Method and system for acquiring oil well parameter regulation and control training sample set based on image enhancement

Abstract

The application discloses a method and system for obtaining oil well parameter regulation and control training sample set based on image enhancement, and comprises the following steps: obtaining geological data of the whole block in an existing oil reservoir model; performing shearing on the geological data by taking the position of each oil well and water well as the center through an image enhancement technology to obtain a first oil-water well parameter regulation and control training sample set; obtaining a second oil-water well parameter regulation and control training sample set by rotating the first oil-water well parameter regulation and control training sample set; and obtaining a third oil-water well parameter regulation and control training sample set by inverting the second oil-water well parameter regulation and control training sample set. The application performs shearing, filling, rotation, inversion and other operations on the extracted oil reservoir data in the simulation oil reservoir model through the image enhancement technology to obtain the oil-water well parameter regulation and control training sample and expand the sample quantity, which is efficient, time-saving and labor-saving, reduces the dependence of the obtained model on certain attributes, and improves the generalization ability of the model.

Description

Technical Field

[0001] The present invention relates to the technical field of image enhancement technology, and in particular to a method and system for obtaining an oil well parameter control training sample set based on image enhancement. Background Art

[0002] The primary goal of oil well parameter control is to find the optimal solution for each well to maximize NPV or oil production, a process that falls under the umbrella of production optimization. In recent years, deep learning and reinforcement learning have become the primary approaches to addressing this problem. However, developing a robust and generalizable oil well parameter control model requires a large number of training samples, which must include relevant geological information about the wells.

[0003] Currently, the main ways to obtain training sample sets include public datasets; sample sets obtained through crawlers, sample sets purchased online, etc.; sample sets obtained through real-world experiments; and sample sets generated through simulations or collected through simulation experiments. However, in many cases, training sample sets for oil well parameter control are rarely publicly available, difficult to obtain through online crawlers or purchase, and obtaining real-world experiments is costly and difficult. Therefore, the most common methods for obtaining training sample sets are still simulation-generated data or samples collected through simulation experiments. However, the number of samples collected in a single simulation is relatively small, requiring multiple simulations or simulations to obtain a sufficient number of samples, which is time-consuming and labor-intensive. Summary of the Invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for obtaining oil well parameter control training sample sets based on image enhancement, which can solve the problems of high cost and difficulty in obtaining data in real experiments and small number of samples collected in simulation experiments.

[0007] To solve the above technical problems, the present invention provides the following technical solution: a method for obtaining an oil well parameter control training sample set based on image enhancement, comprising:

[0008] Obtain geological data on permeability, saturation, pore volume, pressure field, injection and production well locations, pressure, and effective grid for the entire block in the existing reservoir model;

[0009] The geological data is cropped with the location of each oil well as the center by using image enhancement technology to obtain a first oil well parameter control training sample set;

[0010] Rotating the first oil well parameter control training sample set by image enhancement technology to obtain a second oil well parameter control training sample set;

[0011] The second oil well parameter control training sample set is flipped by image enhancement technology to obtain a third oil well parameter control training sample set.

[0012] As a preferred embodiment of the method for preparing an oil well parameter control training sample set by image enhancement according to the present invention, the shearing with the location of each oil well as the center includes:

[0013] When the cut sample size does not meet the target sample size, the sample that does not meet the target sample size is padded using image enhancement technology to ensure that the supplemented sample size is consistent with the target sample size.

[0014] As a preferred embodiment of the method for preparing an oil well parameter control training sample set by image enhancement according to the present invention, the rotation comprises rotating the first oil well parameter control training sample set clockwise.

[0015] When rotating 90 degrees, all geological data of the intercepted block are also rotated 90 degrees accordingly. The geological data of the new block generated by the rotation is similar to the original geological data, but the data position is rotated 90 degrees as a whole;

[0016] When the data position is rotated 90 degrees as a whole, the layout of the injection and production well locations and permeability parameters is changed, thereby reducing the model's dependence on the weights of the two attributes: the injection and production well locations and the permeability parameters.

[0017] As a preferred solution of the method for obtaining oil well parameter control training sample set based on image enhancement according to the present invention, wherein: the rotation further includes:

[0018] When rotating 180 degrees, all geological data of the intercepted block are also rotated 180 degrees accordingly. The geological data of the new block generated by the rotation is similar to the original geological data, but the data position is rotated 180 degrees as a whole;

[0019] When the data position is rotated 180 degrees as a whole, the layout of the permeability and saturation parameters is changed, thereby reducing the model's dependence on the weights of the two attributes.

[0020] As a preferred solution of the method for obtaining a training sample set for oil well parameter control based on image enhancement according to the present invention, when rotating 270 degrees, all geological data of the intercepted block are also rotated 270 degrees accordingly. The geological data of the new block generated by the rotation is similar to the original geological data, but the data position is rotated 270 degrees as a whole.

[0021] When the data position is rotated 270 degrees as a whole, the permeability, saturation, and the layout of the injection and production wells are changed at the same time, which ensures that the model's dependence on the weights of the three attributes of permeability, saturation, and the layout of the injection and production wells is reduced.

[0022] As a preferred solution of the method for obtaining oil well parameter control training sample set based on image enhancement according to the present invention, the flipping includes:

[0023] When flipping left and right, all geological data of the intercepted block will also be flipped left and right. After flipping left and right, the geological data of the block is similar to the original geological data, but the data position is flipped left and right as a whole.

[0024] When the data position is flipped left and right as a whole, the pore volume, pressure, injection and production well location, and effective grid layout change, which ensures that the model's weight dependence on pore volume, pressure, injection and production well location, and effective grid attributes is reduced.

[0025] As a preferred solution of the method for obtaining oil well parameter control training sample set based on image enhancement according to the present invention, wherein: the flipping further includes:

[0026] When flipping upside down, all geological data of the intercepted block will also be flipped upside down. After flipping upside down, the geological data of the block is similar to the original geological data, but the data position is flipped upside down as a whole;

[0027] When the data position is flipped upside down, the layout of permeability, saturation and pressure changes, which ensures that the model's weight dependence on permeability, permeability, saturation and pressure attributes is reduced. A system for obtaining oil well parameter control training sample sets based on image enhancement is characterized by comprising a data acquisition module, a data cropping module, a data rotation module and a data flipping module.

[0028] A data acquisition module, which is used to obtain permeability and saturation geological data of the entire block in the existing reservoir model;

[0029] a data clipping module, which clips the geological data centered on the location of each oil well and water well using image enhancement technology to obtain a first oil and water well parameter control training sample set;

[0030] a data rotation module, wherein the data rotation module rotates the first oil and water well parameter control training sample set by using image enhancement technology to obtain a second oil and water well parameter control training sample set;

[0031] A data flipping module flips the second oil and water well parameter control training sample set by using image enhancement technology to obtain a third oil and water well parameter control training sample set.

[0032] A computer device includes a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the above method when executing the computer program.

[0033] A computer-readable storage medium stores a computer program thereon, wherein the computer program implements the steps of the method described above when executed by a processor.

[0034] Beneficial effects of the present invention: The present invention proposes a method and system for obtaining oil well parameter control training sample sets based on image enhancement. The present invention uses image enhancement technology to perform operations such as cutting, filling, rotating, and flipping on the reservoir data extracted from the simulated reservoir model to obtain oil and water well parameter control training samples and expand the number of samples. Compared with the traditional method of obtaining a sufficient number of training samples through multiple simulations, the present invention only requires several or one simulation simulation to prepare a sufficient number of samples, which is efficient, time-saving and labor-saving. In addition, the samples obtained by the present invention are highly correlated with oil wells or water wells, and similar but different training samples can reduce the dependence of the trained model on certain attributes, thereby improving the generalization ability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0036] Figure 1 A flowchart of a method and system for obtaining a training sample set for oil well parameter control based on image enhancement provided by one embodiment of the present invention;

[0037] Figure 2 A system structure diagram of a method and system for obtaining a training sample set for oil well parameter control based on image enhancement provided by one embodiment of the present invention;

[0038] Figure 3An example diagram of an oil reservoir model of a method and system for obtaining a training sample set for oil well parameter control based on image enhancement provided by one embodiment of the present invention;

[0039] Figure 4 An example diagram of image enhancement shearing effect of a method and system for obtaining an oil well parameter control training sample set based on image enhancement provided by one embodiment of the present invention;

[0040] Figure 5 An example diagram of image enhancement rotation effect of a method and system for obtaining an oil well parameter control training sample set based on image enhancement provided by one embodiment of the present invention;

[0041] Figure 6 An example diagram of image enhancement flipping effects of a method and system for obtaining an oil well parameter control training sample set based on image enhancement provided by one embodiment of the present invention;

[0042] Figure 7 A technical flowchart of a method and system for obtaining a training sample set for oil well parameter control based on image enhancement provided by one embodiment of the present invention;

[0043] Figure 8 An internal structural diagram of a computer device for a method and system for obtaining a training sample set for oil well parameter control based on image enhancement, provided in one embodiment of the present invention; DETAILED DESCRIPTION

[0044] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0047] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0048] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0049] In this disclosure, unless otherwise specified or limited, the terms "mounted, connected, and connected" should be understood broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0050] Example 1

[0051] Reference Figure 1-2 , which is the first embodiment of the present invention, provides a method for obtaining an oil well parameter control training sample set based on image enhancement, comprising:

[0052] Step 102, obtaining permeability, saturation, and effective grid geological data of the entire block in the existing reservoir model;

[0053] Among them, the geological data of the entire block is extracted from the reservoir model, such as permeability, saturation and other geological information. The geological data can be a matrix or a picture.

[0054] Specifically, geological data includes, but is not limited to, permeability, saturation, pore volume, pressure field, injection and production well locations and pressures, and effective grids, making the method versatile and universal. This geological data will serve as the initial data for subsequent sample set preparation.

[0055] Step 104: cropping the geological data with the location of each oil well and water well as the center using image enhancement technology to obtain a first oil and water well parameter control training sample set;

[0056] Among them, if the cut sample pair does not meet the sample size required by the research problem, the sample that does not meet the required sample size is filled using image enhancement technology.

[0057] Specifically, image enhancement technology is used to crop the previously acquired geological data, such as permeability and saturation, with the location of each oil well and water well as the center (the cropped matrix or image size is determined by the actual problem) to obtain the first oil well parameter control training sample set.

[0058] Furthermore, assuming that the permeability data obtained in advance is:

[0059]

[0060] Furthermore, suppose an oil well is located at p 22 Position, in p 22 The sheared matrix is ​​3×3 in size. The sheared oil well parameter control training sample is represented by O1, then O1 is:

[0061]

[0062] It should be noted that if the oil and water wells are located close to the reservoir boundary or other factors cause the sheared samples to not meet the sample size required for the research problem, then it is necessary to use image enhancement technology to fill in the samples that do not meet the requirements.

[0063] Furthermore, suppose an oil well is located at p 43 Position, in p 43 The matrix is ​​sheared to a size of 3×3 at the center. The parameter control training sample obtained by shearing is represented by O2. Because the oil well is located at the reservoir boundary, the sheared sample does not meet the sample size required by the research problem, so sample O2 needs to be padded. Here, the padded value is 0 (the padded value is determined according to the actual problem). Then O2 is:

[0064]

[0065] It should be noted that after the above steps, it can be ensured that all sample data are highly correlated with oil and water wells, and all samples remain uniform in size, which is convenient for training.

[0066] Furthermore, the obtained first oil well parameter control training sample set also facilitates subsequent image enhancement operations, ie, facilitates obtaining new samples. Such a step is also universal.

[0067] Step 106: Rotate the first oil and water well parameter control training sample set using image enhancement technology to obtain a second oil and water well parameter control training sample set;

[0068] Among them, image enhancement technology is used to rotate all samples in the first oil well parameter control training sample set, for example, by rotating them 90 degrees, 180 degrees, and 270 degrees clockwise. At this time, the new samples obtained by rotation and the first oil well parameter control training sample set are collectively referred to as the second oil well parameter control training sample set.

[0069] Specifically, rotate O1 in step 104 90 degrees clockwise to obtain O1 90 °:

[0070]

[0071] At this point, the second oil and water well parameter control training sample set will be four times the size of the first oil well parameter control training sample set. The addition of new samples reduces the trained model's reliance on certain attributes, improving the model's generalization ability. This approach also saves time and effort compared to traditional methods of preparing oil well parameter control sample sets from other reservoirs or building new reservoir models. This step is also universally applicable.

[0072] Furthermore, when rotating 90 degrees, all geological data of the intercepted block are also rotated 90 degrees, thereby generating a new block whose geological data is similar to the original geological data, but the data position is rotated 90 degrees as a whole.

[0073] It should be noted that while new samples were added, the permeability and the layout of the injection and production wells changed due to the 90-degree rotation of the block. Training the model with such diverse samples can also help reduce the impact of the two attributes of permeability and injection and production well locations on the model, thereby improving the generalization ability of the model.

[0074] Furthermore, when rotating 180 degrees, all geological data of the intercepted block will also be rotated 180 degrees, thereby generating a new block whose geological data is similar to but different from the original geological data, but the data position is rotated 180 degrees as a whole.

[0075] It should be noted that the addition of new samples also changes the layout of permeability and saturation locations due to the 180-degree rotation of the block. This diverse sample training helps reduce the trained model's dependence on permeability and saturation attributes, improving the model's generalization ability. Furthermore, this approach saves time and effort compared to the traditional method of preparing well parameter control sample sets from other reservoirs or building new reservoir models. This step is also universally applicable.

[0076] Furthermore, when rotating 270 degrees, all geological data of the intercepted block will also be rotated 270 degrees, thereby generating a new block whose geological data is similar to but different from the original geological data, but the data position is rotated 270 degrees as a whole.

[0077] It should be noted that while adding new samples, the permeability, saturation, and injection and production well locations change due to the 270-degree rotation of the block. This diverse sample training also helps reduce the trained model's dependence on permeability, saturation, and injection and production well location attributes, improving the model's generalization ability. This approach also saves time and effort compared to the traditional method of preparing a set of oil well parameter control samples from other reservoirs or building a new reservoir model. This step is also universally applicable.

[0078] Step 108 : Using image enhancement technology, the second oil and water well parameter control training sample set is flipped to obtain a third oil and water well parameter control training sample set.

[0079] Among them, image enhancement technology is used to flip all samples in the second oil well parameter control training sample set left and right or up and down respectively. At this time, the flipped samples and the second oil well parameter control training sample set are collectively referred to as the third oil well parameter control training sample set.

[0080] Specifically, flip O1 in step 104 left and right to obtain O1 r.l :

[0081]

[0082] Furthermore, O1 in step 104 is flipped upside down to obtain O1 u.d :

[0083]

[0084] It should be noted that the above steps increase the number of samples in the first oil well parameter control training set by an order of magnitude. Specifically, by simply performing steps 104 and 106, the number of samples can be increased eightfold. The third oil well parameter control training sample set can then be used to train the oil and water well parameter control algorithm model. It should be noted that the operations in steps 104, 106, and 108 are interchangeable, and the number of samples can also be increased eightfold.

[0085] Furthermore, when flipping left and right, all geological data of the intercepted block will also be flipped left and right, thus generating a new block whose geological data is similar to but different from the original geological data;

[0086] It should be noted that while adding new samples, the pore volume, pressure, injection and production well locations, and effective grid layout change due to block flipping. This diverse sample training also helps reduce the trained model's dependence on pore volume, pressure, injection and production well locations, and effective grid properties, thereby improving the model's generalization ability. Furthermore, this approach saves time and effort compared to the traditional method of preparing a set of oil well parameter control samples from other reservoirs or building a new reservoir model. This step is also universally applicable.

[0087] Furthermore, when flipping upside down, all geological data of the intercepted block will also be flipped upside down, thus generating a new block whose geological data are similar to but different from the original geological data;

[0088] It should be noted that the addition of new samples also changes the distribution of permeability, saturation, and pressure due to block flipping. This diverse sample training helps reduce the trained model's dependence on permeability, saturation, and pressure, thereby improving the model's generalization ability. Furthermore, this approach saves time and effort compared to the traditional method of preparing a set of oil well parameter control samples from other reservoirs or building a new reservoir model. This step is also universally applicable.

[0089] Specifically, while significantly increasing the sample size, the trained model's reliance on certain attributes can be reduced, improving the model's generalization capabilities. Furthermore, this approach significantly saves time and effort compared to traditional methods of preparing well parameter control sample sets from other reservoirs or by building new reservoir models. All of the above steps also take into account universal applicability.

[0090] A system for obtaining a training sample set of oil well parameter control based on image enhancement, characterized by comprising a data acquisition module 202, a data cropping module 204, a data rotation module 206, and a data flipping module 206.

[0091] A data acquisition module 202 is used to obtain geological data of permeability, saturation, pore volume, pressure field, injection and production well locations, pressure, and effective grids for the entire block in the existing reservoir model;

[0092] A data clipping module 204 is configured to clip the geological data centered on the location of each oil well using image enhancement technology to obtain a first oil well parameter control training sample set;

[0093] A data rotation module 206 is configured to rotate the first oil well parameter control training sample set using image enhancement technology to obtain a second oil well parameter control training sample set;

[0094] The data flipping module 208 flips the second oil well parameter control training sample set by using image enhancement technology to obtain a third oil well parameter control training sample set.

[0095] The above-mentioned unit modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0096] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WiFi, a carrier network, NFC (near field communication), or other technologies. When the computer program is executed by the processor, a method and system for obtaining a training sample set for oil well parameter control based on image enhancement is implemented. The display screen of the computer device can be a liquid crystal display or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or can be a key, trackball, or touchpad provided on the computer device housing, or can be an external keyboard, touchpad, or mouse.

[0097] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0098] Obtain geological data on permeability, saturation, pore volume, pressure field, injection and production well locations, pressure, and effective grid for the entire block in the existing reservoir model;

[0099] The geological data is cropped with the location of each oil well as the center by using image enhancement technology to obtain a first oil well parameter control training sample set;

[0100] Rotating the first oil well parameter control training sample set by image enhancement technology to obtain a second oil well parameter control training sample set;

[0101] The second oil well parameter control training sample set is flipped by image enhancement technology to obtain a third oil well parameter control training sample set.

[0102] Example 2

[0103] Reference Figure 2-7 , which is an embodiment of the present invention, provides a method and system for obtaining oil well parameter control training sample sets based on image enhancement. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0104] The reservoir model used in this paper is as follows: Figure 3 As shown, the model has 238*161*1 grids, with a grid size of 60.20m*58.88m*20.60m. The model has 93 oil wells and 77 water wells. Here, we only use the oil well parameter control training sample set as an example, assuming the required sample size is an 11*11 matrix data.

[0105] Multiple geological data sets for the entire block are extracted from the reservoir model, including permeability, saturation, and effective grid information. Each geological data set is a 238x161 matrix. Geological data can also be described as images, which are used here for illustration.

[0106] Using image enhancement technology, we cut out 93 11*11 grid blocks centered on the location of each oil well in the reservoir model from multiple geological data images obtained in advance, which are called the first oil well parameter control training sample set. The image enhancement and cutting effect of one sample is shown in the following figure: Figure 4 This ensures that all sample data is highly correlated with the oil and water wells. Since all cropped samples meet the sample size required for the research question, there is no need to fill the samples using image enhancement technology.

[0107] Use image enhancement technology to rotate all samples in the first oil well parameter control training sample set by 90 degrees, 180 degrees, and 270 degrees respectively. At this time, the new samples obtained by rotation and the first oil well parameter control training sample set are collectively referred to as the second oil well parameter control training sample set. The image enhancement rotation effect is shown in the following example. Figure 5 At this time, the number of samples in the second oil well parameter control training sample set is 4 times that of the first oil well parameter control training sample set.

[0108] Use image enhancement technology to flip all samples in the second oil well parameter control training sample set left and right respectively. At this time, the flipped samples and the second oil well parameter control training sample set are collectively referred to as the third oil well parameter control training sample set. The image enhancement flip effect is shown in the following example. Figure 6At this point, the number of samples in the third oil well parameter control training sample set will be 8 times that of the first oil well parameter control training sample set. That is, the initial 93 samples in the first oil well parameter control training sample set are expanded to 744 samples through the method of the present invention. Obviously, the number of samples has increased by an order of magnitude.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0111] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt 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. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal translation scripting language JavaScript, etc.

[0112] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0113] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0115] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0116] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for obtaining a training sample set for oil well parameter control based on image enhancement, characterized by: include, Obtain geological data on permeability, saturation, pore volume, pressure field, injection and production well locations, pressure, and effective grid for the entire block in the existing reservoir model; The geological data includes a matrix form or an image form; The geological data is cropped with the location of each oil well as the center by using image enhancement technology to obtain a first oil well parameter control training sample set; Rotating the first oil well parameter control training sample set by image enhancement technology to obtain a second oil well parameter control training sample set; flipping the second oil well parameter control training sample set by image enhancement technology to obtain a third oil well parameter control training sample set; The shearing process based on the location of each oil well includes: When the size of the cropped sample does not meet the target sample size, the sample that does not meet the target sample size is padded using image enhancement technology to ensure that the size of the padded sample is consistent with the target sample size; The rotation includes rotating the first oil well parameter control training sample set clockwise, When rotating 90 degrees, all geological data of the intercepted block are also rotated 90 degrees accordingly. The geological data of the new block generated by the rotation is similar to the original geological data, but the data position is rotated 90 degrees as a whole; When the data position is rotated 90 degrees as a whole, the layout of the injection and production well locations and permeability parameters are changed, thereby reducing the model's dependence on the weight of the two attributes; The rotation also includes, When rotating 180 degrees, all geological data of the intercepted block are also rotated 180 degrees accordingly. The geological data of the new block generated by the rotation is similar to the original geological data, but the data position is rotated 180 degrees as a whole; When the data position is rotated 180 degrees as a whole, the layout of the permeability and saturation parameters is changed, thereby reducing the model's dependence on the weights of the two attributes; The rotation also includes, When rotating 270 degrees, all geological data of the intercepted block are also rotated 270 degrees accordingly. The geological data of the new block generated by the rotation is similar to the original geological data, but the data position is rotated 270 degrees as a whole; When the data position is rotated 270 degrees, the permeability, saturation, and the layout of the injection and production wells are changed at the same time. This ensures that the model's dependence on the weights of the three attributes of permeability, saturation, and the layout of the injection and production wells is reduced. The flipping includes, When flipping left and right, all geological data of the intercepted block will also be flipped left and right. After flipping left and right, the geological data of the block is similar to the original geological data, but the data position is flipped left and right as a whole. When the data position is flipped left and right, the pore volume, pressure, injection and production well location, and effective grid layout are changed, which ensures that the model's weight dependence on pore volume, pressure, injection and production well location, and effective grid attributes is reduced; The flipping also includes, When flipping upside down, all geological data of the intercepted block will also be flipped upside down. After flipping upside down, the geological data of the block is similar to the original geological data, but the data position is flipped upside down as a whole; When the data positions are flipped up and down as a whole, the layout of permeability, saturation, and pressure changes, which ensures that the model's dependence on the weights of permeability, saturation, and pressure attributes is reduced.

2. A system using the method according to claim 1, characterized in that: Including data acquisition module, data cropping module, data rotation module and data flip module, A data acquisition module is used to obtain geological data of permeability, saturation, pore volume, pressure field, injection and production well locations, pressure, and effective grids for the entire block in the existing reservoir model; a data clipping module, wherein the data clipping module clips the geological data with the location of each oil well as the center using image enhancement technology to obtain a first oil well parameter control training sample set; a data rotation module, wherein the data rotation module rotates the first oil well parameter control training sample set by using image enhancement technology to obtain a second oil well parameter control training sample set; A data flipping module is used to flip the second oil well parameter control training sample set by using image enhancement technology to obtain a third oil well parameter control training sample set.

3. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to claim 1 are implemented.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images