Uranium removal method, device and equipment for gamma curve and medium
Through machine learning models and analysis of the characteristic values of logging parameters, the problem that traditional uranium de-uranium methods cannot completely remove the impact of uranium minerals is solved, and high-precision uranium de-uranium treatment of the gamma curve is achieved to support oil and gas exploration.
Patent Information
- Application Number
- CN202411564016.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2025-02-14
AI Technical Summary
The traditional gamma curve treatment method cannot completely eliminate the impact of uranium minerals, resulting in the fact that the part of the gamma curve after uranium removal is still affected by uranium minerals.
Through the machine learning model, the characteristic values of the well logging parameters of the reservoir are obtained, the classification category to which the reservoir belongs is determined, the natural gamma curve and logging parameters are used as training data, and the de-uranium model is trained to obtain the de-uranium gamma Horse curve.
High-precision de-uranium treatment of natural gamma curves is achieved, eliminating the impact of uranium minerals and providing more accurate oil and gas exploration support.
Smart Images
Figure CN119441890A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of natural gamma curve deuranization, and in particular to a gamma curve deuranization method, device, equipment and medium. Background Art
[0002] If the natural gamma curve is affected by uranium minerals, it should not be used directly. Traditional gamma curve processing and deuranization methods include energy spectrum analysis method, ratio method, etc. The above deuranization methods cannot completely eliminate the influence of uranium minerals, resulting in the presence of uranium minerals in the gamma curve after deuranization. Summary of the invention
[0003] The present invention provides a method, device, equipment and medium for deuranization of a gamma curve, which can complete the deuranization of a natural gamma curve through a machine learning model to obtain a gamma curve after deuranization, thereby providing support for subsequent oil and gas exploration.
[0004] According to one aspect of the present invention, a method for removing uranium from a gamma curve is provided, the method comprising:
[0005] Acquire characteristic values of logging parameters of the reservoir; the logging parameters include: resistivity, density, number of thermal neutrons and natural gamma value; the characteristic values reflect the statistical characteristics of the logging parameters;
[0006] Determine the classification category to which the reservoir belongs from among the pre-divided classification categories according to the characteristic values of the logging parameters of the reservoir;
[0007] The natural gamma curve and logging parameters of the reservoir are used as training data, the classification category to which the reservoir belongs is determined as a label, and the uranium removal model of the gamma curve to be trained is trained to obtain the uranium removal model of the trained gamma curve; the uranium removal model of the trained gamma curve is used to remove uranium from the natural gamma curve to obtain the uranium removal gamma curve.
[0008] According to another aspect of the present invention, there is provided a deuranium removal device for a gamma curve, comprising:
[0009] A characteristic value acquisition module is used to acquire characteristic values of logging parameters of the reservoir; the logging parameters include: resistivity, density, number of thermal neutrons and natural gamma value; the characteristic values reflect the statistical characteristics of the logging parameters;
[0010] A classification category determination module, used to determine the classification category to which the reservoir belongs from among the pre-divided classification categories according to the characteristic values of the logging parameters of the reservoir;
[0011] The model training module is used to use the natural gamma curve and logging parameters of the reservoir as training data, determine the classification category to which the reservoir belongs as a label, train the uranium removal model of the gamma curve to be trained, and obtain the uranium removal model of the trained gamma curve; the uranium removal model of the trained gamma curve is used to remove uranium from the natural gamma curve to obtain the uranium removal gamma curve.
[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0013] at least one processor; and
[0014] a memory communicatively connected to the at least one processor; wherein,
[0015] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the deuranium removal method of the gamma curve described in any embodiment of the present invention.
[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the deuranium removal method of a gamma curve described in any embodiment of the present invention when executed.
[0017] The technical solution of the embodiment of the present application includes: obtaining characteristic values of logging parameters of the reservoir; the logging parameters include: resistivity, density, number of thermal neutrons and natural gamma value; the characteristic values reflect the statistical characteristics of the logging parameters; determining the classification category to which the reservoir belongs in each pre-divided classification category according to the characteristic values of the logging parameters of the reservoir; using the natural gamma curve and the logging parameters of the reservoir as training data, determining the classification category to which the reservoir belongs as a label, training the deuranium model of the gamma curve to be trained, and obtaining the deuranium model of the trained gamma curve; the deuranium model of the trained gamma curve is used to deuranium the natural gamma curve to obtain the deuranium gamma curve. By determining the category label of the training data, the technical solution enables the trained deuranium model of the gamma curve to more accurately deuranium the natural gamma curve according to the corresponding category of the input data.
[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0020] Figure 1 It is a flow chart of a deuranium method of a gamma curve provided in accordance with the first embodiment of the present application;
[0021] Figure 2 It is a flow chart of a deuranium method of a gamma curve provided in Example 2 of the present application;
[0022] Figure 3 is a schematic diagram of a deuranium gamma curve provided according to Example 2 of the present application;
[0023] Figure 4 It is a structural schematic diagram of a gamma curve deuranium removal device provided according to Example 3 of the present application. DETAILED DESCRIPTION
[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0025] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0026] Embodiment 1
[0027] Figure 1A flowchart of a method for removing uranium from a gamma curve is provided for the first embodiment of the present application. The embodiment of the present application is applicable to the case of removing uranium from a natural gamma curve. The method can be performed by a device for removing uranium from a gamma curve. The device for removing uranium from a gamma curve can be implemented in the form of hardware and / or software. The device for removing uranium from a gamma curve can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:
[0028] S110, obtaining characteristic values of logging parameters of the reservoir.
[0029] The logging parameters include resistivity, density, thermal neutron number and natural gamma value; the data corresponding to the logging parameters can be obtained through logging. The characteristic value reflects the statistical characteristics of the logging parameters, and the characteristic value is the maximum value, minimum value, mode and variance.
[0030] For example, taking the logging parameter as resistivity, resistivity logging data can be obtained through resistivity logging, and the maximum value, minimum value, mode and variance in the resistivity logging data are counted to obtain the characteristic value of resistivity. The same is true for other logging parameters, and the embodiments of the present application will not be described one by one.
[0031] Specifically, the technical solution of the embodiment of the present application performs deuranization processing on the natural gamma curve through the deuranization model of the gamma curve, and S110, S120 and S130 can reflect the process of obtaining the deuranization model of the trained gamma curve.
[0032] S120, determining the classification category to which the reservoir belongs from among the pre-divided classification categories according to the characteristic values of the logging parameters of the reservoir.
[0033] Among them, the classification categories can be pre-divided, each classification category reflects different reservoir geological information, and each classification category includes the interval range of characteristic values of resistivity, the interval range of characteristic values of density, the interval range of characteristic values of the number of thermal neutrons, and the interval range of characteristic values of natural gamma values.
[0034] Specifically, the classification category that the resistivity may correspond to is determined based on the degree of match between the maximum value, minimum value, mode and variance of the resistivity of the reservoir and each classification category; the classification category that the density may correspond to is determined based on the degree of match between the maximum value, minimum value, mode and variance of the density of the reservoir and each classification category; the classification category that the thermal neutron number may correspond to is determined based on the degree of match between the maximum value, minimum value, mode and variance of the thermal neutron number of the reservoir and each classification category; the classification category that the natural gamma value may correspond to is determined based on the degree of match between the maximum value, minimum value, mode and variance of the natural gamma value of the reservoir and each classification category; and then the classification category with the highest degree of match for the reservoir is determined from the above-determined classification categories.
[0035] S130, taking the natural gamma curve and logging parameters of the reservoir as training data, determining the classification category to which the reservoir belongs as a label, training the uranium removal model of the gamma curve to be trained, and obtaining the trained uranium removal model of the gamma curve.
[0036] The deuranium model of the trained gamma curve is used to perform deuranium processing on the natural gamma curve to obtain a deuranium gamma curve.
[0037] Specifically, since resistivity, density, number of thermal neutrons and natural gamma value reflect the degree to which the reservoir is affected by uranium, and the same logging parameter reflects different degrees of influence of uranium on the reservoir, the embodiment of the present application performs classification according to the characteristic values of the above logging parameters to determine the classification category that matches the characteristic values of the logging parameters of the reservoir; and then when training the uranium removal model of the gamma curve, the category corresponding to each piece of training data can be marked, so that the uranium removal model of the gamma curve can more accurately remove uranium from the natural gamma curve.
[0038] In an embodiment of the present application, when performing model training, the natural gamma curve and logging parameters of the reservoir are used as training data, and the classification category to which the reservoir belongs is determined as a label. When training, supervision is performed through the gamma curve after uranium removal, and a uranium removal model of the trained gamma curve is obtained.
[0039] The technical solution of the embodiment of the present application includes: obtaining characteristic values of logging parameters of the reservoir; the logging parameters include: resistivity, density, number of thermal neutrons and natural gamma value; the characteristic values reflect the statistical characteristics of the logging parameters; determining the classification category to which the reservoir belongs in each pre-divided classification category according to the characteristic values of the logging parameters of the reservoir; using the natural gamma curve and the logging parameters of the reservoir as training data, determining the classification category to which the reservoir belongs as a label, training the deuranium model of the gamma curve to be trained, and obtaining the deuranium model of the trained gamma curve; the deuranium model of the trained gamma curve is used to deuranium the natural gamma curve to obtain the deuranium gamma curve. By determining the category label of the training data, the technical solution enables the trained deuranium model of the gamma curve to more accurately deuranium the natural gamma curve according to the corresponding category of the input data.
[0040] Embodiment 2
[0041] Figure 2 This is a flow chart of a method for removing uranium from a gamma curve provided in Example 2 of the present application. The embodiment of the present application is optimized based on the above embodiment.
[0042] like Figure 2 As shown, the method of the embodiment of the present application specifically includes the following steps:
[0043] S210, obtaining characteristic values of logging parameters of the reservoir.
[0044] The logging parameters include: resistivity, density, thermal neutron quantity and natural gamma value; the characteristic values reflect the statistical characteristics of the logging parameters; the characteristic values include: maximum value, minimum value, mode and variance.
[0045] In an embodiment of the present application, optionally, obtaining characteristic values of logging parameters of the reservoir includes: obtaining resistivity logging data; performing statistics on the resistivity logging data to obtain the maximum value, minimum value, mode and variance of the resistivity; obtaining density logging data; performing statistics on the density logging data to obtain the maximum value, minimum value, mode and variance of the density; obtaining neutron logging data; performing statistics on the neutron logging data to obtain the maximum value, minimum value, mode and variance of the number of thermal neutrons; obtaining natural gamma logging data; performing statistics on the natural gamma logging data to obtain the maximum value, minimum value, mode and variance of the natural gamma value.
[0046] The scheme is configured in this way so that the category corresponding to the logging parameter of the reservoir can be quickly determined through the characteristic value of the logging parameter.
[0047] S220, traversing each well logging parameter, and determining the target classification category to which the current well logging parameter belongs according to the characteristic value of the current well logging parameter in each classification category.
[0048] In an embodiment of the present application, optionally, the classification category includes the interval range of each eigenvalue of each logging parameter; accordingly, in each classification category, the target classification category to which the current logging parameter belongs is determined according to the eigenvalue of the current logging parameter, including: traversing each eigenvalue of the current logging parameter to determine the target interval range to which the current eigenvalue belongs; increasing the integral value of the classification category corresponding to the target interval range; if it is determined that the traversal of each eigenvalue is completed, the classification category with the highest integral is determined as the target classification category to which the current logging parameter belongs.
[0049] In the embodiment of the present application, the classification category corresponding to the reservoir needs to be determined according to the classification category corresponding to each logging parameter. The present technical solution can accurately determine the classification category corresponding to each logging parameter.
[0050] Specifically, for the current logging parameter, its eigenvalues are traversed one by one. During the traversal, the interval range of the eigenvalues of the current logging parameter corresponding to each classification category can be obtained, from which the target interval range to which the current eigenvalue belongs is determined. Since the classification category corresponding to the target interval range is the category corresponding to the current eigenvalue, the integral value of the classification category corresponding to the target interval range can be increased; if it is determined that the traversal of each eigenvalue is completed, the classification category with the highest integral is determined as the target classification category to which the current logging parameter belongs.
[0051] In an embodiment of the present application, optionally, increasing the integral value of the classification category corresponding to the target interval range includes: determining the interval minimum value and the interval maximum value of the target interval range; calculating a first difference between a current eigenvalue and the interval minimum value, and a second difference between the interval maximum value and the current eigenvalue; determining an integral increase value based on a ratio of the first difference to the second difference; and integrally increasing the integral value of the classification category corresponding to the target interval range based on the integral increase value.
[0052] Exemplarily, when increasing the integral value of the classification category corresponding to the target interval range, if the current feature value is in the middle of the target interval range, it means that the current feature value has a higher degree of match with the classification category, and the integral value can be appropriately increased when increasing the integral value, that is: if the ratio of the first difference to the second difference is closer to 1, the determined integral increase value can be higher.
[0053] Specifically, if the ratio of the first difference to the second difference is greater than 1 / 2 and less than 2, the integral increase value is determined to be 2; otherwise, the integral increase value is determined to be 1.
[0054] This scheme is set up so that the integral value can more accurately reflect the correspondence between the current logging parameters and the target classification category.
[0055] S230, increasing the integral value of the target classification category.
[0056] S240: If it is determined that the traversal of the logging parameters is completed, the classification category with the highest score is determined as the classification category to which the reservoir belongs.
[0057] For example, if the classification category to which three logging parameters belong is A and the classification category to which one logging parameter belongs is B, then A is determined to be the classification category to which the reservoir belongs.
[0058] S250, taking the natural gamma curve and logging parameters of the reservoir as training data, determining the classification category to which the reservoir belongs as a label, training the uranium removal model of the gamma curve to be trained, and obtaining the trained uranium removal model of the gamma curve.
[0059] The deuranium model of the trained gamma curve is used to perform deuranium processing on the natural gamma curve to obtain a deuranium gamma curve.
[0060] In an embodiment of the present application, optionally, the method further includes: obtaining a natural gamma curve to be processed and logging data of the area to be processed; inputting the natural gamma curve to be processed and the logging data into a uranium-removed model of the trained gamma curve to obtain a uranium-removed gamma curve.
[0061] Specifically, if the uranium removal model of the gamma curve has been trained, the natural gamma curve to be processed and the logging data of the area to be processed are obtained, and the logging data may include: neutron logging, density logging, resistivity logging and natural gamma logging; the natural gamma curve to be processed and the logging data of the area to be processed are input into the trained uranium removal model of the gamma curve to obtain the uranium removal gamma curve.
[0062] In the embodiment of the present application, optionally, the method further comprises: performing deconvolution processing on the de-uranium gamma curve and the noise function to obtain the de-uranium gamma curve after noise is removed.
[0063] The de-uranium gamma curve is regarded as the convolution of the true value and the noise Sm(z)=St(z)*k(z), assuming that the noise function is Convolution can obtain Sm(z)*k-1(z)=St(z)*k(z)*k-1(z). After Fourier transform of the noise function, the true value of deconvolution St(z) is obtained, that is, the de-uranium gamma curve after noise removal.
[0064] The technical solution of the embodiment of the present application accurately identifies the classification category to which the logging parameters of the reservoir belong through the characteristic values of the logging parameters, and then trains the uranium removal model of the gamma curve to be trained based on the category and training data to obtain the uranium removal model of the trained gamma curve. When the uranium removal model of the trained gamma curve is applied, the uranium removal gamma curve and the noise function output by the model are deconvoluted to obtain the uranium removal gamma curve after noise removal, and the uranium removal gamma curve after noise removal can better reflect the accurate information of the reservoir.
[0065] In a specific example, if Figure 3 As shown, Figure 3 It is a schematic diagram of the deuranium gamma curve. The first track is a comparison between the natural gamma curve (GR) and the measured deuranium gamma curve (KTH). The second track is a comparison between the inverted deuranium gamma curve (KTH_PRED) and the measured deuranium gamma curve (KTH). The third, fourth and fifth tracks are comparisons between the deuranium gamma curves calculated by other methods and the measured deuranium gamma curves. It can be seen that the inversion effect is good.
[0066] Embodiment 3
[0067] Figure 4 This is a schematic diagram of the structure of a deuranium device for a gamma curve provided in the third embodiment of the present application. The device can execute the deuranium method for a gamma curve provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 4 As shown, the device comprises:
[0068] The characteristic value acquisition module 310 is used to acquire characteristic values of logging parameters of the reservoir; the logging parameters include: resistivity, density, number of thermal neutrons and natural gamma value; the characteristic values reflect the statistical characteristics of the logging parameters;
[0069] A classification category determination module 320, for determining the classification category to which the reservoir belongs from among the pre-divided classification categories according to the characteristic values of the logging parameters of the reservoir;
[0070] The model training module 330 is used to use the natural gamma curve and logging parameters of the reservoir as training data, determine the classification category to which the reservoir belongs as a label, train the uranium removal model of the gamma curve to be trained, and obtain the uranium removal model of the trained gamma curve; the uranium removal model of the trained gamma curve is used to remove uranium from the natural gamma curve to obtain a uranium removal gamma curve.
[0071] The technical solution of the embodiment of the present application includes: a feature value acquisition module 310, which is used to obtain the feature values of the logging parameters of the reservoir; the logging parameters include: resistivity, density, number of thermal neutrons and natural gamma value; the feature values reflect the statistical characteristics of the logging parameters; a classification category determination module 320, which is used to determine the classification category to which the reservoir belongs in each pre-divided classification category according to the feature values of the logging parameters of the reservoir; a model training module 330, which is used to use the natural gamma curve and the logging parameters of the reservoir as training data, determine the classification category to which the reservoir belongs as a label, train the deuranization model of the gamma curve to be trained, and obtain the deuranization model of the trained gamma curve; the deuranization model of the trained gamma curve is used to deuranize the natural gamma curve to obtain the deuranization gamma curve. By determining the category label of the training data, the technical solution enables the trained deuranization model of the gamma curve to more accurately deuranize the natural gamma curve according to the corresponding category of the input data.
[0072] In the embodiment of the present application, optionally, the classification category determination module 320 includes:
[0073] A target classification category determination unit is used to traverse each well logging parameter and determine the target classification category to which the current well logging parameter belongs according to the characteristic value of the current well logging parameter in each classification category;
[0074] An integral value increasing unit, used to increase the integral value of the target classification category;
[0075] The classification category determination unit is used to determine the classification category with the highest score as the classification category to which the reservoir belongs if it is determined that the traversal of each logging parameter is completed.
[0076] In the embodiment of the present application, optionally, the classification category includes the interval range of each characteristic value of each logging parameter;
[0077] Accordingly, the target classification category determination unit includes:
[0078] The target interval range determination subunit is used to traverse each characteristic value of the current logging parameter and determine the target interval range to which the current characteristic value belongs;
[0079] An integral value increasing subunit, used to increase the integral value of the classification category corresponding to the target interval range;
[0080] The target classification category determination subunit is used to determine the classification category with the highest integral as the target classification category to which the current logging parameter belongs if it is determined that the traversal of each characteristic value is completed.
[0081] In the embodiment of the present application, optionally, the integral value increasing subunit is specifically used to:
[0082] Determine the minimum and maximum values of the target interval range;
[0083] Calculate the first difference between the current eigenvalue and the minimum value of the interval, and the second difference between the maximum value of the interval and the current eigenvalue;
[0084] determining an integral increase value according to a ratio of the first difference to the second difference;
[0085] The integral value of the classification category corresponding to the target interval range is integrally increased based on the integral increase value.
[0086] In the embodiment of the present application, optionally, the feature value acquisition module 310 is specifically used to:
[0087] Obtain resistivity logging data;
[0088] Performing statistics on the resistivity logging data to obtain the maximum value, minimum value, mode and variance of the resistivity;
[0089] Obtain density logging data;
[0090] Performing statistics on the density logging data to obtain the maximum value, minimum value, mode and variance of the density;
[0091] Acquire neutron logging data;
[0092] Performing statistics on the neutron logging data to obtain the maximum value, minimum value, mode and variance of the number of thermal neutrons;
[0093] Obtain natural gamma logging data;
[0094] The natural gamma logging data are statistically analyzed to obtain the maximum value, minimum value, mode and variance of the natural gamma value.
[0095] In the embodiment of the present application, optionally, the device further includes:
[0096] A module for acquiring data to be processed, used to obtain natural gamma ray curves and well logging data to be processed in the area to be processed;
[0097] The uranium-removed gamma curve determination module is used to input the natural gamma curve to be processed and the logging data into the uranium-removed model of the trained gamma curve to obtain the uranium-removed gamma curve.
[0098] In the embodiment of the present application, optionally, the device further includes:
[0099] The noise removal module is used to perform deconvolution processing on the de-uranium gamma curve and the noise function to obtain the de-uranium gamma curve after noise removal.
[0100] A deuranium removal device for a gamma curve provided in an embodiment of the present application can execute a deuranium removal method for a gamma curve provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.
[0101] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0102] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for removing uranium from a gamma curve, characterized in that: include: Obtaining characteristic values of logging parameters of the reservoir; The logging parameters include: resistivity, density, thermal neutron quantity and natural gamma value; the characteristic value reflects the statistical characteristics of the logging parameters; Determine the classification category to which the reservoir belongs from among the pre-divided classification categories according to the characteristic values of the logging parameters of the reservoir; The natural gamma curve and logging parameters of the reservoir are used as training data, the classification category to which the reservoir belongs is determined as a label, and the uranium removal model of the gamma curve to be trained is trained to obtain the uranium removal model of the trained gamma curve; the uranium removal model of the trained gamma curve is used to remove uranium from the natural gamma curve to obtain the uranium removal gamma curve.
2. The method according to claim 1, characterized in that The classification category to which the reservoir belongs is determined in each pre-divided classification category according to the characteristic values of the reservoir logging parameters, including: Traversing each well logging parameter, and determining the target classification category to which the current well logging parameter belongs according to the characteristic value of the current well logging parameter in each classification category; Increase the integral value of the target classification category; If it is determined that the traversal of each logging parameter is completed, the classification category with the highest score is determined as the classification category to which the reservoir belongs.
3. The method according to claim 2, characterized in that The classification category includes the interval range of each characteristic value of each logging parameter; Accordingly, in each classification category, the target classification category to which the current logging parameter belongs is determined according to the characteristic value of the current logging parameter, including: Traverse each characteristic value of the current logging parameter to determine the target interval range to which the current characteristic value belongs; Increase the integral value of the classification category corresponding to the target interval range; If it is determined that the traversal of each eigenvalue is completed, the classification category with the highest integral is determined as the target classification category to which the current logging parameter belongs.
4. The method according to claim 3, characterized in that Increasing the integral value of the classification category corresponding to the target interval range includes: Determine the minimum and maximum values of the target interval range; Calculate the first difference between the current eigenvalue and the minimum value of the interval, and the second difference between the maximum value of the interval and the current eigenvalue; determining an integral increase value according to a ratio of the first difference to the second difference; The integral value of the classification category corresponding to the target interval range is integrally increased based on the integral increase value.
5. The method according to claim 1, characterized in that Obtain the characteristic values of reservoir logging parameters, including: Obtain resistivity logging data; Performing statistics on the resistivity logging data to obtain the maximum value, minimum value, mode and variance of the resistivity; Obtain density logging data; Performing statistics on the density logging data to obtain the maximum value, minimum value, mode and variance of the density; Acquire neutron logging data; Performing statistics on the neutron logging data to obtain the maximum value, minimum value, mode and variance of the number of thermal neutrons; Obtain natural gamma logging data; The natural gamma logging data are statistically analyzed to obtain the maximum value, minimum value, mode and variance of the natural gamma value.
6. The method according to claim 1, characterized in that The method further comprises: Obtain the natural gamma ray curve and logging data of the area to be processed; The natural gamma curve to be processed and the logging data are input into the deuranium model of the trained gamma curve to obtain the deuranium gamma curve.
7. The method according to claim 6, characterized in that The method further comprises: Deconvolution processing is performed on the de-uranium gamma curve and the noise function to obtain the de-uranium gamma curve after noise removal.
8. A gamma curve deuranium device, characterized in that: include: A characteristic value acquisition module is used to obtain characteristic values of logging parameters of the reservoir; The logging parameters include: resistivity, density, thermal neutron quantity and natural gamma value; the characteristic value reflects the statistical characteristics of the logging parameters; A classification category determination module, used to determine the classification category to which the reservoir belongs from among the pre-divided classification categories according to the characteristic values of the logging parameters of the reservoir; The model training module is used to use the natural gamma curve and logging parameters of the reservoir as training data, determine the classification category to which the reservoir belongs as a label, train the uranium removal model of the gamma curve to be trained, and obtain the uranium removal model of the trained gamma curve; the uranium removal model of the trained gamma curve is used to remove uranium from the natural gamma curve to obtain the uranium removal gamma curve.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the deuranium removal method of the gamma curve according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the deuranium removal method of a gamma curve according to any one of claims 1 to 7 when executed.