Multi-information shale oil geological sweet spot fuzzy fusion method

Abstract

The invention provides a multi-information shale oil geological sweet spot fuzzy fusion method. The fusion method comprises the steps of S1, acquiring multi-source information data related to shale oil sweet spot prediction; s2, predicting crack planes of a plurality of azimuth angle sections to obtain a crack prediction result; s3, predicting the shale oil three-dimensional lithofacies to obtain a lithofacies prediction result; s4, according to the fracture prediction result and the lithofacies prediction result, constructing a fuzzy fusion formula based on an improved Sigmod function and a TS function; and S5, calculating a multi-information shale oil geological sweet spot fuzzy fusion result. High-precision prediction and grading evaluation of the shale oil geological dessert are realized, and the reliability of shale oil geological dessert prediction is improved.

Description

Technical Field

[0001] This invention relates to the field of exploration geophysics, and in particular to a fuzzy fusion method for multi-information shale oil geological sweet spots. Background Technology

[0002] Shale oil resources hold immense potential in both marine and continental oil and gas basins, but numerous challenges remain. The sweet spot of shale oil is controlled by many factors, with lithofacies and fractures being crucial for high-yield enrichment. Shale oil lithofacies are complex, exhibiting rapid horizontal and vertical variations and strong heterogeneity; its structure is also complex, with well-developed fractures and faults. Therefore, shale oil exploration and development require the prediction of dominant lithofacies, analysis of microfractures and fractures, and further improvement in descriptive accuracy.

[0003] For shale oil fracture and lithofacies prediction, conventional methods mainly rely on seismic data, well logging data, core samples, and analytical data. They utilize coherence and ant colony tracking techniques at different scales to perform macroscopic predictions of post-stack small fractures and their development, and employ post-stack deterministic inversion and pre-stack multi-parameter simultaneous inversion techniques to achieve shale oil lithofacies prediction. These conventional methods, based on post-stack seismic or narrow azimuth data, have to some extent advanced the development of shale oil sweet spot prediction technology.

[0004] However, with the development of seismic exploration, interpretation methods based on OVT wide azimuth data have begun to emerge; intelligent prediction technologies based on big data are also gaining a foothold in the oil and gas exploration and development field. OVT data includes rich azimuth information, and by utilizing OVT domain azimuth AVO seismic gathers and their attributes, seismic data interpretation can be performed, including structural interpretation, stratigraphic interpretation, lithological interpretation, fluid interpretation, fracture identification, and geostress studies. Big data technology can fully explore the data mapping relationship between seismic data and target curves, thereby eliminating the influence of low-frequency models and achieving a more accurate characterization of reservoir distribution morphology between wells.

[0005] To better integrate OVT data and big data technologies and leverage the combined strengths of different technologies, it is necessary to achieve effective fusion of multiple results. The improved fuzzy C-means clustering method has been effectively applied in residual oil classification and evaluation, and TS fuzzy neural network technology has been used for hydraulic motor fault diagnosis. However, these technologies have not yet been applied to shale oil geological sweet spot prediction, and the fusion technology of shale oil geological sweet spot based on fractures and lithofacies requires further research.

[0006] How to effectively integrate the same type of limiting factors and different types of limiting factors for shale oil geological sweet spots, and achieve graded evaluation of shale oil sweet spots, remains a relatively difficult problem to solve.

[0007] Chinese patent application CN202210539291.6 discloses a method, apparatus, and computer storage medium for predicting the comprehensive sweet spot of continental shale oil. The method, apparatus, and computer storage medium include: acquiring comprehensive sweet spot evaluation indices for the area to be determined, including geological sweet spot evaluation indices and engineering sweet spot evaluation indices; experimentally calibrating the comprehensive sweet spot evaluation indices; acquiring parameters for each comprehensive sweet spot evaluation index; and determining each comprehensive sweet spot evaluation index, which is the product of the normalized geological sweet spot index and the engineering sweet spot index; determining the predicted sweet spot of continental shale oil based on the comprehensive sweet spot evaluation index; analyzing the vertical distribution characteristics of the continental shale oil sweet spot using an improved well logging method; determining the lower limit value of the comprehensive sweet spot index based on the relationship between the vertical distribution characteristics of the continental shale oil sweet spot and shale oil production; and applying the lower limit value to other areas to be determined to determine their oil and gas resource exploration potential.

[0008] Chinese patent application CN202110445558.0 discloses a method and apparatus for predicting sweet spots in lacustrine shale oil. This method and apparatus includes: drawing geological and engineering sweet spot prediction maps based on preferred geological and engineering parameters and corresponding parameter ranges; overlaying the two maps based on their prediction results; and combining the parameter ranges of each favorable area to create an integrated geological-engineering sweet spot prediction map, identifying areas that meet both geological and engineering favorable criteria for sweet spot prediction. This method can improve the accuracy of sweet spot prediction, avoid the bias of single-factor evaluation, and better guide production.

[0009] Chinese patent application CN202011305423.6 discloses a porosity measuring device for predicting shale oil geological sweet spots. This device includes: a housing, a purification device, a first conveying device, a pressurizing device, a second conveying device, and a kerosene tank. The purification device is located inside the housing on the left side. The first conveying device is horizontally mounted above the workbench, with its left end positioned slightly below and in front of the center of the purification device for easy handling of shale oil measurement samples. The pressurizing device is mounted above the first conveying device, and the second conveying device is mounted flush with its right side. A kerosene tank is mounted at the right end of the first conveying device and below the second conveying device. A weight measuring instrument is located below the kerosene tank. Summary of the Invention

[0010] In view of the above problems, the present invention is proposed to provide a fuzzy fusion method for multi-information shale oil geological sweet spots that overcomes or at least partially solves the above problems.

[0011] According to one aspect of the present invention, a fuzzy fusion method for multi-information shale oil geological sweet spots is provided, the fusion method comprising:

[0012] Step S1: Obtain multi-source information data related to shale oil sweet spot prediction;

[0013] Step S2: Predict the crack plane in multiple azimuth angle segments to obtain crack prediction results;

[0014] Step S3: Predict the three-dimensional lithofacies of shale oil and obtain the lithofacies prediction results;

[0015] Step S4: Based on the fracture prediction results and the lithofacies prediction results, construct a fuzzy fusion formula based on the improved Sigmod function and the TS function;

[0016] Step S5: Calculate the fuzzy fusion result of the multi-information shale oil geological sweet spot.

[0017] Optionally, step S1: obtaining multi-source information data related to shale oil sweetness prediction specifically includes:

[0018] One-dimensional whole-rock analysis data and well logging data; two-dimensional geological data; two-dimensional post-stack seismic data; and five-dimensional OVT data;

[0019] Acquire multi-dimensional, multi-source information data, and perform data processing, analysis, and outlier removal.

[0020] Through fine calibration of well-seismic data, post-stack seismic data in the time domain and five-dimensional OVT data are calibrated to the depth domain, enabling free switching and application of data in multiple dimensions of the time domain and depth domain.

[0021] Optionally, step S2: predicting the crack plane of multiple azimuth angle segments and obtaining the crack prediction result specifically includes:

[0022] Based on azimuth anisotropy technology, multiple azimuth angles are superimposed on OVT data;

[0023] Conduct plane prediction of cracks in multiple azimuth angle segments.

[0024] Optionally, step S3: predicting the three-dimensional lithofacies of shale oil and obtaining the lithofacies prediction results specifically includes: predicting the three-dimensional lithofacies of shale oil based on artificial intelligence technology.

[0025] Optionally, step S4: constructing a fuzzy fusion formula based on the improved Sigmoid function and the TS function according to the fracture prediction result and the lithofacies prediction result specifically includes:

[0026] The importance of the lithofacies and fracture prediction results is ranked according to the degree of constraint of lithofacies and fractures on shale oil geological sweet spots;

[0027] Construct a fuzzy fusion formula based on the improved Sigmod and TS functions.

[0028] Optionally, the method of superimposing multiple azimuth angles on OVT data based on azimuth anisotropy technology specifically includes:

[0029] Extract post-stack coherence and curvature attributes to clarify the fracture plane distribution morphology of the target layer in the study area;

[0030] For fractures in multiple locations and of various forms, the range of azimuth angles perpendicular to the fracture direction is defined.

[0031] Based on the defined azimuth angle ranges, OVT data are superimposed by azimuth angle to obtain superimposed azimuth data for multiple azimuth angle ranges.

[0032] Optionally, the step of performing crack plane prediction across multiple azimuth angle segments specifically includes:

[0033] Based on the overlay data from different directions, likelihood attributes, ant-like structures, and curvature attributes are extracted along the layers to examine the planar distribution morphology of cracks in multiple directions and to conduct a difference analysis.

[0034] Optionally, the prediction of shale oil three-dimensional lithofacies based on artificial intelligence technology specifically includes:

[0035] Shale oil facies classification starts with TOC and carbonate content, using carbonate content as a target to predict shale oil facies;

[0036] Using machine learning algorithms, starting from carbonate content data in whole-rock experimental data, a time window covering curve morphology information was selected to establish and optimize the training model.

[0037] The training model was then applied to actual drilling operations throughout the entire work area.

[0038] The spatial distribution characteristics of carbonate content in the entire work area were obtained by using a feedforward neural network.

[0039] Optionally, the construction of the fuzzy fusion formula based on the improved Sigmoid function and the TS function specifically includes:

[0040] Fuzzy logic methods are introduced to address the uncertainties and fuzzinesses in shale oil sweet spots caused by shale facies and fracture analysis.

[0041] Given that the lithofacies prediction results and fracture identification results are not on the same dimension, the improved Sigmod function is used to normalize the favorable lithofacies development zone or fracture development zone to the [0,1] interval, and the improved TS function is used to carry out fuzzy inference.

[0042] The improved TS function is as follows:

[0043]

[0044] Where α and β are the scores of fractures and lithofacies, respectively, in the analysis of the main controlling factors for predicting shale oil sweet spots; both are positive values. i B and A' are the normalized prediction results of fractures and lithofacies in different azimuths, respectively, where n is the number of azimuth divisions, and A' is the number of divisions. i The improved Sigmod function for B is calculated as follows:

[0045]

[0046] If the input data is positively correlated with the shale oil sweet spot, then c = 1; if the input data is negatively correlated with the shale oil sweet spot, then c = 2; Q is a fractured area or a favorable lithofacies area.

[0047] By using formulas (1) and (2), the effective integration of the same type of constraint factors and multiple types of constraint factors is achieved for the geological sweet spots of shale oil.

[0048] Optionally, step S5: calculating the fuzzy fusion result of multi-information shale oil geological sweet spot specifically includes: realizing the graded evaluation of shale oil geological sweet spot based on the fuzzy fusion result.

[0049] This invention provides a fuzzy fusion method for multi-information shale oil geological sweet spots. The fusion method includes: Step S1: acquiring multi-source information data related to shale oil sweet spot prediction; Step S2: predicting fracture planes in multiple azimuth angle segments to obtain fracture prediction results; Step S3: predicting the three-dimensional lithofacies of shale oil to obtain lithofacies prediction results; Step S4: constructing a fuzzy fusion formula based on the improved Sigmoid and TS functions according to the fracture prediction results and the lithofacies prediction results; Step S5: calculating the fuzzy fusion result of the multi-information shale oil geological sweet spot. This method achieves high-precision prediction and hierarchical evaluation of shale oil geological sweet spots, improving the reliability of shale oil geological sweet spot prediction.

[0050] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A flowchart of a multi-information shale oil geological sweet spot fuzzy fusion method provided in an embodiment of the present invention;

[0053] Figure 2 This is a post-stack coherence property diagram according to a specific embodiment of the present invention;

[0054] Figure 3 This is a gather azimuth division diagram according to a specific embodiment of the present invention;

[0055] Figure 4 This is a specific embodiment of the present invention for identifying crack planar diagrams based on the orientation likelihood attributes;

[0056] Figure 5 This is a planar prediction diagram of carbonate content according to a specific embodiment of the present invention;

[0057] Figure 6 This is a fuzzy fusion image of shale oil sweet spot according to a specific embodiment of the present invention;

[0058] Figure 7 This invention relates to a plan view of cracks in a certain industrial area, which is identified by the orientation likelihood attribute. Detailed Implementation

[0059] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0060] The terms "comprising" and "having," and any variations thereof, in the specification, embodiments, claims, and drawings of this invention are intended to cover non-exclusive inclusion, such as including a series of steps or units.

[0061] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0062] like Figure 1 As shown, Figure 1 This is a flowchart of the multi-information shale oil geological sweet spot fuzzy fusion method of the present invention.

[0063] The multi-information shale oil geological sweet spot fuzzy fusion method of the present invention includes the following steps:

[0064] Step 1: Input multi-source information data related to shale oil sweet spot prediction;

[0065] Step 2: Based on azimuth anisotropy technology, perform overlay of OVT data at different azimuth angles;

[0066] Step 3: Conduct plane prediction of cracks at different azimuth angles;

[0067] Step 4: Based on artificial intelligence technology, realize three-dimensional lithofacies prediction of shale oil;

[0068] Step 5: Rank the lithofacies and fracture prediction results according to their relative importance based on the degree of constraint of lithofacies and fractures on the geological sweet spot of shale oil.

[0069] Step 6: Construct a fuzzy fusion formula based on the improved Sigmod function and the TS function;

[0070] Step 7: Calculate the fuzzy fusion result of the multi-information shale oil geological sweet spot.

[0071] Example 1

[0072] In a specific embodiment 1 of the present invention, the multi-information shale oil geological sweet spot fuzzy fusion method includes:

[0073] In step 1, multi-source information data related to shale oil sweet spot prediction is input. There is a wealth of data related to shale oil sweet spot prediction, including one-dimensional whole-rock analysis data and well logging data; two-dimensional geological data; two-dimensional post-stack seismic data; and five-dimensional and OVT data. These multi-source information data of different dimensions are input, and data processing, analysis, and outlier removal are performed. Then, through fine well-seismic calibration, the time-domain post-stack seismic data and five-dimensional OVT data are calibrated to the depth domain, allowing for free switching and use of different dimensions of time-domain and depth-domain data.

[0074] In step 2, based on azimuth anisotropy technology, OVT data are stacked at different azimuth angles. By extracting post-stack coherence, curvature, and other attributes, the fracture plane distribution morphology of the target layer in the study area is clarified, such as... Figure 2 As shown, Figure 2 The coherence properties clearly characterize the planar distribution morphology of the faults in the study area, including their fault strike.

[0075] Figure 2This is a post-stack coherence attribute map of the embodiment. The coherence attributes in the map clearly characterize the planar distribution morphology of the fractures in the study area, including their fracture strike. For fractures of different locations and morphologies, azimuth angle ranges perpendicular to the fracture direction are defined. According to the defined azimuth angle ranges, OVT data are stacked by azimuth angle to obtain azimuth stacked data for different azimuth angle ranges. Figure 3 This is an example of a azimuth angle division diagram. In this example, four azimuth angle segments are divided: 0-25°, 80-100°, 110-145°, and 170-180°.

[0076] In step 3, crack plane prediction is performed for different azimuth angle segments. For the azimuth-stacked data, likelihood attributes, ant-like volumes, curvature, and other attributes are extracted along the layers to examine the crack plane distribution morphology in different azimuths and perform difference analysis. Figure 4 This is an example of identifying crack planar maps using the orientation likelihood attribute, from... Figure 4 It can be seen that the maximum likelihood property after superimposing different azimuth angle segments depicts different crack development details, especially within the elliptical frame, which depicts more crack development areas and the detailed features of the cracks are more obvious.

[0077] In step 4, three-dimensional lithofacies prediction of shale oil is achieved based on artificial intelligence technology. Shale oil lithofacies classification mainly starts with TOC and carbonate content; this invention uses carbonate content as the target to predict shale oil lithofacies. First, a machine learning algorithm is used, starting with carbonate content data from whole-rock experimental data, selecting a time window to cover curve morphology information, establishing and optimizing a training model, and then extending this model to actual drilling across the entire work area; then, a feedforward neural network is used to obtain the spatial distribution characteristics of carbonate content across the entire work area. Figure 5 The above is a planar prediction map of carbonate content in an embodiment. As can be seen from the map, the planar distribution of carbonate content shows a ring-depression distribution, which is consistent with the current structural morphology and conforms to geological understanding.

[0078] As can be seen from the figure, the shale oil sweet spots in this area are divided into three categories: the first category is the overlapping area of ​​favorable lithofacies and fracture development, as shown in the red ellipse area in the figure; the second category is the area of ​​favorable lithofacies or fracture development; and the third category is the area of ​​unfavorable lithofacies and undeveloped fractures.

[0079] In step 5, the prediction results of lithofacies and fractures are ranked according to their degree of constraint on the geological sweet spot of shale oil. The importance of different constraint factors is determined by the score.

[0080] In step 6, a fuzzy fusion formula based on the improved Sigmoid function and the TS function is constructed. Fuzzy logic is introduced to address the uncertainties and fuzzinesses in shale oil facies and fracture analysis for shale oil sweet spots. Since the lithofacies prediction results and fracture identification results are not on the same dimension, the improved Sigmoid function is used to normalize favorable lithofacies development zones or fracture development zones to the [0,1] interval, and then the improved TS function is used to perform fuzzy inference.

[0081] The improved TS function is as follows:

[0082]

[0083] Where α and β are the scores of fractures and lithofacies, respectively, in the analysis of the main controlling factors for predicting shale oil sweet spots; both are positive values. i B and A' are the normalized prediction results of fractures and lithofacies in different azimuths, respectively, where n is the number of azimuth divisions, and A' is the number of divisions. i The improved Sigmod function for B is calculated as follows:

[0084]

[0085] If the input data is positively correlated with the shale oil sweet spot, then c = 1; if the input data is negatively correlated with the shale oil sweet spot, then c = 2; Q is a fractured area or a favorable lithofacies area.

[0086] By using formulas (1) and (2), the same type of constraint factors and different types of constraint factors are effectively integrated for shale oil geological sweet spots.

[0087] In step 7, the fuzzy fusion result of the multi-information shale oil geological sweet spot is calculated. Based on the fuzzy fusion result, the graded evaluation of the shale oil geological sweet spot is realized. Figure 6 This is a fuzzy fusion diagram of shale oil sweet spots in an embodiment. As can be seen from the diagram, the shale oil sweet spots in this area are divided into three categories: the first category is the overlapping area of ​​favorable lithofacies and fracture development, as shown by the red ellipse in the diagram; the second category is the area of ​​favorable lithofacies or fracture development; and the third category is the area of ​​unfavorable lithofacies and undeveloped fractures.

[0088] Example 2

[0089] In a specific embodiment 2 of the present invention, the multi-information shale oil geological sweet spot fuzzy fusion method includes:

[0090] In step 1, multi-source information data related to shale oil sweet spot prediction is input. There is a wealth of data related to shale oil sweet spot prediction, including one-dimensional whole-rock analysis data and well logging data; two-dimensional geological data; two-dimensional post-stack seismic data; and five-dimensional and OVT data. These multi-source information data of different dimensions are input, and data processing, analysis, and outlier removal are performed. Then, through fine well-seismic calibration, the time-domain post-stack seismic data and five-dimensional OVT data are calibrated to the depth domain, allowing for free switching and use of different dimensions of time-domain and depth-domain data.

[0091] In step 2, based on azimuth anisotropy technology, OVT data are stacked at different azimuth angles. By extracting post-stack coherence, curvature, and other attributes, the fracture plane distribution morphology of the target layer in the study area is clarified. For fractures of different locations and morphologies, azimuth angle ranges perpendicular to the fracture direction are defined. According to the defined azimuth angle ranges, OVT data are stacked at different azimuth angles to obtain azimuth stacked data at different azimuth angle ranges.

[0092] In step 3, crack plane prediction is performed for different azimuth angle segments. For the azimuth-stacked data, likelihood attributes, ant-like volumes, curvature, and other attributes are extracted along the layers to examine the crack plane distribution morphology in different azimuths and perform difference analysis. Figure 7 This is a plan view of cracks identified by the azimuth likelihood attribute in a certain work area. It can be seen from the figure that there are differences in the crack development depicted in the azimuth angle segments of 129-139 degrees and 19-29 degrees, especially within the elliptical frame area.

[0093] In step 4, three-dimensional lithofacies prediction of shale oil is achieved based on artificial intelligence technology. Shale oil lithofacies classification mainly starts with TOC and carbonate content; this invention uses carbonate content as the target to predict shale oil lithofacies. First, a machine learning algorithm is used, starting with carbonate content data from whole-rock experimental data, selecting a time window to cover curve morphology information, establishing and optimizing a training model, and then extending this model to actual drilling across the entire work area; then, a feedforward neural network is used to obtain the spatial distribution characteristics of carbonate content across the entire work area.

[0094] In step 5, the prediction results of lithofacies and fractures are ranked according to their degree of constraint on the geological sweet spot of shale oil. The importance of different constraint factors is determined by the score.

[0095] In step 6, a fuzzy fusion formula based on the improved Sigmoid function and the TS function is constructed. Fuzzy logic is introduced to address the uncertainties and fuzzinesses in shale oil facies and fracture analysis for shale oil sweet spots. Given that the lithofacies prediction results and fracture identification results are not on the same dimension, the improved Sigmoid function is used to normalize favorable lithofacies development zones or fracture development zones to the [0,1] interval, and the improved TS function is used to perform fuzzy inference.

[0096] The improved TS function is as follows:

[0097]

[0098] Where α and β are the scores of fractures and lithofacies, respectively, in the analysis of the main controlling factors for predicting shale oil sweet spots; both are positive values. i B and A' are the normalized prediction results of fractures and lithofacies in different azimuths, respectively, where n is the number of azimuth divisions, and A' is the number of divisions. i The improved Sigmod function for B is calculated as follows:

[0099]

[0100] If the input data is positively correlated with the shale oil sweet spot, then c = 1; if the input data is negatively correlated with the shale oil sweet spot, then c = 2; Q is a fractured area or a favorable lithofacies area.

[0101] Formulas (1) and (2) can be used to effectively integrate the same type of constraint factors and different types of constraint factors for shale oil geological sweet spots.

[0102] In step 7, the fuzzy fusion result of the multi-information shale oil geological sweet spot is calculated. Based on the fuzzy fusion result, the graded evaluation of the shale oil geological sweet spot is realized.

[0103] Beneficial effects: The multi-information shale oil geological sweet spot fuzzy fusion method in this invention integrates multi-source information such as whole-rock analysis data, well logging data, OVT data, post-stack seismic data, and geological data. It utilizes azimuth anisotropy analysis technology and artificial intelligence technology to perform in-depth multi-source data mining and application. Furthermore, it creates a fuzzy fusion technology based on improved Sigmoid and TS functions, achieving high-precision prediction and hierarchical evaluation of shale oil geological sweet spots and improving the reliability of shale oil geological sweet spot prediction.

[0104] The above specific embodiments further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A fuzzy fusion method for multi-information shale oil geological sweet spots, characterized in that, The fusion method includes: Step S1: Obtain multi-source information data related to shale oil sweet spot prediction; Step S2: Predict the crack plane in multiple azimuth angle segments to obtain crack prediction results; Step S3: Predict the three-dimensional lithofacies of shale oil and obtain the lithofacies prediction results; Step S4: Based on the fracture prediction results and the lithofacies prediction results, construct a fuzzy fusion formula based on the improved Sigmod function and the TS function; Step S5: Calculate the fuzzy fusion result of the multi-information shale oil geological sweet spot.

2. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 1, characterized in that, Step S1, acquiring multi-source information data related to shale oil sweet spot prediction, specifically includes: One-dimensional whole-rock analysis data and well logging data; two-dimensional geological data; two-dimensional post-stack seismic data; and five-dimensional OVT data; Acquire multi-dimensional, multi-source information data, and perform data processing, analysis, and outlier removal. Through fine calibration of well-seismic data, post-stack seismic data in the time domain and five-dimensional OVT data are calibrated to the depth domain, enabling free switching and application of data in multiple dimensions of the time domain and depth domain.

3. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 1, characterized in that, Step S2: Predicting the crack plane in multiple azimuth angle segments and obtaining the crack prediction results specifically includes: Based on azimuth anisotropy technology, multiple azimuth angles are superimposed on OVT data; Conduct plane prediction of cracks in multiple azimuth angle segments.

4. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 1, characterized in that, Step S3: Predicting the three-dimensional lithofacies of shale oil and obtaining the lithofacies prediction results specifically includes: Based on artificial intelligence technology, predict the three-dimensional lithofacies of shale oil.

5. The fuzzy fusion method for multi-information shale oil geological sweet spots according to claim 1, characterized in that, Step S4: Constructing a fuzzy fusion formula based on the improved Sigmoid function and the TS function according to the fracture prediction results and the lithofacies prediction results specifically includes: The importance of the lithofacies and fracture prediction results is ranked according to the degree of constraint of lithofacies and fractures on shale oil geological sweet spots; Construct a fuzzy fusion formula based on the improved Sigmod and TS functions.

6. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 3, characterized in that, The method of superimposing multiple azimuth angles on OVT data based on azimuth anisotropy technology specifically includes: Extract post-stack coherence and curvature attributes to clarify the fracture plane distribution morphology of the target layer in the study area; For fractures in multiple locations and of various forms, the range of azimuth angles perpendicular to the fracture direction is defined. Based on the defined azimuth angle ranges, OVT data are superimposed by azimuth angle to obtain superimposed azimuth data for multiple azimuth angle ranges.

7. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 3, characterized in that, The specific steps of conducting crack plane prediction across multiple azimuth angle segments include: Based on the overlay data from different directions, likelihood attributes, ant-like structures, and curvature attributes are extracted along the layers to examine the planar distribution morphology of cracks in multiple directions and to conduct a difference analysis.

8. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 1, characterized in that, The prediction of shale oil three-dimensional lithofacies based on artificial intelligence technology specifically includes: Shale oil facies classification starts with TOC and carbonate content, using carbonate content as a target to predict shale oil facies; Using machine learning algorithms, starting from carbonate content data in whole-rock experimental data, a time window covering curve morphology information was selected to establish and optimize the training model. The training model was then applied to actual drilling operations throughout the entire work area. The spatial distribution characteristics of carbonate content in the entire work area were obtained by using a feedforward neural network.

9. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 1, characterized in that, The specific steps involved in constructing the fuzzy fusion formula based on the improved Sigmoid and TS functions are as follows: Fuzzy logic methods are introduced to address the uncertainties and fuzzinesses in shale oil sweet spots caused by shale facies and fracture analysis. Given that the lithofacies prediction results and fracture identification results are not on the same dimension, the improved Sigmod function is used to normalize the favorable lithofacies development zone or fracture development zone to the [0,1] interval, and the improved TS function is used to carry out fuzzy inference. The improved TS function is as follows: Where α and β are the scores of fractures and lithofacies, respectively, in the analysis of the main controlling factors for predicting shale oil sweet spots; both are positive values. i B and A' are the normalized prediction results of fractures and lithofacies in different azimuths, respectively, where n is the number of azimuth divisions, and A' is the number of divisions. i The improved Sigmod function for B is calculated as follows: If the input data is positively correlated with the shale oil sweet spot, then c = 1; if the input data is negatively correlated with the shale oil sweet spot, then c = 2; Q is a fractured area or a favorable lithofacies area. By using formulas (1) and (2), the effective integration of the same type of constraint factors and multiple types of constraint factors is achieved for the geological sweet spots of shale oil.

10. The multi-information shale oil geological sweet spot fuzzy fusion method according to claim 1, characterized in that, Step S5: Calculating the fuzzy fusion result of multi-information shale oil geological sweet spot specifically includes: achieving a graded evaluation of shale oil geological sweet spot based on the fuzzy fusion result.

Images