Logging data expansion method, device and equipment and storage medium

Abstract

The application provides a well logging data expansion method, device, equipment and storage medium, and relates to the technical field of oil exploration. The well logging data expansion method comprises the following steps: acquiring original well logging data; and acquiring new data meeting the law of the original well logging data as expansion data by using a random sampling method. The application uses the law between the existing well logging data, adopts the Monte Carlo random sampling method to obtain a large number of new data meeting the law of the original well logging data, and the data can be further applied to various inversion and reservoir prediction method technologies, so that the certainty of oil and gas exploration and development is improved.

Description

Technical Field

[0001] This application relates to the field of petroleum exploration technology, and in particular to a method, apparatus, equipment and storage medium for expanding well logging data. Background Technology

[0002] Well logging is a method of measuring geophysical parameters by utilizing the electrochemical, electrical, acoustic, and radioactive properties of rock formations. Well logging data reflects the true lithology of the subsurface structure. With sufficient well logging data, rock physical modeling can be performed, reducing uncertainties in reservoir prediction techniques such as seismic inversion.

[0003] Well logging data plays a crucial role in oil and gas exploration and development. However, in the initial stages of exploration and development, well logging and other data are usually scarce, and seismic data is often the only guiding information for reservoir attribute prediction outside of well locations. Due to the limitations of seismic data in terms of signal-to-noise ratio and resolution, reservoir description based solely on seismic data usually involves significant uncertainty, increasing the risks of later reservoir development. Summary of the Invention

[0004] To address the aforementioned issues, this application provides a method, apparatus, equipment, and storage medium for expanding well logging data, which can solve the problem of insufficient well logging data in the early stages of oil and gas exploration and development.

[0005] This application provides a method for expanding well logging data, including: acquiring original well logging data; and using a random sampling method to acquire new data that conforms to the patterns of the original well logging data as expanded data.

[0006] In some embodiments, a Monte Carlo random sampling method is used to obtain new data that conforms to the patterns of the original well logging data as supplementary data.

[0007] In some embodiments, obtaining new data that conforms to the patterns of the original well logging data using the Monte Carlo random sampling method specifically includes:

[0008] S1. Fit the relationship between the first parameter and the second parameter to obtain the fitting formula;

[0009] S2. Calculate the standard deviation between the fitting result and the actual measured value based on the fitting relationship;

[0010] S3. Calculate the cumulative probability distribution of the first parameter in the original well logging data;

[0011] S4. Generate random numbers based on the cumulative probability distribution of the first parameter;

[0012] S5. Calculate the first extended value of the first parameter corresponding to the generated random number based on the cumulative probability distribution of the first parameter;

[0013] S6. Obtain the fitted value of the second parameter based on the expanded value of the first parameter and the fitted relationship.

[0014] S7. Calculate the first augmented value of the second parameter based on the standard deviation and the fitted value of the second parameter.

[0015] In some embodiments, calculating the standard deviation between the fitting result and the actual measured value based on the fitting relationship includes:

[0016] For all sample points of the first parameter, calculate the fitted value of the corresponding second parameter according to the fitting relationship; then calculate the standard deviation (std) of the difference between the true value of the second parameter and the calculated fitted value.

[0017] In some embodiments, generating a random number based on the cumulative probability distribution of the first parameter specifically includes: generating a random number that conforms to a uniform distribution within the range of 0 to 1.

[0018] In some embodiments, the fitting relationship obtained in step S1 is a linear fitting relationship y = a*x + b, where x is the first parameter, y is the second parameter, and a and b are constant coefficients;

[0019] The fitted value of the second parameter obtained in step S6 is: par2 = a*par1 + b, where par1 is the first expanded value of the first parameter and par2 is the fitted value of the second parameter.

[0020] The first extended value of the second parameter calculated in step S7 is: par2'=par2+std*randn(1), where randn(1) represents a randomly generated value that conforms to a normal distribution with a mean of 0 and a variance of 1.

[0021] In some embodiments, obtaining new data that conforms to the pattern of the original logging data using the Monte Carlo random sampling method further includes: repeating steps S4-S7 N times to obtain N sets of randomly simulated logging data of the first parameter and the second parameter as supplementary data, where N is a natural number greater than zero.

[0022] In some embodiments, the first parameter and the second parameter are the porosity and clay content of the same target area, respectively.

[0023] This application also provides a well logging data expansion device, including:

[0024] The acquisition module is used to acquire raw well logging data;

[0025] The expansion module is used to obtain new data that conforms to the patterns of the original well logging data as expansion data by using random sampling methods.

[0026] In some embodiments, the expansion module uses a Monte Carlo random sampling method to obtain new data that conforms to the patterns of the original well logging data. The expansion module specifically includes:

[0027] The fitting module is used to fit the relationship between the first parameter and the second parameter to obtain the fitting formula.

[0028] The standard deviation calculation module is used to calculate the standard deviation between the fitting result and the actual measured value based on the fitting relationship.

[0029] The probability distribution module is used to statistically analyze the cumulative probability distribution of the first parameter in the original well logging data.

[0030] The random number module is used to generate random numbers based on the cumulative probability distribution of the first parameter;

[0031] The first parameter expansion module is used to calculate the first expanded value of the first parameter corresponding to the generated random number based on the cumulative probability distribution of the first parameter.

[0032] The fitting value calculation module is used to obtain the fitting value of the second parameter based on the expanded value of the first parameter and the fitting relationship.

[0033] The second parameter expansion module is used to calculate the first expanded value of the second parameter based on the standard deviation and the fitted value of the second parameter.

[0034] This application provides a well logging data expansion device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, performs any of the well logging data expansion methods described above.

[0035] This application provides a storage medium storing a computer program that can be executed by one or more processors and can be used to implement the well logging data expansion method described in any of the above claims.

[0036] This application provides a method, apparatus, equipment, and storage medium for expanding well logging data. It employs a random sampling method to acquire new data that conforms to the patterns of the original well logging data as expanded data. This invention utilizes the patterns among existing well logging data and uses a random sampling method to obtain a large amount of new data that conforms to the patterns of the original well logging data. This data can be further applied to various inversion and reservoir prediction methods and technologies, improving the certainty of oil and gas exploration and development. Attached Figure Description

[0037] The present application will be described in more detail below based on embodiments and with reference to the accompanying drawings.

[0038] Figure 1 A schematic diagram illustrating the implementation process of a well logging data augmentation method provided in this application embodiment;

[0039] Figure 2 A schematic diagram illustrating the implementation process of another method for expanding well logging data provided in this application embodiment;

[0040] Figure 3 This is the logging data (porosity and clay content) for a well where the lithofacies is sandstone.

[0041] Figure 4 A schematic diagram illustrating the implementation process of another method for expanding well logging data provided in this application embodiment;

[0042] Figure 5 Relationship between sandstone porosity and clay content in a certain well (circles represent actual logging data, triangles represent simulated data);

[0043] Figure 6 Relationship between sandstone porosity and P-wave velocity in a well (circles represent actual logging data, triangles represent simulated data);

[0044] Figure 7 Relationship between sandstone mudstone content and P-wave velocity in wells (circles represent actual logging data, triangles represent simulated data);

[0045] Figure 8 Relationship between P-wave velocity and density in well sandstone (circles represent actual logging data, triangles represent simulated data).

[0046] Figure 9 This application provides a schematic diagram of the structure of a well logging data augmentation device according to an embodiment;

[0047] Figure 10 A schematic diagram of the structure of another logging data augmentation device provided in the application embodiment;

[0048] Figure 11 A schematic diagram of the composition structure of the logging data expansion device provided in the application embodiment;

[0049] In the accompanying drawings, the same components use the same reference numerals. Circles represent actual well logging data, and triangles represent simulated data. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0052] If the application documents contain similar descriptions such as "first, second, third", the following explanation shall be added: In the following description, the terms "first, second, third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0054] To address the problems existing in related technologies, this application provides a method for expanding logging data. The method is applied to a logging data expansion device and a reservoir parameter determination device including a logging data expansion module. The logging data expansion device or reservoir parameter determination device can be an electronic device, such as a computer or mobile terminal. The functions implemented by the logging data expansion method provided in this application can be achieved by the processor of the electronic device calling program code, wherein the program code can be stored in a computer storage medium.

[0055] Example 1

[0056] This application provides a method for expanding well logging data. Figure 1 This is a schematic diagram illustrating the implementation process of a method for expanding well logging data provided in an embodiment of this application, as shown below. Figure 1 As shown, it includes:

[0057] Step S101: Obtain raw well logging data;

[0058] Step S102: Use random sampling to obtain new data that conforms to the patterns of the original well logging data as supplementary data.

[0059] Well logging, also known as geophysical logging, is a method of measuring geophysical parameters by utilizing the electrochemical, electrical, acoustic, and radioactive properties of rock formations. It belongs to the category of applied geophysical methods. By rationally selecting well logging methods based on geological and geophysical conditions, it is possible to conduct detailed studies of borehole geological profiles, detect valuable mineral deposits, provide detailed data necessary for calculating reserves, such as the effective thickness of oil-bearing layers, porosity, hydrocarbon saturation, and permeability, and study borehole technology.

[0060] Raw logging data refers to geophysical parameters obtained through actual logging activities, specifically by measuring the electrochemical, electrical, acoustic, and radioactive properties of rock formations. While logging data plays a crucial role in oil and gas exploration and development, in the initial stages, well logging and other data are typically limited, and seismic data is often the only guiding information for reservoir attribute prediction outside of well locations. However, due to limitations in signal-to-noise ratio and resolution, reservoir description based solely on seismic data usually carries significant uncertainty, increasing the risks of later reservoir development.

[0061] To address the scarcity of logging data in the early stages of oil and gas exploration and development, this invention proposes a random sampling method for expanding logging data. This method utilizes the patterns among existing logging data, employing random sampling to obtain a large amount of new data consistent with the patterns of the original logging data as supplementary data. This supplementary data, including both the original and expanded logging data, can be further applied to various inversion and reservoir prediction methods, improving the certainty of oil and gas exploration and development. This embodiment of the method obtains new data by simulating the patterns of the original logging data through random sampling. This new data can expand the logging data and improve the accuracy of reservoir parameter prediction.

[0062] In this embodiment, the original logging data can be determined by logging the target reservoir area. The original logging data can be pre-stored in a server. The logging data expansion device obtains the original logging data of the target reservoir by communicating with the server. In some embodiments, the original logging data can also be directly measured by the logging equipment. The logging data expansion device directly obtains the original logging data from the measuring equipment.

[0063] In this embodiment, a random sampling method is used to obtain new data that conforms to the patterns of the original well logging data as supplementary data. In some embodiments, a Monte Carlo random sampling method is used to obtain new data that conforms to the patterns of the original well logging data as supplementary data.

[0064] Example 2

[0065] In this embodiment, the original well logging data is acquired; then, a Monte Carlo random sampling method is used to obtain new data that conforms to the patterns of the original well logging data, such as... Figure 2 As shown, the steps for obtaining new data specifically include:

[0066] S1. Fit the relationship between the first parameter and the second parameter to obtain the fitting formula;

[0067] The first parameter and the second parameter are two parameters from a certain well logging data. For example, parameter 1 and parameter 2 to be fitted can be statistically identified from the well logging data under a certain lithofacies, and used as the first parameter and the second parameter. The relationship between the first parameter and the second parameter is fitted based on the statistical regularity of the measured values ​​of the first parameter and the second parameter in the original well logging data to obtain a fitted expression. The fitted expression can represent the general trend between the two parameters. This embodiment does not specifically limit the form of the fitted expression, as long as it conforms to the regularity between the two parameters. In some embodiments, the fitted expression in this step can be linear, which can be expressed as y = a*x + b, where x is the first parameter, y is the second parameter, a is a constant coefficient, and b is also a constant coefficient.

[0068] In addition, the first parameter and the second parameter can be, for example, two of the logging parameters of the target layer in the borehole, such as effective porosity, water saturation, sandstone content, clay content, resistivity, natural gamma, P-wave velocity, S-wave velocity, density, and permeability.

[0069] In some embodiments, in order to obtain more accurate augmented data, the first parameter and the second parameter are preferably two parameters that are recognized in the art as having a certain relationship.

[0070] Generally, clay content, porosity, and water saturation play a decisive role in formation evaluation. Porosity is significantly affected by clay content but less so by hydrocarbon fluids. As clay content increases, porosity decreases. Water saturation is significantly affected by resistivity; its value decreases as resistivity increases. Therefore, the first parameter and the second parameter may, for example, represent the porosity and clay content of the same target area. In other embodiments, the first parameter and the second parameter may, for example, represent the water saturation and resistivity of the same target area.

[0071] In other embodiments, the first parameter and the second parameter are the sandstone porosity and longitudinal wave velocity of the same target region, respectively.

[0072] In other embodiments, the first parameter and the second parameter are mud content and longitudinal wave velocity, respectively.

[0073] In other embodiments, the first parameter and the second parameter are the longitudinal wave velocity and density of sandstone, respectively.

[0074] S2. Calculate the standard deviation between the fitting result and the actual measured value based on the fitting relationship;

[0075] This step substitutes the measured value of the first parameter in the original well logging data into the fitting formula to calculate the fitting result of the second parameter. Then, the standard deviation between the fitting result of the second parameter and the actual measured value is calculated to obtain the main distribution range of the second parameter data.

[0076] S3. Calculate the cumulative probability distribution of the first parameter in the original well logging data;

[0077] This step involves calculating the cumulative probability distribution of the first parameter measurement value in the original well logging data.

[0078] S4. Generate random numbers based on the cumulative probability distribution of the first parameter;

[0079] This step, based on the cumulative probability distribution of the first parameter in step S3, generates a random simulation parameter that conforms to the distribution law according to the principle of uniform distribution. Specifically, in some embodiments, generating a random number based on the cumulative probability distribution of the first parameter specifically includes generating a random number conforming to a uniform distribution within the range of 0 to 1. Then, steps S5-S7 are executed to generate simulation parameter data with a random simulation measurement value distribution law as supplementary data.

[0080] S5. Calculate the first extended value of the first parameter corresponding to the generated random number based on the cumulative probability distribution of the first parameter;

[0081] like Figures 4-8 As shown, based on the principle of uniform distribution, the first extended value of the first parameter corresponding to the random number is calculated around the measured value according to the cumulative probability distribution of the first parameter.

[0082] S6. Obtain the fitted value of the second parameter based on the expanded value of the first parameter and the fitted relationship; substitute the expanded value of the first parameter into the fitted relationship to obtain the fitted value of the second parameter.

[0083] S7. Calculate the first augmented value of the second parameter based on the standard deviation and the fitted value of the second parameter.

[0084] The expanded value of the first parameter and the first expanded value of the second parameter generated according to the above steps are used as the expanded data of the first and second parameters.

[0085] Repeat steps S4-S7 N times to obtain N sets of randomly simulated logging data for the first parameter and the second parameter as supplementary data, where N is a natural number greater than zero. Each time step S4 is executed, when generating random numbers based on the cumulative probability distribution of the first parameter, different random numbers are selected each time to generate different randomly simulated logging data as supplementary data.

[0086] This method can simulate both the approximate trend relationship between parameters and the distribution range of parameters, thus enabling a better stochastic simulation of the true relationship of well logging data. Extensive random sampling can significantly expand the original well logging data.

[0087] The first parameter and the second parameter are the porosity and clay content of the same target area, respectively.

[0088] In some embodiments, calculating the standard deviation between the fitting result and the actual measured value based on the fitting relationship includes:

[0089] For all sample points of the first parameter, calculate the fitted value of the corresponding second parameter according to the fitting relationship; then calculate the standard deviation (std) of the difference between the true value of the second parameter and the calculated fitted value.

[0090] In some embodiments, the fitting relationship obtained in step S1 is a linear fitting relationship y = a*x + b, where x is the first parameter, y is the second parameter, and a and b are constant coefficients;

[0091] The fitted value of the second parameter obtained in step S6 is: par2 = a*par1 + b, where par1 is the first expanded value of the first parameter and par2 is the fitted value of the second parameter.

[0092] The first extended value of the second parameter calculated in step S7 is: par2'=par2+std*randn(1), where randn(1) represents a randomly generated value that conforms to a normal distribution with a mean of 0 and a variance of 1, which is the first extended value of the first parameter.

[0093] In some embodiments, obtaining new data that conforms to the pattern of the original logging data using the Monte Carlo random sampling method further includes: repeating steps S4-S7 N times to obtain N sets of randomly simulated logging data of the first parameter and the second parameter as supplementary data, where N is a natural number greater than zero.

[0094] Example 3

[0095] This embodiment illustrates the basic idea of ​​the invention through a specific example. The method proposed in this invention is tested using actual well logging data from a certain region.

[0096] Appendix Figure 3 This example presents a scatter plot of porosity and clay content for a certain well. It primarily characterizes the relationship between this set of data by describing two key features. First, the linear relationship between porosity and clay content (solid line) represents the general trend between the two parameters. Then, the variance between the scatter plot data and the linear trend line is calculated to represent the main distribution range of the data (the range defined by the two dashed lines). By capturing these two main characteristics of the data, this invention proposes a well logging data augmentation method based on Monte Carlo random sampling.

[0097] Specifically, this method is illustrated using two parameters from a well logging dataset as an example. These two parameters are denoted as parameter 1 and parameter 2, respectively. For instance, in this example, parameter 1 represents porosity and parameter 2 represents clay content. The implementation steps are as follows (see appendix). Figure 4 Appendix Figure 4 A flowchart illustrating the process of augmenting logging data based on Monte Carlo random sampling.

[0098] (1) Statistically determine the fitting parameter 1 and fitting parameter 2 under a certain lithofacies from the well logging data, and represent them as x and y respectively;

[0099] (2) For the parameters to be fitted, 1 and 2, first fit the linear relationship between them to obtain the linear fitting relationship y = a*x + b, where a and b are constant coefficients;

[0100] (3) For all sample points (x1, x2, ..., xn) of parameter 1, the corresponding fitted values ​​(y1, y2, ..., yn) of parameter 2 can be calculated according to the above linear relationship (y = a*x + b), and then the standard deviation std of the difference between the true value and the fitted value of parameter 2 is calculated.

[0101] (4) Statistical distribution of the cumulative probability of parameter 1 in well logging data;

[0102] (5) Generate a random number that conforms to a uniform distribution within the range of 0-1;

[0103] (6) Based on the cumulative probability distribution of the random number generated in (5) and parameter 1, calculate the first extended value of parameter 1 corresponding to the random number, which is par1;

[0104] (7) Substitute the first extended value par1 of parameter 1 into the linear fitting relationship in (2) above to obtain the fitting value of parameter 2, that is, par2=a*par1+b;

[0105] (8) The first extended value of the final parameter 3 can be obtained by random sampling, which is par2'=par2+std*randn(1), where randn(1) represents a value that is randomly generated according to a normal distribution with a mean of 0 and a variance of 1; thus, a set of data (i.e. a set of random simulation data of parameter 1 and parameter 2) is obtained by Monte Carlo random sampling.

[0106] (9) Repeat steps (5)-(8) N times to obtain N sets of randomly simulated logging data for parameters 1 and 2;

[0107] (10) If there are other parameters, such as parameter 3, parameter 4, etc., you can refer to the above steps to simulate the relationship between parameter 3, parameter 4 and parameter 1, and obtain random simulation data of parameter 3 and parameter 4.

[0108] This method can simulate both the approximate trend relationship between parameters and the distribution range of parameters, thus enabling a better stochastic simulation of the true relationship of well logging data. Extensive random sampling can significantly expand the original well logging data.

[0109] Appendix Figures 5-8 The figures show Monte Carlo random sampling results of sandstone data from a certain well (circles represent actual logging data, and triangles represent simulated data). According to the attached... Figures 5-8 As can be seen, the Monte Carlo stochastic simulation results are in good agreement with the actual values, thus verifying the effectiveness of the method. Therefore, the logging data obtained from stochastic simulation can be used as an extension of the original data and further applied to subsequent processing, interpretation, and other stages.

[0110] Appendix Figure 5 Relationship between sandstone porosity and clay content in a certain well (circles represent actual logging data, triangles represent simulated data);

[0111] The above method was used to augment the data on sandstone porosity and P-wave velocity in a certain well. The results are shown in the appendix. Figure 6 Appendix Figure 6 The relationship between sandstone porosity and P-wave velocity in a certain well is shown, where circles represent actual logging data and triangles represent the results of augmented data obtained using the aforementioned Monte Carlo random sampling method; according to Figure 6 As can be seen, the Monte Carlo random simulation results are in good agreement with the actual values, thus verifying the effectiveness of the method.

[0112] Appendix Figure 7The relationship between sandstone argillaceous content and P-wave velocity in a certain well. Circles represent actual well logging data, i.e., measured values ​​of sandstone argillaceous content and P-wave velocity, while triangles represent augmented data obtained using the aforementioned Monte Carlo random sampling. Based on... Figure 6 As can be seen, the Monte Carlo random simulation results are in good agreement with the actual values, which verifies the effectiveness of the method.

[0113] Appendix Figure 8 The relationship between P-wave velocity and density of sandstone in a certain well. Circles represent actual well logging data, i.e., measured values ​​of P-wave velocity and density of sandstone in the well, while triangles represent the results of augmented data obtained using the aforementioned Monte Carlo random sampling. Based on... Figure 6 As can be seen, the Monte Carlo random simulation results are in good agreement with the actual values, which verifies the effectiveness of the method.

[0114] This invention utilizes the patterns among existing well logging data and employs the Monte Carlo random sampling method to obtain a large amount of new data that conforms to the patterns of the original well logging data. This data can be applied to various inversion and reservoir prediction methods and technologies, which helps to improve the certainty of oil and gas exploration and development.

[0115] Example 4

[0116] Based on the foregoing embodiments, this application provides a well logging data expansion device. The various modules and units included in the device can be implemented by a processor in a computer device; of course, they can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0117] This application provides a device for expanding well logging data. Figure 9 This is a schematic diagram of the structure of a well logging data augmentation device provided in an embodiment of this application, as shown below. Figure 9 As shown, the well logging data augmentation device 10 includes:

[0118] Module 11 is used to acquire raw well logging data;

[0119] The expansion module 12 is used to obtain new data that conforms to the pattern of the original well logging data as expansion data by using a random sampling method.

[0120] The original logging data can be determined by logging the target reservoir area. This original logging data may be pre-stored on a server. The logging data expansion device communicates with the server, and the acquisition module 11 acquires the original logging data of the target reservoir. In some embodiments, the original logging data may also be directly measured by the logging equipment, and the acquisition module 11 of the expansion device directly acquires the original logging data from the measuring equipment. The expansion module 12 utilizes existing logging data to obtain more new data that conforms to the patterns of the original logging data through random simulation as expansion data. The expansion module 12 is used to design new data that conforms to the patterns of the original logging data using a random sampling method.

[0121] In some embodiments, the expansion module 12 uses a Monte Carlo random sampling method to obtain new data that conforms to the patterns of the original well logging data; such as Figure 10 As shown, the expansion module 12 may specifically include:

[0122] The fitting module 121 is used to fit the relationship between the first parameter and the second parameter to obtain a fitting formula.

[0123] The standard deviation calculation module 122 is used to calculate the standard deviation between the fitting result and the actual measured value based on the fitting relationship.

[0124] The probability distribution module 123 is used to statistically analyze the cumulative probability distribution of the first parameter in the original well logging data;

[0125] The random number module 124 is used to generate random numbers based on the cumulative probability distribution of the first parameter;

[0126] The first parameter expansion module 125 is used to calculate the first expanded value of the first parameter corresponding to the random number based on the generated random number and the cumulative probability distribution of the first parameter.

[0127] The fitting value calculation module 126 is used to obtain the fitting value of the second parameter based on the expanded value of the first parameter and the fitting relationship.

[0128] The second parameter expansion module 127 is used to calculate the first expanded value of the second parameter based on the standard deviation and the fitted value of the second parameter.

[0129] Taking two parameters from a well logging data as an example, this paper introduces the data augmentation device for the well logging data. These two parameters are denoted as parameter 1 and parameter 2 (for example, parameter 1 represents porosity and parameter 2 represents clay content). The implementation steps are as follows.

[0130] From the well logging data, we can statistically determine the fitting parameter 1 and fitting parameter 2 for a certain lithofacies, which are represented by x and y, respectively.

[0131] For parameters 1 and 2 to be fitted, the fitting module 121 first fits the linear relationship between them to obtain y = a*x + b (a and b are constant coefficients);

[0132] For all sample points (x1, x2, ..., xn) of parameter 1, the standard deviation calculation module 122 can calculate the corresponding fitted value (y1, y2, ..., yn) of parameter 2 according to the above linear relationship (y = a*x + b), and then calculate the standard deviation std of the difference between the true value and the fitted value of parameter 2.

[0133] The cumulative probability distribution of parameter 1 in the statistical logging data is calculated using the probability distribution module 123.

[0134] The random number module 124 generates a single random number that conforms to a uniform distribution within the range of 0-1.

[0135] The first parameter expansion module 125 calculates the first expanded value of parameter 1 corresponding to the random number generated by the random number module 124 and the cumulative probability distribution of parameter 1, which is par1;

[0136] The fitting value calculation module 126 substitutes the value par1 of parameter 1 into the linear fitting relationship obtained by the fitting module 121 above to obtain the fitting value of parameter 2, that is, par2=a*par1+b.

[0137] The second parameter expansion module 127 can obtain the final relational expression par2'=par2+std*randn(1) through random sampling, where randn(1) represents a randomly generated value that conforms to a normal distribution with a mean of 0 and a variance of 1; thus, a set of data (random simulation of parameters 1 and 2) is obtained through Monte Carlo random sampling.

[0138] If the logging data augmentation device is repeated N times, N sets of randomly simulated logging data for parameters 1 and 2 can be obtained.

[0139] If there are other parameters, such as parameter 3, parameter 4, etc., the logging data expansion device can refer to the above steps to simulate the relationship between parameter 3, parameter 4, etc. and parameter 1, and obtain random simulation data of parameter 3, parameter 4, etc.

[0140] This method can simulate both the approximate trend relationship between parameters and the distribution range of parameters, thus enabling a better stochastic simulation of the true relationship of well logging data. Extensive random sampling can significantly expand the original well logging data.

[0141] It should be noted that, in the embodiments of this application, if the above-mentioned method for expanding well logging data is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0142] Accordingly, this application provides a logging data expansion device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, performs any of the logging data expansion methods described above.

[0143] This application provides a storage medium storing a computer program that can be executed by one or more processors and can be used to implement the well logging data expansion method described in any of the above claims.

[0144] This application provides a reservoir parameter determination device, including the logging data expansion device described in any of the above claims.

[0145] This application provides a reservoir parameter determination device that uses raw logging data and simulated logging data based on the raw logging data and random sampling to simulate the raw logging data to perform various inversions and reservoir predictions, which can improve the certainty of oil and gas exploration and development.

[0146] Example 5

[0147] This application provides a device for expanding well logging data; Figure 11 A schematic diagram of the composition structure of the logging data expansion device provided in the application embodiment is shown below. Figure 11 The logging data expansion device 600 includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, performs the logging data expansion method as described in the foregoing embodiments.

[0148] In one implementation, the logging data expansion device 600 includes a processor 601, at least one communication bus 602, a user interface 603, at least one external communication interface 604, and a memory 605. The communication bus 602 is configured to enable communication between these components. The user interface 603 may include a display screen, and the external communication interface 604 may include standard wired and wireless interfaces. The processor 601 is configured to execute a program for expanding logging data stored in the memory, to implement the steps in the logging data expansion method provided in the above embodiments.

[0149] The descriptions of the display device and storage medium embodiments above are similar to those of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the computer device and storage medium embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0150] It should be noted that the descriptions of the storage medium and device embodiments above are similar to those of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0151] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0152] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0154] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0155] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0156] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0157] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a controller to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0158] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for expanding well logging data, characterized in that, include: Obtain raw well logging data; New data conforming to the patterns of the original well logging data were obtained using the Monte Carlo random sampling method as supplementary data, specifically including: S1. Fit the relationship between the first parameter and the second parameter based on the statistical regularity of the measured values ​​of the first parameter and the second parameter in the original well logging data to obtain the fitting formula; S2. Substitute the measured value of the first parameter in the original well logging data into the fitting formula, calculate the fitting result of the second parameter, and calculate the standard deviation between the fitting result of the second parameter and the actual measured value. S3. Calculate the cumulative probability distribution of the first parameter in the original well logging data; S4. Generate random numbers based on the cumulative probability distribution of the first parameter; S5. Calculate the first extended value of the first parameter corresponding to the generated random number based on the cumulative probability distribution of the first parameter; S6. Obtain the fitted value of the second parameter based on the expanded value of the first parameter and the fitted relationship. S7. Calculate the second expanded value of the second parameter based on the standard deviation and the fitted value of the second parameter; The first extended value of the first parameter and the second extended value of the second parameter are respectively used as the extended data of the first parameter and the second parameter.

2. The expansion method according to claim 1, characterized in that, The step of calculating the standard deviation between the fitting result and the actual measured value based on the fitting relationship includes: For all sample points of the first parameter, calculate the corresponding fitted value of the second parameter according to the fitting relationship; Then calculate the standard deviation (std) of the difference between the true value of the second parameter and the calculated fitted value.

3. The expansion method according to claim 1, characterized in that, The step of generating random numbers based on the cumulative probability distribution of the first parameter specifically includes: Generate a random number that conforms to a uniform distribution within the range of 0 to 1.

4. The expansion method according to claim 1, characterized in that, The fitting relationship obtained in step S1 is a linear fitting relationship y=a*x+b, where x is the first parameter, y is the second parameter, and a and b are constant coefficients; The fitted value of the second parameter obtained in step S6 is: par2=a*par1+b, where par1 is the first expanded value of the first parameter and par2 is the fitted value of the second parameter. The second extended value of the second parameter calculated in step S7 is: par2'=par2+std*randn(1), where randn(1) represents a randomly generated value that conforms to a normal distribution with a mean of 0 and a variance of 1.

5. The expansion method according to any one of claims 1-4, characterized in that, The method of obtaining new data that conforms to the patterns of the original well logging data using Monte Carlo random sampling also includes: Repeat steps S4-S7 N times to obtain N sets of randomly simulated well logging data for the first parameter and the second parameter as supplementary data, where N is a natural number greater than zero.

6. The expansion method according to any one of claims 1-4, characterized in that, The first parameter and the second parameter are the porosity and clay content of the same target area, respectively.

7. A device for expanding well logging data, characterized in that, include: The acquisition module is used to acquire raw well logging data; An expansion module is used to obtain new data that conforms to the patterns of the original well logging data using the Monte Carlo random sampling method. The expansion module specifically includes: a fitting module, used to fit the relationship between the first parameter and the second parameter based on the statistical regularity of the measured values ​​of the first parameter and the second parameter in the original well logging data, to obtain a fitting formula; The standard deviation calculation module is used to substitute the measured value of the first parameter in the original well logging data into the fitting relationship, calculate the fitting result of the second parameter, and calculate the standard deviation between the fitting result of the second parameter and the actual measured value. The probability distribution module is used to statistically analyze the cumulative probability distribution of the first parameter in the original well logging data. The random number module is used to generate random numbers based on the cumulative probability distribution of the first parameter; The first parameter expansion module is used to calculate the first expanded value of the first parameter corresponding to the generated random number based on the cumulative probability distribution of the first parameter. The fitting value calculation module is used to obtain the fitting value of the second parameter based on the expanded value of the first parameter and the fitting relationship. The second parameter expansion module is used to calculate the second expanded value of the second parameter based on the standard deviation and the fitted value of the second parameter. Wherein, the first extended value of the first parameter and the second extended value of the second parameter are respectively used as the extended data of the first parameter and the second parameter.

8. A well logging data augmentation device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, performs the well logging data expansion method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the method for expanding logging data as described in any one of claims 1 to 6.

Images