asphalt-bearing reservoir can be obtained efficiently, quickly, and accurately, improving the evaluation efficiency and accuracy of the entire layer section of the asphalt-bearing reservoir to guide efficient exploration in the asphalt-bearing field.

[0007] To achieve the above object, in the first aspect of the present invention, a method for obtaining reservoir asphalt content is provided. The method includes the following steps: based on the interactive analysis of logging curves and mud logging data, obtain calibrated logging curves; based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve, and the calibrated logging curves, obtain the reconstructed natural gamma curve; based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve, obtain the resistivity difference curve; based on the correlation between the asphalt content, the calibrated logging curves, the reconstructed natural gamma curve, and the resistivity difference curve, obtain the asphalt content prediction model; use the asphalt content prediction model to calculate and obtain the asphalt content in the asphalt-bearing reservoir.

[0008] In an exemplary embodiment of the present invention, the logging curve may be at least one of a density curve, a sonic curve, a resistivity curve, a neutron curve, a caliper curve, and a spontaneous potential curve.

[0009] In an exemplary embodiment of the present invention, the step of obtaining the reconstructed natural gamma curve based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve, and the calibrated logging curves may include: based on the measured core gamma curve and at least one calibrated logging curve, determine the first weight of each calibrated logging curve through multiple regression fitting; based on the first weight of each calibrated logging curve, construct a reconstructed gamma value prediction model; based on the reconstructed gamma value prediction model, obtain the reconstructed natural gamma curve; the reconstructed gamma value prediction model is:

[0010] GR new = GR + a 1 X 1 + a 2 X 2 …… + a n X n ,

[0011] where GR new is the reconstructed natural gamma value, GR is the logging natural gamma value corresponding to the measured core gamma curve, X 1 、X 2 ……Xn They are the calibrated log values corresponding to each calibrated log curve, a 1 、a 2 ……a n They are the first weights of each calibrated log curve respectively.

[0012] In another 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 calibrated log curve may include: inputting a first training data set into a neural network, determining the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the calibrated log curve through the neural network, and obtaining a trained reconstructed gamma value prediction model; inputting the measured core gamma curve and at least one calibrated log 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 reconstructed natural gamma values, sample data of log natural gamma values, and sample data of at least one calibrated log 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 calibrated log curve may further include: performing a correlation analysis on the reconstructed natural gamma curve and the measured core gamma curve to obtain a first correlation degree between the reconstructed natural gamma curve and the measured core gamma curve; determining whether the first correlation degree is less than a first preset value; in the case where it is determined that the first correlation degree is less than the first preset value, re-obtaining the reconstructed natural gamma curve; in the case where it is determined that the first correlation degree 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, the obtaining of the resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve may include: respectively taking the logarithm of the deep resistivity curve and the shallow resistivity curve to obtain the logarithm value of the deep resistivity curve and the logarithm value of the shallow resistivity curve; taking the difference between the logarithm value of the deep resistivity curve and the logarithm value of the shallow resistivity curve to obtain the resistivity logarithm difference; taking the absolute value of the resistivity logarithm difference to obtain the resistivity difference; obtaining the resistivity difference curve based on the resistivity difference.

[0015] In an exemplary embodiment of the present invention, the obtaining of the asphalt content prediction model based on the correlation between the asphalt content, the calibrated log curve, the reconstructed natural gamma curve and the resistivity difference curve may include: determining the second weights of each calibrated log curve through multiple regression fitting based on at least one calibrated log curve, the reconstructed natural gamma curve and the resistivity difference curve; constructing the asphalt content prediction model based on the second weights of each calibrated log curve; the asphalt content prediction model is:

[0016] BC = GR new +Re + b 1 X 1 +b 2 X 2 …… + b n X n ;

[0017] 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, X 1 、X 2 ……X n are the calibrated log values corresponding to each calibrated log curve respectively, b 1 、b 2 ……b n are the second weights of each calibrated log curve respectively.

[0018] In another exemplary embodiment of the present invention, the obtaining of the asphalt content prediction model based on the correlation between the asphalt content, the calibrated log curves, the reconstructed natural gamma curve and the resistivity difference curve may include: inputting the second training data set into a neural network, determining the correlation between the asphalt content, the calibrated log curves, the reconstructed natural gamma curve and the resistivity difference curve through the neural network, and obtaining the 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 calibrated log value.

[0019] In an exemplary embodiment of the present invention, the calculation of the asphalt content in the asphalt-bearing reservoir by using the asphalt content prediction model may include: calculating the asphalt content value predicted by the model by using the asphalt content prediction model; performing a correlation analysis on the asphalt content value predicted by the model and the asphalt content value measured in the core to obtain the second correlation degree between the asphalt content value predicted by the model and the asphalt content value measured in the core; determining whether the second correlation degree is less than a second preset value; re-obtaining the asphalt content prediction model in the case where it is determined that the second correlation degree is less than the second preset value; and determining the asphalt content value predicted by the model as the asphalt content in the asphalt-bearing reservoir in the case where it is determined that the second correlation degree is greater than or equal to the second preset value.

[0020] In a second aspect of the present invention, a device for obtaining the asphalt content of a reservoir is provided. The device includes: a calibration module, a natural gamma reconstruction module, a resistivity difference obtaining module, an asphalt content prediction model obtaining module, and an asphalt content calculation module; the calibration module is configured to obtain calibrated logging curves based on the interactive analysis of logging curves and logging data; the natural gamma reconstruction module is configured 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 curves; the resistivity difference obtaining module is configured 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 obtaining module is configured to obtain an asphalt content prediction model based on the correlation between the asphalt content, the calibrated logging curves, the reconstructed natural gamma curve, and the resistivity difference curve; the asphalt content calculation module is configured to calculate and obtain the asphalt content in the asphalt-bearing reservoir by using the asphalt content prediction model.

[0021] In a third aspect of the present invention, an electronic device is provided. The electronic device includes a processor and a memory. 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 so that the processor executes the above-mentioned method for obtaining the asphalt content of a reservoir.

[0022] In a fourth aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores at least one program code, and the program code is loaded and executed by a processor so that a computer executes the above-mentioned method for obtaining the asphalt content of a reservoir.

[0023] Through the technical solution provided by the present invention, the present invention has at least the following technical effects:

[0024] (1) The method for obtaining the asphalt content provided by the present invention effectively solves the problem of inaccurate prediction existing in the existing methods for obtaining the asphalt content. By fully considering the influencing factors of the asphalt content, reconstructing the logging natural gamma curve according to the correlation between the measured core gamma curve and the calibrated logging curves, and constructing an asphalt content prediction model according to the correlation between the calibrated logging curves, the reconstructed natural gamma curve, and the resistivity difference curve, the asphalt content of the entire layer section in the asphalt-bearing reservoir can be accurately obtained, and the predicted asphalt content value has a high correlation with the measured core value.

[0025] (2) The asphalt content acquisition method provided by the present invention effectively solves the problem of difficult acquisition of asphalt content in non-coring sections. In exploration practice, especially in ultra-deep exploration, due to the high cost of coring, the coring data is extremely limited. In the past, there was no way to obtain the asphalt content in non-coring sections, and the asphalt influence was not or hardly considered in reservoir evaluation, resulting in inaccurate reservoir evaluation. However, the asphalt content acquisition method of the present invention effectively solves this problem by making full use of logging data, which not only provides a basis for continuously and accurately carrying out reservoir evaluation for the entire well section, but also improves the efficiency and accuracy of reservoir evaluation for the entire layer section of asphalt-bearing reservoirs;

[0026] (3) The asphalt content acquisition method provided by the present invention effectively solves the problem of insufficient timeliness in asphalt content acquisition. For the existing methods of obtaining asphalt content by grinding fluorescence thin sections and nuclear magnetic resonance, under the condition that local experimental conditions are available and long-distance transportation is not required, the entire process from sampling, sample delivery, sample preparation to analysis takes at least 3 working days. However, the asphalt content acquisition method of the present invention can achieve the purpose of predicting asphalt content in only 4 hours at most, with high timeliness;

[0027] (4) The asphalt content acquisition method provided by the present invention effectively solves the problem of limitations in asphalt content caused by poor sample representativeness. The sample particle size of the existing asphalt content acquisition methods is basically at the centimeter level. However, the heterogeneity of asphalt content in actual reservoirs is relatively strong, and the sample sampling methods in the prior art may not be able to fully represent the spatial variation of asphalt content in the real 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 avoid the problem of sampling limitations, make full use of the advantages of high vertical resolution and longitudinal continuity of logging data, and select a data point every 0.125 m, so as to maximize the requirement for the diversity of sample data points for asphalt content;

[0028] (5) The asphalt content acquisition method provided by the present invention can greatly save exploration and development costs. For example, the cost of preparing one sample by the method of obtaining asphalt content by grinding fluorescence thin sections is about 200 yuan, and the cost of using nuclear magnetic resonance technology once by the method of obtaining asphalt content by nuclear magnetic resonance technology is about 1000 yuan. Compared with the above methods, the asphalt content acquisition method of the present invention neither requires special sample preparation nor 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, which not only improves the timeliness but also greatly saves the research cost;

[0029] (6) The asphalt content results obtained by using the asphalt content acquisition method provided by the present invention have relatively high precision, which helps to expand the exploration and development fields. On the one hand, according to the quantitative results, it can be determined whether there are oil and gas reservoirs with lateral asphalt sealing in the basin. On the other hand, since there is a strong correlation between the asphalt content and the oil and gas layers, it is also beneficial to avoid the possibility of missing oil and gas-bearing layers due to mud pollution of the reservoir. In addition, through the quantitative acquisition of the asphalt content in a large number of wells in the basin, it helps to determine the amount of oil and gas destruction resources during the geological period, and further helps to understand the hydrocarbon accumulation law of the basin and promote the exploration and development process of the basin.

[0030] Other features and advantages of the present invention will be described in detail in the following specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The 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 specific implementation, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0032] Figure 1 is the technical roadmap of the reservoir asphalt content acquisition method provided by the embodiment of the present invention;

[0033] Figure 2 is the flow schematic diagram of the reservoir asphalt content acquisition method provided by the embodiment of the present invention;

[0034] Figure 3 is the correlation diagram between the reconstructed gamma and the measured core of Well XX provided by the embodiment of the present invention;

[0035] Figure 4 is the comprehensive columnar diagram of the asphalt content prediction of Well XX provided by the embodiment of the present invention;

[0036] Figure 5 is the correlation diagram between the predicted asphalt content and the measured value of Well XX provided by the embodiment of the present invention;

[0037] Figure 6 is the structural schematic diagram of the reservoir asphalt content acquisition device provided by the embodiment of the present invention;

[0038] Figure 7 is the structural schematic diagram of the electronic device provided by the embodiment of the present invention.

[0039] DESCRIPTION OF THE REFERENCE NUMERALS

[0040] 101 - calibration 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 OF THE INVENTION

[0041] The following will describe in detail the specific implementation manners of the embodiments of the present invention with reference to the accompanying drawings. It should be understood that the specific implementation manners described herein are only for explaining and illustrating the embodiments of the present invention, and are not used to limit the embodiments of the present invention.

[0042] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. In the present invention, "first", "second", etc. are only for convenient description and easy distinction, and cannot be understood as indicating or implying relative importance.

[0043] In the prior art, the asphalt content of an asphalt-bearing reservoir can be obtained by observing the fluorescence characteristics of polished fluorescence thin sections and nuclear magnetic resonance technology. Although these methods can quantitatively obtain the asphalt content, the core samples used are basically in the centimeter level, and the heterogeneity of asphalt in the reservoir is relatively strong. The asphalt content values obtained only from centimeter-level core samples have certain limitations and cannot fully represent the asphalt content of the entire layer in the asphalt-bearing reservoir. In addition, there are often large differences in the asphalt content of different reservoir sections. In order to ensure that the asphalt content of the entire layer in the asphalt-bearing reservoir can be accurately obtained, it is necessary to obtain core samples in different reservoir sections and calculate the asphalt content of different reservoir sections. However, in exploration practice, especially in ultra-deep exploration, it is difficult and costly to drill and core in ultra-deep oil and gas-bearing layers. The core-taking length of a single well only accounts for 2% - 15% of the reservoir section, resulting in the inability to carry out the calculation of the asphalt content of the entire layer in the asphalt-bearing reservoir.

[0044] Considering the problem that the obtained results of the asphalt content of the entire layer in the asphalt-bearing reservoir in the prior art are inaccurate, the present invention proposes a method for obtaining the asphalt content of a reservoir. As Figure 1 shown, this method first performs correction processing such as data normalization, calibration, and outlier removal on the logging curve values to obtain a calibrated logging curve; then, by fully considering the influencing factors of the asphalt content, the natural gamma ray is reconstructed based on the calibrated logging curve to obtain a reconstructed natural gamma ray curve, and the resistivity is reconstructed to obtain a resistivity difference curve; finally, multiple fitting is performed on the reconstructed natural gamma ray curve, the resistivity difference curve, and the calibrated logging curve to establish an asphalt content prediction model, so as to obtain the asphalt content prediction value. In this method, neither core samples need to be prepared nor nuclear magnetic resonance technology needs to be introduced. The asphalt content of the reservoir can be obtained only based on the existing logging data, which can improve the prediction accuracy of the asphalt content compared with the existing methods for obtaining the asphalt content. In specific implementation, the above method can be executed by an electronic device, and the electronic device can be a device with processing functions such as a server or a terminal.

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

[0046] As Figure 2 shown, an embodiment of the present invention provides a method for obtaining the asphalt content of a reservoir, and the method includes the following steps:

[0047] Step S101: Based on the interactive analysis of well logging curves and mud logging data, obtain corrected well logging curves.

[0048] Step S102: Based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected well logging curve, obtain the reconstructed natural gamma curve.

[0049] Step S103: Based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve, obtain the resistivity difference curve.

[0050] Step S104: Based on the correlation between the asphalt content, the corrected well logging curve, the reconstructed natural gamma curve and the resistivity difference curve, obtain the asphalt content prediction model.

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

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

[0053] Wherein, when there is an obvious deviation between the lithology information provided by the well logging curve and the lithology information during drilling, perform data normalization, correction and elimination on the lithology information provided by the well logging curve based on the drilling information to obtain the corrected well logging curve, and the accuracy of the corrected well logging curve should be higher than that of the original well logging curve.

[0054] The well logging curve refers to the curve formed during well logging, and this curve can reflect the characteristics of different lithologies and horizons. Judging the specific lithology, horizon, etc. according to the well logging curve, and correcting the well logging curve in combination with the mud logging data and drilling conditions, so as to improve the accuracy of the well logging curve, which provides strong support for finally obtaining the asphalt content.

[0055] Further, in a possible implementation, the logging curves may include at least one of a density curve, an acoustic curve, a resistivity curve, a neutron curve, a borehole diameter curve, and a spontaneous potential curve. The logging curves are downhole measurement data. After logging is completed, the logging curves form a database for subsequent extraction and use. For different well conditions, different logging curves are selected, which can be determined according to the actual situation.

[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 curves. In the asphalt content acquisition method provided by the embodiments of the present invention, the selected logging curves can be determined according to the actual situation, which can be one of them or any combination.

[0057] Further, 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 curves, 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 calibrated logging curve, determine the first weight of each calibrated logging curve through multiple regression fitting.

[0059] Sub-step S1022: Based on the first weights of each calibrated logging curve, construct a reconstructed gamma value prediction model.

[0060] Here, the reconstructed gamma value prediction model is:

[0061] GR new = GR + a 1 X 1 + a 2 X 2 …… + a n X n (1)

[0062] In formula (1), GR new is the reconstructed natural gamma value, GR is the logging natural gamma value corresponding to the measured core gamma curve, X 1 , X 2 …… X n are the calibrated logging values corresponding to each calibrated logging curve, and a 1 , a 2 …… a n are the first weights of each calibrated logging curve.

[0063] Sub-step S1023: Based on the reconstructed gamma value prediction model, obtain the reconstructed natural gamma curve.

[0064] By performing multiple regression fitting on the measured core gamma curve and the calibrated logging curve, the first weight of each calibrated logging curve can be determined, thereby reconstructing the logging natural gamma curve. The reconstructed logging natural gamma curve is the calibrated curve of the natural gamma measured downhole, which can improve work efficiency and provide support for subsequent work.

[0065] For example, assuming that the density curve is selected as the logging curve required for subsequent calculations, at this time, the correlation between the reconstructed natural gamma curve, the measured core gamma curve, and the calibrated logging curve is: GR new -GR-a 1 ×X 1 =0. Then, the specific process for obtaining the reconstructed natural gamma curve based on this logging curve is as follows: First, select several groups (such as i groups) of logging gamma values in the measured core gamma curve, which are GR 1 、GR 2 ……GR i respectively. At the same time, select several groups (such as i groups) of calibrated density values in the calibrated density curve, which are X 11 、X 12 ……X 1i respectively. Then, take the above several groups of logging gamma values and several groups of calibrated density values as fitting data, and determine the first weight value a 1 of the calibrated density curve through multiple regression fitting, thereby constructing a reconstructed gamma value prediction model. Finally, calculate the reconstructed gamma value according to the constructed reconstructed gamma value prediction model and draw a curve to obtain the reconstructed natural gamma curve.

[0066] Another example, assuming that the density curve and the acoustic curve are selected as the logging curves required for subsequent calculations, at this time, the correlation between the reconstructed natural gamma curve, the measured core gamma curve, and the calibrated logging curve is: GR new -GR-a 1 ×X 1 -a 2 ×X 2 =0. Then, the specific process for obtaining the reconstructed natural gamma curve based on this logging curve is as follows: First, select several groups (such as j groups) of logging gamma values in the measured core gamma curve, which are GR 1 、GR 2 ……GR j respectively. At the same time, select several groups (such as j groups) of calibrated density values in the calibrated density curve, which are X 11 、X 12 ……X 1j , and select several groups (such as j groups) of calibrated acoustic values in the calibrated acoustic curve, which are X 21 、X 22 ……X 2j; Then, using the above-mentioned several groups of logging gamma values, several groups of corrected density values, and several groups of corrected acoustic values as fitting data, respectively determine the first weight value a of the corrected density curve 1 and the first weight value a of the corrected acoustic curve 2 through multiple regression fitting, thereby constructing a reconstructed gamma value prediction model; finally, calculate the reconstructed gamma value according to the constructed reconstructed gamma value prediction model and draw a curve to obtain the reconstructed natural gamma curve.

[0067] It should be noted that the present invention is not limited thereto. In another possible implementation manner, in step S102, based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve, and the corrected 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 sub-step S1023'.

[0068] Sub-step S1021': Obtain a first training data set, which includes: sample data of reconstructed natural gamma values, sample data of logging natural gamma values, and sample data of at least one corrected logging value.

[0069] Sub-step S1022': Input the first training data set into a neural network, and determine the correlation between the reconstructed natural gamma curve, the measured core gamma curve, and the corrected logging curve through the neural network to obtain a trained reconstructed gamma value prediction model.

[0070] Sub-step S1023': Input the measured core gamma curve and at least one corrected logging curve as a first test data set into the trained reconstructed gamma value prediction model to obtain the prediction result of the reconstructed natural gamma curve.

[0071] For example, the reconstructed natural gamma curve, the measured core gamma curve, and the corrected logging curve in the test wells that have completed the reservoir asphalt content test in the target block can be selected as the first training data set, and the neural network can be trained using this first training data set to obtain a trained reconstructed gamma value prediction model; then, input the measured core gamma curve and the corrected logging curve in the target well to be tested in the target block into the trained reconstructed gamma value prediction model to accurately predict the reconstructed natural gamma curve of the target well.

[0072] Of course, the present invention is not limited thereto. Other machine learning models such as support vector regression models, linear regression models, ridge regression models, or Lasso regression models can also be applied to train the reconstructed gamma value prediction model of the present invention, as long as the machine learning model can satisfy the determination of 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.

[0073] Further, in a possible implementation manner, 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.

[0074] Sub-step S1024: Perform a correlation analysis on the reconstructed natural gamma curve and the measured core gamma curve to obtain a first correlation degree between the reconstructed natural gamma curve and the measured core gamma curve.

[0075] Sub-step S1025: Determine whether the first correlation degree is less than a first preset value.

[0076] Sub-step S1026: In the case where it is determined that the first correlation degree is less than the first preset value, re-obtain the reconstructed natural gamma curve.

[0077] Sub-step S1027: In the case where it is determined that the first correlation degree is greater than or equal to the first preset value, output the reconstructed natural gamma curve.

[0078] Through correlation analysis, it is possible to verify whether the data of the reconstructed 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.

[0079] 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 in the cored 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%.

[0080] The measured core gamma curve is the measured gamma value obtained by measuring the core taken from the wellbore on the ground with a gamma ray instrument. Since the cored section is only the core of a specific depth interval and cannot represent the core data of the entire formation, in the embodiments of the present invention, through the above steps, a correlation analysis is performed on the corresponding parts of the core in the measured core gamma curve and the reconstructed natural gamma curve, so as to be able to determine whether the reconstructed natural gamma curve meets the requirements.

[0081] Further, in a possible implementation manner, in step S103, based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve, the process of obtaining the resistivity difference curve may include but is not limited to the following sub-steps S1031 to S1034.

[0082] Sub-step S1031: Take the logarithm 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.

[0083] Sub-step S1032: Subtract the logarithm of the deep resistivity curve from the logarithm of the shallow resistivity curve to obtain the resistivity logarithm difference.

[0084] Sub-step S1033: Take the absolute value of the resistivity logarithm difference to obtain the resistivity difference.

[0085] Sub-step S1034: Based on the resistivity difference, obtain the resistivity difference curve.

[0086] During the drilling process, the pressure of the mud column in the wellbore is greater than the formation pressure, and the pressure difference will cause the mud to infiltrate into the formation, and even displace the fluid in the pores of the original permeable layer, that is, the mud invasion phenomenon. Resistivity logging is a method to distinguish the rock properties in the drilling section according to the different wire-conducting abilities of various lithologies and minerals in nature. The resistivity curves obtained by logging can reflect lithology information, and there are usually two types: deep resistivity curves and shallow resistivity curves. Since the residence time of the mud at different depths is different, which has a greater impact on the resistivity, combined with other influencing factors, the final prediction result has a large deviation. When the difference between the deep and shallow resistivity is relatively small, the relationship between the resistivity curve and the lithology is relatively poor. In the embodiment of the present invention, by taking the logarithms of the deep resistivity curve and the shallow resistivity difference, subtracting the logarithm of the deep resistivity curve from the logarithm of the shallow resistivity curve, and taking the absolute value of the difference, the influence of the influencing factors on the resistivity curve is weakened or eliminated, and a corrected resistivity difference curve is obtained.

[0087] Further, in a possible implementation manner, 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 sub-step S1042.

[0088] Sub-step S1041: Based on at least one corrected logging curve, the reconstructed natural gamma curve, and the resistivity difference curve, determine the second weight of each corrected logging curve by multiple regression fitting.

[0089] Sub-step S1042: Based on the second weights of each corrected logging curve, construct the asphalt content prediction model.

[0090] Here, the asphalt content prediction model is:

[0091] BC = GR new +Re + b 1 X 1 +b 2 X 2 ……+b n X n (2)

[0092] In Equation (2), BC is the predicted asphalt content value, GR new is the reconstructed natural gamma value, Re is the resistivity difference, X 1 , X 2 ... X n are the logging values corresponding to each calibrated logging curve respectively, and b 1 , b 2 ... b n are the second weights of each calibrated logging curve respectively.

[0093] By performing multiple regression fitting on the calibrated logging curves, the reconstructed natural gamma curve, and the resistivity difference curve, the second weights of each calibrated logging curve can be determined, thereby constructing an asphalt content prediction model. This prediction model can be used to quickly obtain the asphalt content of the entire interval of asphalt-bearing reservoirs and can meet the requirements of accuracy and timeliness in oil and gas exploration.

[0094] For example, assuming that the density curve is selected as the logging curve required for subsequent calculations, at this time, 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 - b 1 × X 1 = 0. Then, the specific process of constructing an asphalt content prediction model based on this logging curve is as follows: First, select several groups (such as i groups) of calibrated density values in the calibrated density curve, which are X 11 , X 12 ... X 1i respectively. At the same time, select several groups (such as i groups) of reconstructed gamma values in the reconstructed natural gamma curve, which are GRnew 1 , GRnew 2 ... GRnew i respectively. Select several groups (such as i groups) of resistivity differences in the resistivity difference curve, which are Re 1 , Re 2 ... Re i respectively. Then, take the above-mentioned several groups of reconstructed gamma values, several groups of resistivity differences, and several groups of calibrated density values as fitting data, and determine the second weight value b 1 of the calibrated density curve through multiple regression fitting, thereby constructing an asphalt content prediction model.

[0095] Another example, assuming that the density curve and the acoustic curve are selected as the logging curves required for subsequent calculations, at this time, 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 - b 1 × X 1 - b 2 × X 2= 0, then the specific process of constructing the asphalt content prediction model based on this logging curve is as follows: First, select several groups (such as j groups) of corrected density values in the corrected density curve, which are X 11 、X 12 ……X 1j , and select several groups (such as j groups) of corrected acoustic wave values in the corrected acoustic wave curve, which are X 21 、X 22 ……X 2j ; At the same time, select several groups (such as j groups) of reconstructed gamma values in the reconstructed natural gamma curve, which are GRnew 1 、GRnew 2 ……GRnew j , select several groups (such as j groups) of resistivity differences in the resistivity difference curve, which are Re 1 、Re 2 ……Re j , then use the above-mentioned several groups of reconstructed gamma values, several groups of resistivity differences, several groups of corrected density values and several groups of corrected acoustic wave values as fitting data, and respectively determine the second weight value b 1 of the corrected density curve and the second weight value b 2 of the corrected acoustic wave curve through multiple regression fitting, so as to construct the asphalt content prediction model.

[0096] It should be noted that the present invention is not limited thereto. In another possible implementation manner, 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 also include but is not limited to the following sub-steps S1041' to sub-step S1042'.

[0097] Sub-step S1041': Obtain a second training data set, which 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.

[0098] Sub-step S1042': Input the second training data set into the neural network, and determine the correlation between the asphalt content, the corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve through the neural network to obtain the trained asphalt content prediction model.

[0099] For example, the asphalt content, the reconstructed natural gamma curve, the resistivity difference curve, and the calibrated 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 this second training data set to obtain a trained asphalt content prediction model; then, the reconstructed natural gamma curve, the resistivity difference curve, and the calibrated logging curve of the non-cored section of the target well are input into the trained asphalt content prediction model, and the accurate prediction of the asphalt content value of the non-cored section of the target well can be achieved.

[0100] Of course, the present invention is not limited thereto, and other machine learning models such as support vector regression models, linear regression models, ridge regression models, or Lasso regression models are also equally applicable to training the asphalt content prediction model of the present invention, as long as the machine learning model can satisfy the determination of the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve, and the resistivity difference curve, and obtain the prediction result of the asphalt content prediction model.

[0101] Furthermore, in a possible implementation manner, in step S105, the process of calculating and obtaining the asphalt content in the asphalt-bearing reservoir using the asphalt content prediction model may include but is not limited to the following sub-steps S1051 to sub-step S1055.

[0102] Sub-step S1051: Calculate and obtain the asphalt content value predicted by the model using the asphalt content prediction model.

[0103] Sub-step S1052: Perform a correlation analysis on the asphalt content value predicted by the model and the asphalt content value measured by the core to obtain the second correlation degree between the asphalt content value predicted by the model and the asphalt content value measured by the core.

[0104] Sub-step S1053: Determine whether the second correlation degree is less than the second preset value.

[0105] Sub-step S1054: In the case where it is determined that the second correlation degree is less than the second preset value, re-obtain the asphalt content prediction model.

[0106] Sub-step S1055: In the case where it is determined that the second correlation degree is greater than or equal to the second preset value, determine the asphalt content value predicted by the model as the asphalt content in the asphalt-bearing reservoir.

[0107] Through the correlation analysis, it is possible to verify whether the prediction data of the asphalt content prediction model is available, thereby improving the accuracy of the results.

[0108] For example, the second preset value can be set to 80%. After obtaining the asphalt content prediction model, the correlation between the asphalt content value predicted by the model and the asphalt content value measured from the core can be analyzed. When the correlation between the asphalt content value predicted by the model and the asphalt content value measured from the core is less than 80%, steps S101 - S104 are repeated to eliminate some deviations that may also exist in the manual operation process, so as to reconstruct the asphalt content prediction model until the correlation between the asphalt content value predicted by the model and the asphalt content value measured from the core is greater than 80%.

[0109] To verify the effectiveness and practicality of the reservoir asphalt content acquisition method of the present invention, taking Well XX in the Tarim Oilfield as an example, the reservoir asphalt content acquisition method of the embodiment of the present invention is implemented for this well to obtain the asphalt content.

[0110] The Silurian in the Tarim Basin is one of the areas with the most developed asphalt-bearing reservoirs in China. The distribution area of the asphalt-bearing reservoirs is about 59,200 square kilometers, with a maximum thickness of 158 meters. It is mainly distributed in areas such as Gudong, Badong, and Tabei - Tazhong. The accurate and efficient acquisition of asphalt content has always been one of the difficult problems restricting the exploration and development in this area. The accurate and rapid determination of asphalt content directly affects the efficiency and accuracy of reservoir evaluation.

[0111] In the Tazhong area, asphalt-bearing reservoirs are developed over a large area, with an area of 42,000 square kilometers. However, relying only on existing methods, it is impossible to accurately and rapidly obtain the asphalt content, especially the asphalt content in non-core sections. To solve this problem and promote the exploration and development process in this area, the asphalt content acquisition method provided in the embodiment of the present invention is used to quickly and efficiently obtain the asphalt content of the entire well section in the asphalt-bearing reservoirs of the Kalpin Tag Formation in the Silurian system in the Tazhong area.

[0112] Figure 3 After implementing the asphalt content acquisition method of the embodiment of the present invention, the correlation diagram between the reconstructed gamma ray and the measured core of Well XX is reconstructed; Figure 4 After implementing the asphalt content acquisition method of the embodiment of the present invention, the comprehensive histogram of asphalt content prediction of Well XX; Figure 5 After implementing the asphalt content acquisition method of the embodiment of the present invention, the correlation diagram between the predicted asphalt content and the measured value of Well XX.

[0113] As Figure 3 shown, after reconstructing the natural gamma ray curve for Well XX, the correlation between the reconstructed natural gamma ray curve and the measured core gamma ray curve is analyzed, and its first correlation degree reaches 88.82%, which is greater than the first preset value of 80%, indicating that the accuracy of the reconstructed natural gamma ray curve is relatively high.

[0114] As Figure 4As shown, the asphalt content results of Well XX calculated using the asphalt content prediction model are as follows: for the fine sandstone reservoir, the asphalt content is mainly between 7.0% and 15.9%, and for the siltstone reservoir, the asphalt content is mainly between 0.1% and 7.0%.

[0115] As Figure 5 shown, after using the asphalt content prediction model to calculate Well XX and obtaining the asphalt content value predicted by the model, a correlation analysis is performed between the asphalt content value predicted by the above model and the asphalt content value measured by the core. The second correlation degree reaches 90.66%, indicating that the accuracy of the asphalt content in the asphalt-bearing reservoir is relatively high.

[0116] In addition, the implementation environment of this embodiment includes at least one terminal and a server, and this method is executed on the terminal or the server respectively. The terminal and the server can be communicatively connected to achieve the interactive transmission of information.

[0117] Among them, the terminal can be any electronic product that can perform human-computer interaction with the user through one or more methods such as a keyboard, a touchpad, a touch screen, and voice interaction, such as a PC (Personal Computer), a PPC (Pocket Personal Computer), a tablet computer, etc.

[0118] The server can be a single server, a server cluster composed of multiple servers, or 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), and big data and artificial intelligence platforms.

[0119] As Figure 6 shown, the embodiment of the present invention also provides a device for obtaining the asphalt content of a reservoir. The device includes: a calibration module 101, a natural gamma reconstruction module 102, a resistivity difference acquisition module 103, an asphalt content prediction model acquisition module 104, and an asphalt content calculation module 105.

[0120] The calibration module 101 is used to obtain a calibrated logging curve based on the interactive analysis of the logging curve and the logging data.

[0121] The natural gamma reconstruction module 102 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.

[0122] The resistivity difference acquisition module 103 is used to obtain a resistivity difference curve based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve.

[0123] The asphalt content prediction model acquisition module 104 is configured to acquire an asphalt content prediction model based on the correlation between the asphalt content, the calibrated logging curves, the reconstructed natural gamma curve, and the resistivity difference curve.

[0124] The asphalt content calculation module 105 is configured to calculate and obtain the asphalt content in the asphalt-bearing reservoir by using the asphalt content prediction model.

[0125] Further, in a possible implementation manner, the natural gamma reconstruction module 102 may include: a first fitting sub-module, a multivariate function model construction sub-module, and a gamma curve reconstruction sub-module.

[0126] The first fitting sub-module is configured to determine the first weight of each calibrated logging curve by multivariate regression fitting based on the measured core gamma curve and at least one calibrated logging curve.

[0127] The multivariate function model construction sub-module is configured to construct a reconstructed gamma value prediction model based on the first weights of the calibrated logging curves.

[0128] The gamma curve reconstruction sub-module is configured to obtain a reconstructed natural gamma curve based on the reconstructed gamma value prediction model.

[0129] Further, in a possible implementation manner, the natural gamma reconstruction module 102 may further include: a first correlation analysis sub-module, a first judgment sub-module, a first update sub-module, and a first output sub-module.

[0130] The first correlation analysis sub-module is configured to perform a correlation analysis on the reconstructed natural gamma curve and the measured core gamma curve to obtain a first correlation degree between the reconstructed natural gamma curve and the measured core gamma curve.

[0131] The first judgment sub-module is configured to judge whether the first correlation degree is less than a first preset value.

[0132] The first update sub-module is configured to re-obtain the reconstructed natural gamma curve when it is determined that the first correlation degree is less than the first preset value.

[0133] The first output sub-module is configured to output the reconstructed natural gamma curve when it is determined that the first correlation degree is greater than or equal to the first preset value.

[0134] Further, in a possible implementation manner, the resistivity difference acquisition module 103 may include: a logarithm acquisition sub-module, a difference calculation sub-module, an absolute value acquisition sub-module, and a resistivity difference curve determination sub-module.

[0135] A logarithm acquisition sub-module, configured to take 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.

[0136] A difference calculation sub-module, configured to calculate the difference between the logarithm value of the deep resistivity curve and the logarithm value of the shallow resistivity curve, to obtain the resistivity logarithm difference.

[0137] An absolute value acquisition sub-module, configured to take the absolute value of the resistivity logarithm difference, to obtain the resistivity difference.

[0138] A resistivity difference curve determination sub-module, configured to obtain a resistivity difference curve based on the resistivity difference.

[0139] Further, in a possible implementation manner, the asphalt content prediction model acquisition module 104 may include: a second fitting sub-module and a prediction module construction sub-module.

[0140] The second fitting sub-module is configured to determine the second weight of each calibrated logging curve through multiple regression fitting based on at least one calibrated logging curve, the reconstructed natural gamma curve, and the resistivity difference curve.

[0141] The prediction module construction sub-module is configured to construct an asphalt content prediction model based on the second weights of each calibrated logging curve.

[0142] Further, in a possible implementation manner, the asphalt content calculation module 105 may include: a predicted value calculation sub-module, a second correlation analysis sub-module, a second judgment sub-module, a second update sub-module, and a second output sub-module.

[0143] The predicted value calculation sub-module is configured to calculate and obtain the asphalt content value predicted by the model using the asphalt content prediction model.

[0144] The second correlation analysis sub-module is configured to perform a correlation analysis on the asphalt content value predicted by the model and the asphalt content value measured by the core, to obtain the second correlation degree between the asphalt content value predicted by the model and the asphalt content value measured by the core.

[0145] The second judgment sub-module is configured to judge whether the second correlation degree is less than a second preset value.

[0146] The second update sub-module is configured to re-obtain the asphalt content prediction model when it is determined that the second correlation degree is less than the second preset value.

[0147] The second output sub-module is configured to determine the asphalt content value predicted by the model as the asphalt content in the asphalt-bearing reservoir when it is determined that the second correlation degree is greater than or equal to the second preset value.

[0148] It should be noted that when the above-provided device implements its functions, only the division of the above-mentioned functional modules is used for illustration. In actual applications, the above functions can be allocated 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 belong to the same concept. For the specific implementation process, please refer to the method embodiment and will not be elaborated here.

[0149] As Figure 7 shown, an embodiment of the present invention further provides an electronic device, which includes a processor 201 and a memory 202. 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, so that the processor implements the reservoir asphalt content acquisition method in the above embodiment.

[0150] 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 implementing the functions of the device, which will not be elaborated here.

[0151] An embodiment of the present invention further provides a computer-readable storage medium, in which at least one program code is stored, and the program code is loaded and executed by a processor, so that a computer implements the reservoir asphalt content acquisition method in the above embodiment.

[0152] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical disc data storage device, etc. Those skilled in the art can understand that all or part of the steps in implementing the method in the above embodiment can be completed by a program instructing relevant hardware. 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 foregoing storage media include: USB flash drives, mobile hard disks, read-only memories (ROMs, Read-Only Memories), random access memories (RAMs, Random Access Memories), magnetic disks, or optical discs and other media that can store program codes.

[0153] The preferred embodiments of the present invention have been 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 scope of the technical concept of the present invention, various simple modifications can be made to the technical solutions of the present invention, and these simple modifications all fall within the protection scope of the present invention.

[0154] In addition, it should be noted that, in the various specific technical features described in the above specific embodiments, they can be combined in any appropriate manner without conflict. To avoid unnecessary repetition, the present invention will not separately describe various possible combination methods.

[0155] Furthermore, any combination can be made between various different embodiments of the present invention as long as it does not violate the idea of the present invention, and it should equally be regarded as the content disclosed by the present invention.

Claims

1. A method for obtaining reservoir asphalt content, characterized in that, the method includes: Based on the interactive analysis of logging curves and mud logging data, obtain corrected logging curves; Based on the correlation between the reconstructed natural gamma curve, the measured core gamma curve and the corrected logging curve, obtain the reconstructed natural gamma curve; Based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve, obtain the resistivity difference curve; Based on the correlation between the asphalt content, the corrected logging curve, the reconstructed natural gamma curve and the resistivity difference curve, obtain the asphalt content prediction model; Use the asphalt content prediction model to calculate and obtain the asphalt content in the asphalt-bearing 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 curve, a resistivity curve, a neutron curve, a borehole diameter curve and a spontaneous potential curve.

3. The method for obtaining reservoir asphalt content according to claim 1, characterized in that, the 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, determine the first weight of each corrected logging curve by multiple regression fitting; Based on the first weights of each corrected logging curve, construct a reconstructed gamma value prediction model; Based on the reconstructed gamma value prediction model, obtain the reconstructed natural gamma curve; the reconstructed gamma value prediction model is: GR new = GR + a 1 X 1 + a 2 X 2 …… + a n X n , Among them, GR new is the reconstructed natural gamma value, GR is the well logging natural gamma value corresponding to the measured core gamma curve, X 1 、X 2 ……X n are the corrected well logging values corresponding to each corrected well logging curve, a 1 、 a 2 ……a n They are the first weights of the respective calibrated logging curves.

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

5. The method for obtaining reservoir asphalt content according to claim 3 or 4, characterized in that, the 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 further includes: Conduct a correlation analysis between the reconstructed natural gamma curve and the measured core gamma curve to obtain the first correlation degree between the reconstructed natural gamma curve and the measured core gamma curve; Judge whether the first correlation degree is less than the first preset value; In the case where it is determined that the first correlation degree is less than the first preset value, re-obtain the reconstructed natural gamma curve; In the case where it is determined that the first correlation degree is greater than or equal to the first preset value, output the reconstructed natural gamma curve.

6. The method for obtaining reservoir asphalt content according to claim 1, characterized in that, the Based on the resistivity difference between the deep resistivity curve and the shallow resistivity curve, obtain a resistivity difference curve, including: Take the logarithm 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; Subtract the logarithm value of the deep resistivity curve from the logarithm value of the shallow resistivity curve to obtain a resistivity logarithm difference; Take the absolute value of the resistivity logarithm difference to obtain a resistivity difference; Based on the resistivity difference, obtain a resistivity difference curve.

7. The method for obtaining reservoir asphalt content according to claim 1, characterized in that the obtaining of 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 includes: Based on at least one calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve, determine the second weight of each calibrated logging curve through multiple regression fitting; Based on the second weights of each calibrated logging curve, construct an asphalt content prediction model; The asphalt content prediction model is: BC = GR new +Re + b 1 X 1 +b 2 X 2 …… + 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, X 1 、X 2 ……X n are the calibrated log values corresponding to the respective calibrated log curves, b 1 、b 2 ……b n are the second weights of the respective calibrated log curves.

8. The method for obtaining reservoir asphalt content according to claim 1, characterized in that the obtaining of 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 includes: Input the second training data set into a neural network, and determine the correlation between the asphalt content, the calibrated logging curve, the reconstructed natural gamma curve and the resistivity difference curve through the neural network to obtain 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 calibrated logging value.

9. The method for obtaining reservoir asphalt content according to claim 1, characterized in that the calculating and obtaining the asphalt content in the asphalt-bearing reservoir by using the asphalt content prediction model includes: Calculate and obtain the asphalt content value predicted by the model by using the asphalt content prediction model; Perform a correlation analysis on the asphalt content value predicted by the model and the asphalt content value measured by the core to obtain a second correlation degree between the asphalt content value predicted by the model and the asphalt content value measured by the core; Judge whether the second correlation degree is less than a second preset value; In the case of determining that the second correlation degree is less than the second preset value, re-obtain the asphalt content prediction model; In the case of determining that the second correlation degree is greater than or equal to the second preset value, determine the asphalt content value predicted by the model as the asphalt content in the asphalt-bearing reservoir.

10. A device for obtaining reservoir asphalt content, characterized in that the device includes: a calibration module, a natural gamma reconstruction module, a resistivity difference acquisition module, an asphalt content prediction model acquisition module and an asphalt content calculation module; The calibration module is used to obtain a calibrated logging curve based on the interactive analysis of the logging curve and the logging data; The 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, configured to acquire a resistivity difference curve based on the resistivity difference between a deep resistivity curve and a shallow resistivity curve; An asphalt content prediction model acquisition module, configured 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; An asphalt content calculation module, configured to calculate the asphalt content in the asphalt-bearing reservoir by using the asphalt content prediction model.

11. An electronic device characterized in that the electronic device includes a processor and a memory, and 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, so that the processor executes the reservoir asphalt content acquisition method according to 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, so that a computer executes the reservoir asphalt content acquisition method according to any one of claims 1 to 10.

Images