Three-dimensional Spatial Expansion Modeling Method, Device, Equipment and Storage Medium for Logging Data

Abstract

This specification provides a method, apparatus, device, and storage medium for three-dimensional spatial expansion modeling of logging data. The method includes: establishing a wellbore model in a three-dimensional grid geological model using wellbore trajectory data; according to the spatial position relationship between the logging data and the wellbore model, storing different types of logging data within the same formation into different data subsets respectively to obtain multiple logging data subsets corresponding to each formation; determining the mean and standard deviation of the multiple logging data subsets corresponding to each formation; randomly generating different types of logging simulation data sets for each formation using the mean and standard deviation; performing smoothing and denoising processing on the different types of logging simulation data sets for each formation; and configuring the same type of logging simulation data sets after smoothing and denoising for each formation into the same three-dimensional grid geological model, thereby generating a three-dimensional geophysical logging model of this type. The embodiments of this specification can obtain a three-dimensional geophysical logging model with higher accuracy.

Description

Technical Field

[0001] This specification relates to the technical field of geophysical logging, and particularly to a method, device, equipment, and storage medium for three-dimensional spatial expansion modeling of logging data. Background Art

[0002] Intelligentization is an important development direction in drilling engineering. Intelligent drilling requires the drill string to have the ability of autonomous perception, decision-making, and control. Logging data is important perception data in drilling engineering. Establishing logging data with three-dimensional spatial distribution is crucial for realizing autonomous perception in drilling.

[0003] In the prior art, there are various logging numerical simulation methods, and different logging numerical simulation methods have different applicable conditions. Based on machine learning technology, the optimal algorithm can be automatically and optimally selected according to the characteristics of different logging numerical simulation methods to construct logging data with three-dimensional spatial distribution. However, the inventors of this application have found that these logging numerical simulation methods all perform three-dimensional spatial expansion of logging data through pure mathematical means, without considering the problem of interaction between logging data and three-dimensional strata. Therefore, the accuracy of the three-dimensional geophysical logging model constructed by the prior art is not high. Summary of the Invention

[0004] The purpose of the embodiments of this specification is to provide a method, device, equipment, and storage medium for three-dimensional spatial expansion modeling of logging data to obtain a three-dimensional geophysical logging model with higher accuracy.

[0005] To achieve the above object, on the one hand, the embodiments of this specification provide a method for three-dimensional spatial expansion modeling of logging data, including:

[0006] Establish a wellbore model in a three-dimensional grid geological model using wellbore trajectory data;

[0007] According to the spatial position relationship between logging data and the wellbore model, different types of logging data within the same formation are respectively stored in different data subsets to obtain multiple logging data subsets corresponding to each formation;

[0008] Determine the mean and standard deviation of multiple logging data subsets corresponding to each formation;

[0009] Use the mean and standard deviation of multiple logging data subsets corresponding to each formation to randomly generate different types of logging simulation data sets for each formation;

[0010] Perform smoothing and denoising processing on different types of logging simulation data sets for each formation;

[0011] Configure the same type of logging simulation data sets after smoothing and denoising for each formation into the same three-dimensional grid geological model, thereby generating a three-dimensional geophysical logging model of this type.

[0012] In the logging data three-dimensional space expansion modeling method according to the embodiments of the present specification, before establishing a wellbore model in a three-dimensional gridded geological model using wellbore trajectory data, the following steps are further included:

[0013] Dividing strata based on formation lithology data and establishing a three-dimensional geological model;

[0014] Performing three-dimensional gridding on the three-dimensional geological model to generate a three-dimensional gridded geological model.

[0015] In the logging data three-dimensional space expansion modeling method according to the embodiments of the present specification, determining the mean and standard deviation of multiple logging data subsets corresponding to each stratum includes:

[0016] Using the normal distribution function to fit multiple logging data subsets corresponding to each stratum respectively to obtain the mean and standard deviation of multiple logging data subsets corresponding to each stratum.

[0017] In the logging data three-dimensional space expansion modeling method according to the embodiments of the present specification, using the mean and standard deviation of multiple logging data subsets corresponding to each stratum to randomly generate different types of logging simulation data sets for each stratum includes:

[0018] Taking the mean of multiple logging data subsets corresponding to each stratum as the reference value and taking the standard deviation of multiple logging data subsets corresponding to each stratum as the fluctuation range, and randomly generating different types of logging simulation data sets for each stratum correspondingly.

[0019] In the logging data three-dimensional space expansion modeling method according to the embodiments of the present specification, performing smooth denoising processing on different types of logging simulation data sets for each stratum includes:

[0020] Performing smooth denoising processing on different types of logging simulation data sets for each stratum based on the SG filtering method.

[0021] In the logging data three-dimensional space expansion modeling method according to the embodiments of the present specification, before configuring the same type of logging simulation data sets after smooth denoising of each stratum into the same three-dimensional gridded geological model, the following steps are further included:

[0022] Based on a pre-trained machine learning model, performing lithology identification on the logging data, the logging simulation data sets, and the different types of logging simulation data sets after smooth denoising respectively to verify whether the data accuracy of the different types of logging simulation data sets after smooth denoising is greater than the data accuracy of the logging data and the logging simulation data sets;

[0023] If the data accuracy of the different types of well logging simulation data sets after smooth denoising is greater than that of the well logging data and the well logging simulation data sets, it is allowed to configure the same type of well logging simulation data sets after smooth denoising for each formation into the same three-dimensional grid geological model.

[0024] On the other hand, the embodiments of this specification also provide a device for three-dimensional spatial expansion modeling of well logging data, including:

[0025] A building module, configured to build a wellbore model in the three-dimensional grid geological model by using wellbore trajectory data;

[0026] An acquisition module, configured to deposit different types of well logging data within the same formation into different data subsets respectively according to the spatial position relationship between the well logging data and the wellbore model, and obtain multiple well logging data subsets corresponding to each formation;

[0027] A determination module, configured to determine the mean and standard deviation of the multiple well logging data subsets corresponding to each formation;

[0028] A generation module, configured to randomly generate different types of well logging simulation data sets for each formation by using the mean and standard deviation of the multiple well logging data subsets corresponding to each formation;

[0029] A denoising module, configured to perform smooth denoising processing on different types of well logging simulation data sets for each formation;

[0030] A configuration module, configured to configure the same type of well logging simulation data sets after smooth denoising for each formation into the same three-dimensional grid geological model, so as to generate a three-dimensional geophysical well logging model of this type.

[0031] On the other hand, the embodiments of this specification also provide a computer device, including a memory, a processor, and a computer program stored on the memory. When the computer program is run by the processor, it executes the instructions of the above method.

[0032] On the other hand, the embodiments of this specification also provide a computer storage medium, on which a computer program is stored. When the computer program is run by the processor of a computer device, it executes the instructions of the above method.

[0033] On the other hand, the embodiments of this specification also provide a computer program product, which includes a computer program. When the computer program is run by the processor of a computer device, it executes the instructions of the above method.

[0034] As can be seen from the technical solutions provided in the embodiments of this specification above, in the embodiments of this specification, on the basis of establishing a wellbore model in a three-dimensional grid geological model using wellbore trajectory data, according to the spatial position relationship between well logging data and the wellbore model, different types of well logging data within the same formation can be respectively stored into different data subsets to obtain multiple well logging data subsets corresponding to each formation; then, using the mean and standard deviation of the multiple well logging data subsets corresponding to each formation, different types of well logging simulation data sets for each formation are randomly generated, and the different types of well logging simulation data sets for each formation are subjected to smoothing and denoising processing; then, the same type of well logging simulation data sets after smoothing and denoising for each formation are configured into the same three-dimensional grid geological model to generate a three-dimensional geophysical well logging model of this type, thereby realizing the generation of different types of three-dimensional geophysical well logging models on the basis of considering the interaction between well logging data and three-dimensional formations, and improving the model accuracy of the three-dimensional geophysical well logging model. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0036] Figure 1 shows the flowchart of the three-dimensional spatial expansion modeling method for well logging data in some embodiments of this specification;

[0037] Figure 2 shows the schematic diagram of a three-dimensional grid geological model in an embodiment of this specification (without a wellbore model established);

[0038] Figure 3 shows the schematic diagram of a three-dimensional grid geological model in an embodiment of this specification (with a wellbore model established);

[0039] Figure 4a shows the comparison schematic diagram of the original data SP and the random SP in an embodiment of this specification;

[0040] Figure 4b shows the comparison schematic diagram of the original data RT and the random RT in an embodiment of this specification;

[0041] Figure 4c shows the comparison schematic diagram of the original data PE and the random PE in an embodiment of this specification;

[0042] Figure 4d shows the comparison schematic diagram of the original data GR and the random GR in an embodiment of this specification;

[0043] Figure 4e Shows a comparison schematic diagram of the original data DEN and the random DEN in an embodiment of this specification;

[0044] Figure 4f Shows a comparison schematic diagram of the original data CNL and the random CNL in an embodiment of this specification;

[0045] Figure 4g Shows a comparison schematic diagram of the original data CAL and the random CAL in an embodiment of this specification;

[0046] Figure 4h Shows a comparison schematic diagram of the original data AC and the random AC in an embodiment of this specification;

[0047] Figure 5a Shows a comparison schematic diagram of the original data SP and the smooth SP in an embodiment of this specification;

[0048] Figure 5b Shows a comparison schematic diagram of the original data RT and the smooth RT in an embodiment of this specification;

[0049] Figure 5c Shows a comparison schematic diagram of the original data PE and the smooth PE in an embodiment of this specification;

[0050] Figure 5d Shows a comparison schematic diagram of the original data GR and the smooth GR in an embodiment of this specification;

[0051] Figure 5e Shows a comparison schematic diagram of the original data DEN and the smooth DEN in an embodiment of this specification;

[0052] Figure 5f Shows a comparison schematic diagram of the original data CNL and the smooth CNL in an embodiment of this specification;

[0053] Figure 5g Shows a comparison schematic diagram of the original data CAL and the smooth CAL in an embodiment of this specification;

[0054] Figure 5h Shows a comparison schematic diagram of the original data AC and the smooth AC in an embodiment of this specification;

[0055] Figure 6 Shows a comparison schematic diagram of the lithology results predicted based on different data and the in-situ formation lithology in some embodiments of this specification;

[0056] Figure 7a Shows a schematic diagram of the three-dimensional geophysical SP logging model obtained in an embodiment of this specification;

[0057] Figure 7b Shows a schematic diagram of a three-dimensional geophysical RT logging model obtained in an embodiment of this specification;

[0058] Figure 7c Shows a schematic diagram of a three-dimensional geophysical PE logging model obtained in an embodiment of this specification;

[0059] Figure 7d Shows a schematic diagram of a three-dimensional geophysical GR logging model obtained in an embodiment of this specification;

[0060] Figure 7e Shows a schematic diagram of a three-dimensional geophysical DEN logging model obtained in an embodiment of this specification;

[0061] Figure 7f Shows a schematic diagram of a three-dimensional geophysical CNL logging model obtained in an embodiment of this specification;

[0062] Figure 7g Shows a schematic diagram of a three-dimensional geophysical CAL logging model obtained in an embodiment of this specification;

[0063] Figure 7h Shows a schematic diagram of a three-dimensional geophysical AC logging model obtained in an embodiment of this specification;

[0064] Figure 8 Shows a structural block diagram of a logging data three-dimensional space expansion modeling device in some embodiments of this specification;

[0065] Figure 9 Shows a structural block diagram of a computer device in some embodiments of this specification.

[0066]

Explanation of Reference Numerals

[0067] 81. Establishment module;

[0068] 82. Acquisition module;

[0069] 83. Determination module;

[0070] 84. Generation module;

[0071] 85. Denoising module;

[0072] 86. Configuration module;

[0073] 902. Computer device;

[0074] 904. Processor;

[0075] 906. Memory;

[0076] 908. Driving mechanism;

[0077] 910. Input / Output Interface;

[0078] 912. Input Device;

[0079] 914. Output Device;

[0080] 916. Presentation Device;

[0081] 918. Graphical User Interface;

[0082] 920. Network Interface;

[0083] 922. Communication Link;

[0084] 924. Communication Bus. Detailed Implementation Manner

[0085] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0086] In view of the problem of low accuracy of the three-dimensional geophysical logging model constructed based on the prior art, the embodiments of this specification provide an improved three-dimensional spatial expansion modeling scheme for logging data. Referring to Figure 1 as shown, the embodiments of this specification provide a method for three-dimensional spatial expansion modeling of logging data, which may include the following steps:

[0087] Step 101: Establish a wellbore model in a three-dimensional gridded geological model using wellbore trajectory data.

[0088] Before establishing a wellbore model in a three-dimensional gridded geological model using wellbore trajectory data, the strata can be divided and a three-dimensional geological model can be established based on formation lithology data; among them, the formation lithology data can be obtained based on logging data, core sample analysis data, etc.; then, by performing three-dimensional grid division on the three-dimensional geological model, a three-dimensional gridded geological model can be generated. The three-dimensional gridded geological model can represent the lithology distribution of the strata in a three-dimensional grid. For example, in an exemplary embodiment, the three-dimensional gridded geological model can be as Figure 2 shown.

[0089] The wellbore trajectory data includes the path trajectory and spatial position distribution of the wellbore. Therefore, a wellbore model can be established in the three-dimensional gridded geological model based on the wellbore trajectory data. For example, in an exemplary embodiment, based on the wellbore trajectory data, it can be in Figure 2A wellbore model is established in the three-dimensional gridded geological model shown, so as to form a three-dimensional gridded geological model with a wellbore model as shown in Figure 3 the three-dimensional gridded geological model with a wellbore model shown.

[0090] Step 102: According to the spatial position relationship between the logging data and the wellbore model, different types of logging data within the same formation are respectively stored in different data subsets, and multiple logging data subsets corresponding to each formation are obtained.

[0091] The logging data in the embodiments of this specification may include multiple different types of logging data for the same work area. For example, in some embodiments, the logging data may include spontaneous potential (SP) logging data, true formation resistivity (RT) logging data, photoelectric absorption cross-section index (PE) logging data, natural gamma (GR) logging data, density (DEN) logging data, compensated neutron (CNL) logging data, caliper (CAL) logging data, and acoustic travel time (AC) logging data, etc. for the same work area.

[0092] Assume that the wellbore model corresponds to three formations L1, L2, and L3 in sequence in the depth direction. If the logging data adopts the above-mentioned SP logging data, RT logging data, PE logging data, GR logging data, DEN logging data, CNL logging data, CAL logging data, and AC logging data; according to the spatial position relationship between the logging data and the wellbore model, there are:

[0093] The logging data subset corresponding to formation L1 includes:

[0094] the first subset of SP logging data, the first subset of RT logging data, the first subset of PE logging data, the first subset of GR logging data, the first subset of DEN logging data, the first subset of CNL logging data, the first subset of CAL logging data, and the first subset of AC logging data;

[0095] The logging data subset corresponding to formation L2 includes:

[0096] the second subset of SP logging data, the second subset of RT logging data, the second subset of PE logging data, the second subset of GR logging data, the second subset of DEN logging data, the second subset of CNL logging data, the second subset of CAL logging data, and the second subset of AC logging data;

[0097] The logging data subset corresponding to formation L3 includes:

[0098] the third subset of SP logging data, the third subset of RT logging data, the third subset of PE logging data, the third subset of GR logging data, the third subset of DEN logging data, the third subset of CNL logging data, the third subset of CAL logging data, and the third subset of AC logging data.

[0099] Step 103: Determine the mean and standard deviation of multiple subsets of logging data corresponding to each formation.

[0100] In the embodiments of this specification, it is assumed that the logging response characteristic data of formations with the same lithology conform to the same normal distribution. Therefore, determining the mean and standard deviation of multiple subsets of logging data corresponding to each formation may include: using the normal distribution function to fit multiple subsets of logging data corresponding to each formation respectively to obtain the mean and standard deviation of multiple subsets of logging data corresponding to each formation. Among them, the mean refers to the sum of all data points in the same subset of logging data divided by the number of data points, which represents the average size of the data set; the standard deviation represents the degree of dispersion of the data points in the same subset of logging data.

[0101] For example, taking the first subset of SP logging data corresponding to the above-mentioned formation L1 as an example, the mean and standard deviation of all data points in the first subset of SP logging data can be calculated (i.e., the mean and standard deviation of the first subset of SP logging data). Similarly, the mean and standard deviation of the remaining subsets of logging data in the above-mentioned formation L1 can be calculated respectively. In this way, the mean and standard deviation of each subset of logging data in formation L1 can be obtained. Similarly, the mean and standard deviation of each subset of logging data in formation L2 and the mean and standard deviation of each subset of logging data in formation L3 can be calculated.

[0102] Step 104: Use the mean and standard deviation of multiple subsets of logging data corresponding to each formation to randomly generate different types of logging simulation data sets for each formation.

[0103] In some embodiments, using the mean and standard deviation of multiple subsets of logging data corresponding to each formation to randomly generate different types of logging simulation data sets for each formation may include: taking the mean of multiple subsets of logging data corresponding to each formation as the reference value and taking the standard deviation of multiple subsets of logging data corresponding to each formation as the fluctuation range to randomly generate different types of logging simulation data sets for each formation.

[0104] For example, taking the first subset of SP logging data corresponding to the above-mentioned formation L1 as an example, assuming the mean of the first subset of SP logging data is and the variance is σ, then random values can be taken within the value range and accordingly, random values are assigned to the part of formation L1 except the wellbore model, so as to form the SP logging simulation data set of formation L1.

[0105] Similarly, the SP logging simulation data set, RT logging simulation data set, PE logging simulation data set, GR logging simulation data set, DEN logging simulation data set, CNL logging simulation data set, CAL logging simulation data set and AC logging simulation data set of formation L1 can be formed; thus, different types of logging simulation data sets of formation L1 can be obtained. Different types of logging simulation data sets of formation L2 and different types of logging simulation data sets of formation L3 can be obtained.

[0106] Step 105: Perform smoothing and denoising processing on different types of logging simulation data sets of each formation.

[0107] Since the randomly generated logging simulation data sets have large fluctuations and more noise, it is necessary to perform smoothing and denoising on the different types of logging simulation data sets for each formation to make the logging simulation data sets closer to the original logging data.

[0108] For example, in some embodiments, different types of logging simulation data sets for each formation can be smoothed and denoised based on the SG (Savitzky Golay Filter) filtering method. The SG filtering method is a filtering method based on local polynomial least squares fitting in the time domain. The biggest feature of this filter is that it can ensure that the shape and width of the signal remain unchanged while filtering out noise; therefore, when the SG filtering method is applied to the randomly generated logging simulation data set for smooth denoising, the overall fluctuation of the data after smooth denoising is reduced and is closer to the original logging data.

[0109] In order to intuitively understand the difference between the logging simulation data set and the original logging data, Figures 4a to 4h In the exemplary embodiment shown, original data SP and random SP (i.e., SP well logging original data and SP well logging simulation data), original data RT and random RT (i.e., RT well logging original data and RT well logging simulation data), original data PE and random PE (i.e., PE well logging original data and PE well logging simulation data), original data GR and random GR (i.e., GR well logging original data and GR well logging simulation data), original data DEN and random DEN (i.e., DEN well logging original data and DEN well logging simulation data), original data CNL and random CNL (i.e., CNL well logging original data and CNL well logging simulation data), original data CAL and random CAL (i.e., CAL well logging original data and CAL well logging simulation data), and original data AC and random AC (i.e., AC well logging original data and AC well logging simulation data) are respectively shown for comparison. Figures 4a to 4h It can be seen that compared with the original logging data (i.e. Figures 4a to 4h The solid line shows that the logging simulation data has large fluctuations and more noise. Figures 4a to 4h In the figure, the horizontal axis DEPTH represents the depth.

[0110] In Figures 5a to 5h the exemplary embodiment shown, the original data SP and the smoothed SP (i.e., the original SP log data and the smoothed and denoised SP log simulation data), the original data RT and the smoothed RT (i.e., the original RT log data and the smoothed and denoised RT log simulation data), the original data PE and the smoothed PE (i.e., the original PE log data and the smoothed and denoised PE log simulation data), the original data GR and the smoothed GR (i.e., the original GR log data and the smoothed and denoised GR log simulation data), the original data DEN and the smoothed DEN (i.e., the original DEN log data and the smoothed and denoised DEN log simulation data), the original data CNL and the smoothed CNL (i.e., the original CNL log data and the smoothed and denoised CNL log simulation data), the original data CAL and the smoothed CAL (i.e., the original CAL log data and the smoothed and denoised CAL log simulation data), and the original data AC and the smoothed AC (i.e., the original AC log data and the smoothed and denoised AC log simulation data) are respectively shown in a comparison schematic diagram. In Figures 5a to 5h , the abscissa DEPTH represents depth. By Figures 5a to 5h corresponding and Figures 4a to 4h comparing with Figures 4a to 4h it can be found that: compared with the log simulation data without smoothing and denoising in Figures 4a to 4h , the fluctuation change of the log simulation data after smoothing and denoising is smaller and closer to the original log data, which is beneficial to obtaining a more accurate three-dimensional geophysical log model.

[0111] Step 106: Configure the log simulation data sets of the same type after smoothing and denoising for each formation into the same three-dimensional grid geological model, so as to generate the three-dimensional geophysical log model of this type.

[0112] The three-dimensional grid geological model can be copied into N copies according to the type number N of the log simulation data sets; the log simulation data of the same type after smoothing and denoising for each formation are configured into the same three-dimensional grid geological model to form the three-dimensional geophysical log model of this type.

[0113] For example, taking the eight log simulation data sets after smoothing and denoising in Figures 5a to 5h as an example, the three-dimensional grid geological model can be copied into eight copies (assuming the numbers corresponding to the eight three-dimensional grid geological models are No. 1 to No. 8), then:

[0114] Input the SP log simulation data after smoothing and denoising for each formation into the No. 1 three-dimensional grid geological model, and the three-dimensional geophysical log model as shown in Figure 7h can be obtained;

[0115] Input the PE log simulation data after smoothing and denoising for each formation into the No. 2 three-dimensional grid geological model, and the three-dimensional geophysical log model as shown inFigure 7f The three-dimensional geophysical logging model shown;

[0116] Inputting the DEN logging simulation data after smoothing and denoising each formation into the No. 3 three-dimensional gridded geological model, the three-dimensional geophysical logging model as shown in Figure 7d can be obtained;

[0117] Inputting the CAL logging simulation data after smoothing and denoising each formation into the No. 4 three-dimensional gridded geological model, the three-dimensional geophysical logging model as shown in Figure 7b can be obtained;

[0118] Inputting the RT logging simulation data after smoothing and denoising each formation into the No. 5 three-dimensional gridded geological model, the three-dimensional geophysical logging model as shown in Figure 7g can be obtained;

[0119] Inputting the GR logging simulation data after smoothing and denoising each formation into the No. 6 three-dimensional gridded geological model, the three-dimensional geophysical logging model as shown in Figure 7e can be obtained;

[0120] Inputting the CNL logging simulation data after smoothing and denoising each formation into the No. 7 three-dimensional gridded geological model, the three-dimensional geophysical logging model as shown in Figure 7c can be obtained;

[0121] Inputting the AC logging simulation data after smoothing and denoising each formation into the No. 8 three-dimensional gridded geological model, the three-dimensional geophysical logging model as shown in Figure 7a can be obtained.

[0122] In Figures 7a to 7h , the abscissa DEPTH represents the depth.

[0123] In some other embodiments, before configuring the same type of logging simulation data sets after smoothing and denoising each formation into the same three-dimensional gridded geological model, the following steps may further be included:

[0124] Based on a pre-trained machine learning model (such as a random forest model, etc.), performing lithology identification on the logging data, the logging simulation data sets, and the different types of logging simulation data sets after smoothing and denoising respectively, to verify whether the data accuracy of the different types of logging simulation data sets after smoothing and denoising is greater than the data accuracy of the logging data and the logging simulation data sets;

[0125] If the data accuracy of the different types of well logging simulation data sets after smooth denoising is greater than that of the well logging data and the well logging simulation data sets, then it is allowed to configure the same type of well logging simulation data sets after smooth denoising for each formation into the same three-dimensional grid geological model. If the data accuracy of the different types of well logging simulation data sets after smooth denoising is not greater than that of the well logging data and the well logging simulation data sets, then the mean and standard deviation of multiple well logging data subsets corresponding to each formation can be used to randomly generate different types of well logging simulation data sets for each formation again, and reprocess accordingly. In this way, it is beneficial to further ensure that the obtained three-dimensional grid geological model is accurate.

[0126] For example, in Figure 6 the illustrated embodiment, a result comparison schematic diagram of real data, original data prediction (i.e., lithology prediction result based on original well logging data), random data prediction (i.e., lithology prediction result based on well logging simulation data sets), and smooth data prediction (i.e., lithology prediction result of well logging simulation data sets after smooth denoising) is shown. Figure 6 In the illustrated embodiment, the lithology prediction accuracy rates based on each data are shown in Table 1 below.

[0127] Table 1

[0128] Original data lithology prediction accuracy Random data lithology prediction accuracy Smoothing data lithology prediction accuracy 90.76％ 73.96％ 85.07％

[0129] It can be seen from Table 1 that the lithology prediction accuracy rate based on the well logging simulation data sets reaches 73.96%, and most lithology characteristics can be identified; while the lithology prediction accuracy rate based on the well logging simulation data sets after smooth denoising is increased to 85.07%, which is roughly close to the lithology prediction accuracy rate based on the original well logging data (90.76%), thus verifying the feasibility of the embodiments of this specification.

[0130] In the embodiments of this specification, on the basis of establishing a wellbore model in a three-dimensional grid geological model using wellbore trajectory data, different types of well logging data within the same formation can be separately stored into different data subsets according to the spatial position relationship between the well logging data and the wellbore model, to obtain multiple well logging data subsets corresponding to each formation; then the mean and standard deviation of multiple well logging data subsets corresponding to each formation are used to randomly generate different types of well logging simulation data sets for each formation correspondingly, and smooth denoising processing is performed on the different types of well logging simulation data sets for each formation; then the same type of well logging simulation data sets after smooth denoising for each formation are configured into the same three-dimensional grid geological model to generate a three-dimensional geophysical well logging model of this type, so as to realize the generation of different types of three-dimensional geophysical well logging models on the basis of considering the interaction between well logging data and three-dimensional formations, and improve the model accuracy of the three-dimensional geophysical well logging models.

[0131] Although the process flow described above includes multiple operations that occur in a specific order, it should be clearly understood that these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel (e.g., using parallel processors or multi-threaded environments).

[0132] Corresponding to the above-described method for three-dimensional spatial expansion modeling of logging data, an embodiment of this specification also provides a device for three-dimensional spatial expansion modeling of logging data. Refer to Figure 8 As shown, the device for three-dimensional spatial expansion modeling of logging data may include:

[0133] A building module 81, which can be used to build a wellbore model in a three-dimensional grid geological model using wellbore trajectory data;

[0134] An acquisition module 82, which can be used to deposit different types of logging data within the same formation into different data subsets respectively according to the spatial position relationship between the logging data and the wellbore model, and obtain multiple logging data subsets corresponding to each formation;

[0135] A determination module 83, which can be used to determine the mean and standard deviation of multiple logging data subsets corresponding to each formation;

[0136] A generation module 84, which is used to randomly generate different types of logging simulation data sets for each formation by using the mean and standard deviation of multiple logging data subsets corresponding to each formation;

[0137] A denoising module 85, which can be used to perform smoothing denoising processing on different types of logging simulation data sets for each formation;

[0138] A configuration module 86, which can be used to configure the same type of logging simulation data sets after smoothing denoising for each formation into the same three-dimensional grid geological model, so as to generate a three-dimensional geophysical logging model of this type.

[0139] In the device for three-dimensional spatial expansion modeling of logging data in some embodiments, the above building module can also be used to: before building the wellbore model in the three-dimensional grid geological model using the wellbore trajectory data, divide the formation based on formation lithology data and build a three-dimensional geological model; perform three-dimensional meshing on the three-dimensional geological model to generate a three-dimensional grid geological model.

[0140] In the device for three-dimensional spatial expansion modeling of logging data in some embodiments, the determination of the mean and standard deviation of multiple logging data subsets corresponding to each formation includes:

[0141] Using the normal distribution function to fit multiple logging data subsets corresponding to each formation respectively, and obtaining the mean and standard deviation of multiple logging data subsets corresponding to each formation.

[0142] In the logging data three-dimensional space expansion modeling device of some embodiments, the method of correspondingly and randomly generating different types of logging simulation data sets for each formation by using the mean and standard deviation of multiple logging data subsets corresponding to each formation includes:

[0143] Taking the mean of multiple logging data subsets corresponding to each formation as the reference value, and taking the standard deviation of multiple logging data subsets corresponding to each formation as the fluctuation range, correspondingly and randomly generating different types of logging simulation data sets for each formation.

[0144] In the logging data three-dimensional space expansion modeling device of some embodiments, the method of performing smoothing and denoising processing on different types of logging simulation data sets for each formation includes:

[0145] Performing smoothing and denoising processing on different types of logging simulation data sets for each formation based on the SG filtering method.

[0146] In the logging data three-dimensional space expansion modeling device of some embodiments, the logging data three-dimensional space expansion modeling device may further include a verification module, which can be used for:

[0147] Before configuring the same type of logging simulation data sets after smoothing and denoising of each formation into the same three-dimensional grid geological model, based on a pre-trained machine learning model, performing lithology identification on the logging data, the logging simulation data sets, and the different types of logging simulation data sets after smoothing and denoising, so as to verify whether the data accuracy of the different types of logging simulation data sets after smoothing and denoising is greater than the data accuracy of the logging data and the logging simulation data sets; if the data accuracy of the different types of logging simulation data sets after smoothing and denoising is greater than the data accuracy of the logging data and the logging simulation data sets, then allow the same type of logging simulation data sets after smoothing and denoising of each formation to be configured into the same three-dimensional grid geological model.

[0148] For the convenience of description, when describing the above device, various units are described separately according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0149] It should be noted that in the embodiments of this specification, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are all information and data that have been authorized and agreed by the user and fully authorized by all parties.

[0150] The embodiments of this specification also provide a computer device. As Figure 9As shown, in some embodiments of this specification, the computer device 902 may include one or more processors 904, such as one or more central processing units (CPUs) or graphics processing units (GPUs), and each processing unit may implement one or more hardware threads. The computer device 902 may also include any memory 906 for storing any kind of information such as code, settings, data, etc. In a specific embodiment, a computer program stored on the memory 906 and executable on the processor 904, when run by the processor 904, may execute the instructions of the three-dimensional space expansion modeling method for logging data described in any of the above embodiments. Non-limitingly, for example, the memory 906 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical discs, etc. More generally, any memory may store information using any technology. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 902. In one case, when the processor 904 executes the associated instructions stored in any memory or combination of memories, the computer device 902 may perform any operation of the associated instructions. The computer device 902 also includes one or more drive mechanisms 908 for interacting with any memory, such as a hard disk drive mechanism, an optical disc drive mechanism, etc.

[0151] The computer device 902 may also include an input / output interface 910 (I / O) for receiving various inputs (via the input device 912) and for providing various outputs (via the output device 914). A specific output mechanism may include a presentation device 916 and an associated graphical user interface 918 (GUI). In other embodiments, the input / output interface 910 (I / O), the input device 912, and the output device 914 may not be included, and it may only be a computer device in a network. The computer device 902 may also include one or more network interfaces 920 for exchanging data with other devices via one or more communication links 922. One or more communication buses 924 couple the components described above together.

[0152] The communication link 922 may be implemented in any way, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 922 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0153] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), computer-readable storage media, and computer program products according to some embodiments of the present specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processors to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processors produce a means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more of the blocks.

[0154] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processors to operate in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more of the blocks.

[0155] These computer program instructions can also be loaded onto a computer or other programmable data processors, such that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more of the blocks.

[0156] In a typical configuration, a computer device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0157] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0158] A computer-readable medium includes permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computer device. As defined in this specification, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0159] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0160] The embodiments of this specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The embodiments of this specification can also be practiced in a distributed computing environment where tasks are performed by remote processors connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0161] It should also be understood that in the embodiments of this specification, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0162] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the description of the method embodiment.

[0163] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0164] The above are only the embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A three-dimensional spatial expansion modeling method for logging data, characterized in that, Including: Establishing a wellbore model in a three-dimensional gridded geological model using wellbore trajectory data; According to the spatial position relationship between logging data and the wellbore model, storing different types of logging data within the same formation into different data subsets respectively, to obtain multiple logging data subsets corresponding to each formation; Determining the mean and standard deviation of multiple logging data subsets corresponding to each formation, specifically including: using the normal distribution function to fit multiple logging data subsets corresponding to each formation respectively, to obtain the mean and standard deviation of multiple logging data subsets corresponding to each formation; Using the mean and standard deviation of multiple logging data subsets corresponding to each formation, randomly generating different types of logging simulation data sets for each formation correspondingly, specifically including: taking the mean of multiple logging data subsets corresponding to each formation as the reference value, and taking the standard deviation of multiple logging data subsets corresponding to each formation as the fluctuation range, randomly generating different types of logging simulation data sets for each formation correspondingly; Performing a smoothing and denoising process on different types of logging simulation data sets for each formation; Configuring the same type of logging simulation data sets after smoothing and denoising for each formation into the same three-dimensional gridded geological model, thereby generating a three-dimensional geophysical logging model of this type.

2. The 3D spatial expansion modeling method for logging data according to claim 1, characterized in that Before the step of establishing a wellbore model in a three-dimensional gridded geological model using wellbore trajectory data, it further includes: Dividing formations based on formation lithology data and establishing a three-dimensional geological model; Performing three-dimensional gridding on the three-dimensional geological model to generate a three-dimensional gridded geological model.

3. The 3D spatial extension modeling method for logging data according to claim 1, characterized in that The step of performing a smoothing and denoising process on different types of logging simulation data sets for each formation includes: Performing a smoothing and denoising process on different types of logging simulation data sets for each formation based on the SG filtering method.

4. The 3D spatial expansion modeling method for logging data according to claim 1, wherein, Before the step of configuring the same type of logging simulation data sets after smoothing and denoising for each formation into the same three-dimensional gridded geological model, it further includes: Based on a pre-trained machine learning model, respectively performing lithology identification on the logging data, the logging simulation data sets, and the different types of logging simulation data sets after smoothing and denoising, to verify whether the data accuracy of the different types of logging simulation data sets after smoothing and denoising is greater than the data accuracy of the logging data and the logging simulation data sets; If the data accuracy of the different types of logging simulation data sets after smoothing and denoising is greater than the data accuracy of the logging data and the logging simulation data sets, then allowing the same type of logging simulation data sets after smoothing and denoising for each formation to be configured into the same three-dimensional gridded geological model.

5. A three-dimensional spatial expansion modeling device for logging data, characterized in that, Including: A establishing module, for establishing a wellbore model in a three-dimensional gridded geological model using wellbore trajectory data; An obtaining module, for according to the spatial position relationship between logging data and the wellbore model, storing different types of logging data within the same formation into different data subsets respectively, to obtain multiple logging data subsets corresponding to each formation; A determining module, for determining the mean and standard deviation of multiple logging data subsets corresponding to each formation, specifically including: using the normal distribution function to fit multiple logging data subsets corresponding to each formation respectively, to obtain the mean and standard deviation of multiple logging data subsets corresponding to each formation; A generation module, configured to randomly generate different types of well logging simulation data sets for each formation by using the mean and standard deviation of multiple subsets of well logging data corresponding to each formation, specifically including: using the mean of multiple subsets of well logging data corresponding to each formation as a reference value, and using the standard deviation of multiple subsets of well logging data corresponding to each formation as a fluctuation range, to randomly generate different types of well logging simulation data sets for each formation; A denoising module, configured to perform smooth denoising processing on different types of well logging simulation data sets for each formation; An arrangement module, configured to configure the same type of well logging simulation data sets after smooth denoising of each formation into the same three-dimensional grid geological model, so as to generate a three-dimensional geophysical well logging model of this type.

6. A computer device, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, When the computer program is run by the processor, it executes the instructions of the method according to any one of claims 1-4.

7. A computer storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor of the computer device, it executes the instructions of the method according to any one of claims 1-4.

8. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is run by the processor, it executes the instructions of the method according to any one of claims 1-4.

Images