Method, device and computer equipment for determining volume of carbonate fracture-cavity reservoir

Abstract

The present disclosure provides a method, device, and computer equipment for determining the volume of carbonate fracture-cavity reservoirs, and belongs to the technical field of oil and gas reservoir development. The seismic attribute values ​​of three-dimensional seismic data and carbonate rocks can reflect the existence of fractures and caves, but the correspondence between the existence of fractures and caves is not accurate enough. Therefore, the actual fracture-cavity thickness values ​​of multiple measuring points in multiple wells in the carbonate rock area can be directly obtained first, and then a neural network model for reflecting the mapping relationship between the seismic attribute values ​​and the fracture-cavity thickness values ​​in the carbonate rock area is established. A relatively accurate correspondence can be established between the seismic attribute values ​​and the actual fracture-cavity thickness values. Based on the relatively accurate neural network model, a relatively accurate volume of the fracture-cavity reservoir in the carbonate rock area can be further obtained, which can effectively adjust the specific distribution of subsequent development wells, maximize the development of oil and natural gas, and be conducive to the good development of oil and natural gas.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas reservoir development, and in particular to a method, device and computer equipment for determining the volume of a carbonate fracture-vuggy reservoir. Background Art

[0002] Carbonate rock areas are very rich in oil and natural gas resources and are also very common areas for the production of oil and natural gas. Oil and natural gas are mainly stored in the fractures and caves in carbonate rock areas. The fractures and caves in carbonate rock areas are usually distributed irregularly, and this unevenly distributed fracture and cave part is often called a fracture-cave reservoir.

[0003] In the process of oil and gas development, it is necessary to estimate the volume of fracture-cavity reservoirs in carbonate rock areas and adjust the positions of some development wells according to the volume of fracture-cavity reservoirs. In related technologies, the shape and volume of fracture-cavity reservoirs are often inferred using acquired 3D seismic data. However, 3D seismic data is indirect data related to the strata in carbonate rock areas. Using 3D seismic data to infer the shape and volume of fracture-cavity reservoirs is not accurate enough, which is not conducive to the good development of oil and gas. Summary of the invention

[0004] The embodiments of the present disclosure provide a method, device, and computer equipment for determining the volume of a carbonate fracture-cavity reservoir, which can improve the accuracy of the determined volume of the fracture-cavity reservoir and facilitate the good development of oil and natural gas. The technical solution is as follows:

[0005] The present disclosure provides a method for determining the volume of a carbonate fracture-vuggy reservoir, the method comprising:

[0006] Obtain fracture-vuggy thickness values ​​at a plurality of measuring points in a plurality of wells in a carbonate rock region, wherein the plurality of measuring points are respectively distributed in the plurality of wells;

[0007] Acquiring three-dimensional seismic data of the carbonate rock region;

[0008] Obtaining a neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-hole thickness values ​​of the plurality of measurement points, wherein the neural network model is used to reflect a mapping relationship between the seismic attribute values ​​of the carbonate rock region and the fracture-hole thickness values;

[0009] The neural network model is used to determine the volume of the fracture-cavity reservoir in the carbonate rock region.

[0010] Optionally, obtaining the neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-cavity thickness values ​​of the plurality of measurement points includes:

[0011] Obtaining the plane position coordinates corresponding to the multiple measurement points;

[0012] Performing time-depth conversion on the depths corresponding to the multiple measurement points to obtain the time points corresponding to the multiple measurement points;

[0013] Acquire seismic attribute values ​​corresponding to the multiple measuring points according to the three-dimensional seismic data, the plane position coordinates corresponding to the multiple measuring points, and the time points corresponding to the multiple measuring points;

[0014] The feedforward neural network model is trained using the fracture-hole thickness values ​​corresponding to the multiple measurement points and the seismic attribute values ​​corresponding to the multiple measurement points as training samples to obtain the neural network model.

[0015] Optionally, the seismic attribute value includes a maximum positive curvature attribute value and an edge gradient attribute value; and obtaining the seismic attribute values ​​corresponding to the multiple measuring points according to the three-dimensional seismic data, the plane position coordinates corresponding to the multiple measuring points, and the time points corresponding to the multiple measuring points includes:

[0016] Acquire a dip data volume and an azimuth data volume of the strata in the carbonate rock region according to the three-dimensional seismic data, wherein the dip data volume reflects the change of the strata in the carbonate rock region in the x direction over time, and the azimuth data volume reflects the change of the strata in the carbonate rock region in the y direction over time, wherein the x direction and the y direction are perpendicular to each other and parallel to the horizontal plane;

[0017] Determining the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock region according to the dip data volume and the azimuth data volume;

[0018] According to the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area, the plane position coordinates corresponding to the multiple measurement points and the time points corresponding to the multiple measurement points, the maximum positive curvature attribute value and the edge gradient attribute value corresponding to the multiple measurement points are determined.

[0019] Optionally, the inclination data volume and the azimuth data volume are determined according to the following formula:

[0020]

[0021]

[0022] Among them, p(x,y,t) is the inclination data volume, q(x,y,t) is the azimuth data volume, and υ 1x (x,y,t) is the vector of the three-dimensional seismic data in the x direction, υ 1y (x,y,t) is the vector of the three-dimensional seismic data in the y direction, υ 1t(x, y, t) is the vector of the three-dimensional seismic data in the t direction, the x direction and the y direction are both parallel to the horizontal plane, and the x direction and the y direction are perpendicular to each other, and t is the time direction.

[0023] Optionally, the maximum positive curvature attribute value and the edge gradient attribute value of each measuring point in the carbonate rock region are determined according to the following formula:

[0024]

[0025] in,

[0026]

[0027]

[0028] τ x =tan(p)sinq,τ y =tan(p)cosq;

[0029] K(x, y, t) = (a + b) + [(ab) 2 +c 2 ] 1 / 2 ,

[0030]

[0031]

[0032] Among them, S(x,y,t) is the edge gradient attribute, M x and M y are the templates of the Sobel operator in two orthogonal directions, D i,j,k (x, y, t) are the coordinates of all measurement points selected in the carbonate rock area, Δt is the sampling rate of the carbonate rock area, and are the delay times of the three-dimensional seismic data in the x direction and the y direction, respectively. The x direction and the y direction are both parallel to the horizontal plane and perpendicular to each other. n is the total number of measurement points, i is the step length in the x direction, j is the step length in the y direction, k is the step length in the t direction, K is the total number of measurement points in the t direction, p(x,y,t) and p are both dip data volumes, q(x,y,t) and q are both azimuth data volumes, K(x,y,t) is the maximum positive curvature attribute, a, b, c are the coefficients in the quadratic surface fitting equation of the local area of ​​the three-dimensional seismic data, respectively.

[0033] Optionally, the step of obtaining fracture-cavity layer thickness curves of multiple wells in a carbonate rock region includes:

[0034] Obtain an imaging logging picture of each well in the carbonate rock area; mark a plurality of measuring points on the imaging logging picture; and obtain a fracture-cavity thickness value at each measuring point according to the imaging logging picture.

[0035] Optionally, the using the neural network model to determine the volume of the fracture-vuggy reservoir in the carbonate rock region includes:

[0036] The fracture-cavity volume function at any point in the carbonate rock region is obtained according to the neural network model; the volume of the fracture-cavity reservoir in the carbonate rock region is obtained by integrating the fracture-cavity volume function.

[0037] Optionally, the volume of the fracture-cavity reservoir in the carbonate rock region is determined according to the following formula:

[0038]

[0039] V′(x i ,y j ,t k )=P 3 (x,y,t j );

[0040] Where V is the volume of the carbonate fracture reservoir, m, n and l are the number of grid points in the carbonate region in the x, y and t directions, respectively. i ,y j ,t k ) is the volume of the fracture cavity at any point in the carbonate rock region, V and V′(x i ,y j ,t k ) are all in m 3 ,P(x,y,t j ) is the function of crack thickness.

[0041] The present disclosure provides a volume determination device for a carbonate fracture-vuggy reservoir, the volume determination device comprising:

[0042] A first data acquisition module is used to acquire fracture-vuggy thickness values ​​at a plurality of measurement points in a plurality of wells in a carbonate rock region, wherein the plurality of measurement points are respectively distributed in the plurality of wells;

[0043] A second data acquisition module, used to acquire three-dimensional seismic data of the carbonate rock area;

[0044] A first processing module, configured to obtain a neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-hole thickness values ​​of the plurality of measurement points, wherein the neural network model is configured to reflect a mapping relationship between the seismic attribute value of the carbonate rock region and the fracture-hole thickness value;

[0045] The second processing module is used to determine the volume of the fracture-cavity reservoir in the carbonate rock area by using the neural network model.

[0046] An embodiment of the present disclosure provides a computer device, the computer device comprising:

[0047] processor;

[0048] a memory for storing processor-executable instructions;

[0049] Wherein, the processor is configured to execute the volume determination method of the carbonate fracture-vuggy reservoir as described above.

[0050] The embodiment of the present disclosure provides a non-transitory computer-readable storage medium, wherein the storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the method for determining the volume of a carbonate fracture-vuggy reservoir as described above.

[0051] The beneficial effects brought by the technical solution provided by the embodiments of the present disclosure include at least:

[0052] The neural network model is used to reflect the mapping relationship between the seismic attribute values ​​and the fracture-cavity thickness values ​​in the carbonate rock area. Some seismic attribute values ​​of the three-dimensional seismic data are closely related to the existence of fractures and caves in the carbonate rock area, but the seismic attribute values ​​are secondary calculation data, and the corresponding relationship between the existence of fractures and caves is not accurate enough. Therefore, the actual fracture-cavity thickness values ​​of multiple measuring points in multiple wells in the carbonate rock area can be directly obtained first, and the multiple measuring points are distributed in multiple wells. Then, based on the three-dimensional seismic data and the fracture-cavity thickness values ​​of multiple measuring points, a neural network model for reflecting the mapping relationship between the seismic attribute values ​​and the fracture-cavity thickness values ​​in the carbonate rock area is obtained. A relatively accurate corresponding relationship can be established between the seismic attribute values ​​and the actual fracture-cavity thickness values. Finally, based on the relatively accurate neural network model, a relatively accurate volume of the fracture-cavity reservoir in the carbonate rock area is further obtained, which can effectively adjust the specific distribution of subsequent development wells, maximize the development of oil and natural gas, and is conducive to the good development of oil and natural gas. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 It is a flow chart of a method for determining the volume of a carbonate fracture-vuggy reservoir provided by an embodiment of the present disclosure;

[0055] Figure 2 is a flow chart of another method for determining the volume of a carbonate fracture-vuggy reservoir provided by an embodiment of the present disclosure;

[0056] Figure 3 is a schematic diagram of an imaging logging picture of a well provided by an embodiment of the present disclosure;

[0057] Figure 4 is a schematic diagram of a curved portion of a carbonate rock region provided by an embodiment of the present disclosure;

[0058] Figure 5 is a schematic diagram of discontinuous parts of a carbonate rock region provided by an embodiment of the present disclosure;

[0059] Figure 6 is a location distribution map of fracture-cavity reservoirs in a carbonate rock region provided by an embodiment of the present disclosure;

[0060] Figure 7 It is a schematic diagram of the principle of a device for determining the volume of a carbonate fracture-vuggy reservoir provided by an embodiment of the present disclosure;

[0061] Figure 8 It is a structural block diagram of a computer device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0062] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0063] Figure 1 is a flow chart of a method for determining the volume of a carbonate fracture-vuggy reservoir provided by an embodiment of the present disclosure, with reference to Figure 1 It can be seen that the volume determination method of the carbonate fracture-vuggy reservoir includes:

[0064] S101: Obtain fracture-vuggy thickness values ​​at a plurality of measuring points in a plurality of wells in a carbonate rock region, where the plurality of measuring points are respectively distributed in the plurality of wells.

[0065] S102: Acquire three-dimensional seismic data of the carbonate rock area.

[0066] S103: Obtaining a neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-vug thickness values ​​of the plurality of measurement points, wherein the neural network model is used to reflect the mapping relationship between the seismic attribute values ​​of the carbonate rock region and the fracture-vug thickness values.

[0067] S104: Using a neural network model, determine the volume of the fracture-cavity reservoir in the carbonate rock region.

[0068] The neural network model is used to reflect the mapping relationship between the seismic attribute values ​​and the fracture-cavity thickness values ​​in the carbonate rock area. Some seismic attribute values ​​of the three-dimensional seismic data are closely related to the existence of fractures and caves in the carbonate rock area, but the seismic attribute values ​​are secondary calculation data, and the corresponding relationship between the existence of fractures and caves is not accurate enough. Therefore, the actual fracture-cavity thickness values ​​of multiple measuring points in multiple wells in the carbonate rock area can be directly obtained first, and the multiple measuring points are distributed in multiple wells. Then, based on the three-dimensional seismic data and the fracture-cavity thickness values ​​of multiple measuring points, a neural network model for reflecting the mapping relationship between the seismic attribute values ​​and the fracture-cavity thickness values ​​in the carbonate rock area is obtained. A relatively accurate corresponding relationship can be established between the seismic attribute values ​​and the actual fracture-cavity thickness values. Finally, based on the relatively accurate neural network model, a relatively accurate volume of the fracture-cavity reservoir in the carbonate rock area is further obtained, which can effectively adjust the specific distribution of subsequent development wells, maximize the development of oil and natural gas, and is conducive to the good development of oil and natural gas.

[0069] In addition, the neural network model that reflects the mapping relationship between the seismic attribute values ​​and the fracture thickness values ​​in the carbonate rock region can also be used as a basis for judging whether development can be carried out at a certain location in the carbonate rock region. For example, the seismic attribute values ​​of a certain location in the carbonate rock region can be obtained, and the seismic attribute values ​​can be substituted into the neural network model to deduce the fracture thickness value of the location. If the fracture thickness value is qualified, development can be carried out.

[0070] It should be noted that the fracture-vuggy thickness at a certain depth measurement point is the thickness of the fracture-vuggy thickness intercepted by a plane perpendicular to the depth of the development well at the depth measurement point.

[0071] It should be noted that seismic attribute values ​​refer to the geometric, kinematic, dynamic or statistical characteristic values ​​of seismic waves obtained by mathematical transformation of three-dimensional seismic data.

[0072] Figure 2 is a flow chart of another method for determining the volume of a carbonate fracture-vuggy reservoir provided by an embodiment of the present disclosure, with reference to Figure 2 It can be seen that the method for determining the volume of the carbonate fracture-vuggy reservoir may include:

[0073] S201: Obtain fracture-vuggy thickness values ​​at a plurality of measuring points in a plurality of wells in a carbonate rock region, where the plurality of measuring points are respectively distributed in the plurality of wells.

[0074] Step S201 may include:

[0075] Obtain imaging logging data of multiple development wells in the carbonate rock area; obtain fracture-cavity thickness values ​​of multiple measuring points of each development well based on the imaging logging data of multiple development wells. Based on the imaging logging data, it is easy to obtain the fracture-cavity thickness value of the measuring point.

[0076] Optionally, the imaging logging data includes an imaging logging picture of each well, and the fracture-vuggy thickness values ​​of multiple measuring points of each development well are obtained according to the imaging logging data of multiple development wells, including:

[0077] Mark multiple measurement points on the imaging logging picture; obtain the fracture-hole thickness value of each measurement point according to the imaging logging picture. This can facilitate the direct acquisition of the fracture-hole thickness value of the measurement point.

[0078] It should be noted that the measurement points are all selected from the points where the corresponding fractures and holes are located, and the measurement points are depth points set along the gravity direction. The depths of the measurement points in different wells can be the same or different. The fracture and hole thickness values ​​at each measurement point are all fracture and hole thickness values ​​determined in parallel with the horizontal direction, and are the sum of the thicknesses of the fracture and holes intercepted by a plane parallel to the horizontal direction and perpendicular to the gravity direction.

[0079] It should be noted that the fractures and holes provided in the present disclosure are all fluid fractures and holes containing oil and gas, and such fractures and holes appear as sine-cosine curves or clusters on the imaging logging images.

[0080] Exemplarily, the imaging logging pictures can be obtained through an imaging logging device, which is convenient to obtain.

[0081] Optionally, a first fracture-vug thickness curve may also be obtained according to the imaging logging picture, and the first fracture-vug thickness curve reflects the mapping relationship between the depth of the well and the fracture-vug thickness value.

[0082] The depth point corresponding to the non-zero hole thickness value on the first hole thickness curve is the measurement point. On the first hole thickness curve, the hole thickness value corresponding to the measurement point with a hole is non-zero, and the hole thickness value corresponding to the measurement point without a hole is zero. The extraction of the first hole thickness curve can facilitate the selection and determination of the measurement point, as well as the subsequent data calculation and processing.

[0083] Figure 3 is a schematic diagram of an imaging logging picture of a well provided in an embodiment of the present disclosure, with reference to Figure 3 , Figure 3 Where a represents the depth direction, b represents the horizontal direction, and the thickness value of the crack hole at the measuring point is the thickness value of the crack hole in the b direction. Figure 3 The dark area in the figure is the area where fractures and holes exist on the well. Figure 3 The data on the left are the depth values ​​of the well.

[0084] S202: Acquire three-dimensional seismic data of the carbonate rock area.

[0085] In the implementation method provided by the present disclosure, three-dimensional seismic data can be obtained through seismic exploration technology. Three-dimensional seismic data can reflect the correspondence between the geological characteristics of the carbonate rock area and the time domain. The time domain includes the time point when the seismic wave receiving point starts to receive the first seismic wave from a certain source, until the time point when the seismic wave receiving point receives the last seismic wave from the same source, and the collection of all time points between the two time points.

[0086] It should be noted that in the implementation method provided in the present disclosure, the seismic sources in the seismic exploration technology are all located on the ground.

[0087] In one implementation provided by the present disclosure, three-dimensional seismic data can be obtained by using E i (t j )represent.

[0088] S203: Obtaining the plane position coordinates corresponding to the multiple measurement points.

[0089] In step S203, the plane position coordinates of the measuring point can be determined by a plane map of the carbonate rock area.

[0090] In the implementation provided by the present disclosure, the plane position coordinates corresponding to the measurement point may be coordinates in the x-direction and coordinates in the y-direction. The x-direction and the y-direction are both parallel to the horizontal plane and perpendicular to each other.

[0091] S204: Perform time-depth conversion on the depths corresponding to the multiple measurement points to obtain the time points corresponding to the multiple measurement points.

[0092] For example, performing time-depth conversion on the depths corresponding to the multiple measurement points may include: dividing the depth of each measurement point by the average velocity of the seismic wave to obtain the time point corresponding to each measurement point, so as to achieve rapid conversion between the depth and time point of the measurement point.

[0093] The average velocity of seismic waves, with a certain horizontal interface as the boundary, is the ratio of the total thickness of all strata above the horizontal interface that the seismic waves vertically pass through to the total propagation time.

[0094] S205: Acquire seismic attribute values ​​corresponding to the multiple measuring points according to the three-dimensional seismic data, the plane position coordinates corresponding to the multiple measuring points, and the time points corresponding to the multiple measuring points.

[0095] Optionally, step S205 may include:

[0096] The maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area are obtained according to the three-dimensional seismic data; the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area corresponding to the multiple measuring points are determined according to the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area, the time points and the plane position coordinates corresponding to the multiple measuring points.

[0097] The maximum positive curvature attribute value reflects the degree of stratum curvature in carbonate rock areas, and the edge gradient attribute value reflects the degree of stratum continuity in carbonate rock areas. The maximum positive curvature attribute value is high in areas with greater stratum curvature, and the edge gradient attribute value is high in areas with lower stratum continuity. Areas with high stratum curvature and discontinuity are all areas with high fracture-cavity development. These two seismic attributes are highly correlated with the development of fractures and caves, so the connection between the two and the fracture-cavity thickness value is selected to establish a connection, and the accuracy of the fracture-cavity development area in the carbonate rock area finally reflected is also high.

[0098] For ease of understanding, here is provided Figure 4 and Figure 5 , Figure 4 is a schematic diagram of a curved portion of a carbonate rock region provided in an embodiment of the present disclosure, Figure 4 The medium-dark areas are curved areas in the carbonate rock region, and the maximum positive curvature attribute value corresponding to the dark areas will be larger.

[0099] Figure 5 is a schematic diagram of discontinuous parts of a carbonate rock region provided by an embodiment of the present disclosure, Figure 5 The light-colored areas are discontinuous areas in the carbonate rock region, and the edge gradient attribute values ​​corresponding to the light-colored areas are larger. Figure 4 and Figure 5 It can be seen that Figure 4 The depth of the Figure 5 The light-colored parts of the image have a higher degree of overlap. Figure 4 The darker part of Figure 5 The degree of development of cracks and holes in the overlapping parts of the light-colored areas is higher.

[0100] It should be noted that Figure 4 and Figure 5 All of them are schematic diagrams of the projection of the carbonate rock area on the horizontal plane.

[0101] Optionally, obtaining the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock region according to the three-dimensional seismic data may include:

[0102] The dip data volume and azimuth data volume of the strata in the carbonate rock area are obtained based on the 3D seismic data. The dip data volume reflects the changes of the strata in the carbonate rock area over time in the x direction, and the azimuth data volume reflects the changes of the strata in the carbonate rock area over time in the y direction. The x direction and the y direction are perpendicular to each other and parallel to the horizontal plane. Based on the dip data volume and the azimuth data volume, the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area are determined.

[0103] The maximum positive curvature attribute value and edge gradient attribute value obtained based on the dip data volume and the azimuth data volume are more accurate.

[0104] Optionally, the inclination data volume and the azimuth data volume can be determined according to the following formula:

[0105]

[0106]

[0107] Among them, p(x,y,t) is the inclination data volume, q(x,y,t) is the azimuth data volume, and υ 1x (x,y,t) is the vector of the three-dimensional seismic data in the x direction, υ 1y (x,y,t) is the vector of the three-dimensional seismic data in the y direction, υ 1t (x, y, t) is the vector of the three-dimensional seismic data in the t direction, the x direction and the y direction are both parallel to the horizontal plane, and the x direction and the y direction are perpendicular to each other, and t is the time direction.

[0108] The derivation process of the dip data volume and the azimuth data volume is as follows:

[0109] Decompose the three-dimensional seismic data, construct the three-dimensional seismic data matrix GST (x, y, t), and perform feature decomposition on the three-dimensional seismic data matrix, as shown in the following formula:

[0110]

[0111] In formula (3), υ i and λ i (i=1,2,3) are the three eigenvectors and eigenvalues ​​corresponding to the seismic wave amplitude attribute matrix. The three-dimensional seismic data matrix is ​​a symmetric semi-positive definite matrix, so the eigenvalues ​​are all non-negative. Sort the eigenvalues ​​to satisfy λ1>λ2>λ3 and get the maximum eigenvalue λ1. Use the vector υ1(x,y,t) in the x direction corresponding to the calculated maximum eigenvalue λ1 1x (x,y,t), vector υ in the y direction 1y (x,y,t) and the vector υ in the t direction 1t(x, y, t), the inclination data volume p(x, y, t) in formula (1) and the azimuth data volume q(x, y, t) in formula (2) are calculated.

[0112] It should be noted that the three-dimensional seismic data matrix can be a gradient structure tensor matrix.

[0113] Optionally, the maximum positive curvature attribute value and the edge gradient attribute value of each measuring point in the carbonate rock region are determined according to the following formula:

[0114]

[0115] in,

[0116]

[0117]

[0118] τ x =tan(p)sinq (8);

[0119] τ y =tan(p)cosq (9);

[0120] K(x, y, t) = (a + b) + [(ab) 2 +c 2 ] 1 / 2 (10);

[0121]

[0122]

[0123]

[0124] Among them, S(x,y,t) is the edge gradient attribute, M x and M y are the templates of the Sobel operator in two orthogonal directions, D i,j,k (x, y, t) are the coordinates of all measurement points selected in the carbonate rock area, Δt is the sampling rate of the carbonate rock area, and are the delay times of the three-dimensional seismic data in the x direction and the y direction, respectively. The x direction and the y direction are both parallel to the horizontal plane and perpendicular to each other. n is the total number of measurement points, i is the step length in the x direction, j is the step length in the y direction, k is the step length in the t direction, K is the total number of measurement points in the t direction, p(x,y,t) and p are both dip data volumes, q(x,y,t) and q are both azimuth data volumes, K(x,y,t) is the maximum positive curvature attribute, a, b, c are the coefficients in the quadratic surface fitting equation of the local area of ​​the three-dimensional seismic data, respectively.

[0125] Formula (4) and formula (10) are used to facilitate the calculation and processing of the edge gradient attribute and the maximum positive curvature attribute, and the obtained results of the edge gradient attribute and the maximum positive curvature attribute are also relatively accurate.

[0126] Exemplarily, step S204 may further include: normalizing the maximum positive curvature attribute value and the edge gradient attribute value to facilitate subsequent training processing.

[0127] Normalizing the maximum positive curvature attribute value and the edge gradient attribute value may include: determining an upper limit value of an interval;

[0128] The ratio of the upper limit value of the interval to the maximum positive curvature attribute value with the largest value corresponding to multiple measurement points is used as the first coefficient, and the maximum positive curvature attribute values ​​corresponding to multiple measurement points are all multiplied by the first coefficient to obtain the first value range interval corresponding to the multiple measurement points; the ratio of the upper limit value of the interval to the maximum edge gradient attribute value corresponding to multiple measurement points is used as the second coefficient, and the edge gradient attribute values ​​corresponding to the multiple measurement points are all multiplied by the second coefficient to obtain the second value range interval corresponding to the multiple measurement points. Both the first value range interval and the second value range interval are within the range from zero to the upper limit value of the interval (including the upper limit value of the interval).

[0129] It should be noted that the upper limit of the interval is a positive number.

[0130] Normalization is a method of simplifying calculations, which is used to transform the dimensional maximum positive curvature attribute value and the edge gradient attribute value into dimensionless data.

[0131] Both the first value range interval and the second value range interval can be within the range of 0 to 1. In this case, 1 is the upper limit of the interval, which is convenient for calculation and processing.

[0132] In the range of the maximum positive curvature attribute value and the edge gradient attribute value, the minimum value 0 can indicate the lowest degree of fracture-hole development, and the maximum value 1 can indicate the highest degree of fracture-hole development.

[0133] S206: Using the fracture-hole thickness values ​​corresponding to the plurality of measurement points and the seismic attribute values ​​corresponding to the plurality of measurement points as training samples, the feedforward neural network model is trained to obtain a trained neural network model.

[0134] It should be noted that when training the fracture thickness values ​​corresponding to multiple measurement points and the seismic attribute values ​​corresponding to multiple measurement points, the seismic attribute values ​​of the multiple measurement points are input values, and the fracture thickness values ​​of the multiple measurement points are output values.

[0135] Optionally, the neural network model may be determined according to the following formula:

[0136]

[0137]

[0138]

[0139] In formulas (14) to (16), E i (t j ) is the three-dimensional seismic data; P(x,y,t j ) is the crack thickness function, w j is the weight of the edge gradient attribute in the neural network model, w′ j is the weight of the maximum positive curvature attribute in the neural network model, is the correspondence between the edge gradient attribute and the crack thickness value, is the correspondence between the maximum positive curvature attribute and the crack thickness value, and N is the number of measurement points.

[0140] S207: Using a neural network model, determine the volume of the fracture-cavity reservoir in the carbonate rock region.

[0141] Step S207 may include:

[0142] According to the neural network model, the fracture-cavity volume function of any point in the carbonate rock area is obtained; the volume of the fracture-cavity reservoir in the carbonate rock area is obtained by integrating the fracture-cavity volume function. The volume of the fracture-cavity reservoir in the carbonate rock area can be obtained more accurately.

[0143] Optionally, the crack volume function can be determined according to the following formula:

[0144] V′(x i ,y j ,t k )=P 3 (x,y,t j ) (17);

[0145] V′(x i ,y j ,tk ) is the fracture volume function, P(x,y,t j ) is the function of crack thickness.

[0146] The volume of the fracture-cavity reservoir in the carbonate rock region is obtained by integrating the fracture-cavity volume function according to formula (18):

[0147]

[0148] In formula (18), V is the volume of the carbonate fracture-vuggy reservoir, m, n and l are the number of grid points in the carbonate rock region in the x, y and t directions, respectively. i ,y j ,t k ) is the volume of the fracture cavity at any point in the carbonate rock region, V and V′(x i ,y j ,t k ) are all in m 3 .

[0149] Optionally, after formula (18) is obtained, the volume of fractures and holes corresponding to the three-dimensional coordinate points in the carbonate rock region can be obtained through all the three-dimensional coordinate points in the carbonate rock region and the seismic attribute values ​​corresponding to the three-dimensional coordinate points. The distribution position of fractures and holes in the carbonate rock region can be drawn using a three-dimensional coordinate system established by modeling software. This is convenient for observing the position of fractures and holes in the carbonate rock region.

[0150] Figure 6 is a location distribution map of fracture-cavity reservoirs in a carbonate rock region provided by an embodiment of the present disclosure, Figure 6 The light-colored outline in the figure indicates where the crack hole is located.

[0151] Figure 7 : is a schematic diagram of the principle of a volume determination device for a carbonate fracture-vuggy reservoir provided by an embodiment of the present disclosure, the volume determination device comprising:

[0152] The first data acquisition module 10 is used to obtain fracture-vuggy thickness values ​​at measurement points in a plurality of wells in a carbonate rock region, wherein the plurality of measurement points are respectively distributed in the plurality of wells.

[0153] The second data acquisition module 20 is used to acquire three-dimensional seismic data of the carbonate rock region.

[0154] The first processing module 30 is used to obtain a neural network model of the carbonate rock region based on the three-dimensional seismic data and the fracture thickness values ​​of multiple measurement points. The neural network model is used to reflect the mapping relationship between the seismic attribute values ​​and the fracture thickness values ​​of the carbonate rock region.

[0155] The second processing module 40 is used to determine the volume of the fracture-cavity reservoir in the carbonate rock region by using a neural network model.

[0156] Optionally, the first data acquisition module 10 is further used to: acquire imaging logging data of multiple development wells in the carbonate rock region; and acquire fracture-vuggy thickness values ​​of multiple measuring points of each development well according to the imaging logging data of the multiple development wells. The fracture-vuggy thickness values ​​of the measuring points can be easily acquired based on the imaging logging data.

[0157] Optionally, the first data acquisition module 10 may also be used for:

[0158] Mark multiple measurement points on the imaging logging picture; obtain the fracture-hole thickness value of each measurement point according to the imaging logging picture. This can facilitate the direct acquisition of the fracture-hole thickness value of the measurement point.

[0159] Exemplarily, the volume determination device of the carbonate fracture-vuggy reservoir may also include a third processing module 50, which is used to: perform time-depth conversion on the depths corresponding to multiple measuring points, which may include: obtaining the average velocity of the seismic wave, dividing the depth of each measuring point by the average velocity of the seismic wave, and obtaining the time point corresponding to each measuring point.

[0160] Exemplarily, the fourth processing module 50 can also be used to: obtain the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area based on the three-dimensional seismic data; determine the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area corresponding to multiple measuring points based on the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area, the time points and plane position coordinates corresponding to the multiple measuring points.

[0161] Optionally, the fourth processing module 50 can also be used to: obtain the dip data body and azimuth data body of the strata in the carbonate rock area according to the three-dimensional seismic data, the dip data body reflects the change of the strata in the carbonate rock area in one direction parallel to the horizontal plane over time, and the azimuth data body reflects the change of the strata in the carbonate rock area in another direction parallel to the horizontal plane over time; the change direction of the strata reflected by the dip data body and the change direction of the strata reflected by the azimuth data body are perpendicular to each other. According to the dip data body and the azimuth data body, determine the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area.

[0162] Optionally, the fourth processing module 50 may also determine the inclination data volume and the azimuth data volume according to formula (1) and formula (2) respectively. The fourth processing module 50 may also determine the edge gradient attribute value and the maximum positive curvature attribute value according to formula (4) and formula (10) respectively.

[0163] Exemplarily, the fourth processing module 50 may also perform normalization processing on the maximum positive curvature attribute value and the edge gradient attribute value.

[0164] Exemplarily, the first processing module 30 may determine the neural network model according to formula (16).

[0165] The second processing module 40 can also be used to: obtain a fracture-cavity volume function of any point in the carbonate rock region according to the neural network model; and integrate the fracture-cavity volume function to obtain the volume of the fracture-cavity reservoir in the carbonate rock region.

[0166] The second processing module 40 can determine the fracture-cavity volume function of any point in the carbonate rock region according to formula (17), and determine the volume of the fracture-cavity reservoir in the carbonate rock region according to formula (18):

[0167] Figure 7 The technical effect of the volume determination device of the carbonate fracture-vuggy reservoir shown in FIG. Figure 2 The technical effects of the characteristic method for determining the volume of a carbonate fracture-vuggy reservoir shown in the figure are shown, so the technical effects of the device for determining the volume of a carbonate fracture-vuggy reservoir will not be described in detail here.

[0168] Figure 8 is a structural block diagram of a computer device provided by an embodiment of the present disclosure, with reference to Figure 8 It can be seen that computer equipment includes:

[0169] A processor 100; a memory 200 for storing processor executable instructions; wherein the processor 100 is configured to execute the method for determining the volume of a carbonate fracture-vuggy reservoir as described above.

[0170] Optionally, the storage medium stores at least one instruction, and the at least one instruction can be loaded and executed by the processor 100 to implement the above-mentioned method for determining the volume of a carbonate fracture-vuggy reservoir.

[0171] This can facilitate the implementation and execution of the method embodiment.

[0172] Figure 8 In the embodiment, the processor 100 executes various functional applications and information processing by running software programs and modules. The memory 200 can be connected to the processor 100 via a bus 300. The memory 200 can be used to store at least one instruction, and the processor 100 is used to execute the at least one instruction to implement each step in the above method embodiment.

[0173] In addition, the memory 200 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the volatile or non-volatile storage device includes but is not limited to: a magnetic disk or an optical disk, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a static random access memory (SRAM), a read-only memory (ROM), a magnetic memory, a flash memory, and a programmable read-only memory (PROM).

[0174] The above description is not intended to limit the present invention in any form. Although the present invention has been disclosed as above through the embodiments, it is not intended to limit the present invention. Any technician familiar with the profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A method for determining the volume of a carbonate fracture-vuggy reservoir, characterized in that: The volume determination method comprises: Obtain fracture-vuggy thickness values ​​at a plurality of measuring points in a plurality of wells in a carbonate rock region, wherein the plurality of measuring points are respectively distributed in the plurality of wells; Acquiring three-dimensional seismic data of the carbonate rock region; Obtaining a neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-hole thickness values ​​of the plurality of measurement points, wherein the neural network model is used to reflect a mapping relationship between the seismic attribute values ​​of the carbonate rock region and the fracture-hole thickness values; Using the neural network model, determining the volume of the fracture-cavity reservoir in the carbonate rock region; The step of obtaining a neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-cavity thickness values ​​of the plurality of measurement points comprises: Obtaining the plane position coordinates corresponding to the multiple measurement points; Performing time-depth conversion on the depths corresponding to the multiple measurement points to obtain the time points corresponding to the multiple measurement points; Acquire seismic attribute values ​​corresponding to the multiple measuring points according to the three-dimensional seismic data, the plane position coordinates corresponding to the multiple measuring points, and the time points corresponding to the multiple measuring points; The feedforward neural network model is trained by using the fracture-hole thickness values ​​corresponding to the plurality of measurement points and the seismic attribute values ​​corresponding to the plurality of measurement points as training samples to obtain the neural network model; The seismic attribute values ​​include a maximum positive curvature attribute value and an edge gradient attribute value; and obtaining the seismic attribute values ​​corresponding to the multiple measuring points according to the three-dimensional seismic data, the plane position coordinates corresponding to the multiple measuring points, and the time points corresponding to the multiple measuring points includes: Acquire a dip data volume and an azimuth data volume of the strata in the carbonate rock region according to the three-dimensional seismic data, wherein the dip data volume reflects the change of the strata in the carbonate rock region in the x direction over time, and the azimuth data volume reflects the change of the strata in the carbonate rock region in the y direction over time, wherein the x direction and the y direction are perpendicular to each other and parallel to the horizontal plane; Determining the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock region according to the dip data volume and the azimuth data volume; According to the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area, the plane position coordinates corresponding to the multiple measurement points and the time points corresponding to the multiple measurement points, the maximum positive curvature attribute value and the edge gradient attribute value corresponding to the multiple measurement points are determined.

2. The volume determination method according to claim 1, characterized in that: The inclination data volume and the azimuth data volume are determined according to the following formula: Among them, p(x,y,t) is the inclination data volume, q(x,y,t) is the azimuth data volume, and υ 1x (x,y,t) is the vector of the three-dimensional seismic data in the x direction, υ 1y (x,y,t) is the vector of the three-dimensional seismic data in the y direction, υ 1t (x, y, t) is the vector of the three-dimensional seismic data in the t direction, the x direction and the y direction are both parallel to the horizontal plane, and the x direction and the y direction are perpendicular to each other, and t is the time direction.

3. The volume determination method according to claim 2, characterized in that: The maximum positive curvature attribute value and the edge gradient attribute value of each measuring point in the carbonate rock region are determined according to the following formula: in, τ x =tan(p)sinq,τ y =tan(p)cosq; K(x,y,t)=(a+b)+[(a-b) 2 +c 2 ] 1 / 2 , Among them, S(x,y,t) is the edge gradient attribute, M x and M y are the templates of the Sobel operator in two orthogonal directions, D i,j,k (x, y, t) are the coordinates of all measurement points selected in the carbonate rock area, Δt is the sampling rate of the carbonate rock area, and are the delay times of the three-dimensional seismic data in the x direction and the y direction, respectively. The x direction and the y direction are both parallel to the horizontal plane and perpendicular to each other. n is the total number of measurement points, i is the step length in the x direction, j is the step length in the y direction, k is the step length in the t direction, K is the total number of measurement points in the t direction, p(x,y,t) and p are both dip data volumes, q(x,y,t) and q are both azimuth data volumes, K(x,y,t) is the maximum positive curvature attribute, a, b, c are the coefficients in the quadratic surface fitting equation of the local area of ​​the three-dimensional seismic data, respectively.

4. The volume determination method according to any one of claims 1 to 3, characterized in that: The method of obtaining fracture-cavity layer thickness curves of multiple wells in a carbonate rock region includes: Obtain an imaging logging picture of each well in the carbonate rock area; mark a plurality of measuring points on the imaging logging picture; and obtain a fracture-cavity thickness value of each measuring point according to the imaging logging picture.

5. The volume determination method according to any one of claims 1 to 3, characterized in that: The method of using the neural network model to determine the volume of the fracture-cavity reservoir in the carbonate rock region includes: The fracture-cavity volume function at any point in the carbonate rock region is obtained according to the neural network model; the volume of the fracture-cavity reservoir in the carbonate rock region is obtained by integrating the fracture-cavity volume function.

6. The volume determination method according to claim 5, characterized in that: The volume of the fracture-cavity reservoir in the carbonate rock region is determined according to the following formula: V′(x i ,y j ,t k )=P 3 (x,y,t j ); Where V is the volume of the carbonate fracture reservoir, m, n and l are the number of grid points in the carbonate region in the x, y and t directions, respectively. i ,y j ,t k ) is the volume of the fracture cavity at any point in the carbonate rock region, V and V′(x i ,y j ,t k ) are all in m 3 ,P(x,y,t j ) is the crack thickness function.

7. A device for determining the volume of a carbonate fracture-vuggy reservoir, characterized in that: The volume determination device comprises, A first data acquisition module is used to acquire fracture-vuggy thickness values ​​at a plurality of measurement points in a plurality of wells in a carbonate rock region, wherein the plurality of measurement points are respectively distributed in the plurality of wells; A second data acquisition module, used to acquire three-dimensional seismic data of the carbonate rock area; A first processing module, configured to obtain a neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-hole thickness values ​​of the plurality of measurement points, wherein the neural network model is configured to reflect a mapping relationship between the seismic attribute value of the carbonate rock region and the fracture-hole thickness value; A second processing module is used to determine the volume of the fracture-cavity reservoir in the carbonate rock region by using the neural network model; The step of obtaining a neural network model of the carbonate rock region according to the three-dimensional seismic data and the fracture-cavity thickness values ​​of the plurality of measurement points comprises: Obtaining the plane position coordinates corresponding to the multiple measurement points; Performing time-depth conversion on the depths corresponding to the multiple measurement points to obtain the time points corresponding to the multiple measurement points; Acquire seismic attribute values ​​corresponding to the multiple measuring points according to the three-dimensional seismic data, the plane position coordinates corresponding to the multiple measuring points, and the time points corresponding to the multiple measuring points; The feedforward neural network model is trained by using the fracture-hole thickness values ​​corresponding to the plurality of measurement points and the seismic attribute values ​​corresponding to the plurality of measurement points as training samples to obtain the neural network model; The seismic attribute values ​​include a maximum positive curvature attribute value and an edge gradient attribute value; and obtaining the seismic attribute values ​​corresponding to the multiple measuring points according to the three-dimensional seismic data, the plane position coordinates corresponding to the multiple measuring points, and the time points corresponding to the multiple measuring points includes: Acquire a dip data volume and an azimuth data volume of the strata in the carbonate rock region according to the three-dimensional seismic data, wherein the dip data volume reflects the change of the strata in the carbonate rock region in the x direction over time, and the azimuth data volume reflects the change of the strata in the carbonate rock region in the y direction over time, wherein the x direction and the y direction are perpendicular to each other and parallel to the horizontal plane; Determining the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock region according to the dip data volume and the azimuth data volume; According to the maximum positive curvature attribute value and the edge gradient attribute value of the carbonate rock area, the plane position coordinates corresponding to the multiple measurement points and the time points corresponding to the multiple measurement points, the maximum positive curvature attribute value and the edge gradient attribute value corresponding to the multiple measurement points are determined.

8. A computer device, characterized in that: The computer device comprises: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the method for determining the volume of a carbonate fracture-vuggy reservoir as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the method for determining the volume of a carbonate fracture-vuggy reservoir as described in any one of claims 1 to 6.

Images