Lamellar shale free oil content prediction method, device, equipment and storage medium

Abstract

The application provides a method, device and equipment for predicting free oil content of laminated shale and a storage medium, and relates to the technical field of oil geological exploration. The method comprises the following steps: acquiring logging data of a target interval of laminated shale collected by a logging instrument, and acquiring a same-depth core image corresponding to the target interval. The laminated configuration structure of the target interval is determined based on the same-depth core image, and the thickness proportion of the shale interval corresponding to the laminated configuration structure in the target interval is calculated. Then, the logging data and the thickness proportion are input into a preset shale free oil content prediction model to determine the free oil content prediction result of the target interval generated by the preset shale free oil content prediction model. The method can improve the accuracy of the free oil content prediction result.

Description

Technical Field

[0001] This application relates to the field of petroleum geological exploration technology, and in particular to a method, apparatus, equipment and storage medium for predicting the free oil volume of layered shale. Background Technology

[0002] Laminated shale is a type of shale with thin, layered structures ranging from millimeters to micrometers, composed of alternating layers of different mineral components. Laminated shale is an important reservoir type for unconventional oil and gas resources such as shale oil. Free oil, being the most readily exploitable resource in shale oil production in the short term, can be identified by predicting its content, thus pinpointing high-yield oil-producing areas within laminated shale.

[0003] Existing technologies employ statistical methods to fit linear or nonlinear relationships between well logging data and laboratory-measured free oil volume in laminated shale. With the development of artificial intelligence, existing technologies have incorporated machine learning algorithms such as support vector machines, random forests, and neural networks. These algorithms, while assuming the laminated shale to be a homogeneous whole, use machine learning to uncover the mapping relationship between well logging data and laboratory-measured free oil volume.

[0004] However, laminated shale actually has significant heterogeneity. Existing technologies do not take into account the heterogeneity of the microstructure of laminated shale, resulting in a relatively large deviation in the prediction of free oil volume. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and storage medium for predicting the free oil volume in layered shale, in order to solve the technical problem of inaccurate prediction results of free oil volume in the prior art.

[0006] In a first aspect, this application provides a method for predicting the free oil content in layered shale, including:

[0007] The method involves acquiring logging data of a target segment of laminated shale collected by a logging instrument, and acquiring a core image of the same depth corresponding to the target segment; wherein the logging data is used to quantify the laminated structural characteristics of the target segment, and the core image of the same depth represents a core image obtained based on the target segment using drilling coring technology.

[0008] Based on the core images at the same depth, the lamellar configuration structure of the target layer is determined; the thickness percentage of the shale layer corresponding to the lamellar configuration structure in the target layer is calculated.

[0009] The well logging data and the thickness percentage are input into a preset shale free oil volume prediction model to determine the free oil volume prediction result of the target layer generated by the preset shale free oil volume prediction model.

[0010] In one possible design, the lamellar configuration structure includes a source-source brittle lamellar structure and a source-reservoir symbiotic lamellar structure; the source-source brittle lamellar structure indicates that the source rock and reservoir rock included in the lamellar shale are located in different lamellar layers, and the lamellar layers containing the source rock and the reservoir rock are alternately interbedded; the source-reservoir symbiotic lamellar structure indicates that the source rock and the reservoir rock are mixed within the same lamellar layer;

[0011] Calculating the thickness percentage of the shale segment corresponding to the lamellar configuration structure within the target segment includes:

[0012] Determine the first thickness of the shale segment corresponding to the adjacent source brittle lamellar structure, the second thickness of the shale segment corresponding to the source-reservoir symbiotic lamellar structure, and the total thickness of the target segment in the direction perpendicular to the lamellar structure;

[0013] The ratio of the first thickness to the total thickness is determined as the first thickness percentage of the shale segment corresponding to the adjacent source brittle lamellar structure in the target segment; the ratio of the second thickness to the total thickness is determined as the second thickness percentage of the shale segment corresponding to the source-reservoir symbiotic lamellar structure in the target segment.

[0014] In one possible design, the preset shale free oil quantity prediction model includes a first free oil quantity prediction sub-model and a second free oil quantity prediction sub-model; the first free oil quantity prediction sub-model is used to predict the free oil quantity of the shale segment corresponding to the adjacent source brittle lamellar structure, and the second free oil quantity prediction sub-model is used to predict the free oil quantity of the shale segment corresponding to the source-reservoir symbiotic lamellar structure.

[0015] The well logging data and the thickness percentage are input into a preset shale free oil quantity prediction model, including:

[0016] The well logging data and the first thickness ratio are input into the first free oil volume prediction sub-model;

[0017] The well logging data and the second thickness percentage are input into the second free oil volume prediction sub-model.

[0018] In one possible design, based on the core image at the same depth, the laminar configuration structure of the target segment is determined, including:

[0019] Determine the total number of pixels corresponding to the laminae included in the core image at the same depth, and determine the number of reservoir pixels corresponding to the reservoir rocks included in the laminae;

[0020] Calculate the ratio of the number of reservoir pixels to the total number of pixels; determine the structure of the texture corresponding to the ratio less than a preset threshold as a brittle texture structure with adjacent source, and determine the structure of the texture corresponding to the ratio greater than or equal to the preset threshold as a source-reservoir symbiotic texture structure.

[0021] The texture configuration structure includes the adjacent source brittle texture structure and the source-storage symbiotic texture structure.

[0022] In one possible design, the laminated shale comprises multiple vertically stacked layers;

[0023] Obtaining core images of the same depth corresponding to the target layer includes:

[0024] Obtain the core of the laminated shale obtained by drilling and coring along a direction perpendicular to the laminae; and extract a core of the same depth corresponding to the target layer based on the core.

[0025] The core samples at the same depth are sliced, and core images at the same depth are created based on the sliced ​​core samples.

[0026] In one possible design, the method further includes:

[0027] The geological parameters and measured free oil volume of the preset layer of the laminated shale are obtained; wherein, the geological parameters include well logging data of the preset layer, the third thickness proportion of the shale layer corresponding to the adjacent source brittle laminated structure in the preset layer, and the fourth thickness proportion of the shale layer corresponding to the source-reservoir symbiotic laminated structure in the preset layer.

[0028] The geological parameters are used as input features, and the measured value of free oil volume is used as output features. These are input into a preset linear weighted model for model training. The preset linear weighted model after model training is determined to be the preset shale free oil volume prediction model.

[0029] In one possible design, after inputting the geological parameters as input features and the measured free oil volume as output features into a preset linear weighted model for model training, the method further includes:

[0030] Obtain a pre-constructed test set, and perform performance testing on the trained pre-defined linear weighted model based on the test set;

[0031] If the trained preset linear weighted model passes the performance test, the model training is considered complete; if the trained preset linear weighted model fails the performance test, the trained preset linear weighted model is optimized.

[0032] Secondly, this application provides a device for predicting the free oil content of layered shale, comprising:

[0033] The acquisition module is used to acquire logging data of the target segment of the laminated shale collected by the logging instrument, and to acquire core images of the same depth corresponding to the target segment; wherein, the logging data is used to quantify the laminated structure characteristics of the target segment, and the core images of the same depth represent core images acquired based on the target segment using drilling coring technology.

[0034] The determination module is used to determine the laminar configuration structure of the target segment based on the core image at the same depth;

[0035] The calculation module is used to calculate the thickness percentage of the shale segment corresponding to the lamellar configuration structure in the target segment;

[0036] The determining module is further configured to input the well logging data and the thickness ratio into a preset shale free oil volume prediction model, and determine the free oil volume prediction result of the target layer generated by the preset shale free oil volume prediction model.

[0037] In one possible design, the lamellar configuration structure includes a source-source brittle lamellar structure and a source-reservoir symbiotic lamellar structure; the source-source brittle lamellar structure indicates that the source rock and reservoir rock included in the lamellar shale are located in different lamellar layers, and the lamellar layers containing the source rock and the reservoir rock are alternately interbedded; the source-reservoir symbiotic lamellar structure indicates that the source rock and the reservoir rock are mixed within the same lamellar layer;

[0038] The calculation module includes: a first determining submodule, used for:

[0039] Determine the first thickness of the shale segment corresponding to the adjacent source brittle lamellar structure, the second thickness of the shale segment corresponding to the source-reservoir symbiotic lamellar structure, and the total thickness of the target segment in the direction perpendicular to the lamellar structure;

[0040] The ratio of the first thickness to the total thickness is determined as the first thickness percentage of the shale segment corresponding to the adjacent source brittle lamellar structure; the ratio of the second thickness to the total thickness is determined as the second thickness percentage of the shale segment corresponding to the source-reservoir symbiotic lamellar structure.

[0041] In one possible design, the preset shale free oil quantity prediction model includes a first free oil quantity prediction sub-model and a second free oil quantity prediction sub-model; the first free oil quantity prediction sub-model is used to predict the free oil quantity of the shale segment corresponding to the adjacent source brittle lamellar structure, and the second free oil quantity prediction sub-model is used to predict the free oil quantity of the shale segment corresponding to the source-reservoir symbiotic lamellar structure.

[0042] The determining module includes: an input submodule, used for:

[0043] The well logging data and the first thickness ratio are input into the first free oil volume prediction sub-model;

[0044] The well logging data and the second thickness percentage are input into the second free oil volume prediction sub-model.

[0045] In one possible design, the determining module further includes:

[0046] The second determining submodule is used to determine the total number of pixels corresponding to the laminae included in the core image at the same depth, and to determine the number of reservoir pixels corresponding to the reservoir rocks included in the laminae.

[0047] The calculation submodule is used to calculate the ratio of the number of reservoir pixels to the total number of pixels;

[0048] The second determining submodule is further configured to determine the structure of the texture corresponding to a ratio less than a preset threshold as a neighboring source brittle texture structure, and to determine the structure of the texture corresponding to a ratio greater than or equal to the preset threshold as a source-storage symbiotic texture structure; wherein the texture configuration structure includes the neighboring source brittle texture structure and the source-storage symbiotic texture structure.

[0049] In one possible design, the laminated shale comprises multiple vertically stacked layers;

[0050] The acquisition module includes:

[0051] The acquisition submodule is used to acquire the core of the laminated shale obtained by drilling and coring the laminated shale in a direction perpendicular to the laminae;

[0052] The core extraction submodule is used to extract core samples of the same depth as the target layer based on the core sample.

[0053] The processing submodule is used to slice the core at the same depth and create a core image at the same depth based on the sliced ​​core.

[0054] In one possible design, the acquisition module is further configured to acquire geological parameters and measured free oil volume of a preset segment of the laminated shale; wherein the geological parameters include well logging data of the preset segment, the third thickness percentage of the shale segment corresponding to the adjacent source brittle lamellar structure in the preset segment, and the fourth thickness percentage of the shale segment corresponding to the source-reservoir symbiotic lamellar structure in the preset segment;

[0055] The device for predicting free oil volume in the layered shale further includes: an input module, used to input the geological parameters as input features and the measured free oil volume as output features into a preset linear weighted model for model training;

[0056] The determining module is further used to determine the preset linear weighted model after the model training is completed as the preset shale free oil quantity prediction model.

[0057] In one possible design, the acquisition module is also used to acquire a pre-built test set;

[0058] The free oil volume prediction device for the laminated shale further includes: a testing module, used to perform performance testing on the trained preset linear weighted model based on the test set;

[0059] The determining module is further configured to determine that model training is complete if the trained preset linear weighted model passes the performance test.

[0060] The device for predicting free oil volume in layered shale further includes an optimization module, used to optimize the trained preset linear weighted model if the trained preset linear weighted model fails the performance test.

[0061] Thirdly, this application provides an electronic device comprising: at least one processor and a memory; the memory storing computer-executable instructions; the at least one processor executing the computer-executable instructions stored in the memory, causing the at least one processor to perform the method described in the first aspect above and various possible designs.

[0062] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the methods described in the first aspect above and various possible designs.

[0063] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the methods described in the first aspect above and various possible designs.

[0064] This application provides a method, apparatus, equipment, and storage medium for predicting free oil volume in laminated shale. It acquires well logging data of the target segment of laminated shale collected by logging instruments, and obtains core images of the corresponding depth for the target segment. The well logging data is used to quantify the lamellar structure characteristics of the target segment, and the core images of the same depth are obtained using drilling coring technology based on the target segment. Then, based on the core images of the same depth, the lamellar configuration structure of the target segment is determined, and the thickness percentage of the shale segment corresponding to the lamellar configuration structure within the target segment is calculated. The well logging data and thickness percentage are further input into a preset shale free oil volume prediction model to determine the predicted free oil volume of the target segment generated by the preset shale free oil volume prediction model. The heterogeneity of the laminated shale is identified by analyzing the core images of the same depth, and the relevant microscopic reservoir parameters, i.e., the thickness percentage, are quantified. In addition, the microscopic reservoir parameters and macroscopic logging responses are input into the preset shale free oil quantity prediction model, enabling the preset shale free oil quantity prediction model to combine microscopic and macroscopic data to predict free oil quantity, thereby improving the accuracy of free oil quantity prediction results. Attached Figure Description

[0065] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0066] Figure 1 A schematic flowchart illustrating the method for predicting free oil volume in layered shale provided in this application embodiment;

[0067] Figure 2 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 1 ;

[0068] Figure 3 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 2 ;

[0069] Figure 4 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 3 ;

[0070] Figure 5 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 4 ;

[0071] Figure 6 A schematic diagram of the free oil volume prediction device for laminated shale provided in this application embodiment;

[0072] Figure 7This is a hardware structure diagram of the electronic device provided in the embodiments of this application.

[0073] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0074] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0075] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0076] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0077] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0078] Existing technologies employ statistical methods to fit linear or nonlinear relationships between well logging data and laboratory-measured free oil volume in laminated shale. With the development of artificial intelligence, existing technologies have incorporated machine learning algorithms such as support vector machines, random forests, and neural networks. These algorithms, while assuming the laminated shale to be a homogeneous whole, use machine learning to uncover the mapping relationship between well logging data and laboratory-measured free oil volume.

[0079] However, laminated shale exhibits significant heterogeneity, with organic matter and inorganic minerals deposited alternately in millimeter- to micrometer-scale laminations, forming source-reservoir symbiotic or adjacent-source brittle micro-reservoir structures. This geological structure results in high spatial heterogeneity of hydrocarbons in laminated shale during their generation, migration, and occurrence.

[0080] On the one hand, in-situ retained oil (such as kerogen pyrolysis products) and micro-migrated oil (liquid hydrocarbons migrating through laminae or pores) exhibit overlapping signals in well logging responses, making them difficult to distinguish. On the other hand, the distribution differences between brittle minerals such as quartz and calcite in laminated shale and calcareous cement can further alter well logging data of laminated shale, thereby interfering with the prediction of free oil volume.

[0081] Therefore, without considering the heterogeneity of the microstructure of laminated shale in existing technologies, it is impossible to accurately determine the differential contribution of millimeter to micrometer-level lamination structure to free oil volume, resulting in a relatively large prediction deviation of free oil volume.

[0082] To address the aforementioned technical problems, the inventors, starting from the issues of existing technologies and the heterogeneity of laminated shale, discovered that existing technologies, by not considering the heterogeneity of the microstructure of laminated shale, lead to significant deviations between predicted free oil content and actual oil content. Subsequently, they proposed quantifying the microscopic reservoir parameters of laminated shale through core image analysis and using these parameters as input features for the prediction model. Simultaneously, well logging data collected considering the microstructure is also used as input features for the prediction model, enabling multi-source information processing and thus improving the accuracy of free oil content prediction.

[0083] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0084] This application provides a method for predicting the free oil content in layered shale. Figure 1 This is a schematic flowchart illustrating the method for predicting free oil volume in layered shale provided in an embodiment of this application. Figure 1 As shown, the method for predicting the free oil volume of this layered shale includes:

[0085] S101. Obtain logging data of the target layer of the laminated shale collected by the logging instrument, and obtain core images of the same depth corresponding to the target layer.

[0086] Interpretively, laminated shale comprises multiple vertically stacked lamellar layers. Each lamellar layer is the smallest stratifying unit in laminated shale, essentially a very thin sedimentary layer. After drilling and coring the laminated shale using drilling instruments in a direction perpendicular to the lamellar layers, a wellbore is formed, and a section of shale solid is obtained—the core of the laminated shale. Both the wellbore and the core are typically cylindrical, with the wellbore diameter slightly larger than the core diameter.

[0087] The logging instrument is lowered into the wellbore and actively transmits measurement signals to the surrounding layered shale. These measurement signals interact with the surrounding layered shale, and the logging instrument receives the physical response information fed back by the layered shale, i.e., the logging data. It should be noted that the logging data acquired in this step is only for the target layer of the layered shale, not the logging data for the entire layered shale surrounding the wellbore. It should be understood that the logging data in this embodiment is only used to quantify the layered structural characteristics of the target layer.

[0088] The logging data in this embodiment includes, but is not limited to: natural gamma ray (GR) logging data, acoustic log (AC) logging data, density (DEN) logging data, and deep investigation induction log (RILD) logging data.

[0089] For core samples retrieved from laminated shale, the depth of the core may not match the depth of the same formation characteristics within the laminated shale due to factors such as changes in the wellbore environment and mechanical errors in drilling instruments during the core extraction process. Therefore, depth repositioning processing is required to determine the depth mapping relationship between the core and well logging data. Interpretatively, depth repositioning refers to the process of accurately placing the core back to its original depth position within the laminated shale based on the correspondence between the core's lithological characteristics and well logging data.

[0090] Furthermore, based on the depth mapping relationship between the core and logging data, core samples of the same depth as the target layer are extracted from the core. Obviously, the length of the core is the same as the length of the wellbore, and the length of the core at the same depth is the same as the length of the target layer. After obtaining the core at the same depth, slicing is performed on the core at the same depth along a direction perpendicular to the laminae. It should be understood that the sliced ​​core at the same depth is a continuous thin slice that can penetrate the vertical sequence of the core at the same depth.

[0091] Subsequently, the aforementioned continuous thin sections are observed using a microscope or photographed using a camera to generate core images at the same depth. It should be noted that when observing the aforementioned continuous thin sections under a microscope or photographing them with a camera, if the direction of the laminae included in the continuous thin sections is tilted, the continuous thin sections can be simply rotated to make the direction of the laminae approximately horizontal.

[0092] To facilitate subsequent data retrieval and image use, a basic database containing well logging data and core images at the same depth can be established.

[0093] S102. Based on core images at the same depth, determine the laminar configuration structure of the target layer; calculate the thickness percentage of the shale layer corresponding to the laminar configuration structure in the target layer.

[0094] Interpretatively, based on the differences in optical properties, brightness, and texture among different laminae in laminated shale, the laminae within laminated shale can be classified into different laminar configuration structures. These configurations typically include adjacent-source brittle laminar structures and source-reservoir symbiotic laminar structures. In adjacent-source brittle laminar structures, the source rocks and reservoir rocks within the laminated shale are located in different laminae, and the laminae containing the source rocks and reservoir rocks alternate between each other. In source-reservoir symbiotic laminar structures, the source rocks and reservoir rocks are mixed within the same laminar structure. In this case, the source rocks are used for oil generation, and the reservoir rocks are used for oil storage.

[0095] Specifically, Figure 2 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 1 ,like Figure 2 As shown, core images of the same depth are obtained from the basic database and imported into image processing software for binarization to obtain the corresponding binary images. Figure 2 In the image, (a) and (c) are core images at the same depth, and (b) and (d) are binary images.

[0096] Furthermore, by combining the binary image, the total number of pixels corresponding to each layer in the image is determined, as well as the number of reservoir pixels corresponding to the reservoir rocks included in each layer. The ratio of the number of reservoir pixels to the total number of pixels is calculated, and this ratio represents the proportion of reservoir rocks in each layer.

[0097] Because the source rock and reservoir rock in a proximal brittle lamellar structure are located in different lamellars, while in a source-reservoir symbiotic lamellar structure the source rock and reservoir rock are mixed within the same lamellar, if the proportion of reservoir rock in a certain lamellar is less than a preset threshold, the structure of that lamellar is a proximal brittle lamellar structure. Conversely, if the proportion of reservoir rock in a certain lamellar is greater than or equal to the preset threshold, the structure of that lamellar is a source-reservoir symbiotic lamellar structure. It should be understood that... Figure 2(a) and (b) show the adjacent source brittle laminar structure, while (c) and (d) show the source-reservoir symbiotic laminar structure.

[0098] Next, the thickness percentage of the shale segments corresponding to adjacent-source brittle lamellar structures and source-reservoir co-existing lamellar structures within the target segment is calculated. Specifically, the thickness percentage is determined in the direction perpendicular to the lamellar structure (refer to...). Figure 2 In the vertical direction, the thickness of the shale segment corresponding to the adjacent source-reservoir brittle lamellar structure, the thickness of the shale segment corresponding to the source-reservoir symbiotic lamellar structure, and the total thickness of the target segment are considered. It should be understood that since the continuous thin sections used to generate the core image at the same depth traverse the vertical sequence of cores at the same depth, the thickness of the entire field of view of the core image or binary map at the same depth is the total thickness of the target segment.

[0099] Then, the ratio of the first thickness to the total thickness is determined as the proportion of the first thickness of the shale segment corresponding to the adjacent source brittle lamellar structure in the target segment, and the ratio of the second thickness to the total thickness is determined as the proportion of the second thickness of the shale segment corresponding to the source-reservoir symbiotic lamellar structure in the target segment.

[0100] S103. Input the logging data and thickness percentage into the preset shale free oil volume prediction model, and determine the free oil volume prediction result of the target layer generated by the preset shale free oil volume prediction model.

[0101] It should be noted that, since the lamellar configuration of the target strata includes adjacent-source brittle lamellar structures and source-reservoir symbiotic lamellar structures, the preset shale free oil volume prediction model in this embodiment also includes two types of sub-models: a first free oil volume prediction sub-model and a second free oil volume prediction sub-model. The first free oil volume prediction sub-model is used to predict the free oil volume of shale strata corresponding to adjacent-source brittle lamellar structures, while the second free oil volume prediction sub-model is used to predict the free oil volume of shale strata corresponding to source-reservoir symbiotic lamellar structures.

[0102] Therefore, this step inputs the first thickness percentage of the shale interval corresponding to the source-reservoir brittle lamellar structure into the first free oil volume prediction sub-model, and the second thickness percentage of the shale interval corresponding to the source-reservoir symbiotic lamellar structure into the second free oil volume prediction sub-model. It is worth noting that, since the well logging data in this embodiment includes various types, to reduce the computational complexity of the model, only four types of well logging data with typical characteristics—GR, AC, DEN, and RILD—are selected and input into the first and second free oil volume prediction sub-models.

[0103] Obviously, the first free oil volume prediction sub-model generates free oil volume prediction results for shale intervals corresponding to adjacent source brittle lamellar structures, while the second free oil volume prediction sub-model generates free oil volume prediction results for shale intervals corresponding to source-reservoir co-existing lamellar structures. Then, the preset shale free oil volume prediction model sums these two free oil volume prediction values ​​to obtain the free oil volume prediction result for the target interval.

[0104] Understandably, the preset shale free oil volume prediction model is obtained through model training. The following explains the model training process of the preset shale free oil volume prediction model. Before model training, a preset layer, different from the target layer, is selected, and relevant data from the preset layer are collected as the training set.

[0105] Specifically, the geological parameters and measured free oil volume of the preset intervals of the laminated shale are obtained. The geological parameters include well logging data (GR, AC, DEN and RILD four types of well logging data), the proportion of the third thickness of the shale interval corresponding to the adjacent source brittle laminated structure in the preset interval, and the proportion of the fourth thickness of the shale interval corresponding to the source-reservoir symbiotic laminated structure in the preset interval.

[0106] Furthermore, geological parameters are used as input features, and measured free oil volume is used as output features, both input into a pre-defined linear weighted model for training. It is worth noting that since the final trained pre-defined shale free oil volume prediction model includes two sub-models, the pre-defined linear weighted model should also include two sub-models. Well logging data and the third thickness percentage are input into one sub-model of the pre-defined linear weighted model, and well logging data and the fourth thickness percentage are input into the other sub-model.

[0107] It should be understood that training a pre-defined linear weighted model essentially involves finding a set of weight coefficients and biases that make the output of the pre-defined linear weighted model as close as possible to the actual observed value, i.e., the measured value of free oil volume. This embodiment uses a controlled variable method to train the pre-defined linear weighted model.

[0108] Specifically, Figure 3 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 2 ,like Figure 3 The diagram illustrates the training process for a pre-defined linear weighted model. Figure 3 Taking (a) as an example, keeping the four types of logging data (GR, AC, DEN, and RILD) unchanged, the output of the preset linear weighted model is obtained by changing the value of the third thickness percentage (dashed line in the figure). Furthermore, the weight coefficients corresponding to the bias and the third thickness percentage are adjusted so that the output of the preset linear weighted model is close to the measured value of free oil (black dot in the figure).

[0109] Interpretive, in the process of adjusting the weighting coefficients corresponding to the bias and the proportion of the third thickness, the determination coefficients (R²) of the preset linear weighted model are continuously calculated. 2 The coefficient of determination is used to reflect the goodness of fit of the preset linear weighted model, and its value ranges from [0, 1]. When the coefficient of determination is greater than the preset threshold, the weight coefficient at this time is determined as the final weight coefficient corresponding to the third thickness proportion, and it will not be changed.

[0110] Similarly, the determination process for the weighting coefficients corresponding to the four types of logging data (GR, AC, DEN, RILD) and the fourth thickness percentage is similar to the determination process for the weighting coefficients corresponding to the third thickness percentage, and will not be repeated here. Figure 4 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 3 ,like Figure 4 As shown, it is clear that the final weighting coefficients for the third thickness proportion, the fourth thickness proportion, and the four types of well logging data (GR, AC, DEN, and RILD) reflect their respective contributions to the output of the preset linear weighted model. It should be understood that... Figure 4 Only one possible example is given. The contribution of the third thickness proportion, the fourth thickness proportion, and the four types of logging data (GR, AC, DEN, and RILD) to the output of the preset linear weighted model is determined by the actual final weight coefficients.

[0111] For the bias of the preset linear weighted model, since there will be a corresponding bias when each final weight coefficient is determined, the bias of the preset linear weighted model can be obtained by weighting and averaging the corresponding biases according to the determined weight coefficients.

[0112] Thus, a pre-defined linear weighted model is obtained after model training. Further, a pre-constructed test set is acquired, and the performance of the trained pre-defined linear weighted model is tested based on this test set. It should be noted that this test set includes relevant data from other layers that are distinct from both the target and pre-defined layers, namely, the geological parameters and measured values ​​of free oil volume in other layers. It is worth noting that the measured values ​​of free oil volume include both those from adjacent source-reservoir brittle laminae and those from source-reservoir symbiotic laminae.

[0113] Specifically, Figure 5 A scenario illustration of the free oil content prediction method for laminated shale provided in this application embodiment. Figure 4 ,like Figure 5As shown, the geological parameters of other strata included in the test set are input into the trained preset linear weighted model to obtain the output of the preset linear weighted model. Then, it is observed whether this output is as close as possible to the measured values ​​of free oil volume in the other strata included in the test set. If so, it means that the trained preset linear weighted model has passed the performance test, i.e., the model training is complete. If not, it means that the trained preset linear weighted model has failed the performance test, and it is necessary to continue adjusting the weight coefficients and biases in the trained preset linear weighted model for model optimization.

[0114] Understandably, the preset linear weighted model after model training is the final preset shale free oil quantity prediction model.

[0115] The free oil volume prediction method for laminated shale provided in this application acquires well logging data of the target segment of laminated shale collected by well logging instruments, and acquires core images of the same depth corresponding to the target segment. The well logging data is used to quantify the lamellar structure characteristics of the target segment, and the core images of the same depth are obtained using drilling coring technology based on the target segment. Then, the lamellar configuration structure of the target segment is determined based on the core images of the same depth, wherein the lamellar configuration structure includes adjacent source brittle lamellar structures and source-reservoir symbiotic lamellar structures. The first thickness percentage of the shale segment corresponding to the adjacent source brittle lamellar structure and the second thickness percentage of the shale segment corresponding to the source-reservoir symbiotic lamellar structure are determined within the target segment. Furthermore, the well logging data and the first thickness percentage are input into a first free oil volume prediction sub-model included in a preset shale free oil volume prediction model, and the well logging data and the second thickness percentage are input into a second free oil volume prediction sub-model included in the preset shale free oil volume prediction model. The final free oil volume prediction results for the target stratigraphic segment generated by the pre-defined shale free oil volume prediction model were determined. The heterogeneity of layered shale was identified by analyzing core images at the same depth, and relevant microscopic reservoir parameters, i.e., thickness proportions, were quantified. Furthermore, the microscopic reservoir parameters and macroscopic logging responses were input into the pre-defined shale free oil volume prediction model, enabling it to combine microscopic and macroscopic data to predict free oil volume, thereby improving the accuracy of the prediction results.

[0116] Figure 6 This is a schematic diagram of the free oil volume prediction device for laminated shale provided in the embodiments of this application, as shown below. Figure 6 As shown, the free oil volume prediction device 600 for the layered shale includes: an acquisition module 601, a determination module 602, and a calculation module 603.

[0117] The acquisition module 601 is used to acquire logging data of the target layer of the laminated shale collected by the logging instrument, and to acquire core images of the same depth corresponding to the target layer. The logging data is used to quantify the laminated structure characteristics of the target layer, and the core images of the same depth are core images obtained based on the target layer using drilling coring technology.

[0118] The determination module 602 is used to determine the laminar configuration structure of the target segment based on core images at the same depth;

[0119] Calculation module 603 is used to calculate the thickness percentage of the shale segment corresponding to the layered configuration structure in the target segment;

[0120] The determination module 602 is also used to input well logging data and thickness ratio into the preset shale free oil volume prediction model, and determine the free oil volume prediction result of the target layer generated by the preset shale free oil volume prediction model.

[0121] In one possible design, the lamellar configuration structure includes a source-source brittle lamellar structure and a source-reservoir symbiotic lamellar structure; the source-source brittle lamellar structure indicates that the source rocks and reservoir rocks in the lamellar shale are located in different lamellars, and the lamellars containing the source rocks and the lamellars containing the reservoir rocks are alternately interbedded; the source-reservoir symbiotic lamellar structure indicates that the source rocks and reservoir rocks are mixed within the same lamellar.

[0122] Calculation module 603 includes: a first determining submodule 6031, used for:

[0123] Determine the first thickness of the shale segment corresponding to the adjacent source brittle lamellar structure, the second thickness of the shale segment corresponding to the source-reservoir symbiotic lamellar structure, and the total thickness of the target segment in the direction perpendicular to the lamellar structure;

[0124] The ratio of the first thickness to the total thickness is determined as the proportion of the first thickness of the shale segment corresponding to the adjacent source brittle lamellar structure in the target segment; the ratio of the second thickness to the total thickness is determined as the proportion of the second thickness of the shale segment corresponding to the source-reservoir symbiotic lamellar structure in the target segment.

[0125] In one possible design, the pre-defined shale free oil quantity prediction model includes a first free oil quantity prediction sub-model and a second free oil quantity prediction sub-model; the first free oil quantity prediction sub-model is used to predict the free oil quantity of shale segments corresponding to adjacent source brittle lamellar structures, and the second free oil quantity prediction sub-model is used to predict the free oil quantity of shale segments corresponding to source-reservoir symbiotic lamellar structures.

[0126] Determining module 602 includes: input submodule 6021, used for:

[0127] Input the well logging data and the first thickness percentage into the first free oil volume prediction sub-model;

[0128] The well logging data and the second thickness ratio are input into the second free oil volume prediction sub-model.

[0129] In one possible design, module 602 further includes:

[0130] The second determining submodule 6022 is used to determine the total number of pixels corresponding to the laminae included in the core image at the same depth, and to determine the number of reservoir pixels corresponding to the reservoir rocks included in the laminae.

[0131] The calculation submodule 6023 is used to calculate the ratio of the number of reservoir pixels to the total number of pixels;

[0132] The second determining submodule 6022 is further configured to determine the structure of the texture corresponding to a ratio less than a preset threshold as a neighboring source brittle texture structure, and to determine the structure of the texture corresponding to a ratio greater than or equal to a preset threshold as a source-storage symbiotic texture structure; wherein the texture configuration structure includes a neighboring source brittle texture structure and a source-storage symbiotic texture structure.

[0133] In one possible design, laminated shale comprises multiple vertically stacked layers;

[0134] Module 601 includes:

[0135] The acquisition submodule 6011 is used to acquire the core of the laminated shale obtained by drilling and coring operations along a direction perpendicular to the laminae;

[0136] The core extraction submodule 6012 is used to extract core samples of the same depth as the target layer based on the core samples.

[0137] The processing submodule 6013 is used to slice the core at the same depth and create a core image at the same depth based on the sliced ​​core.

[0138] In one possible design, the acquisition module 601 is also used to acquire the geological parameters and measured free oil volume of a preset segment of the laminated shale; wherein, the geological parameters include well logging data of the preset segment, the third thickness percentage of the shale segment corresponding to the adjacent source brittle laminated structure in the preset segment, and the fourth thickness percentage of the shale segment corresponding to the source-reservoir symbiotic laminated structure in the preset segment.

[0139] The device 600 for predicting free oil volume in layered shale also includes: an input module 604, which takes geological parameters as input features and measured free oil volume as output features, and inputs them into a preset linear weighted model for model training.

[0140] The determination module 602 is also used to determine that the preset linear weighted model after the model training is completed is a preset shale free oil quantity prediction model.

[0141] In one possible design, module 601 is also used to retrieve a pre-built test set;

[0142] The free oil volume prediction device 600 for layered shale also includes: a test module 605, used to perform performance testing on a pre-trained linear weighted model based on a test set;

[0143] The determination module 602 is also used to determine that model training is complete if the trained preset linear weighted model passes the performance test;

[0144] The device 600 for predicting free oil volume in layered shale also includes an optimization module 606, which optimizes the pre-trained linear weighted model if the pre-trained model fails the performance test.

[0145] The free oil volume prediction device for laminated shale provided in this application embodiment can be used to execute the free oil volume prediction method for laminated shale in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0146] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented in software via processing element calls, while others are implemented in hardware. Additionally, these modules can be fully or partially integrated together, or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through the integrated logic circuits in the hardware of the processor element or through software instructions.

[0147] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device may include: a transceiver 71, a processor 72, and a memory 73.

[0148] Processor 72 executes computer execution instructions stored in memory, causing processor 72 to perform the scheme in the above embodiments. Processor 72 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0149] The memory 73 is connected to the processor 72 via the system bus and completes communication between them. The memory 73 is used to store computer program instructions.

[0150] Transceiver 71 can be used to communicate and interact with other devices.

[0151] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. Transceivers are used to enable communication between database access devices and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and may also include non-volatile memory.

[0152] The electronic device provided in this application embodiment can be used to execute the method provided in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0153] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the methods provided in any of the above embodiments.

[0154] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, it can implement the method provided in any of the above embodiments.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0156] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0157] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0158] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0159] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0160] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0161] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0162] The aforementioned storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0163] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. The processor and storage medium can reside in application-specific integrated circuits (ASICs). Alternatively, the processor and storage medium can exist as discrete components in an electronic control unit or main control device.

[0164] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for predicting free oil volume in layered shale, characterized in that, include: The logging data of the target segment of the laminated shale collected by the logging instrument is obtained, as well as the core image of the target segment at the same depth is obtained; wherein, the logging data is used to quantify the laminated structure characteristics of the target segment, and the core image at the same depth is a core image obtained based on the target segment using drilling coring technology. Based on the core images at the same depth, the lamellar configuration structure of the target layer is determined; the thickness percentage of the shale layer corresponding to the lamellar configuration structure in the target layer is calculated. The well logging data and the thickness percentage are input into a preset shale free oil volume prediction model to determine the free oil volume prediction result of the target layer generated by the preset shale free oil volume prediction model.

2. The method according to claim 1, characterized in that, The lamellar configuration includes a source-source brittle lamellar structure and a source-reservoir symbiotic lamellar structure; the source-source brittle lamellar structure indicates that the source rock and reservoir rock included in the lamellar shale are located in different lamellar layers, and the lamellar layers where the source rock is located and the lamellar layers where the reservoir rock is located alternately interbedded; the source-reservoir symbiotic lamellar structure indicates that the source rock and the reservoir rock are mixed within the same lamellar layer; Calculating the thickness percentage of the shale segment corresponding to the lamellar configuration structure within the target segment includes: Determine the first thickness of the shale segment corresponding to the adjacent source brittle lamellar structure, the second thickness of the shale segment corresponding to the source-reservoir symbiotic lamellar structure, and the total thickness of the target segment in the direction perpendicular to the lamellar structure; The ratio of the first thickness to the total thickness is determined as the first thickness percentage of the shale segment corresponding to the adjacent source brittle lamellar structure in the target segment; the ratio of the second thickness to the total thickness is determined as the second thickness percentage of the shale segment corresponding to the source-reservoir symbiotic lamellar structure in the target segment.

3. The method according to claim 2, characterized in that, The preset shale free oil volume prediction model includes a first free oil volume prediction sub-model and a second free oil volume prediction sub-model; the first free oil volume prediction sub-model is used to predict the free oil volume of the shale segment corresponding to the adjacent source brittle lamellar structure, and the second free oil volume prediction sub-model is used to predict the free oil volume of the shale segment corresponding to the source-reservoir symbiotic lamellar structure. The well logging data and the thickness percentage are input into a preset shale free oil quantity prediction model, including: The well logging data and the first thickness ratio are input into the first free oil volume prediction sub-model; The well logging data and the second thickness percentage are input into the second free oil volume prediction sub-model.

4. The method according to claim 1, characterized in that, Based on the core images at the same depth, the laminar configuration structure of the target layer is determined, including: Determine the total number of pixels corresponding to the laminae included in the core image at the same depth, and determine the number of reservoir pixels corresponding to the reservoir rocks included in the laminae; Calculate the ratio of the number of reservoir pixels to the total number of pixels; determine the structure of the texture corresponding to the ratio less than a preset threshold as a brittle texture structure with adjacent source, and determine the structure of the texture corresponding to the ratio greater than or equal to the preset threshold as a source-reservoir symbiotic texture structure. The texture configuration structure includes the adjacent source brittle texture structure and the source-storage symbiotic texture structure.

5. The method according to claim 1, characterized in that, The laminated shale comprises multiple vertically stacked layers; Obtaining core images of the same depth corresponding to the target layer includes: Obtain the core of the laminated shale obtained by drilling and coring along a direction perpendicular to the laminae; and extract a core of the same depth corresponding to the target layer based on the core. The core samples at the same depth are sliced, and core images at the same depth are created based on the sliced ​​core samples.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The geological parameters and measured free oil volume of the preset layer of the laminated shale are obtained; wherein, the geological parameters include well logging data of the preset layer, the third thickness proportion of the shale layer corresponding to the adjacent source brittle laminated structure in the preset layer, and the fourth thickness proportion of the shale layer corresponding to the source-reservoir symbiotic laminated structure in the preset layer. The geological parameters are used as input features, and the measured value of free oil volume is used as output features. These are input into a preset linear weighted model for model training. The preset linear weighted model after model training is determined to be the preset shale free oil volume prediction model.

7. The method according to claim 6, characterized in that, After inputting the geological parameters as input features and the measured free oil volume as output features into a preset linear weighted model for model training, the method further includes: Obtain a pre-constructed test set, and perform performance testing on the trained pre-defined linear weighted model based on the test set; If the trained preset linear weighted model passes the performance test, the model training is considered complete; if the trained preset linear weighted model fails the performance test, the trained preset linear weighted model is optimized.

8. A device for predicting the free oil content of layered shale, characterized in that, include: The acquisition module is used to acquire logging data of the target segment of the laminated shale collected by the logging instrument, and to acquire core images of the same depth corresponding to the target segment; wherein, the logging data is used to quantify the laminated structure characteristics of the target segment, and the core images of the same depth represent core images acquired based on the target segment using drilling coring technology. The determination module is used to determine the laminar configuration structure of the target segment based on the core image at the same depth; The calculation module is used to calculate the thickness percentage of the shale segment corresponding to the lamellar configuration structure in the target segment; The determining module is further configured to input the well logging data and the thickness ratio into a preset shale free oil volume prediction model, and determine the free oil volume prediction result of the target layer generated by the preset shale free oil volume prediction model.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method for predicting free oil volume in layered shale as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for predicting free oil volume in layered shale as described in any one of claims 1 to 7.

Images