Intelligent mudstone identification method for seismic indication crossing fracturing

Abstract

The invention discloses a mudstone intelligent identification method for seismic indication crossing fracturing, and belongs to the technical field of unconventional oil and gas fracturing development. The intelligent mudstone identification method comprises the steps of making a horizontal well actual drilling track 2D lithologic label, solving a depth domain inversion body, constructing a lithologic sample earthquake 4D intelligent discrimination label, calculating a lithologic comprehensive evaluation body S5, intelligently indicating cross-layer fracturing transformation and the like. By using three-dimensional seismic data to carry out technical means such as accurate identification of a spatial mudstone section, accurate identification of effective reservoirs around the mudstone section and comprehensive evaluation of a reservoir structure and a combination relation of the reservoir structure, intelligent prompting of a strata-penetrable fracturing section in space is realized, and an accurate judgment basis can be provided for accurate strata-penetrable fracturing transformation of an unconventional oil and gas horizontal well; and the purpose of fully utilizing underground geological reserves is achieved. The intelligent identification method provided by the invention can be applied to fracturing development of unconventional oil and gas.

Description

Technical Field

[0001] The invention belongs to the technical field of unconventional oil and gas fracturing development, and relates to a mudstone intelligent identification method, in particular to a mudstone intelligent identification method for seismic-indicated layer-penetrating fracturing. Background Art

[0002] Domestic shale oil and gas resources are huge, and their scale-effective development is of great strategic significance to ensuring national energy security and the sustainable development of oil fields. In order to fully and efficiently utilize recoverable geological reserves, many oil fields have carried out concentrated deployment of long horizontal wells, large well clusters, small well spacing, and three-dimensional well networks based on platforms. However, due to the characteristics of low porosity and ultra-low permeability, large-scale volume fracturing transformation is currently the key means to increase production. Horizontal well fracturing is mainly aimed at the sandstone section encountered during drilling, and the mudstone section is often abandoned without fracturing. However, as the drilling blocks become increasingly complex, exploring through-layer fracturing in interlayered areas is an effective measure to tap potential and increase production. Through-layer fracturing refers to the well section where the horizontal well encounters a mudstone section, but there are high-quality reservoirs developed within a close distance from the top and bottom of the trajectory. The reserves of the top and bottom high-quality reservoirs are communicated vertically through fracturing. It is currently an effective means to communicate and utilize reserves to the greatest extent, and improves the fracturing transformation effect and the single well production.

[0003] The accurate design of through-layer fracturing requires the location of the mudstone section encountered by the horizontal well, as well as the spatial position, structure, and combination relationship of the top and bottom reservoirs of the trajectory. This requires accurate identification, comprehensive evaluation, and rapid positioning of the lithology and spatial changes of the wellbore and its surroundings.

[0004] There are several main methods for existing through-layer fracturing schemes: 1. Using drilling, logging or seismic research results to simulate the spatial characteristics of sweet spots and explore through-layer fracturing in mudstone sections. However, due to the strong multi-solution and large error of this method, it has not been promoted and implemented; 2. Using three-dimensional seismic data to obtain a certain elastic parameter body that can reflect the lithology through inversion, but in the face of ultra-thin shale oil and tight gas reservoirs, due to the limitations of seismic data resolution and prediction methods, the prediction of the fine combination relationship of sand and mudstone around the wellbore is highly multi-solution and has large errors, so it is impossible to meet the accuracy requirements of indicating precise through-layer fracturing in the horizontal section; 3. Using three-dimensional seismic inversion bodies, manually identifying the reservoir sections around the mudstone section of the wellbore where through-layer fracturing can be implemented has problems such as low efficiency, large human influence factors, and large errors, so it has not been widely promoted and applied in engineering fracturing.

[0005] Therefore, providing a mudstone intelligent identification method that can accurately indicate through-layer fracturing has become a technical problem that needs to be solved urgently in the field of unconventional oil and gas development. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a mudstone intelligent identification method based on three-dimensional seismic, to provide a basis for the precise penetration and fracturing transformation of shale oil horizontal wells, and to achieve the purpose of fully utilizing underground geological reserves.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is:

[0008] A method for intelligently identifying mudstone indicated by seismic interlayer fracturing, the method comprising the following steps performed in sequence:

[0009] S1. Create 2D lithology labels for horizontal well drilling trajectory

[0010] Using the parameters measured by actual drilling logging, vector correction is performed on the comprehensive geological orientation image of the horizontal well, the lithology changes encountered in the horizontal well trajectory and the corresponding coordinates are extracted, and 2D lithology labels of the horizontal well trajectory are produced;

[0011] S2. Obtaining the depth domain inversion volume

[0012] The three-dimensional seismic data is used to obtain the seismic characteristic attribute time domain inversion volume reflecting the spatial changes of lithology and oil content. Sample control points are added according to the 2D lithology labels of the horizontal well actual drilling trajectory, and the spatial velocity field is updated iteratively in real time. The above seismic characteristic attribute time domain inversion volume is converted from the time domain to the space domain to obtain the depth domain inversion volume.

[0013] S3. Constructing 4D intelligent seismic discrimination labels for lithology samples

[0014] According to the degree of conformity between seismic characteristic attributes and drilling, logging and geological research results, the depth domain inversion body is optimized to obtain the optimized depth domain inversion body, and the correlation between the seismic and geological lithology values ​​of each lithology sample point is established. The lithology elements are superimposed on the optimized depth domain inversion body, and a comprehensive evaluation is performed to construct the lithology sample seismic 4D intelligent discrimination label;

[0015] S4. Calculate the comprehensive lithology evaluation body S 5

[0016] The lithology sample seismic 4D intelligent discrimination label constructed in step S3 is intelligently trained to obtain a lithology comprehensive evaluation body S 5 and comprehensive lithology evaluation value S;

[0017] S5. Intelligent indication of layer-penetrating fracturing transformation

[0018] Automatically scan the lithology comprehensive evaluation volume S along the well trajectory in a custom scanning mode 5 According to the comprehensive lithology evaluation value S, different intelligent instructions are given for the through-layer fracturing transformation.

[0019] The present invention defines the following terms:

[0020] 2D lithology labels are two-dimensional identifiable labels formed by combining any point on the horizontal well trajectory with the lithology encountered;

[0021] Vector correction is a method of calibrating an image without spatial position meaning to its real spatial position by positioning the entire image at two or more points;

[0022] The 4D intelligent seismic identification label refers to a four-dimensional spatial domain composed of the deep spatial domain, the three-dimensional seismic superposition of the lithology domain, which can be used for intelligent and accurate pattern recognition.

[0023] As a first limitation of the method for intelligently identifying mudstones by seismic-indicated through-layer fracturing according to the invention, step S5 further includes step S6. A through-layer fracturing indication test for horizontal wells, i.e., a through-layer fracturing test is performed on the horizontal well, steps S1 to S5 are executed in sequence, the rationality of each step is tested, and the rationality and intelligence of the method for intelligently identifying mudstones by seismic-indicated through-layer fracturing are detected. When a mudstone section is encountered during drilling of the horizontal well and there is a high-quality reservoir within 3 m from the top and bottom, through-layer fracturing and direction prompts are made. After the through-layer section is fractured according to the indication, if the through-layer section contributes to production, it indicates that the method for intelligently identifying mudstones by seismic-indicated through-layer fracturing meets the requirements.

[0024] As a second limitation of the method for intelligently identifying mudstone with seismic indication of through-layer fracturing according to the present invention, in step S1, the parameters measured by the actual drilling logging include at least one of well coordinates, trajectory, gas logging while drilling and gamma.

[0025] As a third limitation of the method for intelligent identification of mudstone with seismic indication of through-layer fracturing described in the present invention, in step S2, the seismic characteristic attributes include aspect ratio, brittleness, porosity, Poisson's ratio, porosity, clay mineral content, permeability, density and acoustic impedance.

[0026] As a fourth limitation of the method for intelligently identifying mudstone with seismic indication of trans-layer fracturing according to the present invention, step S3 comprises the following steps:

[0027] S31. Establish lithology samples based on well logging data, geological data and 2D lithology labels of horizontal well drilling trajectories in the study area;

[0028] S32. optimizing the depth domain inversion volume according to the degree of conformity between the seismic characteristic attributes and the drilling, logging and geological research results, and obtaining the optimized depth domain inversion volume;

[0029] S33. respectively extract the value range of the depth domain inversion volume after optimization for each lithology sample point, further establish the correlation between the seismic and geological lithology values ​​of each lithology sample point, and remove the sample points in the overlapping area of ​​each attribute;

[0030] S34. Overlay the lithologic elements onto the three-dimensional space of the optimized depth domain inversion volume, conduct a comprehensive assessment, and construct a 4D intelligent seismic discrimination label for the lithologic sample.

[0031] As a fifth limitation of the intelligent identification method of mudstone indicated by seismic through-layer fracturing of the present invention, in step S4, the intelligent training includes applying artificial intelligence techniques such as K-nearest neighbor method and Gaussian mixture model for calculation.

[0032] As a sixth limitation of the method for intelligently identifying mudstone with seismic indication of trans-layer fracturing according to the present invention, step S5 comprises the following steps:

[0033] S51. Set n S 5 The threshold, i.e. S 1 , S 2 , S 3 ,...S n , where S 1 represents the comprehensive evaluation value of mudstone lithology, S 2 represents the comprehensive evaluation value of oil spot sandstone properties, S 3 Represents the comprehensive evaluation value of oil-stained sandstone, S4~S n Represents the comprehensive lithology evaluation value of various types of sandstone;

[0034] Each threshold is based on the S 5 The value determines its S imin , S imax (i=1,2,3,...n);

[0035] S52. Use custom scanning mode to automatically scan the lithology comprehensive evaluation volume along the well trajectory direction. 5 According to the comprehensive lithology evaluation value S, different intelligent instructions are issued for the through-layer fracturing transformation, specifically:

[0036] ①When S=[S imin , S imax ](i=2,3,...n), the output is α, indicating a red light, which is a normal transformation section, and the cycle ends;

[0037] ②When S=[S 1min , S 1max ], it is determined to be a mudstone section, β is output, the green light is indicated, and S is output at the same time 1 5 And enter the next cycle;

[0038] Define the upper and lower time windows D along the horizontal well trajectory top ~D bottom , for the first round output S 1 5 Automatic scanning, when S(x, y, D z+Δd )=[S imin , S imax](i=2,3), output Δd, if Δd>0, output γ, indicating downward penetration, if Δd<0, output δ, indicating upward penetration;

[0039] Among them, S refers to the comprehensive lithology evaluation value of any point in space; D is the depth value of a certain point; Z refers to any point on the horizontal well trajectory, and its coordinates are (x, y); D z Refers to the depth value corresponding to any point Z(x, y) on the horizontal well trajectory; Δd refers to the depth deviation D from the horizontal well trajectory at the same position as Z(x, y) in space. z The difference in size, D z+Δd Refers to the depth value at the same position in space as the horizontal well trajectory Z(x, y); S(x, y, D z+Δd ) refers to the comprehensive lithology evaluation value at any depth at the same coordinate (x, y) as the horizontal well trajectory; α, β, γ and δ represent different values.

[0040] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0041] ① The present invention uses 3D seismic data to obtain various elastic inversion bodies that directly or indirectly reflect the spatial changes of lithology and oil content through high-resolution prestack geostatistical inversion. It integrates core samples, laboratory data, geological data, etc. to perform comprehensive intelligent identification of mudstones on various elastic inversion bodies, and intelligently indicates the areas around mudstones where through-layer fracturing can be implemented, providing accurate identification basis for precise through-layer fracturing transformation of shale oil and gas horizontal wells, so as to achieve the purpose of fully utilizing underground geological reserves;

[0042] ② Compared with the existing horizontal well through-layer fracturing related technologies, the present invention greatly improves the accuracy of spatial combination identification of lithology in and around the wellbore; it can intelligently indicate the layer sections that can be transformed by through-layer fracturing. The intelligent identification accuracy of mudstone is significantly improved, with the absolute error increased from more than 4m to within 0.45m, and it can efficiently and accurately indicate the sections around the wellbore where through-layer fracturing can be implemented, and the through-layer sections have a significant production contribution;

[0043] ③ In the method for intelligent identification of mudstone by seismic indication of layer-penetrating fracturing provided by the present invention, in step S2, the sample control point N is added. 1 、N 2 、N 3 ......, a method for real-time iterative updating of the spatial velocity field, the purpose of which is to obtain a high-precision depth domain inversion volume, providing a basis for intelligent and accurate identification of earthquake 4D;

[0044] ④ Taking into account the multiple solutions, low efficiency, artificial uncertainty and large errors of single elastic parameter body and manual discrimination methods, the present invention adopts methods such as "4D seismic intelligent discrimination label", "lithology complex intelligent assessment", "through-layer fracturing transformation intelligent prompt", etc., which significantly improves the accuracy of intelligent identification of mudstone sections and surrounding reservoir sections where through-layer fracturing can be implemented, and solves the technical bottleneck of accurate and efficient design of through-layer fracturing transformation schemes for shale oil horizontal wells;

[0045] ⑤ The intelligent identification method of mudstone for seismic-indicated layer-penetrating fracturing provided by the present invention plays a technical leading and important supporting role in future engineering fracturing transformation, can enrich and improve the seismic-geological-engineering integrated technology series, and further broaden the business chain of seismic application in engineering;

[0046] In summary, the intelligent identification method of mudstone indicated by seismic through-layer fracturing provided by the present invention uses three-dimensional seismic data to carry out accurate identification of spatial mudstone segments, accurate identification of effective reservoirs around mudstone segments, and comprehensive evaluation of reservoir structures and their combined relationships, and other technical means, further realizing intelligent prompting of spatial through-layer fracturing segments, and can provide accurate judgment basis for accurate through-layer fracturing transformation of unconventional oil and gas horizontal wells, so as to achieve the purpose of fully utilizing underground geological reserves. At the same time, the intelligent identification method of mudstone has a technical leading and important supporting role in future engineering fracturing transformation, and is also in line with the development trend of increasingly digital and intelligent transformation in my country's energy exploration field.

[0047] The intelligent mudstone identification method for seismic-indicated layer-penetrating fracturing provided by the present invention can be applied to the fracturing development of unconventional oil and gas. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0049] Figure 1 It is a technical flow chart of the intelligent identification method of mudstone for seismic-indicated layer-penetrating fracturing in an embodiment of the present invention;

[0050] Figure 2 It is a 2D lithology label of the actual drilling trajectory of the HH102-5 horizontal well in the embodiment of the present invention;

[0051] Figure 3 5 kinds of depth domain inversion bodies after optimization of the study area in the embodiment of the present invention, wherein Figure a is a depth domain inversion body diagram of the longitudinal and transverse wave velocity ratio, Figure b is a depth domain inversion body diagram of the brittleness, Figure c is a depth domain inversion body diagram of the porosity, Figure d is a depth domain inversion body diagram of the permeability, and Figure e is a depth domain inversion body diagram of the clay mineral content;

[0052] Figure 4 It is the seismic 4D intelligent discrimination label of some lithology samples of HH102-5 horizontal well and H2 horizontal well in the embodiment of the present invention;

[0053] Figure 5 It is the comprehensive lithology assessment body of the HH102 well area in the embodiment of the present invention;

[0054] Figure 6 This is a comprehensive identification and intelligent prompt diagram of HH102-5 horizontal well through-layer fracturing in an embodiment of the present invention;

[0055] Figure 7 This is a diagram showing the fracturing effect of the mudstone penetration section in the HH102-5 horizontal well in the embodiment of the present invention;

[0056] Figure 8 This is a cross-sectional diagram of the comprehensive lithology evaluation of the H2 horizontal well in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The present invention will be further described in detail below by specific embodiments in conjunction with the accompanying drawings. It should be understood that the described embodiments are preferred examples of the present invention and are only used to explain the present invention and do not limit the present invention. Unless otherwise specifically defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those of ordinary skill in the relevant art.

[0058] Example

[0059] The present invention provides a method for intelligently identifying mudstone indicated by seismic interlayer fracturing, and its technical flow chart is as follows: Figure 1 As shown, this embodiment uses the M area of ​​the Ordos Basin as the study area to conduct a shale oil horizontal well through-layer fracturing test. Since the study area used a single reservoir prediction result to manually identify the through-layer fracturing section in the early stage, it failed to be applied and promoted in the shale oil horizontal well through-layer fracturing due to errors (the absolute error reached 4m); this embodiment uses the study area as an example to specifically illustrate the mudstone intelligent identification method for seismic indication through-layer fracturing, and the mudstone intelligent identification method specifically includes the following steps performed in sequence:

[0060] S1. Create 2D lithology labels for horizontal well drilling trajectory

[0061] Using the well coordinates, trajectory, gas logging while drilling, gamma and other parameter data measured by actual drilling logging, vector correction is performed on the comprehensive geological guidance picture of the horizontal well, and the lithology changes encountered by the horizontal well trajectory and the corresponding coordinates are extracted;

[0062] With the horizontal well target as the horizontal coordinate and the lithology as the vertical coordinate, a 2D lithology label of the horizontal well actual drilling trajectory is produced;

[0063] In this example, 2D lithology labels of the actual drilling trajectories of 15 wells in the M area of ​​the Ordos Basin were prepared, among which the 2D lithology labels of the actual drilling trajectories of the HH102-5 horizontal well are as follows: Figure 2 As shown;

[0064] S2. Obtaining the depth domain inversion volume

[0065] The 3D seismic data is used to obtain the seismic characteristic attribute time domain inversion volume that directly or indirectly reflects the spatial changes of lithology and oil content. The sample control point N is added according to the 2D lithology label of the horizontal well actual drilling trajectory. 1 、N 2 、N 3 ..., iteratively update the spatial velocity field in real time;

[0066] According to the updated spatial velocity field, the obtained seismic characteristic attribute time domain inversion volume is converted from the time domain to the spatial domain to further obtain the corresponding depth domain inversion volume. Because when converting the time domain inversion volume to the depth domain inversion volume, the spatial velocity field is obtained by adding sample control points according to the 2D lithology label of the actual drilling trajectory of the horizontal well, and the obtained depth domain inversion volume has a higher accuracy.

[0067] Among them, the seismic characteristic attributes here include the ratio of longitudinal and transverse wave velocities, brittleness, porosity, Poisson's ratio, porosity, clay mineral content, permeability, density and acoustic impedance;

[0068] S3. Constructing 4D intelligent seismic discrimination labels for lithology samples

[0069] S31. Establish lithology samples based on well logging data, geological data and 2D lithology labels of horizontal well drilling trajectories in the study area;

[0070] In this embodiment, according to the actual situation and needs of the study area, the lithology is divided into four categories: oil-spotted sand, oil-trace sand, dry sand and mudstone; when the method described in the present invention is applied to other study areas, the lithology categories can be divided according to the actual situation and needs of the study area;

[0071] S32. According to the correspondence between the seismic characteristic attributes and the drilling, logging and geological research results, the depth domain inversion volume obtained in step S2 is optimized to obtain the optimized depth domain inversion volume;

[0072] In this embodiment, the corresponding characteristic values ​​of the five inversion bodies of the longitudinal and transverse wave velocity ratio, brittleness, porosity, clay mineral content and permeability in the study area have a good correspondence with the drilling, logging and geological research results, and are the five depth domain inversion bodies after optimization in the study area; among them, the five depth domain inversion bodies after optimization in the study area are as follows Figure 3 As shown, Figure 3 Figure a in the middle is the depth domain inversion volume map of the ratio of longitudinal and transverse wave velocities, Figure b is the depth domain inversion volume map of brittleness, Figure c is the depth domain inversion volume map of porosity, Figure d is the depth domain inversion volume map of permeability, and Figure e is the depth domain inversion volume map of clay mineral content;

[0073] S33. extract the value ranges of the five depth domain inversion bodies after optimization for each lithology sample point, further establish the correlation between the seismic and geological lithology values ​​of each lithology sample point, and remove the sample points in the overlapping area of ​​each attribute;

[0074] S34. Superimpose the four lithology elements on the three-dimensional space of the depth domain inversion volume, conduct a comprehensive assessment, and construct a 4D intelligent seismic discrimination label for the lithology sample;

[0075] Among them, the seismic 4D intelligent discrimination labels of some lithology samples of HH102-5 horizontal well and H2 horizontal well in this study area are as follows: Figure 4 shown.

[0076] S4. Calculate the comprehensive lithology evaluation body S 5

[0077] The lithology sample seismic 4D intelligent discrimination label constructed in step S3 is intelligently trained, and the K-nearest neighbor method and Gaussian mixture model are used for calculation to obtain the lithology comprehensive evaluation body S 5 ;

[0078] Among them, the comprehensive lithology evaluation system of HH102-5 horizontal well is as follows Figure 5 As shown;

[0079] S5. Intelligent indication of layer-penetrating fracturing transformation

[0080] S51. Set 4 S 5 The threshold, i.e. S 1 , S 2 , S 3 , S 4 They represent the comprehensive evaluation values ​​of mudstone, oil-spotted sand, oil-stained sand and dry sand. Each threshold is determined by the S 5 The value determines its S imin , S imax (i=1,2,3,4);

[0081] S52. Use custom scanning mode to automatically scan the lithology comprehensive evaluation volume along the well trajectory direction. 5 According to the comprehensive lithology evaluation value S, different intelligent instructions are issued in real time for the through-layer fracturing transformation, specifically:

[0082] ①When S=[S imin , S imax ](i=2,3,4), the output is 0, indicating a red light, which is a normal transformation section, and the cycle ends;

[0083] ②When S=[S 1min , S 1max ], it is determined to be a mudstone section, output 1, indicating a green light, and output S 15 And enter the next cycle;

[0084] Define the upper and lower time windows D along the horizontal well trajectory top ~D bottom , for the first round output S 1 5 Automatic scanning, when S(x, y, D z+Δd )=[S imin , S imax ](i=2,3), output Δd, if Δd>0, output 00, indicating downward penetration, if Δd<0, output 01, indicating upward penetration;

[0085] Among them, S refers to the comprehensive lithology evaluation value of any point in space; D is the depth value of a certain point; Z refers to any point on the horizontal well trajectory, and its coordinates are (x, y); D z Refers to the depth value corresponding to any point Z(x, y) on the horizontal well trajectory; Δd refers to the depth deviation D from the horizontal well trajectory at the same position as Z(x, y) in space. z The difference in size, D z+Δd Refers to the depth value at the same position in space as the horizontal well trajectory Z(x, y); S(x, y, D z+Δd ) refers to the comprehensive lithology evaluation value at any depth at the same coordinate (x, y) as the horizontal well trajectory;

[0086] S6. Horizontal well penetration fracture indication test

[0087] Performing a through-layer fracturing test on a horizontal well, executing steps S1 to S5 in sequence, using a post-test well to test the rationality of each step, and detecting the rationality and intelligence of the intelligent mudstone identification method for through-layer fracturing indicated by seismic indications;

[0088] Among them, the comprehensive identification and intelligent prompt diagram of HH102-5 horizontal well through-layer fracturing is shown in the figure below. Figure 6 As shown in the figure, the fracturing effect diagram of the mudstone penetration section of the HH102-5 horizontal well is as follows Figure 7 As shown. Figure 6-7 It can be seen that when encountering a mudstone section in the HH102-5 horizontal well, the method provided by the present invention can accurately make through-layer fracturing and direction prompts, and after the through-layer section is fractured according to the indication, the through-layer section has production contribution, and the production contribution is more obvious, indicating that the mudstone intelligent identification method for seismic indication through-layer fracturing proposed in the present invention meets the requirements.

[0089] In the early stage, the single reservoir prediction results were used to manually identify the through-layer fracturing section in this study area, which resulted in large errors, with the absolute error reaching 4m. The 15 wells in this study area were subjected to through-layer fracturing using the mudstone intelligent identification method for through-layer fracturing indicated by seismic indication proposed in this invention. The comprehensive lithology evaluation profile of the H2 horizontal well is shown in Figure 1. Figure 8 As shown. Figure 8 It can be seen that by applying the method provided by the present invention, the accuracy of intelligent mudstone identification is significantly improved, and the absolute error between the predicted and measured depths of the through-layer fracturing section is within 0.45m. Since the method provided by the present invention can efficiently and accurately indicate the through-layer fracturing section that can be implemented around the wellbore, after applying this method, a total of 21 mudstone sections in 15 wells in this study area have obvious pressure breakage in high-quality reservoirs within 3m from the top and bottom of the fracturing, and the through-layer section has a significant production contribution, which further confirms that the intelligent mudstone identification method for seismic indication of through-layer fracturing provided by the present invention has played an important role in the precise fracturing transformation of shale oil horizontal wells and the full utilization of reserves.

[0090] The above description is only an optional embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for intelligently identifying mudstone indicated by seismic interlayer fracturing, characterized in that: The mudstone intelligent identification method comprises the following steps performed in sequence: S1. Create 2D lithology labels for horizontal well drilling trajectory Using the parameters measured by actual drilling logging, vector correction is performed on the comprehensive geological orientation image of the horizontal well, the lithology changes encountered in the horizontal well trajectory and the corresponding coordinates are extracted, and 2D lithology labels of the horizontal well trajectory are produced; S2. Obtaining the depth domain inversion volume The three-dimensional seismic data is used to obtain the seismic characteristic attribute time domain inversion volume reflecting the spatial changes of lithology and oil content. Sample control points are added according to the 2D lithology labels of the horizontal well actual drilling trajectory, and the spatial velocity field is updated iteratively in real time. The above seismic characteristic attribute time domain inversion volume is converted from the time domain to the space domain to obtain the depth domain inversion volume. S3. Constructing 4D intelligent seismic discrimination labels for lithology samples According to the degree of conformity between seismic characteristic attributes and drilling, logging and geological research results, the depth domain inversion body is optimized to obtain the optimized depth domain inversion body, and the correlation between the seismic and geological lithology values ​​of each lithology sample point is established. The lithology elements are superimposed on the optimized depth domain inversion body, and a comprehensive evaluation is performed to construct the lithology sample seismic 4D intelligent discrimination label; S4. Calculate the comprehensive lithology evaluation body S 5 The lithology sample seismic 4D intelligent discrimination label constructed in step S3 is intelligently trained to obtain a lithology comprehensive evaluation body S 5 and comprehensive lithology evaluation value S; S5. Intelligent indication of layer-penetrating fracturing transformation Automatically scan the lithology comprehensive evaluation volume S along the well trajectory in a custom scanning mode 5 According to the comprehensive lithology evaluation value S, different intelligent instructions are given for the through-layer fracturing transformation.

2. The method for intelligent identification of mudstone for seismic indication of layer-penetrating fracturing according to claim 1, characterized in that: The step S5 also includes step S6. horizontal well through-layer fracturing indication test, that is, performing through-layer fracturing test on the horizontal well, executing steps S1 to S5 in sequence, testing the rationality of each step, and detecting the rationality and intelligence of the mudstone intelligent identification method of seismic indication through-layer fracturing. When a mudstone section is encountered in the horizontal well and there is a high-quality reservoir within 3m from the top and bottom, through-layer fracturing and direction prompts are made. After the through-layer section is fractured according to the indication, if the through-layer section contributes to production, it means that the mudstone intelligent identification method of seismic indication through-layer fracturing meets the requirements.

3. The method for intelligent identification of mudstone for seismic indication of trans-layer fracturing according to claim 1, characterized in that: In step S1, the parameters measured by the actual drilling logging include at least one of well coordinates, trajectory, gas logging while drilling and gamma.

4. The method for intelligent identification of mudstone for seismic-indicated layer-penetrating fracturing according to claim 1, characterized in that: In step S2, the seismic characteristic attributes include aspect ratio, brittleness, porosity, Poisson's ratio, porosity, clay mineral content, permeability, density and acoustic impedance.

5. The method for intelligent identification of mudstone for seismic-indicated layer-penetrating fracturing according to claim 1, characterized in that: The step S3 comprises the following steps: S31. Establish lithology samples based on well logging data, geological data and 2D lithology labels of horizontal well drilling trajectories in the study area; S32. optimizing the depth domain inversion volume according to the degree of conformity between the seismic characteristic attributes and the drilling, logging and geological research results, and obtaining the optimized depth domain inversion volume; S33. respectively extract the value range of the depth domain inversion volume after optimization for each lithology sample point, further establish the correlation between the seismic and geological lithology values ​​of each lithology sample point, and remove the sample points in the overlapping area of ​​each attribute; S34. Overlay the lithologic elements onto the three-dimensional space of the optimized depth domain inversion volume, conduct a comprehensive assessment, and construct a 4D intelligent seismic discrimination label for the lithologic sample.

6. The method for intelligent identification of mudstone for seismic-indicated layer-penetrating fracturing according to claim 1, characterized in that: In step S4, the intelligent training includes applying K-nearest neighbor method and Gaussian mixture model for calculation.

7. The intelligent mudstone identification method for seismic-indicated layer-penetrating fracturing according to any one of claims 1 to 6, characterized in that: Step S5 includes the following steps: S51. Set n S 5 Thresholds, i.e. S1, S2, S3, ...S n Represent the comprehensive lithology evaluation values ​​of mudstone, oil-spotted sand, oil-trace sand, and at least one type of sandstone, respectively. Each threshold is determined based on the S 5 The value determines its S imin , S imax (i=1,2,3,...n); S52. Use custom scanning mode to automatically scan the lithology comprehensive evaluation volume along the well trajectory direction. 5 According to the comprehensive lithology evaluation value S, different intelligent instructions are issued for the through-layer fracturing transformation, specifically: ①When S=[S imin , S imax ](i=2,3,...n), the output is α, indicating a red light, which is a normal transformation section, and the cycle ends; ②When S=[S 1min , S 1max ], it is determined to be a mudstone section, β is output, the green light is indicated, and S1 is output at the same time 5 And enter the next cycle; Define the upper and lower time windows D along the horizontal well trajectory top ~D bottom , for the first round of output S1 5 Automatic scanning, when S(x, y, D z+Δd )=[S imin , S imax ](i=2,3), output Δd, if Δd>0, output γ, indicating downward penetration, if Δd<0, output δ, indicating upward penetration; Among them, S refers to the comprehensive lithology evaluation value of any point in space; D is the depth value of a certain point; Z refers to any point on the horizontal well trajectory, and its coordinates are (x, y); D z Refers to the depth value corresponding to any point Z(x, y) on the horizontal well trajectory; Δd refers to the depth deviation D from the horizontal well trajectory at the same position as Z(x, y) in space. z The difference in size, D z+Δd Refers to the depth value at the same position in space as the horizontal well trajectory Z(x, y); S(x, y, D z+Δd ) refers to the comprehensive lithology evaluation value at any depth at the same coordinate (x, y) as the horizontal well trajectory; α, β, γ and δ represent different values.

Images