A method and system for horizontal well fracture sweet spot prediction

Abstract

The application discloses a horizontal well fracturing sweet spot prediction method, comprising the following steps: collecting and classifying historical logging information of each pressure section of a horizontal well to be analyzed according to types of oil and gas reservoirs, and obtaining logging evaluation parameters of corresponding types; taking productivity as an evaluation target, screening evaluation parameters affecting productivity from the logging evaluation parameters, and analyzing whether each evaluation parameter related to the productivity is related to a construction parameter, so as to form a sweet spot evaluation parameter combination of the corresponding type, which is composed of multiple evaluation parameters irrelevant to the construction parameter; establishing a sweet spot prediction model of the corresponding type according to the correlation analysis result between each evaluation parameter in the sweet spot evaluation parameter combination and the productivity; and classifying actual logging information of each pressure section of a current horizontal well to be studied and respectively substituting into the sweet spot prediction model of the corresponding type, so as to obtain a fracturing sweet spot distribution result for each pressure section. The method excludes the influence of the construction parameter, and can accurately predict the sweet spot distribution condition of each pressure section of the horizontal well.

Description

Technical Field

[0001] This invention belongs to the field of oil and gas field development, and particularly relates to a method and system for predicting sweet spots in horizontal well fracturing. Background Technology

[0002] Horizontal wells are characterized by long horizontal sections and significant differences in reservoir properties along the wellbore trajectory. These characteristics greatly increase the cost of staged fracturing of horizontal wells. Therefore, comprehensively evaluating the fracturing sweet spot in the horizontal section of a horizontal well to improve the targeting of hydraulic fracturing is crucial for fully releasing production capacity and significantly improving the fracturing success rate.

[0003] Currently, the assessment of the compressibility of horizontal wells has been a key and hot topic in hydraulic fracturing research. Most existing assessment methods have certain limitations, mainly in the following aspects:

[0004] First, for different types of reservoir blocks, the evaluation methods for fracturing sweet spots (e.g., the evaluation parameters and models involved) must vary with the reservoir type. Furthermore, in establishing the evaluation model, not only geological and engineering parameters need to be considered, but also the influence of construction parameters on the production capacity of horizontal wells needs to be eliminated. Existing technology uses geostress profile calculation software to obtain the rock mechanics parameters of the horizontal section of the horizontal well in the Fuling shale gas reservoir. Then, by analyzing the correlation between the gas production profile test results of the fractured section and the rock mechanics parameters, the engineering sweet spot parameters of the Fuling shale gas reservoir are obtained. Therefore, the existing technology fails to eliminate the influence of previous fracturing construction parameters on the gas production profile test results in the step of calculating the correlation between rock mechanics parameters and gas production profile test results, resulting in inaccurate fracturing sweet spot calculation results.

[0005] Secondly, the currently established sweet spot parameters only apply to the sample data source block and fail to develop differentiated evaluation models for other blocks outside the sample data source block. Existing technology uses well logging and completion data to calculate various index parameters for horizontal well sections. Based on the existing section index evaluation system, a combined weighting method combining the analytic hierarchy process (AHP) and the entropy method is used to calculate index weights. Finally, standardized index values ​​and combined weights are combined through multiplicative synthesis to establish a horizontal well section evaluation model. However, this method only uses the combined weighting method to establish the evaluation model and does not employ a comprehensive analysis approach, resulting in an overly simplistic analytical approach.

[0006] Furthermore, existing technologies utilize well logging cross-plot analysis to establish the relationship between TOC / brittleness and Young's modulus × density (E × Rhob). Based on pre-stack elastic parameter inversion, the combined results of elastic parameters (E × Rhob) reflect the brittleness and TUC distribution of shale reservoirs. Finally, a comprehensive analysis is performed on shale reservoir fractures, TOC, brittleness distribution, and the thickness of high-quality shale to select the "sweet spot." In developing this invention, the inventors discovered that the comprehensive evaluation model established using this method does not have a direct relationship with production capacity, and existing technologies have failed to develop a simple and convenient method for finding sweet spot areas. Although this method comprehensively considers geological and engineering parameters, its sweet spot selection method does not reference production data from historical horizontal wells, and the evaluation method is cumbersome.

[0007] In summary, existing methods for identifying the sweet spot region in horizontal well fracturing primarily involve analyzing the relationship between geological parameters (permeability, porosity, saturation, and clay content, etc.) and engineering parameters (brittleness index, toughness index, and compressibility index, etc.) and productivity of the horizontal well section. This establishes the relationship between each evaluation parameter and the horizontal well's productivity, thus forming a sweet spot evaluation model. However, while establishing the relationship between each evaluation parameter and the horizontal well's productivity, the impact of construction parameters during fracturing on productivity is rarely considered. Furthermore, no corresponding calculation models are matched for different types of reservoir blocks, failing to establish a systematic and intuitive method for selecting horizontal well fracturing sections. Consequently, the fracturing sweet spot calculation results obtained using the currently established evaluation models contain certain errors, and the applicability of the evaluation models is poor. Summary of the Invention

[0008] One of the technical problems to be solved by this invention is to provide a method for predicting sweet spots in horizontal well fracturing, comprising: collecting historical logging information of each fracturing section of the horizontal well to be analyzed, classifying the historical logging information of each section according to the oil and gas reservoir type, and further obtaining corresponding logging evaluation parameters for different types of oil and gas reservoirs; taking production capacity as the evaluation target, screening evaluation parameters that affect production capacity from the logging evaluation parameters, and analyzing whether each production capacity-related evaluation parameter is related to the construction parameters, thereby forming a sweet spot evaluation parameter combination corresponding to the oil and gas reservoir type by forming multiple evaluation parameters unrelated to the construction parameters; establishing a sweet spot prediction model for different oil and gas reservoir types based on the correlation analysis results between each evaluation parameter in the sweet spot evaluation parameter combination and production capacity; and substituting the actual logging information of each fracturing section of the current horizontal well to be studied into the corresponding sweet spot prediction model according to the oil and gas reservoir type to which each fracturing section belongs, thereby obtaining the fracturing sweet spot distribution results for each fracturing section.

[0009] Preferably, the step of selecting evaluation parameters that affect production capacity from the well logging evaluation parameters, with production capacity as the evaluation target, includes: obtaining the correlation information between each evaluation parameter and production capacity in the well logging evaluation parameters, and based on this, determining the evaluation parameters related to the production capacity.

[0010] Preferably, one or more of the following methods are used: correlation analysis, Pearson-Mic correlation analysis, analytic hierarchy process, entropy analysis, and expert assignment method to calculate the influence weight value of each evaluation parameter on the production capacity, so as to characterize the corresponding correlation information.

[0011] Preferably, the step of analyzing whether each evaluation parameter related to production capacity is related to the construction parameter includes: based on the influence weight value corresponding to each evaluation parameter related to production capacity, using a preset influence threshold, retaining evaluation parameters whose influence weight value exceeds the influence weight threshold, so as to remove evaluation parameters related to the construction parameter.

[0012] Preferably, the horizontal well fracturing sweet spot prediction method provided in this embodiment of the invention further includes: for the historical logging information belonging to shale gas reservoir logging information, the logging evaluation parameters include a first type of geological parameters and a first type of engineering parameters, wherein the first type of geological parameters include porosity, permeability, water saturation, total organic matter content, and total gas content, and the first type of engineering parameters include Young's modulus, Poisson's ratio, and brittleness index; for the historical logging information belonging to tight gas reservoir logging information, the logging evaluation parameters include a second type of geological parameters and a second type of engineering parameters, wherein the second type of geological parameters include clay content, porosity, permeability, and hydrocarbon saturation, and the second type of engineering parameters include Young's modulus, Poisson's ratio, and brittleness index.

[0013] Preferably, the step of establishing a sweet spot prediction model for different oil and gas reservoir types based on the correlation analysis results between each evaluation parameter in the sweet spot evaluation parameter combination and the production capacity includes: generating a first relational expression characterizing the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the production capacity of the current oil and gas reservoir type by combining the historical logging data and historical production capacity data corresponding to each evaluation parameter in the sweet spot evaluation parameter combination with the influence weight value corresponding to each evaluation parameter in the sweet spot evaluation parameter combination; further converting the first relational expression into a second relational expression characterizing the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the sweetness value prediction result of the current oil and gas reservoir type by using the production capacity parameter as the prediction target to characterize the sweetness prediction result; and obtaining a sweet spot prediction model belonging to the corresponding oil and gas reservoir type based on the second relational expression corresponding to different oil and gas reservoir types.

[0014] Preferably, the first relation is fitted using one or more of the following methods: weighted analysis, backpropagation neural network, multinomial regression, TOPSIS, and expert assignment method.

[0015] Preferably, the step of substituting the actual logging information of each compression section of the current horizontal well under study into the corresponding sweet spot prediction model according to the oil and gas reservoir type to which each compression section belongs includes: if the current horizontal well under study is a single horizontal well, then classifying the actual logging information of the single horizontal well according to the oil and gas reservoir type, and substituting it into the corresponding sweet spot prediction model to predict the fracturing sweet spot of the single horizontal well; if the current horizontal well under study is multiple horizontal wells, then obtaining the fracturing sweet spot prediction result of each of the multiple horizontal wells, and further using the three-dimensional interpolation method to predict the fracturing sweet spot of the multiple horizontal wells.

[0016] Preferably, the horizontal well fracturing sweet spot prediction method provided in this embodiment of the invention further includes: adding the actual logging information of each fracturing section of the current horizontal well to be studied to the historical logging information to update the current historical logging information, and then using the new historical logging information to update the corresponding sweet spot prediction model.

[0017] On the other hand, the present invention also provides a horizontal well fracturing sweet spot prediction system, the system comprising the following modules: a logging evaluation parameter screening module, which is used to collect historical logging information of each fracturing section of the horizontal well to be analyzed, and classify the historical logging information of each section according to the oil and gas reservoir type, and further obtain corresponding logging evaluation parameters for different types of oil and gas reservoirs; a sweet spot evaluation parameter combination generation module, which is used to use production capacity as the evaluation target, screen evaluation parameters that affect production capacity from the logging evaluation parameters, and analyze whether each evaluation parameter related to production capacity is related to the construction parameters, thereby forming a sweet spot evaluation parameter combination corresponding to the corresponding oil and gas reservoir type by forming a combination of multiple evaluation parameters unrelated to the construction parameters; a sweet spot prediction model generation module, which is used to establish a sweet spot prediction model for different oil and gas reservoir types based on the correlation analysis results between each evaluation parameter in the sweet spot evaluation parameter combination and production capacity; and a sweet spot prediction module, which is used to substitute the actual logging information of each fracturing section of the current horizontal well to be studied into the corresponding type of sweet spot prediction model according to the oil and gas reservoir type to which each fracturing section belongs, thereby obtaining the fracturing sweet spot distribution results for each fracturing section.

[0018] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0019] This invention proposes a method and system for predicting sweet spots in horizontal well fracturing. The method and system utilize comprehensive evaluation technology for fracturing sweet spots, obtaining logging evaluation parameters belonging to different oil and gas reservoir types based on historical logging information of each fracturing section of the horizontal well to be analyzed. Then, for the same oil and gas reservoir type, the construction parameters involved in the fracturing process are removed, and various numerical analysis methods are used to analyze and calculate the comprehensive influence of various geological and engineering parameters in the logging evaluation parameters belonging to the current oil and gas reservoir type on production capacity. This leads to the establishment of sweet spot prediction models for different oil and gas reservoir types, and further, the sweet spot distribution results of each fracturing section of the corresponding type of horizontal well are obtained using the corresponding sweet spot prediction model. This invention considers the impact of construction parameters on production capacity during fracturing and establishes corresponding calculation models for different types of reservoir blocks. It effectively solves the problems of certain errors in the fracturing sweet spot calculation results obtained using currently established evaluation models and the poor applicability of the evaluation models, eliminating the influence of construction parameters on the fracturing sweet spot calculation results and accurately predicting the sweet spot distribution of each fracturing section of the horizontal well.

[0020] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0021] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0022] Figure 1 This is a flowchart illustrating the steps of the horizontal well fracturing sweet spot prediction method according to an embodiment of this application.

[0023] Figure 2 This is a schematic diagram of the comprehensive weight analysis results of the horizontal well fracturing sweet spot prediction method according to an embodiment of this application.

[0024] Figure 3 This is a three-dimensional display diagram of the sweet spot of a single well in the horizontal well fracturing sweet spot prediction method of this application embodiment.

[0025] Figure 4 This is a two-dimensional display diagram of the single-well sweet spot of the horizontal well fracturing sweet spot prediction method according to an embodiment of this application.

[0026] Figure 5 This is a three-dimensional display diagram of the multi-well sweet spot prediction method for horizontal well fracturing according to an embodiment of this application.

[0027] Figure 6This is a three-dimensional display diagram of the sweet spot of a multi-well geological body in the horizontal well fracturing sweet spot prediction method according to an embodiment of this application.

[0028] Figure 7 This is a schematic diagram of the comprehensive sweet spot calculation results of the horizontal well fracturing sweet spot prediction method according to an embodiment of this application.

[0029] Figure 8 This is a block diagram of the horizontal well fracturing sweet spot prediction system according to an embodiment of this application. Detailed Implementation

[0030] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples, so that the process of how the present invention uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. It should be noted that, as long as there is no conflict, the various embodiments and features in the various embodiments of the present invention can be combined with each other, and the resulting technical solutions are all within the protection scope of the present invention.

[0031] Furthermore, the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0032] Horizontal wells are characterized by long horizontal sections and significant differences in reservoir properties along the wellbore trajectory. These characteristics greatly increase the cost of staged fracturing of horizontal wells. Therefore, comprehensively evaluating the fracturing sweet spot in the horizontal section of a horizontal well to improve the targeting of hydraulic fracturing is crucial for fully releasing production capacity and significantly improving the fracturing success rate.

[0033] Currently, the assessment of the compressibility of horizontal wells has been a key and hot topic in hydraulic fracturing research. Most existing assessment methods have certain limitations, mainly in the following aspects:

[0034] First, for different types of reservoir blocks, the evaluation methods for fracturing sweet spots (e.g., the evaluation parameters and models involved) must vary with the reservoir type. Furthermore, in establishing the evaluation model, not only geological and engineering parameters need to be considered, but also the influence of construction parameters on the production capacity of horizontal wells needs to be eliminated. Existing technology uses geostress profile calculation software to obtain the rock mechanics parameters of the horizontal section of the horizontal well in the Fuling shale gas reservoir. Then, by analyzing the correlation between the gas production profile test results of the fractured section and the rock mechanics parameters, the engineering sweet spot parameters of the Fuling shale gas reservoir are obtained. Therefore, the existing technology fails to eliminate the influence of previous fracturing construction parameters on the gas production profile test results in the step of calculating the correlation between rock mechanics parameters and gas production profile test results, resulting in inaccurate fracturing sweet spot calculation results.

[0035] Secondly, the currently established sweet spot parameters only apply to the sample data source block and fail to develop differentiated evaluation models for other blocks outside the sample data source block. Existing technology uses well logging and completion data to calculate various index parameters for horizontal well sections. Based on the existing section index evaluation system, a combined weighting method combining the analytic hierarchy process (AHP) and the entropy method is used to calculate index weights. Finally, standardized index values ​​and combined weights are combined through multiplicative synthesis to establish a horizontal well section evaluation model. However, this method only uses the combined weighting method to establish the evaluation model and does not employ a comprehensive analysis approach, resulting in an overly simplistic analytical approach.

[0036] Furthermore, existing technologies utilize well logging cross-plot analysis to establish the relationship between TOC / brittleness and Young's modulus × density (E × Rhob). Based on pre-stack elastic parameter inversion, the combined results of elastic parameters (E × Rhob) reflect the brittleness and TUC distribution of shale reservoirs. Finally, a comprehensive analysis is performed on shale reservoir fractures, TOC, brittleness distribution, and the thickness of high-quality shale to select the "sweet spot." In developing this invention, the inventors discovered that the comprehensive evaluation model established using this method does not have a direct relationship with production capacity, and existing technologies have failed to develop a simple and convenient method for finding sweet spot areas. Although this method comprehensively considers geological and engineering parameters, its sweet spot selection method does not reference production data from historical horizontal wells, and the evaluation method is cumbersome.

[0037] In summary, existing methods for identifying the sweet spot region in horizontal well fracturing primarily involve analyzing the relationship between geological parameters (permeability, porosity, saturation, and clay content, etc.) and engineering parameters (brittleness index, toughness index, and compressibility index, etc.) and productivity of the horizontal well section. This establishes the relationship between each evaluation parameter and the horizontal well's productivity, thus forming a sweet spot evaluation model. However, while establishing the relationship between each evaluation parameter and the horizontal well's productivity, the impact of construction parameters during fracturing on productivity is rarely considered. Furthermore, no corresponding calculation models are matched for different types of reservoir blocks, failing to establish a systematic and intuitive method for selecting horizontal well fracturing sections. Consequently, the fracturing sweet spot calculation results obtained using the currently established evaluation models contain certain errors, and the applicability of the evaluation models is poor.

[0038] Example 1

[0039] Figure 1 This is a flowchart illustrating the steps of the horizontal well fracturing sweet spot prediction method according to an embodiment of this application. See below for reference. Figure 1 This will explain each step of the method.

[0040] like Figure 1 As shown, in step S110, historical logging information of each compression section of the horizontal well to be analyzed is collected, and the historical logging information of each section is classified according to the oil and gas reservoir type. Further, corresponding logging evaluation parameters are obtained for different types of oil and gas reservoirs. In this embodiment, logging data, fracturing schemes, and production status of each compression section of the horizontal wells already in production within the current oil and gas reservoir area are statistically analyzed, and historical logging information of each compression section of horizontal wells belonging to different oil and gas reservoir types, such as shale oil reservoirs, carbonate oil reservoirs, tight sandstone oil reservoirs, shale gas reservoirs, and tight sandstone gas reservoirs, is collected. In this embodiment, the historical logging information mainly includes: historical logging data related to the historical logging evaluation parameters of each compression section of the horizontal well to be analyzed, and historical production capacity data for different oil and gas reservoir types. Then, according to the oil and gas reservoir type to which the historical logging information belongs, the historical logging information of each compression section of the horizontal well is classified and organized, thereby obtaining multiple types of historical logging information belonging to different oil and gas reservoir types. Next, for each type of historical logging information, multiple logging evaluation parameters belonging to different types of oil and gas reservoirs are determined using empirical formulas or inversion calculation methods commonly used in logging operations. Each logging evaluation parameter can characterize the parameter features under a specific oil and gas reservoir type.

[0041] Furthermore, for historical logging information belonging to shale gas reservoirs, logging evaluation parameters include Category I geological parameters and Category I engineering parameters. Category I geological parameters include porosity, permeability, water saturation, total organic matter content, and total gas content, while Category I engineering parameters include Young's modulus, Poisson's ratio, and brittleness index. The calculation methods for Category I geological parameters and Category I engineering parameters in shale gas reservoir logging evaluation parameters will be illustrated with examples below.

[0042] In one embodiment of this application, a porosity calculation model commonly used in well logging is employed to calculate the effective porosity in the first type of geological parameters, as expressed below:

[0043]

[0044] Among them, Ф e Indicates effective porosity, Ф N V represents neutron porosity. clay1 ρ represents the volume of clay. ma ρ represents the density of the rock skeleton. clay1 ρ represents the density of clay. f V represents the density of a fluid. TOC ρ represents the volume of organic matter. TOC This indicates the density of organic matter.

[0045] Next, in one embodiment of this application, based on the HERRON formula, the permeability in the first type of geological parameter is calculated using the following expression:

[0046]

[0047] Where K represents the absolute permeability of the gas-bearing shale layer, and V bm V represents the relative volume of sandy material in gas-bearing shale layers. clay2 This represents the relative volume of limestone in gas-bearing shale layers.

[0048] Next, in one embodiment of this application, the total organic carbon content and kerogen volume in the shale gas reservoir are calculated based on well logging data. Further, utilizing the conversion relationship between the total organic carbon content and kerogen volume in the shale gas reservoir, and combining the density measurement value of the rock in the shale gas reservoir, the total organic matter content in the first type of geological parameter is calculated. Alternatively, based on the total organic carbon content calculated using density logging values ​​from the well logging data, the total organic carbon content is regressed to the rock particle density from the well logging data using the volumetric density method, and then the total organic matter content in the first type of geological parameter is obtained by combining the DEN logging curve from the well logging data. Alternatively, based on the total organic carbon content calculated using gamma values ​​from the well logging data, the total organic carbon content is regressed to the natural gamma value from the well logging data using the natural gamma indicator method, and then the total organic matter content in the first type of geological parameter is obtained by combining the natural gamma logging curve from the well logging data. It should be noted that the embodiments of this invention do not specifically limit the calculation method of the total organic matter content in the first type of geological parameter; those skilled in the art can choose according to actual needs.

[0049] Next, since the total gas content in a shale gas reservoir mainly consists of adsorbed gas and free gas, in one embodiment of this application, the relationship between adsorbed gas content and temperature and pressure is analyzed to obtain the pre-correction calculated adsorbed gas content. Further, based on the total organic carbon content calculated using well logging curves from well logging data, the relationship between the total organic carbon content and the pre-correction adsorbed gas content is analyzed, thus performing the first correction on the calculated adsorbed gas content for the entire shale gas reservoir segment. Then, referring to temperature experimental results of shale gas reservoir samples in foreign literature and domestic coalbed methane, the relationship between the first-corrected calculated adsorbed gas content and temperature is studied and analyzed, thus performing a second correction on the calculated adsorbed gas content. Next, the pressure coefficient and geothermal gradient of the shale gas reservoir are obtained using well logging data to calculate the reservoir pressure and temperature. Based on this, combined with measurements of the current reservoir porosity, water saturation, and rock density, the free gas content is obtained. Finally, the second-corrected calculated adsorbed gas content and the free gas content are summed to obtain the total gas content in the first type of geological parameters.

[0050] Next, in one embodiment of this application, based on the porosity calculation results, the Young's modulus in the first type of engineering parameter is calculated using the following expression:

[0051] E s =E d (0.8-φ e (3)

[0052] Among them, E s E represents the static Young's modulus. dThis represents the dynamic Young's modulus.

[0053] Alternatively, the Young's modulus in the first type of engineering parameters can be calculated using the following expression:

[0054]

[0055] It should be noted that the present invention does not specifically limit the calculation method of Young's modulus in the first type of engineering parameters, and those skilled in the art can choose according to actual needs.

[0056] Next, in one embodiment of this application, Poisson's ratio in the first type of engineering parameter is calculated based on the transverse and longitudinal wave transit times of the rock, as shown in the following expression:

[0057]

[0058] Where v represents Poisson's ratio, e yy Indicates a shortened lateral distance, e xx T1 represents the longitudinal elongation distance, λ represents the normal stress, λ represents the Lamé coefficient, and μ represents the shear modulus.

[0059] Subsequently, based on the calculation results of Young's modulus and Poisson's ratio in the first type of engineering parameters, this embodiment calculates the brittleness index in the first type of engineering parameters. The expression is as follows:

[0060]

[0061]

[0062] BI Rickman =0.5(E BRIT +ν BRIT (8)

[0063] Among them, E BRIT E represents the normalized Young's modulus. min E represents the minimum Young's modulus. max V represents the maximum Young's modulus, E represents Young's modulus, and v BRIT ν represents the normalized Poisson's ratio. min ν represents the minimum Poisson's ratio. max BI represents the maximum Poisson's ratio. Rickman It represents the rock mechanical brittleness index.

[0064] Furthermore, for historical logging information belonging to tight gas reservoirs, logging evaluation parameters include Category II geological parameters and Category II engineering parameters. Category II geological parameters include clay content, porosity, permeability, and hydrocarbon saturation, while Category II engineering parameters include Young's modulus, Poisson's ratio, and brittleness index. The calculation methods for Category II geological parameters and Category II engineering parameters in tight gas reservoir logging evaluation parameters will be illustrated with examples below.

[0065] In one embodiment of this application, the natural gamma logging method is used to calculate the clay content in the second type of geological parameter, as shown in the following expression:

[0066]

[0067]

[0068] Where Sh represents the relative value of natural gamma, GR represents the natural gamma logging value of the target layer, and GR min GR represents the natural gamma-ray logging value of pure lithological formations. max V represents the natural gamma logging value of a pure mudstone formation. sh The value represents the mud content calculated using natural gamma, and GCUR represents the stratigraphic index (2 for older strata).

[0069] Next, in one embodiment of this application, the true porosity of the low-porosity, low-permeability gas layer in the second type of geological parameters is calculated by using the relationship between core and well logging data and by combining sonic transit time-NMR logging data with regression analysis. The expression is as follows:

[0070]

[0071]

[0072] β = 1 - HI g ×P g (13)

[0073] Where Ф represents the true porosity of the low-porosity, low-permeability gas layer, α and β represent intermediate variable parameters in the calculation expression of the true porosity of the low-porosity, low-permeability gas layer, and Δt represents the sonic transit time logging value. ma Rock skeleton acoustic transit time, Δt f Pore ​​fluid acoustic transit time, HI g The hydrogen content index, P, represents the hydrogen content of a gas. g The polarization factor of the gas is represented by PHIS, the porosity calculated by sonic logging, and the porosity calculated by nuclear magnetic resonance.

[0074] Next, in one embodiment of this application, the Kozeny-Carman equation describing permeability in reservoir physics is transformed, retaining the porosity-related portion of the Kozeny-Carman equation and converting the constant portion into a function of clay content to obtain a permeability calculation model. Then, the permeability is calculated using the permeability model, and the calculated result is compared with the actual permeability obtained from well logging data. A univariate linear regression is then used to fit the model, resulting in a corrected permeability calculation model. Based on the corrected permeability calculation model, the permeability in the second type of geological parameters is obtained.

[0075] Next, in one embodiment of this application, based on the transverse and longitudinal waves, the Young's modulus in the second type of engineering parameters is calculated using the following expression:

[0076]

[0077] Where YMOD represents static Young's modulus, DEN represents formation bulk density, RMSC represents rock P-wave transit time, and DTS represents rock S-wave transit time.

[0078] Next, in one embodiment of this application, the Poisson's ratio in the second type of engineering parameter is calculated using the following expression:

[0079]

[0080] Where σ represents Poisson's ratio, v p V represents the longitudinal wave velocity. s This indicates the velocity of the transverse wave.

[0081] Next, in one embodiment of this application, the method for calculating the brittleness index of shale gas formations is applied to tight sandstone formations, and the brittleness index of tight sandstone formations in the second type of engineering parameters is calculated using the following expression:

[0082]

[0083] Where ΔE represents the normalized Young's modulus, Δμ represents the normalized Poisson's ratio, and B R This indicates the brittleness index of dense sandstone formations.

[0084] Further, in step S120, production capacity is used as the evaluation target. Evaluation parameters affecting production capacity are screened from the well logging evaluation parameters, and it is analyzed whether each production capacity-related evaluation parameter is related to the construction parameters. This forms a combination of sweet spot evaluation parameters for different oil and gas reservoir types, consisting of multiple evaluation parameters unrelated to construction parameters. Each well logging evaluation parameter belonging to different oil and gas reservoir types determined in step S110 is processed, and the correlation between each well logging evaluation parameter and the production capacity of the corresponding oil and gas reservoir type is analyzed. Based on the correlation analysis results, evaluation parameters that have a certain impact on the production capacity of the corresponding oil and gas reservoir type are screened from all well logging evaluation parameters belonging to different oil and gas reservoir types. The screened evaluation parameters are the production capacity-related evaluation parameters. Then, based on the degree of influence of each screened evaluation parameter on production capacity, the evaluation parameters belonging to different oil and gas reservoir types are ranked according to their degree of influence. Based on this, it is determined whether each screened production capacity-related evaluation parameter is related to the construction parameters. Subsequently, for logging evaluation parameters belonging to different oil and gas reservoir types, evaluation parameters related to construction parameters were removed, and the remaining evaluation parameters in the logging evaluation parameters of the corresponding oil and gas reservoir type were combined to form the sweet spot evaluation parameter combination of the corresponding oil and gas reservoir type. Thus, the sweet spot evaluation parameter combination corresponding to the corresponding oil and gas reservoir type was obtained, which consists of a variety of evaluation parameters unrelated to construction parameters.

[0085] Furthermore, based on the correlation information between each evaluation parameter and production capacity obtained in step S110, the logging evaluation parameters belonging to different oil and gas reservoir types are used to determine the evaluation parameters related to production capacity. Specifically, in this embodiment, based on historical logging information, historical logging data for each evaluation parameter belonging to different oil and gas reservoir types and historical production capacity data for the corresponding oil and gas reservoir types are calculated. The relationship between each evaluation parameter and production capacity within the same oil and gas reservoir type is then evaluated separately to determine whether there is a correlation between the evaluation parameters and production capacity for different oil and gas reservoir types. If, within the same oil and gas reservoir type, the evaluation parameter changes with production capacity, then there is a correlation between the current evaluation parameter and production capacity, and the current evaluation parameter is determined as a production capacity-related evaluation parameter belonging to the current oil and gas reservoir type.

[0086] The currently selected evaluation parameters related to production capacity include not only those related to geological and engineering parameters, but also those related to construction parameters. To obtain accurate sweet spot calculation results, this embodiment of the invention also needs to eliminate the influence of construction parameters on production capacity. However, while construction parameters have a smaller impact on production capacity compared to geological and engineering parameters, they significantly affect the accuracy of the fracturing sweet spot distribution calculation results. Therefore, this example calculates the influence weight values ​​of evaluation parameters related to production capacity, thereby quantifying the degree of influence of each evaluation parameter in the well logging evaluation parameters on production capacity, thus enabling a more accurate evaluation of the influence of each evaluation parameter on production capacity.

[0087] Furthermore, based on the influence weight value corresponding to each evaluation parameter related to production capacity, a preset influence threshold is used to retain evaluation parameters whose influence weight values ​​exceed the influence threshold, thereby removing evaluation parameters related to construction parameters. In this embodiment of the invention, an influence weight threshold value characterizing the accuracy of the fracturing sweet spot distribution calculation result is preset according to the actual logging situation, and this influence weight threshold value is used as the influence threshold value of this application embodiment. Then, evaluation parameters whose influence weight values ​​are less than the influence threshold value are regarded as evaluation parameters that have a significant impact on the accuracy of the fracturing sweet spot distribution calculation result of this application embodiment (and are regarded as having a small impact on production capacity). These evaluation parameters are removed from the evaluation parameters related to production capacity belonging to different oil and gas reservoir types, and evaluation parameters whose influence weight values ​​are greater than the preset influence threshold value are retained, thereby achieving the purpose of removing evaluation parameters related to construction parameters belonging to different oil and gas reservoir types. It should be noted that this application embodiment does not specifically limit the determination of the influence weight threshold value, and those skilled in the art can set it according to the actual logging situation.

[0088] Furthermore, one or more of the following methods are used: correlation analysis, Pearson-Mic correlation analysis, analytic hierarchy process (AHP), entropy analysis, and expert assignment method. These methods are used to calculate the weight value of each evaluation parameter's influence on production capacity, thus representing the corresponding correlation information. In practical applications, any one of these methods can be used to calculate the weight value of evaluation parameters related to production capacity for different oil and gas reservoir types. Alternatively, a combination of these methods can be applied to calculate the weight value of evaluation parameters related to production capacity for different oil and gas reservoir types, thereby improving the accuracy of the weight value calculation results.

[0089] Next, we will illustrate some of the influence weight value calculation methods involved in the embodiments of this application with examples.

[0090] In one embodiment of this application, a correlation analysis method is used to calculate the influence weight values ​​based on grey system theory. First, the values ​​of each evaluation parameter related to production capacity belonging to different oil and gas reservoir types are normalized. Based on this, the absolute difference between the value of each evaluation parameter and the production capacity of the corresponding oil and gas reservoir type is calculated. Based on the absolute difference calculation results, combined with the values ​​of each evaluation parameter, the two-level minimum difference and two-level maximum difference of the absolute difference calculation results for each evaluation parameter are further determined. Next, the relative difference between the value of each evaluation parameter and the production capacity of the corresponding oil and gas reservoir type is calculated, and the calculation results are used as the correlation coefficients between each evaluation parameter and the production capacity of the corresponding oil and gas reservoir type. Since there are multiple correlation coefficients between each evaluation parameter and the production capacity of the corresponding oil and gas reservoir type, it is necessary to further centrally process the calculation results of the multiple correlation coefficients corresponding to each evaluation parameter to obtain the corresponding correlation data. In the corresponding oil and gas reservoir type, the corresponding evaluation parameters are sequentially processed according to r... i Sort and number the data (i = 1, 2, ..., n), and calculate the correlation degree using the following expression:

[0091]

[0092] Where N represents the number of horizontal wells, i represents the index of the evaluation parameter, and r i ξ represents the correlation degree of the i-th evaluation parameter in the current oil and gas reservoir type. i (k) represents the relative difference between the value of the i-th evaluation parameter and the production capacity data in the current oil and gas reservoir type.

[0093] Through the above calculation process, we can obtain the correlation degree between each evaluation parameter related to production capacity belonging to different oil and gas reservoir types and the production capacity of the corresponding oil and gas reservoir types. The ranking of the correlation degree data is used as the ranking of the influence weight values ​​obtained by using the correlation degree analysis method.

[0094] In one specific embodiment of this application, the weighting influence threshold is set to 8%. Correlation analysis is used to obtain the influence weight values ​​of each evaluation parameter related to production capacity and belonging to the current oil and gas reservoir type. The influence weight values ​​of each evaluation parameter are arranged in descending order as follows: effective reservoir thickness > gas saturation > porosity > horizontal principal stress difference > rock brittleness index > number of fracturing stages > Poisson's ratio > Young's modulus > permeability > water saturation > sand addition > displacement > clay content. Among these, the evaluation parameters greater than the current weighting influence threshold are, in descending order: effective reservoir thickness > gas saturation > porosity > horizontal stress difference > rock brittleness index > Poisson's ratio > number of fracturing stages. These evaluation parameters greater than the current weighting influence threshold are combined to obtain the sweet spot evaluation parameter combination belonging to the current oil and gas reservoir type.

[0095] In one embodiment of this application, the Pearson-MIC correlation analysis method is used to calculate the influence weight values. By combining the Pearson correlation coefficient and the maximum information coefficient (MIC), based on production capacity data, the Pearson correlation coefficients and MICs of various evaluation parameters related to production capacity belonging to different oil and gas reservoir types are comprehensively averaged to obtain the correlation differences between the evaluation parameters related to production capacity belonging to different oil and gas reservoir types and the production capacity of the corresponding oil and gas reservoir types.

[0096] Through the above calculation process, we can obtain the correlation differences between the evaluation parameters related to production capacity of different oil and gas reservoir types and the production capacity of the corresponding oil and gas reservoir types. The ranking of the data representing the correlation differences is used as the ranking of the influence weight values ​​obtained by using the Pearson-Mic correlation analysis method.

[0097] In one specific embodiment of this application, the weighting influence threshold is set to 8%. Correlation analysis is used to obtain the influence weight values ​​of each evaluation parameter related to production capacity and belonging to the current oil and gas reservoir type. The influence weight values ​​of each evaluation parameter are arranged in descending order as follows: horizontal principal stress difference > effective reservoir thickness > clay content > porosity > water saturation > gas saturation > permeability > Young's modulus > Poisson's ratio > rock brittleness index > displacement > proppant addition > number of fracturing stages. Among these, the evaluation parameters greater than the current weighting influence threshold are, in descending order: horizontal principal stress difference > effective reservoir thickness > clay content > porosity > water saturation > gas saturation. These evaluation parameters greater than the current weighting influence threshold are combined to obtain the sweet spot evaluation parameter combination belonging to the current oil and gas reservoir type.

[0098] It should be noted that the calculation of the influence weight values ​​of various evaluation parameters related to production capacity belonging to different oil and gas reservoir types using the analytic hierarchy process, entropy analysis, and expert assignment method is similar to the conventional methods, and will not be described in detail in the embodiments of this application.

[0099] Next, we will explain how to calculate the influence weights by comprehensively applying correlation analysis, Pearson-Mic correlation analysis, analytic hierarchy process (AHP), and entropy analysis.

[0100] The influence weight values ​​of each evaluation parameter that is related to production capacity and belongs to the same oil and gas reservoir type were calculated using correlation analysis, Pearson-Mic correlation analysis, analytic hierarchy process and entropy analysis respectively. The influence weight values ​​of the same evaluation parameter were statistically averaged based on the calculation results. Figure 2 This is a schematic diagram illustrating the comprehensive weighted analysis results of the horizontal well fracturing sweet spot prediction method according to an embodiment of this application. Based on... Figure 2 It can be seen that, except for the analysis results obtained using the entropy method, the calculation results obtained using other analytical methods generally conform to the general trend of the comprehensive influence weight ranking. Based on the influence weight values ​​obtained using the entropy method, and considering the high sensitivity of the entropy method to data dispersion, the main reason for the current comprehensive weight analysis results is the excessive dispersion of the evaluation parameters related to production capacity. Therefore, the influence weight values ​​obtained using the entropy method can be ignored. Thus, the calculation results obtained by other influence weight calculation methods besides the entropy method show good consistency, indicating that these influence weight calculation methods are highly feasible and the current influence weight calculation results are accurate.

[0101] In step S130, based on the correlation analysis results between each evaluation parameter and production capacity in the sweet spot evaluation parameter combination, a sweet spot prediction model for different oil and gas reservoir types is established. Based on the sweet spot evaluation parameter combinations for different oil and gas reservoir types obtained in step S120, the correlation between each evaluation parameter in each sweet spot evaluation parameter combination and the production capacity of the corresponding oil and gas reservoir type is calculated and analyzed. Then, based on the correlation between each evaluation parameter and the corresponding production capacity, the correlation between each evaluation parameter and the corresponding sweetness value is obtained, and a corresponding sweet spot prediction model is established for different oil and gas reservoir types.

[0102] Furthermore, based on the historical logging data and historical production data corresponding to each evaluation parameter in the current sweet spot evaluation parameter combination, and combined with the influence weight value corresponding to each evaluation parameter in the current sweet spot evaluation parameter combination, a first relational expression is generated to characterize the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the production capacity of the current oil and gas reservoir type. Based on historical logging information, relevant information corresponding to each evaluation parameter in the current sweet spot evaluation parameter combination is obtained, and historical logging data is extracted from it, along with historical production data for the current oil and gas reservoir type. Using machine learning methods, combined with the influence weight value corresponding to each evaluation parameter in the current sweet spot evaluation parameter combination, the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the production capacity of the current oil and gas reservoir type is analyzed. A weighted method is used to establish a first relational expression regarding the correlation between each evaluation parameter in the current sweet spot evaluation parameter combination and the comprehensive influence of the current oil and gas reservoir type on the production capacity. Then, by using the production capacity parameter as the prediction target to characterize the sweetness prediction result, the first relational expression is further transformed into a second relational expression characterizing the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the sweetness value prediction result of the current oil and gas reservoir type. In this embodiment, since the sweetness value of a well section cannot be directly obtained through comprehensive analysis, the production capacity parameter is used as the prediction target to represent the sweetness prediction result obtained through comprehensive analysis. Accordingly, based on the first relational expression, the comprehensive influence of each evaluation parameter in the current sweetness evaluation parameter combination on the production capacity of the current oil and gas reservoir type is converted into the comprehensive influence of each evaluation parameter in the current sweetness evaluation parameter combination on the sweetness value prediction result of the current oil and gas reservoir type. This establishes a second relational expression regarding the correlation between the comprehensive influence of each evaluation parameter in the current sweetness evaluation parameter combination on the sweetness value prediction result of the current oil and gas reservoir type. The second relational expressions corresponding to different oil and gas reservoir types are obtained for each type, resulting in a sweetness prediction model for the corresponding oil and gas reservoir type.

[0103] Furthermore, one or more of the following methods are used to fit the first relational expression: weighted analysis, BP neural network, multinomial regression, TOPSIS, and expert assignment. In the embodiments of this application, the first relational expressions belonging to different oil and gas reservoir types are fitted using weighted analysis, BP neural network, multinomial regression, TOPSIS, and expert assignment, or any combination of these methods, respectively. This yields the relationship between the comprehensive influence of each evaluation parameter in the sweet spot evaluation parameter combination for different oil and gas reservoir types on the corresponding oil and gas reservoir type's production capacity and the current oil and gas reservoir type's production capacity parameter.

[0104] Figure 7This is a schematic diagram illustrating the comprehensive sweet spot calculation results of the horizontal well fracturing sweet spot prediction method according to an embodiment of this application. In one embodiment of this application, three machine learning methods—BP neural network, multivariate nonlinear multinomial regression, and TOPSIS (Top-Side Distance Method)—are comprehensively applied. Based on the aforementioned calculation results of influence weight values, machine learning and comprehensive analysis are performed on the evaluation parameters that mainly affect production capacity, thereby establishing corresponding sweet spot calculation models for different oil and gas reservoir types. Then, using the corresponding sweet spot calculation model, the sweetness values ​​of each fracturing section of the horizontal well for the corresponding oil and gas reservoir type are directly calculated (refer to...). Figure 7 This makes the dessert evaluation process more objective, and the accuracy of sweetness value calculation increases with the amount of data belonging to the corresponding evaluation parameter.

[0105] In step S140, the actual logging information of each fracture section of the horizontal well under study is substituted into the corresponding sweet spot prediction model according to the oil and gas reservoir type to which each fracture section belongs, thereby obtaining the fracturing sweet spot distribution results for each fracture section. The actual logging information, including logging data of the horizontal well section, fracturing operation data, and production data, is obtained for each fracture section of the horizontal well under study within the current oil and gas reservoir area. Then, the actual logging information is classified according to the oil and gas reservoir type, and the actual logging information belonging to the corresponding oil and gas reservoir type is substituted into the sweet spot prediction model belonging to the corresponding oil and gas reservoir type. The sweet spot prediction model is then used directly to calculate the fracturing sweet spot distribution of each fracture section belonging to the current oil and gas reservoir type.

[0106] Furthermore, the actual logging information of each pressure section of the current horizontal well under study is added to the historical logging information to update the current historical logging information, and then the corresponding sweet spot prediction model is updated using the new historical logging information. The actual logging information of each pressure section of the current horizontal well under study is collected, and the collected actual logging information is added to the historical logging information to update the current historical logging information. Based on the new historical logging information, this embodiment continues to obtain new sweet spot evaluation parameter combinations belonging to different oil and gas reservoir types according to the aforementioned method, and generates new sweet spot prediction models for the new sweet spot evaluation parameter combinations, thereby updating the sweet spot prediction models.

[0107] In one embodiment of this application, historical logging information and sweet spot evaluation parameters obtained from historical logging information, as well as actual logging information of each pressure section of the current horizontal well under study and new sweet spot evaluation parameters obtained from updated historical logging information, are used as sample data. This sample data is uploaded to a cloud-based sample database in real time for storage and retrieval. The cloud-based sample database allows for importing, deleting, querying, and classifying sample data, and also allows for setting logging evaluation parameters. Specifically, the sample data in the cloud-based sample database is categorized by reservoir type: shale oil reservoirs, carbonate oil reservoirs, tight sandstone oil reservoirs, shale gas reservoirs, and tight sandstone gas reservoirs. Furthermore, this embodiment of the application pre-sets 38 predetermined evaluation parameters and 10 backup parameters in the cloud-based sample database for establishing the sweet spot prediction model. These pre-set evaluation parameters can be automatically adjusted in real time based on the statistical results of real-time sample data in the cloud-based sample database.

[0108] In one specific embodiment of this application, sample data can be imported into a cloud-based sample database in Excel format. By creating an Excel table containing the names and reservoir types of the evaluation parameters involved in the construction of the dessert prediction model, and confirming the import, the prepared sample data can be imported into the cloud-based sample database.

[0109] Furthermore, if the horizontal well under study is a single horizontal well, the actual logging information of the single horizontal well is classified according to the oil and gas reservoir type, and then substituted into the corresponding sweet spot prediction model to predict the fracturing sweet spot of the single horizontal well. Alternatively, if the horizontal well under study is multiple horizontal wells, the fracturing sweet spot prediction results of each of the multiple horizontal wells are obtained, and then a three-dimensional interpolation method is used to predict the fracturing sweet spot of the multiple horizontal wells.

[0110] Figure 3 This is a three-dimensional display diagram of the sweet spot of a single well in the horizontal well fracturing sweet spot prediction method of this application embodiment. Figure 4 This is a two-dimensional display diagram of the sweet spot of a single well in the horizontal well fracturing sweet spot prediction method according to an embodiment of this application. In this embodiment, if the horizontal well under study is a single horizontal well, the actual logging information of each fracturing section of the single horizontal well under study is first collected, and the actual logging information is classified according to the oil and gas reservoir type. Then, the actual logging information of different oil and gas reservoir types is substituted into the corresponding sweet spot prediction model to calculate the sweetness value of the single horizontal well along the well section, and the corresponding sweet spot distribution results are displayed in three-dimensional chromaticity (referencing...). Figure 3 ) and two-dimensional data (refer to) Figure 4 The results are displayed via external devices such as monitors. The display method for the sweet spot distribution results of a single horizontal well can be configured by selecting the reservoir type, block name, well name, and horizontal well display range.

[0111] Figure 5 This is a three-dimensional display diagram of the multi-well sweet spot prediction method for horizontal well fracturing according to an embodiment of this application. Figure 6 This is a three-dimensional display diagram of the sweet spot distribution of a multi-well geological body in the horizontal well fracturing sweet spot prediction method according to an embodiment of this application. In this embodiment, if there are multiple horizontal wells to be studied, the sweet spot distribution results of each individual horizontal well are first obtained according to the aforementioned calculation method for calculating the sweet spot value along the well section of each individual horizontal well. Then, the sweet spot value calculation results of each individual horizontal well are integrated to obtain the sweet spot distribution of multiple horizontal wells (refer to...). Figure 5 Next, based on the current sweet spot distribution of multiple horizontal wells, an inverse distance interpolation method is used to display the sweet spot distribution results of the corresponding geological bodies in the blocks where the multiple horizontal wells are located in a three-dimensional form (after interpolation) (see reference). Figure 6 The display method for the sweet spot distribution results of geological bodies can be set by selecting the display range of the geological bodies.

[0112] Example 2

[0113] Based on the horizontal well fracturing sweet spot prediction method described in Embodiment 1 above, this invention also provides a horizontal well fracturing sweet spot prediction system (hereinafter referred to as "fracturing sweet spot prediction system"). Figure 8 This is a block diagram of the horizontal well fracturing sweet spot prediction system according to an embodiment of this application.

[0114] like Figure 8As shown, the fracturing sweet spot prediction system in this embodiment of the invention includes: a well logging evaluation parameter screening module 81, a sweet spot evaluation parameter combination generation module 82, a sweet spot prediction model generation module 83, and a sweet spot prediction module 84. Specifically, the well logging evaluation parameter screening module 81 is implemented according to the method described in step S110 above, configured to collect historical well logging information belonging to each fracturing section of the horizontal well to be analyzed, and classify the historical well logging information of each section according to the oil and gas reservoir type, and further obtain corresponding well logging evaluation parameters for different types of oil and gas reservoirs; the sweet spot evaluation parameter combination generation module 82 is implemented according to the method described in step S120 above, configured to take production capacity as the evaluation target, screen evaluation parameters that affect production capacity from the well logging evaluation parameters obtained by the well logging evaluation parameter screening module 81, and analyze whether each evaluation parameter related to production capacity is related to the construction parameters, thereby forming a variety of evaluation parameters unrelated to the construction parameters for different oil and gas reservoir types. To form a sweet spot evaluation parameter combination corresponding to the corresponding oil and gas reservoir type; the sweet spot prediction model generation module 83 is implemented according to the method described in step S130 above, and is configured to establish a sweet spot prediction model for different oil and gas reservoir types based on the correlation analysis results between each evaluation parameter and production capacity in the sweet spot evaluation parameter combination generated by the sweet spot evaluation parameter combination generation module 82; the sweet spot prediction module 84 is implemented according to the method described in step S140 above, and is configured to substitute the actual logging information of each compression section of the current horizontal well to be studied into the sweet spot prediction model generated by the corresponding type of sweet spot prediction model generation module 83 according to the oil and gas reservoir type to which each compression section belongs, so as to obtain the fracturing sweet spot distribution results for each compression section.

[0115] This invention discloses a method and system for predicting sweet spots in horizontal well fracturing. The method and system utilize comprehensive evaluation technology for fracturing sweet spots, obtaining logging evaluation parameters belonging to different oil and gas reservoir types based on historical logging information of each fracturing section of the horizontal well to be analyzed. Then, for the same oil and gas reservoir type, the construction parameters involved in the fracturing process are removed, and various numerical analysis methods are used to analyze and calculate the comprehensive influence of various geological and engineering parameters in the logging evaluation parameters belonging to the current oil and gas reservoir type on production capacity. This leads to the establishment of sweet spot prediction models for different oil and gas reservoir types, and further, the sweet spot distribution results of each fracturing section of the corresponding type of horizontal well are obtained using the corresponding sweet spot prediction model. This invention considers the impact of construction parameters during the fracturing process on production capacity, establishes corresponding sweet spot prediction models for different types of reservoir blocks, effectively solves the problems of certain errors and poor applicability of currently established sweet spot evaluation models, eliminates the influence of construction parameters on evaluation results, accurately predicts the sweet spot distribution of each fracturing section of the horizontal well, and achieves the goal of fully utilizing the effect of fracturing stimulation measures. This is of great significance to the development effect and economic benefits of horizontal well segmented fracturing production.

[0116] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0117] Of course, the present invention may 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 modifications according to the present invention, but these corresponding changes and modifications should all fall within the protection scope of the claims of the present invention.

[0118] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, the present invention is not limited to any particular hardware and software combination.

[0119] While the embodiments disclosed in this invention are as described above, the content is merely for the purpose of facilitating understanding of the invention and is not intended to limit the invention. Any person skilled in the art to which this invention pertains may make any modifications and variations in form and detail of the implementation without departing from the spirit and scope disclosed herein; however, the scope of patent protection for this invention shall still be determined by the scope defined in the appended claims.

Claims

1. A method for predicting sweet spots in horizontal well fracturing, characterized in that, include: Historical logging information of each pressure section of the horizontal well to be analyzed is collected, and the historical logging information of each section is classified according to the type of oil and gas reservoir. Then, corresponding logging evaluation parameters are obtained for different types of oil and gas reservoirs. Using production capacity as the evaluation target, evaluation parameters affecting production capacity are screened from the well logging evaluation parameters. It is then analyzed whether each production capacity-related evaluation parameter is related to the construction parameters. This allows for the formation of a sweet spot evaluation parameter combination for different oil and gas reservoir types, consisting of multiple evaluation parameters unrelated to construction parameters. In the step of using production capacity as the evaluation target and screening evaluation parameters affecting production capacity from the well logging evaluation parameters, the correlation information between each evaluation parameter in the well logging evaluation parameters and the production capacity is obtained. Based on this, evaluation parameters related to production capacity are determined. At least two methods from correlation analysis, Pearson-Mic correlation analysis, analytic hierarchy process (AHP), entropy analysis, and expert assignment methods are used to calculate the influence weight values ​​of each evaluation parameter related to production capacity belonging to the same oil and gas reservoir type. The influence weight values ​​of the same evaluation parameter are then statistically averaged based on the calculation results to characterize the corresponding correlation information. Based on the correlation analysis results between the evaluation parameters and production capacity in the sweet spot evaluation parameter combination, a sweet spot prediction model for different oil and gas reservoir types is established. Specifically, based on the historical logging data and historical production capacity data corresponding to each evaluation parameter in the sweet spot evaluation parameter combination, and combined with the influence weight value corresponding to each evaluation parameter in the sweet spot evaluation parameter combination, a first relational expression is generated to characterize the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the production capacity of the current oil and gas reservoir type. Then, by using the production capacity parameter as the prediction target to characterize the sweetness prediction result, the first relational expression is further transformed into a second relational expression to characterize the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the sweetness value prediction result of the current oil and gas reservoir type. Finally, based on the second relational expression corresponding to different oil and gas reservoir types, a sweet spot prediction model belonging to the corresponding oil and gas reservoir type is obtained. The actual logging information of each compression section of the horizontal well under study is substituted into the corresponding sweet spot prediction model according to the oil and gas reservoir type to which each compression section belongs, so as to obtain the fracturing sweet spot distribution results for each compression section.

2. The method according to claim 1, characterized in that, The steps involved in analyzing whether each evaluation parameter related to production capacity is related to construction parameters include: Based on the influence weight value corresponding to each evaluation parameter related to production capacity, and using a preset weight influence threshold, evaluation parameters whose influence weight value exceeds the preset weight influence threshold are retained, so as to remove evaluation parameters related to construction parameters.

3. The method according to claim 1, characterized in that, For the historical logging information belonging to shale gas reservoir logging information, the logging evaluation parameters include a first type of geological parameters and a first type of engineering parameters. The first type of geological parameters include porosity, permeability, water saturation, total organic matter content and total gas content. The first type of engineering parameters include Young's modulus, Poisson's ratio and brittleness index. For the historical logging information belonging to tight gas reservoirs, the logging evaluation parameters include second-class geological parameters and second-class engineering parameters. The second-class geological parameters include clay content, porosity, permeability and hydrocarbon saturation, and the second-class engineering parameters include Young's modulus, Poisson's ratio and brittleness index.

4. The method according to claim 3, characterized in that, The method further includes: The first relation is fitted using one or more of the following methods: weighted analysis, backpropagation neural network, multinomial regression, TOPSIS, and expert assignment.

5. The method according to claim 1, characterized in that, The step of substituting the actual logging information of each pressure section of the horizontal well under study into the corresponding sweet spot prediction model according to the oil and gas reservoir type to which each pressure section belongs includes: If the horizontal well to be studied is a single horizontal well, the actual logging information of the single horizontal well is classified according to the oil and gas reservoir type, and then substituted into the sweet spot prediction model of the corresponding type to predict the fracturing sweet spot of the single horizontal well. If there are multiple horizontal wells to be studied, the fracturing sweet spot prediction results of each of the multiple horizontal wells are obtained, and the fracturing sweet spot of the multiple horizontal wells is further predicted by three-dimensional interpolation.

6. The method according to claim 5, characterized in that, The actual logging information of each pressure section of the current horizontal well under study is added to the historical logging information to update the current historical logging information, and then the corresponding sweet spot prediction model is updated using the new historical logging information.

7. A horizontal well fracturing sweet spot prediction system, characterized in that, The system includes the following modules: The logging evaluation parameter screening module is used to collect historical logging information of each pressure section of the horizontal well to be analyzed, classify the historical logging information of each section according to the oil and gas reservoir type, and further obtain the corresponding logging evaluation parameters for different types of oil and gas reservoirs. The sweet spot evaluation parameter combination generation module is used to select evaluation parameters that affect production capacity from the well logging evaluation parameters, taking production capacity as the evaluation target, and analyze whether each production capacity-related evaluation parameter is related to the construction parameters. This allows for the formation of sweet spot evaluation parameter combinations corresponding to different oil and gas reservoir types, using multiple evaluation parameters unrelated to construction parameters. In the step of selecting evaluation parameters that affect production capacity from the well logging evaluation parameters, the module obtains the correlation information between each evaluation parameter in the well logging evaluation parameters and the production capacity. Based on this, it determines the evaluation parameters related to production capacity. Specifically, it uses at least two of the following methods: correlation analysis, Pearson-Mic correlation analysis, analytic hierarchy process (AHP), entropy analysis, and expert assignment method, to calculate the influence weight values ​​of each evaluation parameter related to production capacity belonging to the same oil and gas reservoir type. The module then performs a statistical average of the influence weight values ​​of the same evaluation parameter based on the calculation results to characterize the corresponding correlation information. The sweet spot prediction model generation module is used to establish sweet spot prediction models for different oil and gas reservoir types based on the correlation analysis results between the evaluation parameters and production capacity in the sweet spot evaluation parameter combination. Specifically, based on the historical logging data and historical production capacity data corresponding to each evaluation parameter in the sweet spot evaluation parameter combination, and combined with the influence weight value corresponding to each evaluation parameter in the sweet spot evaluation parameter combination, a first relational expression is generated to characterize the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the production capacity of the current oil and gas reservoir type. Then, by using the production capacity parameter as the prediction target to characterize the sweetness prediction result, the first relational expression is further converted into a second relational expression to characterize the comprehensive influence of each evaluation parameter in the current sweet spot evaluation parameter combination on the sweetness value prediction result of the current oil and gas reservoir type. Finally, based on the second relational expression corresponding to different oil and gas reservoir types, a sweet spot prediction model belonging to the corresponding oil and gas reservoir type is obtained. The sweet spot prediction module is used to input the actual logging information of each compression section of the horizontal well under study into the corresponding sweet spot prediction model according to the oil and gas reservoir type to which each compression section belongs, so as to obtain the fracturing sweet spot distribution results for each compression section.

Images