Method and system for determining shale gas horizontal well reservoir porosity
By constructing a porosity calculation model based on BP neural network, using element well recording data to calculate the porosity of shale gas horizontal wells, the problem of difficulty in calculating porosity in the absence of well logging data is solved, and the accuracy of reservoir evaluation and fracturing scheme design is improved.
Patent Information
- Application Number
- CN202311594613.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-27
- Publication Date
- 2025-05-27
AI Technical Summary
In the absence of logging data or incomplete logging data, it is difficult to accurately calculate porosity, which affects reservoir evaluation and fracturing scheme design.
By determining the horizontal well section with logging data and elemental well recording data, obtaining porosity data and elemental well recording data, and preferring element types that meet geological characteristics, a porosity calculation model based on BP neural network is constructed, and the porosity of well sections without logging data is calculated using the model.
The porosity calculation of shale gas horizontal wells without logging data or imperfect logging data is realized, which improves the accuracy of reservoir evaluation and targeted fracturing schemes, and saves logging costs.
Smart Images
Figure CN120046452A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of petroleum engineering, and particularly relates to a method and system for determining the porosity of shale gas horizontal well reservoirs. Background Art
[0002] The shale gas work area mainly adopts the development mode of horizontal well factory. Porosity is a parameter that measures the volume of pores contained in oil and gas reservoir rocks, reflects the ability of rocks to store fluids, and is a key parameter for shale gas reservoir evaluation. Therefore, accurately calculating the reservoir porosity is very important for shale gas development.
[0003] Currently, the porosity parameters of shale gas horizontal wells are mainly obtained through logging data. However, due to cost reduction and safety factors, there is no logging data in the horizontal well sections of some shale gas platform wells, and only 1-2 horizontal wells in another part of the shale gas platforms (each shale gas platform contains 8-10 horizontal wells) have logging data, and the remaining horizontal wells have no logging data. However, these missing logging data are essential data for calculating porosity by logging.
[0004] In order to better evaluate the reservoir characteristics of shale gas horizontal wells, effectively guide the test section selection and fracturing scheme design of shale gas horizontal wells, and solve the problem that it is difficult to calculate the porosity of shale gas horizontal wells due to the lack of logging data, there is an urgent need for a new scheme that can calculate the porosity of shale gas horizontal wells without logging data or with imperfect relevant data for calculating porosity in the logging data. Summary of the Invention
[0005] To solve the above problems, an embodiment of the present invention provides a method for determining the porosity of a shale gas horizontal well reservoir, including: determining a horizontal well section that simultaneously has logging data and element logging data in the currently studied target area, and obtaining the porosity data and element logging data of the specified well section; preferably selecting element types that conform to the geological characteristics of the current target area from the element logging data, and determining the corresponding optimal element combination data according to the element logging data of the current horizontal well; constructing a porosity calculation model by using the porosity data and the optimal element combination data; obtaining the optimal element combination data corresponding to the element logging data of the well section to be calculated in the target area, and determining the porosity of the current well section by using the porosity calculation model.
[0006] Preferably, in the step of constructing a porosity calculation model by using the porosity data and the optimal element combination data, it includes: constructing a first preset model; using the optimal element combination data as the input data for model training, and using the porosity data as the output data for model training, and training the first preset model to obtain the porosity calculation model.
[0007] Preferably, the first preset model is constituted based on the BP neural network framework.
[0008] Preferably, in the process of training the first preset model, it includes: performing multiple rounds of iterative calculations on the respective characteristic parameters of the first preset model to obtain the optimal parameters of the first preset model, thereby obtaining the porosity calculation model, wherein the characteristic parameters include but are not limited to: the connection weights from the hidden layer to the output layer, the center parameters of each neuron in the hidden layer, and the width vectors of each neuron in the hidden layer.
[0009] Preferably, the number of neurons in the BP neural network framework is 10.
[0010] Preferably, in the step of selecting element types that conform to the geological characteristics of the current target area from the element logging data and determining the corresponding optimal element combination data according to the element logging data of the current horizontal well, it includes: calculating the correlation between each element type in the element logging data by using the clustering analysis method, screening out the element types whose correlation calculation results exceed a preset first threshold, and recording them as the first type of element types; performing principal component analysis on the first type of element types to determine the corresponding optimal element combination data.
[0011] Preferably, before selecting element types that conform to the geological characteristics of the current target area from the element logging data, the method further includes: successively performing well depth scale unification processing and well depth calibration processing on the logging data and the element logging data belonging to the same horizontal well section, so as to perform depth alignment on the logging data and the element logging data of the corresponding horizontal well section.
[0012] Preferably, in the process of well depth scale unification processing, it includes: configuring sampling intervals for scale unification processing for the logging data and the element logging data respectively; extracting porosity information for the current well section from the logging data obtained during the logging construction process, and sampling the porosity information according to the first sampling interval to obtain the porosity data; obtaining the original element logging data for the current well section obtained during the element logging construction process, and sampling the original element logging data according to the second sampling interval to obtain the element logging data for porosity calculation; integrating the porosity data and the element logging data according to the well depth to unify them under the same depth scale.
[0013] Preferably, in the step of depth alignment of the logging data and the element logging data of the corresponding horizontal well section, it includes: obtaining the cuttings while drilling of the current well section and measuring the total natural GR radioactivity, comparing and analyzing the measured natural GR data with the GR data while drilling in the logging data while drilling, and aligning the well depths of the logging data and the element logging data that have completed depth unification processing according to the comparison and analysis results, so that the aligned well depth is consistent with the actual geological situation.
[0014] On the other hand, the present invention also provides a system for determining the porosity of a shale gas horizontal well reservoir, characterized in that the system includes the following modules: a data acquisition module, which is used to determine the horizontal well section with both logging data and element logging data in the current target area to be studied, and obtain the porosity data and element logging data of the specified well section; a logging data screening module, which is used to preferably select the element types that conform to the geological characteristics of the current target area from the element logging data, and determine the corresponding optimal element combination data according to the element logging data of the current horizontal well; a calculation model generation module, which is used to construct a porosity calculation model by using the porosity data and the optimal element combination data; a porosity calculation module, which is used to obtain the optimal element combination data corresponding to the element logging data of the well section to be calculated in the target area, and determine the porosity of the current well section by using the porosity calculation model.
[0015] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:
[0016] The present invention proposes a method and system for determining the porosity of a shale gas horizontal well reservoir. The method is based on the cuttings element logging data and the GR data while drilling belonging to the same well section, combines a machine learning model, constructs a porosity calculation model for calculating the corresponding porosity by using the cuttings element logging data, and then uses the porosity calculation model and the cuttings element logging data of the well section to be calculated to obtain the porosity of the well section. The present invention solves the problem that it is difficult to calculate the porosity of a shale gas horizontal well without logging data, realizes the porosity calculation of a horizontal well without logging data or with imperfect relevant data for calculating porosity in the logging data, provides technical support for horizontal well reservoir evaluation, test section selection and fracturing plan design optimization, and promotes the optimization of the targeted fracturing plan of "one section, one strategy".
[0017] Other features and advantages of the present invention will be described in the subsequent specification, and part of them will become obvious from the specification, or be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained through the structures specifically pointed out in the specification, claims and drawings. Description of the Drawings
[0018] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the accompanying drawings:
[0019] Figure 1 It is a step diagram of the first example of the method for determining the porosity of the shale gas horizontal well reservoir in the embodiment of the present application.
[0020] Figure 2 It is a step diagram of the second example of the method for determining the porosity of the shale gas horizontal well reservoir in the embodiment of the present application.
[0021] Figure 3 It is a module block diagram of the first example of the system for determining the porosity of the shale gas horizontal well reservoir in the embodiment of the present application.
[0022] Figure 4 It is an example diagram of the neural network framework of the method for determining the porosity of the shale gas horizontal well reservoir in the embodiment of the present application. Detailed implementation manners
[0023] The following will combine the accompanying drawings and embodiments to detail the implementation manners of the present invention, so as to fully understand how the present invention uses technical means to solve technical problems and achieve the implementation process of technical effects and implement accordingly. It should be noted that as long as there is no conflict, each embodiment in the present invention and each feature in each embodiment can be combined with each other, and the formed technical solutions are all within the protection scope of the present invention.
[0024] In addition, the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.
[0025] In order to better evaluate the characteristics of the shale gas horizontal well reservoir, effectively guide the test section selection and fracturing scheme design of the shale gas horizontal well, and solve the problem that it is difficult to calculate the porosity of the shale gas horizontal well due to the lack of logging data, there is an urgent need for a new solution that can calculate the porosity of a shale gas horizontal well without logging data or with incomplete relevant data for calculating porosity in the logging data.
[0026] Therefore, to solve the above problems, embodiments of the present invention propose a method and system for determining the porosity of a shale gas horizontal well reservoir. The method is based on the logging-while-drilling (LWD) elemental logging data and LWD GR data belonging to the same well section, and combines a machine learning model to construct a porosity calculation model for calculating the corresponding porosity using the LWD elemental logging data. Then, the porosity of the well section is obtained by using the porosity calculation model and the LWD elemental logging data of the well section to be calculated. The present invention solves the problem that it is difficult to calculate the porosity of a shale gas horizontal well without logging data, realizes the calculation of the porosity of a horizontal well without logging data or with imperfect relevant data for calculating porosity in the logging data, provides technical support for the reservoir evaluation, test section selection, and optimization of the fracturing plan design of the horizontal well, and promotes the optimization of the targeted fracturing plan of "one section, one strategy".
[0027] Example 1
[0028] Figure 1 It is a step diagram of the first example of the method for determining the porosity of a shale gas horizontal well reservoir according to an embodiment of the present application. The following will refer to Figure 1 to illustrate each step of this method.
[0029] As Figure 1 shown, in step S110, a horizontal well section with both logging data and elemental logging data in the current target area to be studied is determined, and the porosity data and elemental logging data of the specified well section are obtained. Specifically, first, a horizontal well section with both logging data and elemental logging data is determined in the current target area to be studied. Then, the porosity data is extracted from the logging data of the determined horizontal well section, so as to obtain the porosity data and elemental logging data of each determined horizontal well section, and the porosity data and elemental logging data of each determined horizontal well section are used as the porosity data and elemental logging data of the corresponding specified well section. In the embodiments of the present application, the horizontal well sections with both logging data and elemental logging data are in a target formation area where the geological characteristics at each location are similar, and the distribution modes are all located on the same shale gas platform or distributed on adjacent shale gas platforms.
[0030] In the actual application process, the elemental logging data usually includes data of more than 20 elements. Since there are elements in the elemental logging data that are not relevant or weakly relevant to the pore characteristics corresponding to the well section to be calculated in this embodiment, if the elemental logging data is not preprocessed before application, it will not only increase the error of the porosity calculation result but also increase the corresponding calculation workload. Therefore, in order to improve the accuracy of the porosity calculation result and make the porosity calculation result consistent with the actual situation, it is necessary to perform preprocessing operations on the elemental logging data.
[0031] It can be seen that this embodiment also needs to preprocess the element logging data obtained in step S110, and preferably select the element types that conform to the geological characteristics of the current target area to be studied. In step S120, the element types that conform to the geological characteristics of the current target area are preferably selected from the element logging data, and the corresponding optimal element combination data is determined according to the element logging data of the current horizontal well. By preferably selecting the element types that conform to the geological characteristics of the current target area from the element logging data, this embodiment removes the elements in the element logging data that are irrelevant or weakly correlated with the pore characteristics corresponding to the well section to be calculated in this embodiment. The remaining element logging data is the element logging data of the sensitive elements that have a strong correlation with the pore characteristics corresponding to the well section to be calculated in this embodiment. At this time, the remaining element logging data is used as the optimal element combination data.
[0032] Further, in the step of preferably selecting the element types that conform to the geological characteristics of the current target area from the element logging data and determining the corresponding optimal element combination data according to the element logging data of the current horizontal well, first, the clustering analysis method is used to calculate the correlation between each element type in the element logging data, and the element types with the correlation calculation results exceeding the preset first threshold are selected and recorded as the first type of element types; then, the principal component analysis is performed on the first type of element types to determine the corresponding optimal element combination data.
[0033] That is to say, this embodiment first uses the clustering analysis method to preliminarily screen the element types with strong correlations between each element type, and then uses the principal component analysis method to preferably select the element types that conform to the geological characteristics of the current target area to be studied from the element types obtained through the preliminary screening. Furthermore, according to the element logging data of the current horizontal well, the element logging data corresponding to the preferably selected element types is determined and used as the corresponding optimal element combination data.
[0034] Since the clustering analysis method can measure the correlation of the corresponding data between different data sources. In the embodiment of the present application, the hierarchical clustering analysis algorithm is used to calculate the correlation between any two elements in the element logging data of the current target area to be studied respectively, and the correlation calculation results under different element combinations are obtained to characterize the similarity or proximity between each element type. Next, the correlation calculation results under different element combinations are respectively compared with the preset strong correlation threshold of element types (i.e., the first threshold), and multiple groups of element combinations with the correlation calculation results exceeding the preset first threshold are selected, and the element types involved in the current multiple groups of element combinations are marked as the first type of element types (set). In this way, for the elements with strong correlations, the preliminary screening of the element types in the element logging data is completed, and further optimization screening of the element types that conform to the geological characteristics of the current target area to be studied can be carried out based on these elements with strong correlations.
[0035] Next, since the principal component analysis method can retain the original information with as few new variables as possible and has the characteristic of reducing the computational complexity, thus, this method can be used to further optimize and screen the first type of element types, that is, from multiple groups of the first type of element types (sets), the element types that conform to the geological characteristics of the current target area to be studied (i.e., the preferred element types) are preferably selected. Finally, combining the relevant data corresponding to various elements in the element logging construction process (for example: content data), the optimal element combination data corresponding to the preferred element types is screened out from the element logging data of the current horizontal well.
[0036] In the process of screening the data combinations corresponding to the preferred element types, first, all the element types included in the first type of element types (sets) are constructed into a set of candidates. Then, by means of adding, subtracting, or replacing elements or element ratios, element combinations with different quantities and different element types are randomly selected from the current set of candidates to form multiple groups of element combinations. Next, the content of each element within each group of element combinations is combined with the porosity data respectively to determine the conversion relationship between the two types of data (the conversion relationship between the two types of data is determined by similarity calculation), so as to determine the corresponding correlation coefficient for each group of element combinations. Finally, the element combination corresponding to the highest correlation coefficient is determined as the preferred element type. And, the content data corresponding to each element in the preferred element type or the content ratio data between each element is determined as the optimal element combination data.
[0037] For example: in the set of candidates, the element combination formed by elements 1 to 8 and the corresponding content data group are screened out, and the conversion relationship between the content data of each element within the current element combination and the porosity data is calculated, that is, the correlation coefficient is 0.7; in the set of candidates, the element combination formed by elements 1 to 9 and the corresponding content data group are screened out, and the conversion relationship between the content data of each element within the current element combination and the porosity data is calculated, that is, the correlation coefficient is 0.8. Then, the element combination selected with the correlation coefficient result of 0.8 is used as the preferred element type, and the content data of each element or the content ratio data between each element in this preferred element type is used as the optimal element combination data.
[0038] Further, in step S130, a porosity calculation model is constructed by using the porosity data and the optimal element combination data. In the actual application process, due to the collinearity problem between the rock components in the horizontal well section and the logging elements, and the corresponding logging element types with collinearity problems with the rock components cannot be determined, let alone the collinearity degree between the rock components and the corresponding logging elements. Moreover, the influence caused by the collinearity between the rock components in the horizontal well section and the corresponding logging elements cannot be eliminated by using the clustering analysis method. If the first type of element types obtained directly by the clustering analysis method is used, reliable porosity calculation data cannot be obtained. Therefore, in this embodiment, data operations are performed based on the neural network method, and the porosity data in step S110 and the optimal element combination data in step S120 are used to train the corresponding model, so as to realize the construction of the porosity calculation model. By using the constructed porosity calculation model to obtain the porosity data of the well section to be calculated, the influence of the collinearity problem on the porosity calculation result can be effectively eliminated.
[0039] In the step of constructing the porosity calculation model by using the porosity data and the optimal element combination data, first, a first preset model is constructed; then, the optimal element combination data is used as the input data for model training, and the porosity data is used as the output data for model training, and the first preset model is trained to obtain the porosity calculation model. Specifically, in this embodiment, a first preset model is constructed based on machine learning technology. Then, the optimal element combination data is used as the input information of the preset machine learning model (i.e., the first preset model), and the porosity data is used as the output information of the preset machine learning model (i.e., the first preset model) and substituted into the first preset model to start training the first preset model. After the training is completed, the porosity calculation model is obtained.
[0040] The first preset model is constituted based on the BP neural network framework. In actual applications, the BP algorithm is a process of forward information transmission (from the input layer to the output layer) and backward error propagation (from the output layer to the input layer). Therefore, in this embodiment, the BP neural network framework as shown in Figure 4 is used to constitute the first preset model ( Figure 4 is an example diagram of the neural network framework for the method for determining the porosity of the shale gas horizontal well reservoir in the embodiment of the present application), where x1, x2,..., xn are the contents of different elements, and y1, y2,..., ym are the porosities.
[0041] Further, during the training of the first preset model, iterative calculations are performed on various characteristic parameters of the first preset model for multiple rounds to obtain the optimal parameters of the first preset model, thereby obtaining the porosity calculation model. In the embodiments of the present application, various characteristic parameters of the first preset model are all based on iterative calculations for multiple rounds and are adaptively adjusted to the optimal values through learning, thereby achieving the purpose of obtaining the optimal parameters of the first preset model. At this time, the first preset model with the optimal parameters is the porosity calculation model. In a specific embodiment of the present application, the characteristic parameters include, but are not limited to: the connection weights from the hidden layer to the output layer, the center parameters of each neuron in the hidden layer, and the width vectors of each neuron in the hidden layer.
[0042] In a specific embodiment of the present application, the number of neurons in the BP neural network framework is 10.
[0043] Further, in step S140, the optimal element combination data corresponding to the element logging data of the well section to be calculated in the target area is obtained, and the porosity calculation model is used to determine the porosity of the current well section. In the embodiments of the present application, first, the well section to be calculated in the current target area without logging data or with incomplete relevant data in the logging data for calculating porosity (i.e., the relevant data for calculating porosity in the logging data is imperfect) is determined, and the element logging data of the horizontal well where the well section to be calculated is located is obtained. Next, the corresponding optimal element combination data is obtained from the element logging data of the current horizontal well according to step S120. Then, the current optimal element combination data is used as the input data and substituted into the porosity calculation model constructed in step S130. At this time, the output data of the porosity calculation model is the porosity calculation result of the current well section. It can be seen that this embodiment realizes the accurate acquisition of the porosity of shale gas horizontal wells with imperfect logging data or horizontal wells without logging data.
[0044] Example 2
[0045] Based on the above-mentioned Embodiment 1, in order to ensure the accuracy of the porosity calculation result, the porosity calculation method provided by the embodiments of the present invention further includes steps of uniformly processing the well depth scale and calibrating the well depth for the logging data and the element logging data belonging to the same horizontal well section in sequence. Figure 2 This is the step diagram of the second example of the method for determining the reservoir porosity of shale gas horizontal wells in the embodiments of the present application. The following refers to Figure 2 A detailed description of the second example of the porosity calculation method described in the embodiments of the present invention will be given.
[0046] As Figure 2As shown in the figure, in step S210, horizontal well sections with both logging data and element logging data in the current target area to be studied are determined, and porosity data and element logging data of a specified well section are obtained. Then, in step S220, the logging data and element logging data belonging to the same horizontal well section obtained in step S210 are successively subjected to well depth scale unification processing and well depth calibration processing, so as to perform depth alignment on the logging data and element logging data of the corresponding horizontal well section. Then, in step S230, according to the element logging data obtained in step S220 after well depth scale unification processing and well depth calibration processing, element types that conform to the geological characteristics of the current target area are selected from the element logging data, and according to the element logging data of the current horizontal well, the corresponding optimal element combination data is determined. Next, in step S240, a porosity calculation model is constructed according to the porosity data obtained in step S220 after well depth scale unification processing and well depth calibration processing, and the optimal element combination data obtained in step S230. Finally, in step S250, the well section to be calculated in the target area is determined, the optimal element combination data of the well section to be calculated is obtained according to the method for obtaining the optimal element combination data in step S230, and the porosity of the current well section is determined by using the porosity calculation model in step S240.
[0047] It should be noted that in the embodiment of the present application, step S210 is similar to the method described in step S110 above, step S230 is similar to the method described in step S120 above, step S240 is similar to the method described in step S130 above, and step S250 is similar to the method described in step S140 above. Therefore, the embodiments of the present invention will not elaborate on steps S210, S230, S240, and S250 here.
[0048] Specifically, in step S220, according to the porosity data and element logging data obtained in step S210, the logging data and element logging data belonging to the same horizontal well section are successively subjected to well depth scale unification processing and well depth calibration processing, so as to perform depth alignment on the logging data and element logging data of the corresponding horizontal well section. In the embodiment of the present application, first, according to the logging data of the horizontal well section where the porosity data obtained in step S210 is located and the element logging data of the same well section, the logging data and logging data are sorted by using the well depth scale unification processing method. Finally, the well depth of the corresponding horizontal well section is calibrated by using the logging data and element logging data after well depth scale unification processing, and the porosity data and element logging data unified to the same depth scale are obtained, so as to achieve the purpose of depth alignment of the logging data and element logging data of the corresponding horizontal well section.
[0049] Further, in the unified processing of well depth scale, it includes: configuring sampling intervals for scale unified processing for logging data and elemental logging data respectively; extracting porosity information for the current well section from the logging data obtained during the logging construction process, and sampling the porosity information according to the first sampling interval to obtain porosity data; obtaining the original elemental logging data for the current well section obtained during the elemental logging construction process, and sampling the original elemental logging data according to the second sampling interval to obtain elemental logging data for porosity calculation; finally, integrating the porosity data and elemental logging data according to the well depth to unify them under the same depth scale.
[0050] In the actual application process, the data sampling point distance of logging data is generally 0.1 - 0.125 m, and the data sampling point distance of elemental logging data is generally 1 - 2 m. In the embodiment of the present application, by using the method of configuring sampling intervals for scale unified processing for logging data and elemental logging data respectively, the logging data and logging data are sorted out, so that the sorted results of logging data and logging data in the same well section reflect the information of the same layer in this horizontal well section.
[0051] Specifically, sampling intervals for scale unified processing are configured for the logging data and elemental logging data in the same well section respectively. The sampling interval for scale unified processing of logging data is denoted as the first sampling interval, and the sampling interval for scale unified processing of elemental logging data is denoted as the second sampling interval. Next, in the horizontal well section where the above logging data and elemental logging data exist simultaneously, relevant construction data during the logging construction and elemental logging construction are extracted respectively. Porosity information is obtained from the logging construction data, the data points in the porosity information are sampled according to the above first sampling interval, and the data of each sampling data point in the current horizontal well section are integrated into a porosity data set. The original elemental logging data is obtained from the elemental logging construction data, the data points in the original elemental logging data are sampled according to the above second sampling interval, and the data of each sampling data point in the current horizontal well section are integrated into an original elemental logging data set, and porosity calculation is performed based on this original logging data set. According to the well depth data, the porosity data set and the original elemental logging data set in the current horizontal well section are unified under the same well depth scale, thereby unifying the logging data interval and the elemental logging interval in the current horizontal well section under the same depth scale.
[0052] It should be noted that in the embodiment of the present invention, the sizes of the specified first sampling interval and second sampling interval are not specifically limited, and those skilled in the art can set them according to the actual situation.
[0053] Furthermore, since the logging depth is the cable depth and the element logging data is the drill string depth, affected by the systematic error between the cable depth and the drill string depth, the depth data obtained by using the logging construction method and the element logging construction method are not unified. To improve the accuracy of the porosity calculation result, the present application uses a depth alignment method to process the logging data and the element logging data, and then calibrates the actual well depth.
[0054] As Figure 2 shown, in the depth alignment processing step, it includes: obtaining the cuttings while drilling in the current well section and measuring the total natural GR radioactivity, comparing and analyzing the measured natural GR data with the GR data while drilling in the logging while drilling data, and aligning the well depths of the logging data and the element logging data that have completed the depth unification processing according to the comparison and analysis results, so that the aligned well depth is consistent with the actual geological situation.
[0055] Specifically, in the embodiment of the present application, first, obtain the cuttings while drilling in the horizontal well section where the porosity data is located in step S210, measure the total natural GR radioactivity of the cuttings while drilling by using a cuttings natural gamma detector to obtain the natural GR data of the corresponding horizontal well section, compare and analyze the above natural GR data with the GR data while drilling in the logging while drilling data, determine the similar natural GR data and the GR data while drilling, and calibrate the actual well depth corresponding to the natural GR data below the well depth corresponding to the GR data while drilling similar to the current natural GR data. Thus, the actual depth alignment processing of the logging data and the element logging data is completed, and finally, the well depth data consistent with the actual geological situation, as well as the logging data and the element logging data matching the accurate well depth data, are obtained. In this way, the present invention completes the depth unification processing of the logging data and the element logging data and the well depth calibration of the horizontal well section.
[0056] Example 3
[0057] Based on the method for determining the reservoir porosity of a shale gas horizontal well described in the above Embodiment 1, the embodiment of the present invention also provides a system for determining the reservoir porosity of a shale gas horizontal well (hereinafter referred to as "porosity calculation system"). Figure 3 It is a module block diagram of the first example of the system for determining the reservoir porosity of a shale gas horizontal well in the embodiment of the present application.
[0058] As Figure 3As shown in the figure, the porosity calculation system in the embodiment of the present invention includes: a data acquisition module 31, a logging data screening module 32, a calculation model generation module 33, and a porosity calculation module 34. Specifically, the data processing module 31 is implemented according to the method described in step S110 above, and is configured to determine a horizontal well section with both logging data and elemental logging data in the current target area to be studied, and acquire the porosity data and elemental logging data of the specified well section; the logging data screening module 32 is implemented according to the method described in step S120 above, and is configured to optimize the elemental types that conform to the geological characteristics of the current target area from the elemental logging data acquired by the data processing module 31, and determine the corresponding optimal elemental combination data according to the elemental logging data of the current horizontal well; the calculation model generation module 33 is implemented according to the method described in step S130 above, and is configured to construct a porosity calculation model by using the porosity data and the optimal elemental combination data; the porosity calculation module 34 is implemented according to the method described in step S140 above, and is configured to acquire the optimal elemental combination data corresponding to the elemental logging data of the well section to be calculated in the target area, and determine the porosity of the current well section by using the porosity calculation model.
[0059] The present invention proposes a method and system for determining the porosity of a shale gas horizontal well reservoir. The method is based on the logging-while-drilling elemental logging data and logging-while-drilling GR data belonging to the same well section, combines with a machine learning model, constructs a porosity calculation model for calculating the corresponding porosity by using the logging-while-drilling elemental logging data, and then uses the porosity calculation model and the logging-while-drilling elemental logging data of the well section to be calculated to obtain the porosity of the well section. The present invention solves the problem that it is difficult to calculate the porosity of a shale gas horizontal well without logging data, has a wide range of applications, realizes the porosity calculation of horizontal wells without logging data or with imperfect relevant data for calculating porosity in the logging data, provides technical support for the evaluation of horizontal well reservoirs, the selection of test sections, and the optimization of fracturing design, promotes the optimization of the targeted fracturing plan of "one section, one strategy", and effectively saves the logging cost.
[0060] As described above, only the specific embodiments of the present invention are preferred, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
[0061] Of course, the present invention may also have other various embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art can make various corresponding changes and deformations according to the present invention, but these corresponding changes and deformations should all belong to the protection scope of the claims of the present invention.
[0062] Those skilled in the art should understand that the various modules or steps of the present invention described above can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed over a network composed of multiple computing devices. Optionally, they can be implemented with program code executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.
[0063] Although the embodiments disclosed in the present invention are as described above, the content described is only an embodiment adopted for the convenience of understanding the present invention and is not intended to limit the present invention. Any person skilled in the art within the technical field to which the present invention pertains can make any modifications and changes in the form of implementation and details without departing from the spirit and scope disclosed in the present invention. However, the scope of patent protection of the present invention shall still be subject to the scope defined by the appended claims.
Claims
1. A method for determining the porosity of a shale gas horizontal well reservoir, comprising: determining a horizontal well section with both logging data and element logging data in the current target area to be studied, and obtaining porosity data and element logging data of the specified well section; selecting element types that conform to the geological characteristics of the current target area from the element logging data, and determining the corresponding optimal element combination data according to the element logging data of the current horizontal well; using the porosity data and the optimal element combination data to construct a porosity calculation model; obtaining the optimal element combination data corresponding to the element logging data of the well section to be calculated in the target area, and using the porosity calculation model to determine the porosity of the current well section.
2. The method according to claim 1, wherein, in the step of using the porosity data and the optimal element combination data to construct a porosity calculation model, it includes: constructing a first preset model; using the optimal element combination data as the input data for model training and the porosity data as the output data for model training, and training the first preset model to obtain the porosity calculation model.
3. The method according to claim 2, wherein, the first preset model is constituted based on the BP neural network framework.
4. The method according to claim 2 or 3, wherein, in the process of training the first preset model, it includes: performing multiple rounds of iterative calculations on each characteristic parameter of the first preset model to obtain the best parameters of the first preset model, thereby obtaining the porosity calculation model, wherein the characteristic parameters include but are not limited to: the connection weights from the hidden layer to the output layer, the center parameters of each neuron in the hidden layer, and the width vectors of each neuron in the hidden layer.
5. The method according to claim 3 or 4, wherein, the number of neurons in the BP neural network framework is 10.
6. The method according to any one of claims 1 to 5, wherein, in the step of selecting element types that conform to the geological characteristics of the current target area from the element logging data and determining the corresponding optimal element combination data according to the element logging data of the current horizontal well, it includes: using the clustering analysis method to calculate the correlation between each element type in the element logging data, screening out the element types with the correlation calculation results exceeding a preset first threshold, and recording them as the first type of element types; performing principal component analysis on the first type of element types to determine the corresponding optimal element combination data.
7. The method according to any one of claims 1 to 6, wherein, before selecting element types that conform to the geological characteristics of the current target area from the element logging data, the method further includes: successively performing well depth scale unification processing and well depth calibration processing on the logging data and element logging data belonging to the same horizontal well section, so as to perform depth alignment on the logging data and element logging data of the corresponding horizontal well section.
8. The method according to claim 7, wherein, in the process of well depth scale unification processing, it includes: Configure sampling intervals for scale-uniform processing for the well logging data and the elemental logging data respectively; Extract porosity information for the current well section from the well logging data obtained during the well logging operation, and sample the porosity information at a first sampling interval to obtain the porosity data; Obtain the original elemental logging data for the current well section obtained during the elemental logging operation, and sample the original elemental logging data at a second sampling interval to obtain the elemental logging data for porosity calculation; Integrate the porosity data and the elemental logging data according to the well depth to unify them under the same depth scale.
9. The method according to claim 7 or 8, characterized in that, in the step of depth alignment of the well logging data and the elemental logging data for the corresponding horizontal well section, it includes: Obtain the cuttings while drilling for the current well section and conduct a total natural GR radioactivity measurement, compare and analyze the measured natural GR data with the LWD GR data in the well logging data while drilling, and align the well depths of the well logging data and the elemental logging data after completing the depth-uniform processing according to the comparison and analysis results, so that the aligned well depth conforms to the actual geological situation.
10. A system for determining the porosity of a shale gas horizontal well reservoir, characterized in that, the system includes the following modules: A data acquisition module, which is used to determine the horizontal well section with both well logging data and elemental logging data in the current target area to be studied, and acquire the porosity data and the elemental logging data of the specified well section; An elemental logging data screening module, which is used to select the elemental types that conform to the geological characteristics of the current target area from the elemental logging data, and determine the corresponding optimal elemental combination data according to the elemental logging data of the current horizontal well; A calculation model generation module, which is used to construct a porosity calculation model by using the porosity data and the optimal elemental combination data; A porosity calculation module, which is used to acquire the optimal elemental combination data corresponding to the elemental logging data of the well section to be calculated in the target area, and determine the porosity of the current well section by using the porosity calculation model.