Logging curve acquisition method and device and electronic equipment
The logging curve is optimized through the training log phase recognition model and the sensitivity curve screening algorithm, which solves the problem of difficulty in distinguishing electrical characteristics of reservoirs and improves the reservoir recognition ability and inversion accuracy.
Patent Information
- Application Number
- CN202310512868.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-08
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2043-05-08
AI Technical Summary
In areas with complex reservoir conditions such as low permeability, denseness, and lithologic components, it is difficult for the existing technology to effectively distinguish the electrical characteristics of different reservoirs, which affects the inversion accuracy, resulting in poor logging curve reconstruction effect.
The trained logging phase recognition model is used to process seismic response data, obtain predicted logging phases, and optimize the logging curves through different curve logging methods and preset sensitive curve screening algorithms to improve the electrical identification ability of reservoirs.
By optimizing the logging curve, the ability to identify the reservoir by electrical properties is significantly improved, and the inversion accuracy and reservoir prediction accuracy are improved.
Smart Images

Figure CN118915134A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of geophysical exploration, and in particular to a method, device and electronic equipment for acquiring well logging curves. Background Art
[0002] In the process of seismic data interpretation, in areas with complex reservoir conditions such as low permeability, tightness, and multiple lithologic components, improving the ability to identify reservoirs through electrical properties through curve optimization is a common and important task.
[0003] In the related technologies, there are many solutions to the problem of unclear electrical characteristics of different reservoirs, which affects the inversion accuracy. For example, a curve can be refitted by using curve sensitivity intersection analysis and other methods to distinguish different reservoirs and improve the electrical identification ability of reservoirs. However, the above methods do not fully consider the spatial distribution of wells involved in the curve reconstruction, resulting in wells without indicator features also participating in the curve reconstruction, resulting in poor curve reconstruction effect.
[0004] Therefore, how to optimize the logging curve and improve the ability of electrical properties to identify reservoirs is a technical problem that needs to be solved urgently. Summary of the invention
[0005] The embodiments of the present application provide a method, device, electronic device and storage medium for obtaining a well logging curve, which are used to optimize the well logging curve and improve the ability of electrical properties to identify reservoirs.
[0006] One of the embodiments of the present application provides a method for acquiring well logging curves, the method comprising: acquiring seismic response data of each well logging in a target work area; using a trained well logging phase identification model to process the seismic response data of each well logging to obtain predicted well logging phases of each well logging in the target work area; wherein the well logging phase identification model is a trained machine learning model; obtaining multiple target well loggings based on the predicted well logging phases of each well logging in the target work area; wherein the target well logging is a well logging within the dominant phase range; performing the following processing on each of the target well loggings: using different curve logging methods to obtain multiple original well logging curves of the target well logging; using a preset sensitive curve screening algorithm to determine a sensitive curve from the multiple original well logging curves; and according to the sensitive curve, using a preset curve optimization algorithm to obtain a final well logging curve of the target well logging.
[0007] In some embodiments, the well logging phase identification model is obtained in the following manner: obtaining a training sample set; wherein the training sample set includes multiple groups of training samples, each group of the training samples includes seismic response data as sample data and well logging phases as labels; using an initial well logging phase identification model, processing the seismic response data in each group of training samples to obtain the predicted well logging phase corresponding to the seismic response data in each group of the training samples; wherein the initial well logging phase identification model is a clustering model; according to the difference between the predicted well logging phase corresponding to the seismic response data in each group of the training samples and the label of the seismic response data, adjusting the parameters of the initial well logging phase identification model until the convergence condition of the model is met, thereby obtaining a trained well logging phase identification model.
[0008] In some embodiments, the acquisition of the training sample set includes: using well-seismic joint technology to process the logging phases and seismic response data of multiple wells to obtain the correspondence between the logging phases and the seismic response data; based on the correspondence between the logging phases and the seismic response data, each type of seismic response data and the corresponding logging phase are used as a group of training samples in the training sample set.
[0009] In some embodiments, the well logging phase identification model is a clustering model, and the well logging phase identification model after training is used to process the seismic response data of each well logging to obtain the predicted well logging phase of each well logging in the target work area, including: using the well logging phase identification model to cluster the seismic response data of each well logging to obtain multiple seismic response data sets and their corresponding predicted well logging phases; using the predicted well logging phase corresponding to each seismic response data set as the predicted well logging phase of the well logging corresponding to each seismic response data in the seismic response data set.
[0010] One of the embodiments of the present application provides a device for acquiring well logging curves, the device comprising: a first acquisition module, used to acquire seismic response data of each well logging in a target work area; a second acquisition module, used to use a trained well logging phase identification model to process the seismic response data of each well logging to obtain the predicted well logging phase of each well logging in the target work area; wherein the well logging phase identification model is a trained machine learning model; a third acquisition module, used to obtain multiple target well loggings based on the predicted well logging phases of each well logging in the target work area; wherein the target well logging is the well logging within the dominant phase range; a fourth acquisition module, used to perform the following processing on each of the target well loggings: using different curve logging methods to obtain multiple original well logging curves of the target well logging; using a preset sensitive curve screening algorithm to determine a sensitive curve from the multiple original well logging curves; and according to the sensitive curve, using a preset curve optimization algorithm to obtain a final well logging curve of the target well logging.
[0011] An embodiment of the present application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the method described above when running the program.
[0012] An embodiment of the present application provides a storage medium for storing a computer-readable program. When the computer-readable program is executed, the method described above is executed.
[0013] The above technical solution provided by the embodiment of the present application has at least the following advantages compared with the prior art:
[0014] In the embodiment provided by the present application, the seismic response data of each well logging is processed using the trained well logging phase identification model to obtain the predicted well logging phase of each well logging in the target work area; multiple target well loggings are obtained based on the predicted well logging phase of each well logging in the target work area; each target well logging is processed as follows: different curve well logging methods are used to obtain multiple original well logging curves of the target well logging; a preset sensitive curve screening algorithm is used to determine the sensitive curve from multiple original well logging curves; based on the sensitive curve, a preset curve optimization algorithm is used to obtain the final well logging curve of the target well logging. In this way, the well logging curve can be effectively optimized to improve the ability of electrical properties to identify the reservoir. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The present application will be further described in the form of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:
[0016] Figure 1 is an exemplary flow chart of a method for obtaining a well logging curve according to some embodiments of the present application;
[0017] Figure 2 is an exemplary flow chart of a method for training a well logging phase identification model according to some embodiments of the present application;
[0018] Figure 3 is an exemplary schematic diagram of the correspondence between seismic phases and well logging phases according to some embodiments of the present application;
[0019] Figure 4 is an exemplary schematic diagram of clustering results shown in some embodiments of the present application;
[0020] Figure 5 is an exemplary schematic diagram of an optimal sensitivity curve according to the intersection method shown in some embodiments of the present application;
[0021] Figure 6a is an exemplary schematic diagram of an original natural gamma histogram according to some embodiments of the present application;
[0022] Figure 6b is an exemplary schematic diagram of a natural gamma histogram after direct curve optimization according to some embodiments of the present application;
[0023] Figure 6c is an exemplary schematic diagram of a natural gamma histogram after phase control curve optimization according to some embodiments of the present application;
[0024] Figure 7 is an exemplary schematic diagram of a device for acquiring a well logging curve according to some embodiments of the present application;
[0025] Figure 8 It is a schematic diagram of an exemplary structure of an electronic device according to some embodiments of the present application. DETAILED DESCRIPTION
[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.
[0027] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.
[0028] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprises" and "includes" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.
[0029] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, the various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.
[0030] For ease of understanding, the technical solution of the present application is introduced below in conjunction with the accompanying drawings and embodiments.
[0031] Figure 1is an exemplary flow chart of a method for obtaining a logging curve according to some embodiments of the present application. Figure 1 As shown, the method for obtaining the well logging curve includes the following steps:
[0032] Step S110, obtaining seismic response data of each well logging in the target work area.
[0033] The target work area is a work area where the geological structure of the reservoir in which it is located needs to be identified through well logging curves. In some embodiments, the target work area may be an area with complex reservoir conditions such as low permeability, tightness, and multiple lithology components.
[0034] Seismic response data, which may include but are not limited to: the amplitude, continuity, frequency and other characteristics of seismic reflection waves.
[0035] Step S120, using the trained logging phase identification model to process the seismic response data of each well logging, to obtain the predicted logging phase of each well logging in the target work area; wherein the logging phase identification model is a trained machine learning model.
[0036] Well logging phase refers to the curve characteristics, lithology and other characteristics of well logging at different depth sections.
[0037] In the specific implementation process, the logging phase identification model can be constructed based on a variety of machine learning models, including but not limited to: classification models (for example, decision trees, random forests, etc.), clustering models (for example, K-means clustering algorithm), etc.
[0038] For the training method of well logging phase recognition model, see Figure 2 The relevant content in will not be repeated here.
[0039] In some embodiments, the well logging phase identification model is a clustering model, and the input of the well logging phase identification model is seismic response data; the output is a seismic response data set, and a variety of identifiers can be used to represent the seismic response data set. For example, Arabic numerals (1, 2, 3, 4, etc.) can be used to represent different seismic response data sets.
[0040] In some embodiments, the trained logging phase identification model can be used to process the seismic response data of each well logging to obtain the predicted logging phase of each well logging in the target work area in the following manner:
[0041] The seismic response data of each well logging are clustered using a well logging phase identification model to obtain multiple seismic response data sets and their corresponding predicted well logging phases; the predicted well logging phase corresponding to each seismic response data set is used as the predicted well logging phase of the well logging corresponding to each seismic response data in the seismic response data set.
[0042] As an example only, the well logging phase identification model can be used to obtain Figure 4 The clustering results shown ( Figure 4 The clustering result (within the black line) is the plane distribution range with similar reflection characteristics of the river phase.
[0043] Step S130, obtaining a plurality of target well loggings according to the predicted well logging phases of each well logging in the target work area; wherein the target well logging is the well logging within the dominant phase range.
[0044] The dominant phase refers to the phase belt in which the target geological body is the most developed.
[0045] In the specific implementation process, it can be determined whether the geological body corresponding to each well logging in the target work area is the most developed according to the predicted logging phase, and the well logging with the most developed geological body is used as the target logging.
[0046] For each target well log obtained in step S130, the following steps are performed.
[0047] Step S140, using different curve logging methods to obtain a variety of original logging curves of the target well.
[0048] The original logging curve is a curve formed during logging, which can reflect the different lithology and stratigraphic characteristics of different reservoirs, and then the lithology, stratigraphic characteristics and other characteristics of the specific reservoir can be determined based on the logging curve.
[0049] Commonly used curve measurement methods include: natural gamma logging, resistance logging, sonic time difference logging, etc.
[0050] Step S150: using a preset sensitivity curve screening algorithm to determine a sensitivity curve from a plurality of original logging curves.
[0051] Sensitive curve refers to one or several logging curves among various logging curves that best reflect the characteristics of the target geological body.
[0052] In some embodiments, the preset sensitivity curve screening algorithm may be an intersection analysis algorithm, and the intersection analysis algorithm may be used to select the sensitivity curve of the target well logging from the multiple original well logging curves of the target well logging obtained in step S140.
[0053] Just as an example, Figure 5 As shown in the figure, the histogram intersection analysis is performed on the natural gamma curve, resistivity curve, acoustic wave curve and density curve respectively to judge the recognition ability of different curves for the sandstone and mudstone of the target logging. From the analysis results, the natural gamma curve has the best recognition effect, so the natural gamma curve can be used as a sensitive curve.
[0054] In step S160, a final logging curve of the target well logging is obtained according to the sensitivity curve using a preset curve optimization algorithm.
[0055] The curve optimization algorithm is an algorithm to improve the recognition ability of the sensitivity curve to the reservoir, and to refit the sensitivity curve into a new curve according to certain rules.
[0056] In the specific implementation process, you can choose to use a neural network to implement the preset curve optimization algorithm according to the processing effect, or you can use mathematical operations to implement the preset curve optimization algorithm, which is not limited by the description of this specification.
[0057] As an example only, according to Figure 6a , 6b Compared with 6c, the natural gamma after phase control curve optimization has the best effect on distinguishing sandstone and mudstone, that is, the overlap area of sandstone and mudstone in the histogram is the smallest. Therefore, the curve after phase control optimization can be used as the final logging curve of the target logging.
[0058] In the embodiment of the present application, the trained logging phase identification model is used to process the seismic response data of each well logging to obtain the predicted logging phase of each well logging in the target work area. Based on the predicted logging phase of each well logging in the target work area, multiple target well loggings are obtained, which fully utilizes the spatial constraint advantage of the seismic response data, selects the well logging with the most developed geological body, and performs curve logging, which effectively improves the electrical identification ability of the reservoir, and is of great significance to the subsequent inversion and reservoir prediction work.
[0059] Figure 2 is an exemplary flow chart of a method for training a well logging phase identification model according to some embodiments of the present application. Figure 2 As shown, the method includes the following steps.
[0060] Step S210, obtaining a training sample set; wherein the training sample set includes multiple groups of training samples, each group of training samples includes seismic response data as sample data and logging phases as labels.
[0061] For a detailed description of seismic response data and well log facies, see Figure 1 The relevant content in will not be repeated here.
[0062] In the specific implementation process, the well-seismic joint technology can be used to process the logging phases and seismic response data of multiple wells to obtain the corresponding relationship between the logging phases and the seismic response data; according to the corresponding relationship between the logging phases and the seismic response data, each type of seismic response data and the corresponding logging phase are used as a group of training samples in the training sample set.
[0063] Well-seismic integration refers to the use of time-depth calibration methods to establish a relationship between depth-domain well logging and time-domain seismic data in the time domain. Well-seismic integration can clarify the seismic response characteristics corresponding to the characteristics of different logging sections.
[0064] As an example only, for multiple well logging in the target work area (such as Figure 3 The corresponding relationship between the logging phase and the seismic response of each well can be determined by the well-seismic joint technology, and the following can be established: Figure 3 As shown, the correspondence between the lithological characteristics of multiple logging well points and the reflection characteristics of the seismic wave group is used to obtain a training sample set.
[0065] In the specific implementation process, in order to fully understand the geological information of the target work area, macroscopic geological data of the target work area can be collected and studied. Macroscopic geological data helps geophysicists understand the sedimentary environment of the region and has guiding significance for improving the understanding of seismic phases. Macroscopic geological data can include but are not limited to paleogeomorphology, stratigraphic characteristics, sedimentary patterns, sedimentary phases and other data of a region.
[0066] Step S220, using the initial logging phase identification model, processing the seismic response data in each group of training samples to obtain the predicted logging phase corresponding to the seismic response data in each group of training samples; wherein the initial logging phase identification model is a clustering model.
[0067] For a detailed description of using the initial logging phase identification model to process the seismic response data in each set of training samples to obtain the predicted logging phase corresponding to the seismic response data in each set of training samples, please refer to the relevant content in step S120, which will not be repeated here.
[0068] Step S230, according to the difference between the predicted logging phase corresponding to the seismic response data in each group of training samples and the label of the seismic response data, the parameters of the initial logging phase identification model are adjusted until the convergence condition of the model is met, thereby obtaining a trained logging phase identification model.
[0069] As an example only, the initial logging phase identification model is a K-mean clustering model. The loss function can be used to determine the difference between the actual result and the identification result, and the parameters of the K-mean clustering model can be adjusted using an optimization algorithm to iteratively train the initial logging phase identification model.
[0070] The convergence condition of the model may be that the recognition accuracy of the initial logging phase recognition model is greater than a preset threshold (eg, 99%), or the number of training times reaches a preset value.
[0071] Figure 7 It is an exemplary schematic diagram of a device for acquiring logging curves according to some embodiments of the present application.
[0072] like Figure 7 As shown, the device for acquiring the logging curve includes: a first acquisition module 710 , a second acquisition module 720 , a third acquisition module 730 and a fourth acquisition module 740 .
[0073] The first acquisition module 710 is used to acquire the seismic response data of each well logging in the target work area.
[0074] The second acquisition module 720 is used to use the trained logging phase identification model to process the seismic response data of each well logging to obtain the predicted logging phase of each well logging in the target work area; wherein the logging phase identification model is a trained machine learning model.
[0075] The third acquisition module 730 is used to obtain multiple target well loggings according to the predicted well logging phases of each well logging in the target work area; wherein the target well logging is the well logging within the dominant phase range.
[0076] The fourth acquisition module 740 is used to perform the following processing on each of the target well logging: using different curve logging methods to obtain multiple original logging curves of the target well logging; using a preset sensitive curve screening algorithm to determine a sensitive curve from the multiple original logging curves; based on the sensitive curve, using a preset curve optimization algorithm to obtain the final logging curve of the target well logging.
[0077] In some embodiments, the well logging phase identification model is obtained in the following manner: obtaining a training sample set; wherein the training sample set includes multiple groups of training samples, each group of the training samples includes seismic response data as sample data and well logging phases as labels; using an initial well logging phase identification model, processing the seismic response data in each group of training samples to obtain the predicted well logging phase corresponding to the seismic response data in each group of the training samples; wherein the initial well logging phase identification model is a clustering model; according to the difference between the predicted well logging phase corresponding to the seismic response data in each group of the training samples and the label of the seismic response data, adjusting the parameters of the initial well logging phase identification model until the convergence condition of the model is met, thereby obtaining a trained well logging phase identification model.
[0078] In some embodiments, the acquisition of the training sample set includes: using well-seismic joint technology to process the logging phases and seismic response data of multiple wells to obtain the correspondence between the logging phases and the seismic response data; based on the correspondence between the logging phases and the seismic response data, each type of seismic response data and the corresponding logging phase are used as a group of training samples in the training sample set.
[0079] In some embodiments, the well logging phase identification model is a clustering model, and the well logging phase identification model after training is used to process the seismic response data of each well logging to obtain the predicted well logging phase of each well logging in the target work area, including: using the well logging phase identification model to cluster the seismic response data of each well logging to obtain multiple seismic response data sets and their corresponding predicted well logging phases; using the predicted well logging phase corresponding to each seismic response data set as the predicted well logging phase of the well logging corresponding to each seismic response data in the seismic response data set.
[0080] In the above-mentioned embodiment of the device for acquiring well logging curves, the specific processing of each module and the technical effects brought about by it can be referred to the relevant descriptions in the corresponding method embodiment, which will not be repeated here.
[0081] Figure 8 It is a schematic diagram of an exemplary structure of an electronic device according to some embodiments of the present application.
[0082] like Figure 8 As shown, the electronic device includes: at least one processor 801, at least one communication interface 802, at least one memory 803 and at least one communication bus 804; optionally, the communication interface 802 can be an interface of a communication module, such as an interface of a GSM module; the processor 801 may be a processor CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. The memory 803 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Among them, the memory 803 stores a program, and the processor 801 calls the program stored in the memory 803 to execute part or all of the above-mentioned method embodiments.
[0083] The present application relates to a storage medium for storing a computer-readable program. When the computer-readable program is executed, part or all of the above-mentioned method embodiments are executed.
[0084] Alternatively, the storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
[0085] Based on the same inventive concept, an embodiment of the present application further provides a computer program product, including a computer program, which implements part or all of the above-mentioned method embodiments when executed by a processor.
[0086] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.
[0087] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or multiple times in different positions in the present application does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.
[0088] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.
[0089] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.
[0090] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values is as accurate as possible within the feasible range.
[0091] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.
[0092] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.
Claims
1. A method for obtaining a well logging curve, characterized in that: The method comprises: Obtain seismic response data of each well in the target work area; Using the trained logging phase identification model, the seismic response data of each well logging are processed to obtain the predicted logging phase of each well logging in the target work area; wherein the logging phase identification model is a trained machine learning model; According to the predicted logging phases of each well logging in the target work area, a plurality of target well loggings are obtained; wherein the target well loggings are well loggings within the dominant phase range; For each target well log, the following processing is performed: Using different curve logging methods, a plurality of original logging curves of the target well are obtained; Using a preset sensitivity curve screening algorithm, a sensitivity curve is determined from the multiple original logging curves; According to the sensitivity curve, a preset curve optimization algorithm is used to obtain the final logging curve of the target well logging.
2. The method according to claim 1, characterized in that The logging phase identification model is obtained by the following method: Acquire a training sample set; wherein the training sample set includes multiple groups of training samples, each group of training samples includes seismic response data as sample data and logging phases as labels; Using the initial logging phase identification model, the seismic response data in each group of training samples are processed to obtain the predicted logging phase corresponding to the seismic response data in each group of training samples; wherein the initial logging phase identification model is a clustering model; According to the difference between the predicted logging phase corresponding to the seismic response data in each group of the training samples and the label of the seismic response data, the parameters of the initial logging phase identification model are adjusted until the convergence condition of the model is met to obtain a trained logging phase identification model.
3. The method according to claim 2, characterized in that The step of obtaining a training sample set includes: Using well-seismic joint technology, the logging phases and seismic response data of multiple wells are processed to obtain the corresponding relationship between the logging phases and seismic response data; According to the corresponding relationship between the logging phase and the seismic response data, each type of seismic response data and the corresponding logging phase are used as a group of training samples in the training sample set.
4. The method according to claim 1, characterized in that: The well logging phase identification model is a clustering model. The well logging phase identification model after training is used to process the seismic response data of each well logging to obtain the predicted well logging phase of each well logging in the target work area, including: Clustering the seismic response data of each well logging using the well logging phase identification model to obtain multiple seismic response data sets and their corresponding predicted well logging phases; The predicted logging phase corresponding to each of the seismic response data sets is used as the predicted logging phase of the wells corresponding to each of the seismic response data in the seismic response data set.
5. A device for acquiring a well logging curve, characterized in that: The device comprises: The first acquisition module is used to acquire the seismic response data of each well logging in the target work area; A second acquisition module is used to process the seismic response data of each well logging using the trained well logging phase identification model to obtain the predicted well logging phase of each well logging in the target work area; wherein the well logging phase identification model is a trained machine learning model; A third acquisition module is used to obtain a plurality of target well loggings according to the predicted well logging phases of each well logging in the target work area; wherein the target well logging is the well logging within the dominant phase range; The fourth acquisition module is used to perform the following processing on each of the target well logs: Using different curve logging methods, a plurality of original logging curves of the target well are obtained; Using a preset sensitivity curve screening algorithm, a sensitivity curve is determined from the multiple original logging curves; According to the sensitivity curve, a preset curve optimization algorithm is used to obtain the final logging curve of the target well logging.
6. The device according to claim 5, characterized in that The logging phase identification model is obtained by the following method: Acquire a training sample set; wherein the training sample set includes multiple groups of training samples, each group of training samples includes seismic response data as sample data and logging phases as labels; Using the initial logging phase identification model, the seismic response data in each group of training samples are processed to obtain the predicted logging phase corresponding to the seismic response data in each group of training samples; wherein the initial logging phase identification model is a clustering model; According to the difference between the predicted logging phase corresponding to the seismic response data in each group of the training samples and the label of the seismic response data, the parameters of the initial logging phase identification model are adjusted until the convergence condition of the model is met to obtain a trained logging phase identification model.
7. The device according to claim 6, characterized in that The step of obtaining a training sample set includes: Using well-seismic joint technology, the logging phases and seismic response data of multiple wells are processed to obtain the corresponding relationship between the logging phases and seismic response data; According to the corresponding relationship between the logging phase and the seismic response data, each type of seismic response data and the corresponding logging phase are used as a group of training samples in the training sample set.
8. The device according to claim 5, characterized in that The well logging phase identification model is a clustering model. The well logging phase identification model after training is used to process the seismic response data of each well logging to obtain the predicted well logging phase of each well logging in the target work area, including: Clustering the seismic response data of each well logging using the well logging phase identification model to obtain multiple seismic response data sets and their corresponding predicted well logging phases; The predicted logging phase corresponding to each of the seismic response data sets is used as the predicted logging phase of the wells corresponding to each of the seismic response data in the seismic response data set.
9. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the method according to any one of claims 1 to 4 when running the program.
10. A storage medium for storing a computer-readable program, wherein when the computer-readable program is executed, the method according to any one of claims 1 to 4 is executed.
Citation Information
Patent Citations
System and method for facies classification
CN104335074A
Well logging curve identification method based on clustering algorithm
CN110674841A
Logging curve prediction method and system based on deep learning
CN110927798A
Well logging curve standardization method and system based on sedimentary facies constraint
CN110965997A
Shallow lake basin reservoir prediction method and device based on micro-ancient landform recovery
CN111983671A
