Fluid identification method and computer-readable storage medium

Abstract

The present application discloses a fluid identification method and a computer-readable storage medium, the method comprising: performing kernel Fisher discriminant analysis modeling of sample data, so as to linearly separate linearly inseparable sample data, thereby obtaining a projection, on a first unit vector and a second unit vector, of a plurality of sets of characteristic variable data of the sample data, then creating a fluid identification cross-plot, and inverting wide-area resistivity data of a studied area by using well logging data and seismic data of the studied area as constraints to obtain inversion resistivity profile data; creating a resistivity projection mapping relationship according to the inversion resistivity profile data, a plurality of first projection values and a plurality of second projection values; and, according to the inversion resistivity data and the resistivity projection mapping relationship of a formation to be identified, obtaining for said formation a third projection value on the first unit vector and a fourth projection value on the second unit vector, and then determining fluid properties of the formation to be identified according to the third projection value, the fourth projection value, and the fluid identification cross-plot.

Description

Fluid identification method and computer-readable storage medium Technical Field

[0001] The present application relates to the field of oil and gas exploration technology, and in particular to a fluid identification method and a computer-readable storage medium. Background Art

[0002] In oil and gas exploration, the primary method for fluid identification is the crossplot of well logging and seismic data. Other analytical methods include neural networks and Bayesian discriminant methods. However, well logging data can only identify reservoir fluids at drilling locations, leaving areas without wells unidentified. Seismic data, due to its limited resolution, cannot meet production requirements for complex or small reservoirs. Furthermore, these commonly used fluid identification methods are not ideal for tight sandstone reservoirs.

[0003] Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a fluid identification method and a computer-readable storage medium, which can solve the problem that the traditional fluid identification method has an unsatisfactory identification effect.

[0005] The fluid identification method according to the first embodiment of the present application includes:

[0006] Acquiring sample data, wherein the sample data includes characteristic variable data of multiple standard layers of determined fluid types in a study area;

[0007] Establishing a kernel Fisher discriminant analysis model according to the sample data, and obtaining a kernel matrix from the kernel Fisher discriminant analysis model;

[0008] Selecting the two largest eigenvalues ​​and corresponding eigenvectors in the kernel matrix, and constructing normalized vectors according to the two eigenvalues ​​and the corresponding eigenvectors to obtain a first unit vector and a second unit vector;

[0009] Projecting the sample data onto the first unit vector to obtain a plurality of first projection values, and projecting a plurality of the sample data onto the second unit vector to obtain a plurality of second projection values;

[0010] establishing a fluid identification cross-graph according to a plurality of the first projection values ​​and a plurality of the second projection values;

[0011] Acquiring well logging data, seismic data, and wide-area resistivity data in the study area, and inverting the wide-area resistivity data using the well logging data and the seismic data as constraints to obtain inverted resistivity profile data;

[0012] establishing a resistivity projection mapping relationship according to the inverted resistivity profile data, a plurality of the first projection values, and a plurality of the second projection values;

[0013] Obtaining a target resistivity, where the target resistivity is inversion resistivity data of a stratum to be identified in the inversion resistivity profile data, and obtaining a third projection value of the stratum to be identified on the first unit vector and a fourth projection value of the stratum to be identified on the second unit vector based on a relationship between the target resistivity and the resistivity projection mapping;

[0014] The fluid property of the to-be-identified formation is determined according to the third projection value, the fourth projection value, and the fluid identification cross-map.

[0015] The fluid identification method according to the first embodiment of the present application has at least the following beneficial effects:

[0016] By performing kernel Fisher discriminant analysis modeling on the sample data, the linearly inseparable sample data is linearly separated, thereby obtaining projections of multiple sets of characteristic variable data of the sample data on the first unit vector and the second unit vector, that is, projections on the two optimal kernel Fisher discriminant directions, and establishing a fluid identification intersection diagram. The wide-area resistivity data of the study area is inverted with the well logging data and seismic data of the study area as constraints to obtain inverted resistivity profile data. Further, a resistivity projection mapping relationship is established based on the inverted resistivity profile data, multiple first projection values, and multiple second projection values. According to the inverted resistivity data of the formation to be identified and the resistivity projection mapping relationship, a third projection value of the formation to be identified on the first unit vector and a fourth projection value on the second unit vector are obtained. The fluid properties of the formation to be identified are determined according to the third projection value, the fourth projection value, and the fluid identification intersection diagram. Compared with the traditional fluid identification method, the fluid identification method of the first embodiment of the present application can identify fluids in undrilled areas, has a higher vertical resolution, and can also quickly and accurately identify fluid types in tight sandstone reservoirs, with good identification effect.

[0017] According to some embodiments of the present application, the characteristic variable data includes acoustic wave transit time, density, and deep lateral resistivity.

[0018] According to some embodiments of the present application, the sample data includes characteristic variable data of standard layers of two or more fluid types in dry layers, water layers, gas layers, oil layers, gas-water layers, and oil-water layers.

[0019] According to some embodiments of the present application, establishing a kernel Fisher discriminant analysis model based on the sample data and obtaining a kernel matrix from the kernel Fisher discriminant analysis model includes:

[0020] Performing a kernel Fisher discriminant analysis model on the sample data to obtain a kernel intra-class scatter matrix and a kernel inter-class scatter matrix;

[0021] Establishing a generalized characteristic equation based on the intra-kernel scatter matrix and the inter-kernel scatter matrix;

[0022] The generalized characteristic equation is solved to obtain a plurality of eigenvalues ​​and a plurality of eigenvectors corresponding to the eigenvalues, and the kernel matrix is ​​obtained according to the plurality of eigenvalues.

[0023] According to some embodiments of the present application, performing kernel Fisher discriminant analysis modeling on the sample data to obtain a kernel intra-class scatter matrix and a kernel inter-class scatter matrix includes:

[0024] A kernel Fisher discriminant analysis model is performed on the sample data based on a radial basis function to obtain a kernel intra-class scatter matrix and a kernel inter-class scatter matrix.

[0025] According to some embodiments of the present application, inverting the wide-area resistivity data using the well logging data and the seismic data as constraints to obtain inverted resistivity profile data includes:

[0026] Establishing a geological electrical model based on the well logging data, the seismic data and the wide-area resistivity data;

[0027] The geological electrical model is iteratively calculated using an inversion algorithm until the fitting error is within a preset error range, and an inversion result is output to obtain the inverted resistivity profile data.

[0028] According to some embodiments of the present application, determining the fluid properties of the to-be-identified formation according to the third projection value, the fourth projection value, and the fluid identification cross-map includes:

[0029] Inputting the third projection value and the fourth projection value into the fluid identification intersection map to form a projection point;

[0030] Determine a target area, where the target area is a fluid type area closest to the projection point in the fluid identification intersection diagram;

[0031] The fluid type of the target area is used as the fluid type of the formation to be identified.

[0032] According to some embodiments of the present application, before establishing the kernel Fisher discriminant analysis model based on the sample data, the method further includes:

[0033] The sample data is centrally processed.

[0034] According to some embodiments of the present application, after establishing a fluid identification intersection map according to the plurality of first projection values ​​and the plurality of second projection values, the method further includes:

[0035] confirming the accuracy of the fluid type displayed in the fluid identification cross-plot based on the fluid type determined by the sample data and the fluid type displayed in the fluid identification cross-plot based on the sample data;

[0036] If the accuracy is greater than a preset accuracy threshold, it is confirmed that the fluid identification intersection map can be used.

[0037] According to the computer-readable storage medium of the second embodiment of the present application, a program executable by a processor is stored therein, and the program executable by the processor is used to implement the fluid identification method as described above when executed by the processor.

[0038] The computer-readable storage medium according to the second embodiment of the present application has at least the following beneficial effects:

[0039] By performing kernel Fisher discriminant analysis modeling on the sample data, the linearly inseparable sample data is linearly separated, thereby obtaining projections of multiple sets of characteristic variable data of the sample data on the first unit vector and the second unit vector, that is, projections on the two optimal kernel Fisher discriminant directions, and establishing a fluid identification intersection diagram. The wide-area resistivity data of the study area is inverted with the well logging data and seismic data of the study area as constraints to obtain inverted resistivity profile data. Further, a resistivity projection mapping relationship is established based on the inverted resistivity profile data, multiple first projection values, and multiple second projection values. According to the inverted resistivity data of the formation to be identified and the resistivity projection mapping relationship, a third projection value of the formation to be identified on the first unit vector and a fourth projection value on the second unit vector are obtained. The fluid properties of the formation to be identified are determined according to the third projection value, the fourth projection value, and the fluid identification intersection diagram. Compared with the traditional fluid identification method, the fluid identification method of the second aspect of the present application can identify fluids in undrilled areas, has a higher vertical resolution, and can also quickly and accurately identify fluid types in tight sandstone reservoirs, with good identification effect.

[0040] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present application is further described below with reference to the accompanying drawings and embodiments, wherein:

[0042] FIG1 is a flow chart of a fluid identification method according to an embodiment of the present application;

[0043] FIG2 is a fluid identification intersection diagram in one embodiment of the present application;

[0044] FIG3 is a diagram showing the effect of inverting resistivity profile data in one embodiment of the present application;

[0045] FIG4 is a flow chart of obtaining a kernel matrix in one embodiment of the present application;

[0046] FIG5 is a flow chart of obtaining inversion resistivity profile data in one embodiment of the present application;

[0047] FIG6 is a flow chart of determining fluid properties of a formation to be identified in one embodiment of the present application;

[0048] FIG. 7 is a flow chart for confirming that a fluid identification intersection diagram can be used in one embodiment of the present application. DETAILED DESCRIPTION

[0049] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0050] In the description of this application, it should be understood that descriptions involving orientation, such as the orientation or positional relationship indicated by up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0051] In the description of this application, "a plurality" refers to more than two. The use of "first" or "second" is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of technical features indicated, or implicitly indicating the order of the technical features indicated.

[0052] In the description of this application, unless otherwise clearly defined, terms such as setting, installation, and electrical connection should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0053] The following describes a fluid identification method and a computer-readable storage medium according to an embodiment of the present application with reference to FIG1 to FIG7 .

[0054] As shown in FIG1 , the fluid identification method according to an embodiment of the present application includes but is not limited to:

[0055] Step S100: acquiring sample data, where the sample data includes characteristic variable data of multiple standard layers of determined fluid types within the study area;

[0056] In this step, the study area is an area where oil and gas exploration is conducted, and the sample data includes multiple sets of characteristic variable data for multiple standard layers in the study area whose fluid types have been determined through oil testing technology.

[0057] It can be understood that physical quantities that are sensitive to fluid identification are selected as characteristic variables, and their logging values ​​are more sensitive to reservoirs with different fluid properties, which can provide basic conditions for multi-parameter identification of fluid properties. For example, the acoustic time difference, density and deep lateral resistivity are used as characteristic variables, and the acoustic time difference, density and deep lateral resistivity of multiple standard layers are selected as sample data.

[0058] It should be noted that the sample data include characteristic variable data of standard layers of two or more fluid types in dry layers, water layers, gas layers, oil layers, gas-water layers, and oil-water layers.

[0059] Step S200: establishing a kernel Fisher discriminant analysis model based on the sample data, and obtaining a kernel matrix from the kernel Fisher discriminant analysis model;

[0060] In this step, the sample data is modeled by performing kernel Fisher discriminant analysis to linearly separate the linearly inseparable sample data and obtain a kernel matrix. This facilitates the subsequent steps to use the kernel matrix to find two vectors so that the sample data can achieve maximum separation of the projections of sample data of different categories and aggregation of the projections of sample data of the same category after projection transformation in the directions of these two vectors.

[0061] Step S300: selecting the two largest eigenvalues ​​and corresponding eigenvectors in the kernel matrix, and constructing a normalized vector based on the two eigenvalues ​​and the corresponding eigenvectors to obtain a first unit vector and a second unit vector;

[0062] In this step, the two largest eigenvalues ​​and corresponding eigenvectors in the kernel matrix are selected to construct the first unit vector and the second unit vector. The projections of sample data of different categories in the direction of the first unit vector and the second unit vector can achieve the maximum separation, while the projections of sample data of the same type are aggregated, thereby completing linear classification.

[0063] Step S400: projecting the sample data onto a first unit vector to obtain a plurality of first projection values, and projecting the plurality of sample data onto a second unit vector to obtain a plurality of second projection values;

[0064] In this step, the sample data is projected onto the first unit vector and the second unit vector to obtain the first projection value and the second projection value respectively. That is, the sample data is linearly classified using the first unit vector and the second unit vector, so that sample data of different categories are projected and separated in the direction of the first unit vector and the second unit vector, and the projections of sample data of the same category are aggregated.

[0065] Step S500: establishing a fluid identification intersection map according to a plurality of first projection values ​​and a plurality of second projection values;

[0066] In this step, a fluid identification intersection diagram is established using multiple first projection values ​​and second projection values. As shown in Figure 2, sample data of the same type are clustered at each projection point in the fluid identification intersection diagram, and sample data of different types are separated at the projection points in the fluid identification intersection diagram. Different fluid types can be displayed through the fluid identification intersection diagram.

[0067] Step S600: acquiring well logging data, seismic data, and wide-area resistivity data in the study area, and inverting the wide-area resistivity data using the well logging data and seismic data as constraints to obtain inverted resistivity profile data;

[0068] In this step, the wide-area resistivity data is inverted with the well logging data and seismic data as constraints to obtain the inverted resistivity profile data, that is, the resistivity distribution of each formation in the study area is obtained, as shown in Figure 3, which is a rendering of the inverted resistivity profile data.

[0069] It should be noted that after obtaining the inversion resistivity profile data, the target layer depth data of multiple survey lines in the study area are obtained based on the seismic data and well logging data, and the target layer depth data are projected onto the inversion resistivity profile data to facilitate the extraction of the inversion resistivity profile data of the target layer.

[0070] Step S700: establishing a resistivity projection mapping relationship according to the inverted resistivity profile data, a plurality of first projection values, and a plurality of second projection values;

[0071] In this step, based on the same position, the characteristic variable data and the inverted resistivity profile data are in one-to-one correspondence, that is, the inverted resistivity profile data and the characteristic variable data at the same position of the same reservoir in the corresponding study area respectively represent different characteristics of the position. Therefore, the inverted resistivity profile data also has a corresponding relationship with the first projection value and the second projection value. A resistivity projection mapping relationship is established based on the inverted resistivity profile data, multiple first projection values ​​and multiple second projection values.

[0072] Step S800: Obtain target resistivity, where the target resistivity is inversion resistivity data of the stratum to be identified in the inversion resistivity profile data, and obtain a third projection value of the stratum to be identified on the first unit vector and a fourth projection value of the stratum to be identified on the second unit vector based on a mapping relationship between the target resistivity and the resistivity projection.

[0073] In this step, by inputting the inverted resistivity data of the formation to be identified into the resistivity projection mapping relationship, the third projection value of the inverted resistivity data of the formation to be identified on the first unit vector and the fourth projection value on the second unit vector can be calculated.

[0074] Step S900: determining the fluid properties of the formation to be identified based on the third projection value, the fourth projection value and the fluid identification cross-map.

[0075] In this step, the projection point of the inversion resistivity data of the formation to be identified in the fluid identification cross-plot can be determined based on the third projection value and the fourth projection value, thereby determining the fluid properties of the formation to be identified.

[0076] In this embodiment, by performing kernel Fisher discriminant analysis modeling on the sample data, the linearly inseparable sample data is linearly separated, thereby obtaining projections of multiple sets of characteristic variable data of the sample data on the first unit vector and the second unit vector, that is, projections on the two optimal kernel Fisher discriminant directions, and establishing a fluid identification intersection diagram. The wide-area resistivity data of the study area is inverted with the well logging data and seismic data of the study area as constraints to obtain inverted resistivity profile data. Further, a resistivity projection mapping relationship is established based on the inverted resistivity profile data, multiple first projection values, and multiple second projection values. According to the inverted resistivity data of the formation to be identified and the resistivity projection mapping relationship, a third projection value of the formation to be identified on the first unit vector and a fourth projection value on the second unit vector are obtained. The fluid properties of the formation to be identified are determined based on the third projection value, the fourth projection value, and the fluid identification intersection diagram. Compared with the traditional fluid identification method, the fluid identification method of the first embodiment of the present application can identify fluids in undrilled areas, has a higher vertical resolution, and can also quickly and accurately identify fluid types in tight sandstone reservoirs, with good identification effect.

[0077] In one embodiment of the present application, the step S200 of "establishing a kernel Fisher discriminant analysis model based on the sample data and obtaining a kernel matrix from the kernel Fisher discriminant analysis model" is further described. As shown in FIG4 , step S200 includes but is not limited to:

[0078] Step S210: Performing kernel Fisher discriminant analysis modeling on the sample data to obtain the kernel intra-class scatter matrix and the kernel inter-class scatter matrix;

[0079] Step S220: establishing a generalized characteristic equation based on the intra-kernel scatter matrix and the inter-kernel scatter matrix;

[0080] Step S230: Solving the generalized characteristic equation to obtain multiple eigenvalues ​​and multiple eigenvectors corresponding to the eigenvalues, and obtaining a kernel matrix according to the multiple eigenvalues.

[0081] In this embodiment, the principle of kernel Fisher discriminant analysis is to transform data that is linearly inseparable in the input space into a high-dimensional feature space through a mapping, namely a kernel function, and then apply the kernel Fisher discriminant analysis method in the feature space to achieve linear separation in the high-dimensional space. By performing kernel Fisher discriminant analysis modeling on the sample data, the kernel intra-class scatter matrix and the kernel inter-class scatter matrix are obtained. Based on the kernel intra-class scatter matrix and the kernel inter-class scatter matrix, the generalized characteristic equation is established:

[0082] K b α=λK w α,

[0083] Among them, K w is the kernel intra-class divergence matrix, K b is the kernel inter-class divergence matrix, and α is the optimal discriminant vector.

[0084] By solving the generalized characteristic equation, we can obtain multiple eigenvalues ​​and eigenvectors corresponding to the eigenvalues, and form a characteristic matrix with the eigenvalues.

[0085] In one embodiment of the present application, the step S210 of "performing a kernel Fisher discriminant analysis model on the sample data to obtain a kernel intra-class scatter matrix and a kernel inter-class scatter matrix" is further explained. The step S210 includes but is not limited to the step S211.

[0086] Step S211: performing kernel Fisher discriminant analysis modeling on the sample data based on the radial basis function to obtain the kernel intra-class scatter matrix and the kernel inter-class scatter matrix.

[0087] In this embodiment, the expression of the radial basis function is:

[0088] K(x,xi)=exp(-g|x,xi| 2 ),

[0089] Where exp is the exponential function with the natural constant e as the base, and g is the bandwidth parameter.

[0090] Based on the radial basis function, the kernel Fisher discriminant analysis model of the sample data is performed, and the following is obtained:

[0091] δ x =(K(x,x1),K(x,x2)...,K(x,x N )),

[0092] Among them, δ x Represents the inner product operation of the data after projection in the feature space, where N is the total number of sample data.

[0093] Among them, μ o is the population mean of the sample data, i = 1, 2, 3…K.

[0094] Among them, μ i is the intra-class mean of the sample data of class i, Represents the value of the i-th sample data of the j-th class, and Ni is the number of samples of the i-th class.

[0095] Among them, K is the number of sample data categories.

[0096] Using formula (3) and formula (4) to obtain the kernel intra-class scatter matrix K w and the kernel inter-class divergence matrix K b .

[0097] It can be understood that the resistivity projection mapping relationship is an empirical formula of the inverted resistivity profile data and the first projection value and the second projection value, which is as follows:

[0098] y j =α j T [K(x,x1),K(x,x2),…,K(x,x n )] Where: j = 1, 2; n = 1, 2, ..., N, where y1 is the projection value on the first unit vector, y2 is the projection value on the second unit vector, α1 is the first unit vector, and α2 is the second unit vector.

[0099] In one embodiment of the present application, the step S600 of "inverting wide-area resistivity data to obtain inverted resistivity profile data using well logging data and seismic data as constraints" is further explained. As shown in FIG5 , step S600 includes but is not limited to step S610 and step S620.

[0100] Step S610: Establishing a geological electrical model based on well logging data, seismic data, and wide-area resistivity data;

[0101] Step S620: Iteratively calculate the geological electrical model using an inversion algorithm until the fitting error is within a preset error range, and output the inversion result to obtain inverted resistivity profile data.

[0102] In this embodiment, a geological electrical model is established with logging data and seismic data as constraints and combined with wide-area resistivity data. The stratum depth, thickness, stratification information, and resistivity information of the geological electrical model are used as inversion constraints. Through the inversion algorithm, iterative calculations are performed under the constraints of noise and model covariance estimates until the obtained fitting error is within the preset error range, and then the inverted resistivity profile data is output.

[0103] It is understandable that the fitting error is calculated using the inversion objective function, which includes the data objective function and the model objective function, and is constrained by the following mathematical model to control the relative weights of the data objective function and the model objective function:

[0104] P α (m)=||W d ×(d(m)-d obs )| 2 +α×||W m ×(m-m ref )|| 2 ,

[0105] Among them, W d is the weight of the data, W m is the weight of the model; d obs is the wide-area resistivity data; d(m) is the forward theoretical value; m is the model parameter, m ref is the resistivity value of the geological electrical model; α is the regularization factor.

[0106] In one embodiment of the present application, the step S900 of "determining the fluid properties of the formation to be identified based on the third projection value, the fourth projection value and the fluid identification intersection map" is further explained. As shown in FIG6 , the step S900 includes but is not limited to the step S910, the step S920 and the step S930.

[0107] Step S910: inputting the third projection value and the fourth projection value into the fluid identification intersection map to form a projection point;

[0108] Step S920: determining a target area, where the target area is the fluid type area closest to the projection point in the fluid identification intersection diagram;

[0109] Step S930: taking the fluid type of the target area as the fluid type of the formation to be identified.

[0110] In this embodiment, a projection point is formed by inputting the third projection and the fourth projection into a fluid identification intersection diagram. In the fluid identification intersection diagram, the fluid type area closest to the projection point is the fluid type of the formation to be identified.

[0111] In one embodiment of the present application, before “establishing a kernel Fisher discriminant analysis model according to sample data” in step 200 , the process further includes but is not limited to step 201 .

[0112] Step 201: Standardize the sample data.

[0113] In one embodiment of the present application, before “establishing a kernel Fisher discriminant analysis model according to sample data” in step 200 , the process further includes but is not limited to step 202 .

[0114] Step 202: Centralize the sample data.

[0115] In one embodiment of the present application, after "establishing a fluid identification intersection map according to a plurality of first projection values ​​and a plurality of second projection values" in step S500, as shown in FIG7, the process further includes but is not limited to steps S510 and S520.

[0116] Step S510: confirming the accuracy of the fluid type displayed in the fluid identification cross-plot based on the fluid type determined by the sample data and the fluid type displayed in the fluid identification cross-plot based on the sample data;

[0117] Step S520: If the accuracy is greater than the preset accuracy threshold, confirm that the fluid identification cross-graph can be used.

[0118] In this embodiment, the fluid type determined by the sample data through the oil testing process is compared with the fluid type displayed in the fluid identification intersection diagram of the sample data to confirm the accuracy of the fluid type displayed in the fluid identification intersection diagram. When the accuracy is greater than the preset accuracy threshold, it is confirmed that the fluid identification intersection diagram can be used.

[0119] It should be noted that the preset accuracy threshold can be set according to actual application scenarios, for example, the preset accuracy threshold is set to 88%.

[0120] In addition, an embodiment of the present application further discloses a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the fluid identification method as described above.

[0121] In this embodiment, by performing kernel Fisher discriminant analysis modeling on the sample data, the linearly inseparable sample data is linearly separated, thereby obtaining projections of multiple sets of characteristic variable data of the sample data on the first unit vector and the second unit vector, that is, projections on the two optimal kernel Fisher discriminant directions, and establishing a fluid identification intersection diagram. The wide-area resistivity data of the study area is inverted with the well logging data and seismic data of the study area as constraints to obtain inverted resistivity profile data. Further, a resistivity projection mapping relationship is established based on the inverted resistivity profile data, multiple first projection values, and multiple second projection values. According to the inverted resistivity data of the formation to be identified and the resistivity projection mapping relationship, a third projection value of the formation to be identified on the first unit vector and a fourth projection value on the second unit vector are obtained. The fluid properties of the formation to be identified are determined based on the third projection value, the fourth projection value, and the fluid identification intersection diagram. Compared with traditional fluid identification methods, the fluid identification method of the embodiment of the present application can identify fluids in undrilled areas, has a higher vertical resolution, and can also quickly and accurately identify fluid types in tight sandstone reservoirs, with good identification effect.

[0122] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0123] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. Fluid identification method, including: Acquiring sample data, wherein the sample data includes characteristic variable data of multiple standard layers of determined fluid types in a study area; Establishing a kernel Fisher discriminant analysis model according to the sample data, and obtaining a kernel matrix from the kernel Fisher discriminant analysis model; Selecting the two largest eigenvalues ​​and corresponding eigenvectors in the kernel matrix, and constructing normalized vectors according to the two eigenvalues ​​and the corresponding eigenvectors to obtain a first unit vector and a second unit vector; Projecting the sample data onto the first unit vector to obtain a plurality of first projection values, and projecting a plurality of the sample data onto the second unit vector to obtain a plurality of second projection values; establishing a fluid identification cross-graph according to a plurality of the first projection values ​​and a plurality of the second projection values; Acquiring well logging data, seismic data, and wide-area resistivity data in the study area, and inverting the wide-area resistivity data using the well logging data and the seismic data as constraints to obtain inverted resistivity profile data; establishing a resistivity projection mapping relationship according to the inverted resistivity profile data, a plurality of the first projection values, and a plurality of the second projection values; Obtaining a target resistivity, where the target resistivity is inversion resistivity data of a stratum to be identified in the inversion resistivity profile data, and obtaining a third projection value of the stratum to be identified on the first unit vector and a fourth projection value of the stratum to be identified on the second unit vector based on a relationship between the target resistivity and the resistivity projection mapping; The fluid property of the to-be-identified formation is determined according to the third projection value, the fourth projection value, and the fluid identification cross-map.

2. The fluid identification method according to claim 1, wherein: The characteristic variable data include acoustic wave transit time, density and deep lateral resistivity.

3. The fluid identification method according to claim 1, wherein: The sample data include characteristic variable data of standard layers of two or more fluid types in dry layers, water layers, gas layers, oil layers, gas-water layers, and oil-water layers.

4. The fluid identification method according to claim 1, wherein: The step of establishing a kernel Fisher discriminant analysis model based on the sample data and obtaining a kernel matrix from the kernel Fisher discriminant analysis model includes: Performing a kernel Fisher discriminant analysis model on the sample data to obtain a kernel intra-class scatter matrix and a kernel inter-class scatter matrix; A generalized characteristic equation is established based on the intra-kernel divergence matrix and the inter-kernel divergence matrix; The eigenvalues ​​and eigenvectors corresponding to the eigenvalues ​​are obtained by solving the eigenvalue equation, and the kernel matrix is ​​obtained according to the eigenvalues.

5. The fluid identification method according to claim 4, wherein: The kernel Fisher discriminant analysis modeling is performed on the sample data to obtain the kernel intra-class scatter matrix and the kernel inter-class scatter matrix, including: A kernel Fisher discriminant analysis model is performed on the sample data based on a radial basis function to obtain a kernel intra-class scatter matrix and a kernel inter-class scatter matrix.

6. The fluid identification method according to claim 1, wherein: The inverting the wide-area resistivity data to obtain inverted resistivity profile data using the well logging data and the seismic data as constraints includes: Establishing a geological electrical model based on the well logging data, the seismic data and the wide-area resistivity data; The geological electrical model is iteratively calculated using an inversion algorithm until the fitting error is within a preset error range, and an inversion result is output to obtain the inverted resistivity profile data.

7. The fluid identification method according to claim 1, wherein: The determining the fluid property of the to-be-identified formation according to the third projection value, the fourth projection value, and the fluid identification cross-graph includes: Inputting the third projection value and the fourth projection value into the fluid identification intersection map to form a projection point; Determine a target area, where the target area is a fluid type area closest to the projection point in the fluid identification intersection diagram; The fluid type of the target area is used as the fluid type of the formation to be identified.

8. The fluid identification method according to claim 1, wherein: Before establishing the kernel Fisher discriminant analysis model according to the sample data, the method further includes: The sample data is centrally processed.

9. The fluid identification method according to claim 1, wherein: After establishing a fluid identification intersection map according to the plurality of first projection values ​​and the plurality of second projection values, the method further includes: confirming the accuracy of the fluid type displayed in the fluid identification cross-plot based on the fluid type determined by the sample data and the fluid type displayed in the fluid identification cross-plot based on the sample data; If the accuracy is greater than a preset accuracy threshold, it is confirmed that the fluid identification intersection map can be used.

10. A computer-readable storage medium, wherein: A program executable by a processor is stored therein, and when the program executable by the processor is executed by the processor, it is used to implement the fluid identification method according to any one of claims 1 to 9.

Images