Single well configuration recognition method, device and equipment and storage medium

Abstract

The invention discloses a single well configuration recognition method, device and equipment and a storage medium, and belongs to the field of petroleum and natural gas. The method comprises the steps that a plurality of candidate configuration units corresponding to a geological area are obtained, and the geological area comprises a coring well and a single well; obtaining well logging feature information of the cored well and configuration units corresponding to the well logging feature information, wherein the well logging feature information is feature information of which the correlation with the multiple candidate configuration units is superior to a target threshold value; based on the logging characteristic information of the cored well and the configuration units corresponding to the logging characteristic information, constructing a Fisher discriminant formula corresponding to each configuration unit; obtaining logging characteristic information of the single well; and identifying a configuration unit corresponding to the logging characteristic information of the single well based on the Fisher discriminant formula. According to the method, the Fisher discriminant formula is constructed according to the logging characteristic information and the configuration unit of the cored well, and the formula can effectively identify the configuration unit of a single well.

Description

Technical Field

[0001] The present application relates to the field of petroleum and natural gas, and in particular to a single well configuration identification method, device, equipment and storage medium. Background Art

[0002] A reservoir, also known as a reservoir layer, is a rock layer with interconnected pores that allow oil and gas to be stored and infiltrated. When the oil and gas content in a reservoir in a certain area reaches a certain level, it can be mined, and the mined area is called an oil field. The rock layer that stores oil and gas in an oil field is also called an oil layer. During the exploitation of an oil field, in order to maintain the pressure of the oil layer and increase the recovery rate of the oil layer, it is necessary to artificially inject water into the oil layer. As the degree of oil field exploitation continues to increase, the water content of the oil field continues to rise. However, due to the different structural characteristics of the rock layers that constitute the reservoir, such as the geometric shape, size, mutual arrangement and contact relationship, there will still be some areas with higher oil and gas content. Among them, the structural characteristics of the above-mentioned rock layers, such as the geometric shape, size, mutual arrangement and contact relationship, can be called configuration, and the structural characteristics of the rock layers related to the reservoir are called reservoir configuration.

[0003] Since the reservoir is a large area, it is difficult to conduct a direct configuration study of the reservoir when conducting a reservoir configuration study. Therefore, it is necessary to use the configuration of the wells drilled during the oil development process to assist in the study. The configuration of a single well is also called a single well configuration. The first step in the reservoir configuration study is to divide the single well configuration. The single well configuration division is to divide the rock formation into multiple levels of configuration based on the structural characteristics of the rock formation of a single well. The rock formation after the configuration division is also called a configuration unit. With the development of science and technology, the single well configuration division has gradually shifted from qualitative division to quantitative identification.

[0004] According to the cores taken out from the coring wells, manual identification is performed to obtain the configuration division of the area where the coring wells are located. The coring wells are drilled during the drilling process to take out the cores for configuration analysis. In addition to taking out the cores, the coring wells are also detected using precision instruments to obtain the corresponding logging curves. In the related technology, according to the configuration division of the coring wells, the preferred logging curves are selected, and the K-means clustering method is used to construct the configuration unit discrimination formula. According to the configuration unit discrimination formula, the configuration of the wells other than the coring wells is identified, and the reservoir configuration is studied according to the configuration division of the single wells in the area.

[0005] When the above method is applied to single well configuration identification, the return accuracy is not high and cannot meet the needs of reservoir configuration research. Therefore, how to identify the single well configuration more accurately is a problem that needs to be solved urgently. Summary of the invention

[0006] The present application provides a single well configuration identification method, device, equipment and storage medium. The technical solution is as follows:

[0007] According to one aspect of the present application, a single well configuration identification method is provided, the method comprising:

[0008] Acquire a plurality of candidate configuration units corresponding to a geological region, wherein the geological region includes core wells and single wells;

[0009] Acquire well logging characteristic information of the coring well and a configuration unit corresponding to the well logging characteristic information, wherein the well logging characteristic information is characteristic information whose correlation with the plurality of candidate configuration units is better than a target threshold;

[0010] Based on the well logging characteristic information of the coring well and the configuration units corresponding to the well logging characteristic information, constructing a Fisher discriminant formula corresponding to each of the configuration units;

[0011] Acquiring logging characteristic information of the single well;

[0012] The configuration unit corresponding to the logging characteristic information of the single well is identified based on the Fisher discriminant formula.

[0013] On the other hand, a single well configuration identification device is provided, the device comprising:

[0014] A first acquisition module is used to acquire a plurality of candidate configuration units corresponding to a geological region, wherein the geological region includes a core well and a single well;

[0015] A second acquisition module is used to acquire well logging characteristic information of the coring well and a configuration unit corresponding to the well logging characteristic information, wherein the well logging characteristic information is characteristic information whose correlation with the plurality of candidate configuration units is better than a target threshold;

[0016] A construction module, based on the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information, constructs a Fisher discriminant formula corresponding to each of the configuration units;

[0017] A third acquisition module is used to acquire the logging characteristic information of the single well;

[0018] An identification module identifies the configuration unit corresponding to the logging characteristic information of the single well based on the Fisher discriminant formula.

[0019] On the other hand, a computer device is provided, comprising a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement a single well configuration identification method.

[0020] On the other hand, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, a single well configuration identification method is implemented.

[0021] On the other hand, a computer program product is provided, which includes a computer program stored in a computer-readable storage medium; the computer program is read and executed from the computer-readable storage medium by a processor of a computer device, so that the computer device performs a single well configuration identification method.

[0022] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0023] The above technical solution applies the Fisher discriminant method to the single well configuration identification, and when constructing the Fisher discriminant formula, the selected formula parameter is the logging feature information with good correlation with the candidate configuration unit, wherein the target threshold of the correlation can be manually controlled. At the same time, the Fisher discriminant formula is constructed based on the logging feature information and configuration unit of the coring well, and the constructed Fisher discriminant formula has a high discrimination accuracy, and the Fisher discriminant formula can be applied to the configuration identification of single wells in the same area. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 A schematic diagram of a computer system provided by an exemplary embodiment of the present application is shown;

[0026] Figure 2 A flow chart of a single well configuration identification method provided by an exemplary embodiment of the present application is shown;

[0027] Figure 3 A flow chart of a single well configuration identification method provided by an exemplary embodiment of the present application is shown;

[0028] Figure 4 A flow chart of a single well configuration identification method provided by an exemplary embodiment of the present application is shown;

[0029] Figure 5 A schematic diagram showing an exemplary method of using a discriminant formula to divide multiple configuration units in the present application is shown;

[0030] Figure 6 A flow chart of a single well configuration identification method provided by an exemplary embodiment of the present application is shown;

[0031] Figure 7A flow chart of a single well configuration identification method provided by an exemplary embodiment of the present application is shown;

[0032] Figure 8 A flow chart of a single well configuration identification method provided by an exemplary embodiment of the present application is shown;

[0033] Fig. 9 A plurality of intersection diagrams of an exemplary braided sand island and a braided waterway of the present application are shown;

[0034] Fig.10 A structural block diagram of a single well configuration identification device provided by an exemplary embodiment of the present application is shown;

[0035] Fig.11 A structural block diagram of a server provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0036] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0037] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0038] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0039] First, the relevant terms involved in this application are introduced:

[0040] Configuration: The structural characteristics of a rock formation, which include at least one of the geometric form, size, mutual arrangement and contact relationship. The manifestation of the configuration includes at least one of sandpaper units and thin interlayers. The configuration unit is a component of the configuration divided according to the structural characteristics. According to the different division granularity, it can be divided into different levels of configuration units. Generally speaking, the smaller the number, the coarser the granularity. For example, the division granularity of the primary configuration unit is coarser than that of the secondary configuration unit.

[0041] Coring well: A well used to extract cores during drilling. Cores are columnar rock samples taken out during drilling and are used to analyze lithofacies, sedimentary characteristics, etc. Cores are also called rock cores, so coring wells are also called coring wells. Based on the careful observation and description of the cores taken out from the coring wells, a standard configuration profile can be established. The standard configuration profile contains stratigraphic positions, depths and coring section information, logging curves, lithology profiles, typical sedimentary structures, core photos of key configuration interfaces, reservoir properties, oil content test results, coring well configuration divisions, and other information, which can be used to guide the judgment of non-coring well configuration divisions.

[0042] Well logging: A method of measuring geophysical parameters using the geophysical properties of rock formations. The geophysical properties of rock formations include at least one of electrochemical properties, conductive properties, acoustic properties, and radioactivity. It is also called geophysical logging or mine geophysics, or logging for short, and is one of the applied geophysical methods (including gravity, magnetic, electric, seismic, and nuclear). When drilling for oil, logging must be carried out after drilling to the designed well depth to obtain various petroleum geological and engineering technical data. The curve formed during logging is called a logging curve. Logging curves usually include natural potential logging (SP), natural gamma logging (GR), compensated neutron logging (CNL), acoustic time difference logging (AC), resistivity logging (Rt), compensated density logging (DEN), etc.

[0043] Single well: a single well. Drilling refers to the work of drilling holes from the ground using mechanical equipment or manpower. Drilling is usually used in the exploration or development of gaseous and liquid minerals such as oil and natural gas. Drilling is divided into coring wells and non-coring wells according to whether the core is taken out during the drilling process.

[0044] Crossplot: A graph used to represent the relationship between at least two logging parameters of a formation. Logging parameters can be logging curve readings or calculated parameters. Crossplots are widely used in oil and gas exploration and can be used to check the quality of logging curves, calibrate logging curves, determine lithology, evaluate formations, identify the mineral composition of rocks, analyze fluid properties, etc. For example, resistivity-porosity crossplots can be used to interpret the lithology of a well section and can qualitatively distinguish between oil, gas and water layers.

[0045] Fisher discriminant: A method of projecting points in high-dimensional space to low-dimensional space. This method projects k groups of m metadata to a certain direction so that the groups are as separated as possible after projection. Both k and m are positive integers. Usually, the idea of ​​univariate variance analysis is used to measure whether the groups are separated. At the same time, the Fisher discriminant formula is derived. The Fisher discriminant formula can also be called the Fisher discriminant formula.

[0046] It should be understood that, although the terms first, second, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first parameter may also be referred to as the second parameter, and similarly, the second parameter may also be referred to as the first parameter. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0047] Figure 1 A schematic diagram of a computer system provided by an exemplary embodiment of the present application is shown. The computer system may include: a terminal device 110 and a server 120 .

[0048] The terminal device 110 is used to obtain multiple candidate configuration units provided by the user; or, the terminal device 110 is used to obtain the well logging feature information of the core well provided by the user and the configuration unit corresponding to the well logging feature information; or, the terminal device 110 is used to display the Fisher discriminant formula constructed by the server to the user; or, the terminal device 110 is used to obtain the well logging feature information of a single well input by the user; or, the terminal device 110 is used to display the recognition result of the single well configuration. Optionally, the terminal device can be any one of a mobile phone, a tablet computer, a game console, an e-book reader, a multimedia player, a wearable device, and a PC (Personal Computer).

[0049] The server 120 is used to construct a Fisher discriminant formula based on the acquired logging characteristic information of the coring well and the configuration unit corresponding to the logging characteristic information; the server 120 is also used to identify the configuration unit of the single well based on the acquired logging characteristic information of the single well and the Fisher discriminant formula. The server 120 can be any one of a single server, a server cluster composed of multiple servers, a virtual cloud storage, or a cloud computing center.

[0050] In some embodiments, the terminal device 110 and the server 120 are connected via a wired or wireless network.

[0051] It should be noted that, in some embodiments, the terminal device 110 and the server 120 are the same device.

[0052] Figure 2 A schematic diagram showing a method for viewing a history record of a cell provided by an exemplary embodiment of the present application is shown. The method is executed by a server, which may be Figure 1 The method comprises:

[0053] Step 210: obtaining a plurality of candidate configuration units corresponding to a geological region, the geological region including core wells and single wells;

[0054] In some embodiments, the geological region is an alluvial fan; or, the geological region is an alluvial fan; or, the geological region is an alluvial plain; or, the geological region is a delta.

[0055] It should be noted that the embodiments of the present application take the geological region as an alluvial fan for illustration, but the type of geological region is not limited.

[0056] In some embodiments, different geological regions correspond to different configuration units, and the configuration units are component units obtained by dividing the strata in the geological region according to the structural characteristics. According to different division granularities, they can be recorded as configuration units of different levels.

[0057] Step 220: acquiring well logging characteristic information of the coring well and configuration units corresponding to the well logging characteristic information, wherein the well logging characteristic information is characteristic information whose correlation with multiple candidate configuration units is better than a target threshold;

[0058] In some embodiments, the logging characteristic information is a logging curve, that is, a curve drawn based on data collected by logging; or, the logging characteristic information is a value corresponding to a point in the logging curve.

[0059] In some embodiments, the configuration units are divided according to manual analysis of the cores taken out of the coring well; or, the configuration units are divided according to machine analysis and identification of the cores taken out of the coring well.

[0060] In some embodiments, the correlation of the well logging characteristic information is determined based on the cross-plot method.

[0061] Exemplarily, any two well logging feature information are selected, and intersection diagrams between a plurality of candidate configuration units and the any two well logging feature information are drawn, and judgment is performed based on the overlap between the configuration units in the intersection diagram.

[0062] In some embodiments, the target threshold is a threshold set by a user; or, the target threshold is a preset value.

[0063] Exemplarily, the target threshold is that the overlap between the configuration units set by the user is not higher than 10%; or, the target threshold is a preset value, that is, the overlap between the configuration units is not higher than 5%.

[0064] In some embodiments, the characteristic information is standardized before determining the well logging characteristic information.

[0065] In some embodiments, standardization is data preprocessing to remove at least one of outliers, missing values, and unreasonable distribution in feature information. Outliers are values ​​in data that deviate from the mean or standard deviation by more than a target threshold, such as a negative age, an egg weighing 1 ton, etc. Missing values ​​refer to clustering, grouping, loss, or truncation of data due to lack of information; unreasonable distribution refers to data distribution that does not match the actual application background, such as using per capita diploma data obtained from a certain university in national diploma data.

[0066] Step 230: constructing a Fisher discriminant formula corresponding to each configuration unit based on the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information;

[0067] In some embodiments, the well logging characteristic information input by the user and the configuration unit corresponding to the well logging characteristic information are obtained; or, the well logging characteristic information stored in the server and the configuration unit corresponding to the well logging characteristic information are obtained.

[0068] In some embodiments, one configuration unit corresponds to a plurality of well logging feature information.

[0069] Exemplarily, there are logging characteristic information a1 to a5, configuration units G1 and G2, and the corresponding relationship between the logging characteristic information and the configuration units is that b1 corresponds to a1, a3 and a4, and b2 corresponds to a2 and a5.

[0070] In some embodiments, the configuration units are divided based on cores taken from a coring well.

[0071] In some embodiments, Fisher's discriminant formula is used to identify multiple candidate configuration units.

[0072] Step 240: Obtaining logging characteristic information of a single well;

[0073] In some embodiments, the well logging characteristic information of a single well input by a user is obtained; or, the well logging characteristic information of a single well is obtained from a server.

[0074] Step 250: Identify the configuration unit corresponding to the logging characteristic information of the single well based on the Fisher discriminant formula.

[0075] In some embodiments, the logging characteristic information of a single well is substituted into the Fisher discriminant formula to identify the configuration unit corresponding to the logging characteristic information of the single well.

[0076] Exemplarily, the Fisher discriminant formula has three equations f1 to f3, which correspond to three configuration units G1 to G3 respectively. The logging characteristic information c1 of a single well is substituted into f1 to f3 respectively to obtain values ​​d1 to d3. The maximum value among d1 to d3 is determined to be d2, then the configuration unit corresponding to the logging characteristic information c1 of the single well is G2, that is, the configuration unit corresponding to the Fisher discriminant formula that obtains the maximum value after substitution.

[0077] In summary, the method provided in this embodiment constructs the Fisher discriminant formula based on the logging characteristic information and configuration unit of the coring wells in the same area. Since the configurations in the same area are basically the same, the constructed Fisher discriminant formula is applicable to the single well in the area. When constructing the formula, the well logging characteristic information with good correlation is adopted, which can effectively improve the recognition accuracy.

[0078] Based on Figure 2 In an optional embodiment, if Figure 3 As shown, step 230 can be implemented alternatively as steps 231 to 233.

[0079] Step 231: projecting the well logging characteristic information of the core well to a target projection direction, where the target projection direction is a projection direction that maximizes the variance of the mean of the well logging characteristic information corresponding to each configuration unit after projection and minimizes the variance of the well logging characteristic information corresponding to the same configuration unit after projection;

[0080] In some embodiments, the projection direction is represented as an a′ vector; or, the projection direction is represented as i coefficients, where i is a positive integer.

[0081] Step 232: construct a conditional formula, where the conditional formula is the ratio of the variance of the mean of the well logging characteristic information corresponding to each configuration unit after projection to the variance of the well logging characteristic information corresponding to the same configuration unit after projection;

[0082] In some embodiments, in order to obtain the target projection direction, a conditional formula is constructed.

[0083] For example, there are n configuration units, namely configuration unit G1 to configuration unit Gn, wherein configuration unit G1 corresponds to k1 well logging feature information, which is projected as The configuration unit G2 corresponds to k2 logging feature information, which is projected as The configuration unit Gn corresponds to kn logging feature information, which is projected as K1, k2, ..., kn are positive integers. The calculated mean of each configuration unit after projection is to The overall mean of the projected n configuration units is The constructed conditional formula is shown below.

[0084]

[0085] Where a′ is the direction vector of the projection direction; is the vector corresponding to the logging characteristic information, is a vector (x i1 , x i2 , …, x im ), m is a positive integer, i=1,…,kn.

[0086] Step 233: Using the well logging characteristic information of the core well and the configuration unit corresponding to the well logging characteristic information as formula parameters, solve the formula coefficient of the discriminant formula that makes the conditional formula obtain the maximum value, and obtain the Fisher discriminant formula.

[0087] In some embodiments, the logging characteristic information of the coring well and the configuration unit corresponding to the logging characteristic information are substituted into the conditional formula, and the formula coefficient of the discriminant formula that obtains the maximum value of the conditional formula is solved to obtain the Fisher discriminant formula.

[0088] In some embodiments, the formula parameters are formula parameters of the Fisher discriminant formula, and the formula coefficients are formula coefficients of the Fisher discriminant formula.

[0089] In summary, the method provided in this embodiment constructs a Fisher discriminant formula, and the Fisher discriminant formula is constructed using the Fisher discriminant method, and can effectively perform classification and recognition.

[0090] In some embodiments, the characteristic information having a correlation with multiple candidate configuration units better than a target threshold includes at least one of natural potential, resistivity, and acoustic wave time difference. This embodiment is illustrated by including all three.

[0091] In some embodiments, the plurality of candidate configuration units is i configuration units, where i is a positive integer.

[0092] Based on Figure 3 In an optional embodiment, if Figure 4 As shown, step 233 can be implemented alternatively as steps 310 to 330.

[0093] Step 310: With natural potential as the first parameter, resistivity as the second parameter, acoustic time difference as the third parameter, and the configuration unit corresponding to the logging characteristic information as the fourth parameter, n discriminant formulas are constructed, one side of each discriminant formula is the fourth parameter, and the other side is the sum of the product of the first coefficient and the first parameter plus the product of the second coefficient and the second parameter plus the product of the third coefficient and the third parameter plus the first constant;

[0094] Wherein, n is a positive integer not greater than i.

[0095] In some embodiments, the configuration unit category is converted into a numerical value for processing. For example, if there are n configuration units, the first configuration unit corresponds to the numerical value "1", the second configuration unit corresponds to the numerical value "2", ..., and the nth configuration unit corresponds to the numerical value "n".

[0096] In some embodiments, the plurality of configuration units are three configuration units G1 to G3, and three discriminant formulas are constructed, corresponding to straight line A, straight line B, and straight line C, respectively. Figure 5 As shown in the schematic diagram (1).

[0097] In some embodiments, the plurality of configuration units are three configuration units G1 to G3, and two discriminant formulas can be constructed, corresponding to straight line D and straight line E, respectively. The constructed two discriminant formulas satisfy that after the three configuration units are projected onto the straight lines corresponding to the two discriminant formulas, respectively, the overlap length of the projection area of ​​each configuration unit on the straight line corresponding to the same discriminant formula is less than the target threshold, such as Figure 5 As shown in the schematic diagram (2).

[0098] In some embodiments, the plurality of configuration units are 3 configuration units G1 to G3, and a discriminant formula is constructed, corresponding to the straight line F, and the constructed discriminant formula satisfies the projection of the 3 configuration units on the straight line corresponding to the discriminant formula, and the overlap length of the projection area of ​​each configuration unit on the straight line corresponding to the discriminant formula is less than the target threshold value such as Figure 5 As shown in the schematic diagram (3).

[0099] In some embodiments, the n discriminant formulas are shown as follows.

[0100]

[0101] In the formula, y 1 ,y 2 , …, y n Corresponding to the fourth parameter; x 11 , x 21 , …, x n1 Corresponding to the first parameter; x 12 , x 22 , …, x n2 Corresponding to the second parameter; x 13 , x 23 , …, x n3 Corresponding to the third parameter; a 11 , a 21 , …, a n1 Corresponding to the first coefficient; a 12 , a 22 , …, a n2 Corresponding to the second coefficient; a 13 , a 23 , …, a n3Corresponding to the third coefficient; d 1 , d 2 , …, d n Corresponds to the first constant.

[0102] Step 320: Substitute the first parameter, the second parameter, the third parameter and the fourth parameter into the discriminant formula, and solve the first coefficient, the second coefficient, the third coefficient and the first constant respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value;

[0103] In some embodiments, the acquired first parameter, second parameter, third parameter and fourth parameter are substituted into the discriminant formula to construct a corresponding conditional formula, as shown in the following formula.

[0104]

[0105] in, is the vector corresponding to the formula parameter (x j1 , x j2 , x j3 ), a is the direction vector corresponding to the projection direction. For example, a′ is (a 11 , a 12 , a 13 ); or, a′ is (a 21 , a 22 , a 23 ); or, a′ is (a n1 , a n2 , a n3 ).

[0106] Exemplarily, there are 3 configuration units G1 to G3, and configuration unit G1 corresponds to 3 vectors to The configuration unit G2 corresponds to 5 vectors to Configuration unit G3 corresponds to 2 vectors to Among them, each vector corresponds to a set of first parameters, second parameters and third parameters. After substituting, the corresponding three a′ vectors are obtained. The first a′ vector corresponds to the coefficient of the first discriminant formula, the second a′ vector corresponds to the coefficient of the second discriminant formula, and the third a′ vector corresponds to the coefficient of the third discriminant formula.

[0107] In some embodiments, n first constants are solved according to the obtained n first coefficients, n second coefficients, n third coefficients and the first parameter, the second parameter, the third parameter and the fourth parameter.

[0108] Step 330: Substitute the first coefficient, the second coefficient, the third coefficient and the first constant into n discriminant formulas to obtain the Fisher discriminant formula.

[0109] Exemplarily, the 1st first coefficient, the 1st second coefficient, the 1st third coefficient and the 1st first constant are substituted into the 1st discriminant formula; the 2nd first coefficient, the 2nd second coefficient, the 2nd third coefficient and the 2nd first constant are substituted into the 2nd discriminant formula;…; the nth first coefficient, the nth second coefficient, the nth third coefficient and the nth first constant are substituted into the nth discriminant formula to obtain the Fisher discriminant formula.

[0110] In some embodiments, the first parameter, the second parameter and the third parameter are substituted into the Fisher discriminant formula, the configuration units corresponding to the first parameter, the second parameter and the third parameter are calculated, and the obtained configuration units are compared with the fourth parameter to obtain the return judgment accuracy.

[0111] Exemplarily, there are 3 configuration units G1 to G3, and the values ​​corresponding to the first parameter, the second parameter and the third parameter have 5 groups g1 to g5, wherein G1 corresponds to g1 and g4, G2 corresponds to g5, and G3 corresponds to g2 and g3. After substituting g1 to g5 into the Fisher discriminant formula, the configuration units obtained are g1 corresponding to G1, g2 corresponding to G2, g3 corresponding to G3, g4 corresponding to G1, and g5 corresponding to G2, and the obtained Fisher discriminant formula has a return accuracy of 80%.

[0112] In summary, the logging characteristic information selected by the method provided in this embodiment is natural potential, resistivity and acoustic wave time difference. These three logging characteristic information have good correlation with different configuration units, and the Fisher discriminant formula constructed based on the logging characteristic information will also have a good recognition accuracy.

[0113] Based on Figure 3 In an optional embodiment, if Figure 6 As shown, step 233 can be implemented alternatively as steps 340 to 360.

[0114] In some embodiments, the formula parameters further include resistivity logging parameters, which are logging parameters calculated based on at least two resistivity logging feature information.

[0115] Exemplarily, the resistivity logging parameters include: at least one of microelectrode amplitude difference, dual induction invasion factor, and array induction invasion factor. The microelectrode amplitude difference is the difference between micro gradient resistivity (MINV) and micro potential resistivity (MNOR), and the corresponding calculation formula is MINV-MNOR.

[0116] The dual induction intrusion factor is the ratio of the difference between the medium induction resistivity (RILM) and the deep induction resistivity (RILD) to the deep induction resistivity. The corresponding calculation formula is shown below.

[0117]

[0118] The array induced intrusion factor is the cumulative parameter of resistivity changes at adjacent radial depths, and the corresponding calculation formula is shown in the following formula.

[0119]

[0120] Among them, M x R y is a logging curve, x represents the vertical resolution of the array sensing, and the values ​​are 1, 2, and 4, corresponding to 1 foot, 2 feet, and 4 feet, respectively; y represents the lateral detection depth, and the values ​​are 1, 2, 3, 6, 9, and 12, corresponding to 10 inches, 20 inches, 30 inches, 60 inches, 90 inches, and 120 inches, respectively; 12 can also be expressed as x. M 2 R 9 Curve representing 2-foot resolution and 90-inch detection depth.

[0121] Step 340: With k logging feature information as k parameters, resistivity logging parameter as the fifth parameter, and configuration unit corresponding to the logging feature information as the fourth parameter, n discriminant formulas are constructed, one side of each discriminant formula is the fourth parameter, and the other side is the sum of the first sum value, the second sum value, and the second constant, the first sum value is the cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, and the second sum value is the product of the fifth coefficient and the fifth parameter;

[0122] Wherein, n is a positive integer not greater than i, and k is a positive integer.

[0123] In some embodiments, the configuration unit category is converted into a numerical value for processing. For example, if there are n configuration units, the first configuration unit corresponds to the numerical value "1", the second configuration unit corresponds to the numerical value "2", ..., and the nth configuration unit corresponds to the numerical value "n".

[0124] In some embodiments, the n discriminant formulas are shown as follows.

[0125]

[0126] In the formula, y 1 ,y 2 , …, y n Corresponding to the fourth parameter;

[0127] x 11 , x 21 , …, x n1 Parameters corresponding to the first logging feature information; x 12 , x 22 , …, x n2 Parameters corresponding to the second logging characteristic information; ...; x 1k , x 2k , …, xnk Parameters corresponding to the kth logging characteristic information;

[0128] z 1 , z 2 , …, z n Corresponding to the fifth parameter;

[0129] a 11 , a 21 , …, a n1 The unknown coefficient corresponding to the first logging characteristic information; a 12 , a 22 , …, a n2 The unknown coefficient corresponding to the second logging characteristic information; ...; a 1k , a 2k , …, a nk The unknown coefficient corresponding to the kth logging characteristic information;

[0130] b 1 , b 2 , …, b n corresponds to the fifth coefficient;

[0131] d 1 , d 2 , …, d n Corresponds to the second constant.

[0132] Step 350: Substitute the k parameters, the fifth parameter and the fourth parameter into the discriminant formula, and solve the unknown coefficients, the fifth coefficient and the second constant corresponding to the k parameters respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value;

[0133] In some embodiments, the obtained k parameters, the fifth parameter and the fourth parameter are substituted into the discriminant formula to construct a corresponding conditional formula, as shown in the following formula.

[0134]

[0135] in, is the vector corresponding to the formula parameter (x j1 , x j2 , …, x jk , z j ), a′ is the direction vector corresponding to the projection direction. For example, a′ is (a 11 , a 12 , …, a 1k , b 1 ); or, a′ is (a 21 , a 22 , …, a 2k , b 2 ); or, a′ is (a n1 , an2 , …, a nk , b n ).

[0136] In some embodiments, the second constant is solved based on the unknown coefficients corresponding to the k parameters, the fifth coefficient and the k parameters, the fifth parameter and the fourth parameter.

[0137] Step 360: Substitute the unknown coefficients, the fifth coefficient and the second constant corresponding to the k parameters into the n discriminant formulas to obtain the Fisher discriminant formula.

[0138] Exemplarily, the unknown coefficients, the first fifth coefficient and the first second constant corresponding to the first group of k parameters are substituted into the first discriminant formula; the unknown coefficients, the second fifth coefficient and the second second constant corresponding to the second group of k parameters are substituted into the second discriminant formula;…; the unknown coefficients, the nth fifth coefficient and the nth second constant corresponding to the nth group of k parameters are substituted into the nth discriminant formula.

[0139] In some embodiments, the k parameters and the fifth parameter are substituted into the Fisher discriminant formula, the configuration units of the k parameters and the fifth parameter are calculated, and the obtained configuration units are compared with the fourth parameter to obtain the return judgment accuracy.

[0140] Exemplarily, there are 3 configuration units G1 to G3, k parameters, and the values ​​corresponding to the fifth parameter have 10 groups g0 to g9, where G1 corresponds to g1, g4, g8, g9, G2 corresponds to g5, g6, and G3 corresponds to g0, g2, g3, and g7. After substituting g0 to g9 into the Fisher discriminant formula, the obtained configuration units are g0 corresponding to G3, g1 corresponding to G1, g2 corresponding to G3, g3 corresponding to G3, g4 corresponding to G1, g5 corresponding to G2, g6 corresponding to G3, g7 corresponding to G3, g8 corresponding to G1, and g9 corresponding to G1, and the obtained Fisher discriminant formula has a return accuracy of 90%.

[0141] In summary, the method provided in the present application introduces resistivity logging parameters as formula parameters. The resistivity logging parameters are obtained after calculation of resistivity logging information of different series. Due to the different structural characteristics of different configuration units, their corresponding resistivities will also be different accordingly. Introducing resistivity logging parameters into the Fisher discriminant formula can effectively improve the recognition accuracy.

[0142] In some embodiments, the formula parameters also include sandstone thickness.

[0143] In some embodiments, the sandstone thickness is measured based on the rock taken out from a single well; or, the sandstone thickness is obtained based on well logging characteristic information; or, the sandstone thickness is obtained based on seismic attributes. Seismic attribute technology is a method of describing and quantifying the characteristics of seismic data. Seismic data is a collection of seismic signals recorded by artificially exciting seismic waves into the formation and propagating in the formation; or, the sandstone thickness is obtained based on well logging characteristic information and seismic attributes.

[0144] Based on Figure 3 In an optional embodiment, if Figure 7 As shown, step 233 can be implemented alternatively as steps 370 to 390.

[0145] Step 370: With k logging characteristic information as k parameters, sandstone thickness as the sixth parameter, and the configuration unit corresponding to the logging characteristic information as the fourth parameter, n discriminant formulas are constructed, one side of each discriminant formula is the fourth parameter, and the other side is the third sum value, the sum of the fourth sum value and the third constant, the third sum value is the cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, and the fourth sum value is the product of the sixth coefficient and the sixth parameter;

[0146] Wherein, n is a positive integer not greater than i, and k is a positive integer.

[0147] In some embodiments, the configuration unit category is converted into a numerical value for processing. For example, if there are n configuration units, the first configuration unit corresponds to the numerical value "1", the second configuration unit corresponds to the numerical value "2", ..., and the nth configuration unit corresponds to the numerical value "n".

[0148] In some embodiments, the n discriminant formulas are shown as follows.

[0149]

[0150] In the formula, y 1 ,y 2 , …, y n Corresponding to the fourth parameter;

[0151] x 11 , x 21 , …, x n1 Parameters corresponding to the first logging feature information; x 12 , x 22 , …, x n2 Parameters corresponding to the second logging characteristic information; ...; x 1k , x 2k , …, x nk Parameters corresponding to the kth logging characteristic information;

[0152] w 1 , w 2,…,w n Corresponding to the sixth parameter;

[0153] a 11 , a 21 , …, a n1 The unknown coefficient corresponding to the first logging characteristic information; a 12 , a 22 , …, a n2 The unknown coefficient corresponding to the second logging characteristic information; ...; a 1k , a 2k , …, a nk The unknown coefficient corresponding to the kth logging characteristic information;

[0154] c 1 , c 2 , …, c n corresponds to the sixth coefficient;

[0155] d 1 , d 2 , …, d n Corresponds to the third constant.

[0156] Step 380: Substitute the k parameters, the sixth parameter and the fourth parameter into the discriminant formula, and solve the unknown coefficients, the sixth coefficient and the third constant corresponding to the k parameters respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value;

[0157] In some embodiments, the obtained k parameters, the sixth parameter and the fourth parameter are substituted into the discriminant formula to construct a corresponding conditional formula, as shown in the following formula.

[0158]

[0159] in, is the vector corresponding to the formula parameter (x j1 , x j2 , …, x jk , w j ), a′ is the direction vector corresponding to the projection direction. For example, a′ is (a 11 , a 12 , …, a 1k , c 1 ); or, a′ is (a 21 , a 22 , …, a 2k , c 2 ); or, a′ is (a n1 , a n2 , …, a nk , c n ).

[0160] In some embodiments, the third constant is solved based on the unknown coefficients corresponding to the k parameters, the sixth coefficient and the k parameters, the sixth parameter and the fourth parameter.

[0161] Step 390: Substitute the unknown coefficients, the sixth coefficient and the third constant corresponding to the k parameters into the n discriminant formulas to obtain the Fisher discriminant formula.

[0162] Exemplarily, the unknown coefficients, the first sixth coefficient and the first third constant corresponding to the first group of k parameters are substituted into the first discriminant formula; the unknown coefficients, the second sixth coefficient and the second third constant corresponding to the second group of k parameters are substituted into the second discriminant formula;…; the unknown coefficients, the nth sixth coefficient and the nth third constant corresponding to the nth group of k parameters are substituted into the nth discriminant formula.

[0163] In some embodiments, the k parameters and the sixth parameter are substituted into the Fisher discriminant formula, the configuration units of the k parameters and the sixth parameter are calculated, and the obtained configuration units are compared with the fourth parameter to obtain the return judgment accuracy.

[0164] Exemplarily, there are 3 configuration units G1 to G3, k parameters, and the values ​​corresponding to the fifth parameter have 10 groups g0 to g9, where G1 corresponds to g1, g4, g8, g9, G2 corresponds to g5, g6, and G3 corresponds to g0, g2, g3, and g7. After substituting g0 to g9 into the Fisher discriminant formula, the obtained configuration units are g0 corresponding to G3, g1 corresponding to G1, g2 corresponding to G3, g3 corresponding to G3, g4 corresponding to G1, g5 corresponding to G2, g6 corresponding to G3, g7 corresponding to G3, g8 corresponding to G1, and g9 corresponding to G1, and the obtained Fisher discriminant formula has a return accuracy of 90%.

[0165] In summary, the method provided in this embodiment introduces sandstone thickness as a formula parameter. Since sandstone thickness itself has a strong correlation with the configuration unit and is different from the well logging curve, it will be affected by the resolution of the well logging machine and cause errors. Whether it is directly measured or calculated, the difference between the sandstone thickness and the actual sandstone thickness is small. Therefore, introducing sandstone thickness into the Fisher discriminant formula can effectively reduce the uncertainty of the Hill discriminant formula.

[0166] Based on Figure 3 In an optional embodiment, if Figure 8 As shown, step 233 can be implemented alternatively as steps 410 to 430.

[0167] Step 410: With k logging characteristic information as k parameters, resistivity logging parameter as the fifth parameter, sandstone thickness as the sixth parameter, and configuration unit corresponding to the logging characteristic information as the fourth parameter, n discriminant formulas are constructed, one side of each discriminant formula is the fourth parameter, and the other side is the sum of the fifth sum value, the sixth sum value, the seventh sum value and the fourth constant, the fifth sum value is the cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, the sixth sum value is the product of the fifth coefficient and the fifth parameter, and the seventh sum value is the product of the sixth coefficient and the sixth parameter;

[0168] Wherein, n is a positive integer not greater than i, and k is a positive integer.

[0169] In some embodiments, the configuration unit category is converted into a numerical value for processing. For example, if there are n configuration units, the first configuration unit corresponds to the numerical value "1", the second configuration unit corresponds to the numerical value "2", ..., and the nth configuration unit corresponds to the numerical value "n".

[0170] In some embodiments, the n discriminant formulas are shown as follows.

[0171]

[0172] In the formula, y 1 ,y 2 , …, y n Corresponding to the fourth parameter;

[0173] x 11 , x 21 , …, x n1 Parameters corresponding to the first logging feature information; x 12 , x 22 , …, x n2 Parameters corresponding to the second logging characteristic information; ...; x 1k , x 2k , …, x nk Parameters corresponding to the kth logging characteristic information;

[0174] z 1 , z 2 , …, z n Corresponding to the fifth parameter; w 1 , w 2 ,…,w n Corresponding to the sixth parameter;

[0175] a 11 , a 21 , …, a n1 The unknown coefficient corresponding to the first logging characteristic information; a 12 , a 22 , …, a n2The unknown coefficient corresponding to the second logging characteristic information; ...; a 1k , a 2k , …, a nk The unknown coefficient corresponding to the kth logging characteristic information;

[0176] b 1 , b 2 , …, b n Corresponding to the fifth coefficient; c 1 , c 2 , …, c n corresponds to the sixth coefficient;

[0177] d 1 , d 2 , …, d n Corresponds to the fourth constant.

[0178] Step 420: Substitute the k parameters, the fifth parameter, the sixth parameter and the fourth parameter into the discriminant formula, and solve the unknown coefficients, the fifth coefficient, the sixth coefficient and the fourth constant corresponding to the k parameters respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value;

[0179] In some embodiments, the obtained k parameters, the fifth parameter, the sixth parameter and the fourth parameter are substituted into the discriminant formula to construct a corresponding conditional formula, as shown in the following formula.

[0180]

[0181] in, is the vector corresponding to the formula parameter (x j1 , x j2 , …, x jk , z j , w j ), a′ is the direction vector corresponding to the projection direction. For example, a′ is (a 11 , a 12 , …, a 1k , b 1 , c 1 ); or, a′ is (a 21 , a 22 , …, a 2k , b 2 , c 2 ); or, a′ is (a n1 , a n2 , …, a nk , b n , c n ).

[0182] In some embodiments, the fourth constant is solved based on the unknown coefficients, the fifth coefficient, the sixth coefficient and the k parameters, the sixth parameter and the fourth parameter corresponding to the obtained k parameters.

[0183] Step 430: Substitute the unknown coefficients, the fifth coefficient, the sixth coefficient and the fourth constant corresponding to the k parameters into n discriminant formulas to obtain the Fisher discriminant formula.

[0184] Exemplarily, the unknown coefficients, the first fifth coefficient, the first sixth coefficient and the first fourth constant corresponding to the first group of k parameters are substituted into the first discriminant formula; the unknown coefficients, the second fifth coefficient, the second sixth coefficient and the second fourth constant corresponding to the second group of k parameters are substituted into the second discriminant formula;…; the unknown coefficients, the nth fifth coefficient, the nth sixth coefficient and the nth third fourth constant corresponding to the nth group of k parameters are substituted into the nth discriminant formula.

[0185] In some embodiments, the k parameters, the fifth parameter, and the sixth parameter are substituted into the Fisher discriminant formula, the configuration units of the k parameters, the fifth parameter, and the sixth parameter are calculated, and the obtained configuration units are compared with the fourth parameter to obtain the return judgment accuracy.

[0186] Exemplarily, there are 3 configuration units G1 to G3, k parameters, and the values ​​corresponding to the fifth parameter have 10 groups g0 to g9, where G1 corresponds to g1, g4, g8, g9, G2 corresponds to g5, g6, and G3 corresponds to g0, g2, g3, and g7. After substituting g0 to g9 into the Fisher discriminant formula, the obtained configuration units are g0 corresponding to G3, g1 corresponding to G1, g2 corresponding to G3, g3 corresponding to G3, g4 corresponding to G1, g5 corresponding to G2, g6 corresponding to G3, g7 corresponding to G3, g8 corresponding to G1, and g9 corresponding to G1, and the obtained Fisher discriminant formula has a return accuracy of 90%.

[0187] In summary, the method provided in this embodiment introduces resistivity logging parameters and sandstone thickness into the Fisher discriminant formula, which can greatly improve the recognition accuracy of the Fisher discriminant formula.

[0188] In order to more clearly understand the identification method of the embodiment of the present application, the Z oil field will be taken as an example to perform single well configuration identification.

[0189] Step 1: Obtain multiple candidate configuration units corresponding to the address area.

[0190] The geological area corresponding to the Z oilfield is in the alluvial fan. According to the cores taken out from the coring wells, manual observation and identification are carried out to analyze the structural units in the sedimentary fan corresponding to the Z oilfield. At the same time, the logging characteristic information of the coring wells obtained by measurement, namely the logging curve, is obtained.

[0191] The multiple candidate configuration units are level eight configuration units and level nine configuration units. According to geological surveys, the accretionary bodies and fall-siltation layers of the level nine configuration unit to be identified are located inside the sand bodies of the braided flow sand islands of the level eight configuration unit to be identified. The configuration divisions (parts) in the sedimentary fan are shown in Table 1.

[0192] Table 1 Classification of sedimentary fan reservoir architecture (partial)

[0193]

[0194] Step 2: obtaining well logging characteristic information of the coring well and configuration units corresponding to the well logging characteristic information. The well logging characteristic information is characteristic information whose correlation with multiple candidate configuration units is better than a target threshold.

[0195] like Fig. 9 As shown, the cross plot method is used to determine the sensitive logging curves with good correlation with the eighth-order configuration unit and the ninth-order configuration unit in the logging curves of the core well, and the obtained sensitive logging curves are natural potential, resistivity and acoustic time difference.

[0196] According to the sensitive logging curve of the coring well, a logging characteristic information and an eight-level configuration unit corresponding to the logging characteristic information are obtained every 10 meters.

[0197] From the braided flow sand island of the eighth-level configuration unit, a well logging characteristic information and the ninth-level configuration unit corresponding to the well logging characteristic information are obtained every 5 meters.

[0198] Step 3: Based on the well logging characteristic information of the coring well and the configuration units corresponding to the well logging characteristic information, a Fisher discriminant formula corresponding to each configuration unit is constructed.

[0199] The parameters of the Fisher discriminant formula also include resistivity logging parameters, sandstone thickness and other logging characteristic information.

[0200] The resistivity logging parameters include: at least one of microelectrode amplitude difference, dual induction invasion factor, and array induction invasion factor. The microelectrode amplitude difference is the difference between micro gradient resistivity (MINV) and micro potential resistivity (MNOR), and the corresponding calculation formula is MINV-MNOR.

[0201] The dual induction intrusion factor is the ratio of the difference between the medium induction resistivity (RILM) and the deep induction resistivity (RILD) to the deep induction resistivity. The corresponding calculation formula is shown below.

[0202]

[0203] The array induced intrusion factor is the cumulative parameter of resistivity changes at adjacent radial depths, and the corresponding calculation formula is shown in the following formula.

[0204]

[0205] Sandstone thickness is measured based on rock taken out of a single well; or, sandstone thickness is obtained based on well logging characteristic information; or, sandstone thickness is obtained based on seismic attributes. Seismic attribute technology is a method of describing and quantifying the characteristics of seismic data. Seismic data is a collection of seismic signals recorded by artificially exciting seismic waves into the formation and propagating in the formation; or, sandstone thickness is obtained based on well logging characteristic information and seismic attributes.

[0206] Other logging curves are logging curves that are not sensitive logging curves but can still improve the recognition accuracy of the Fisher discriminant formula.

[0207] 1. When the parameters of the Fisher discriminant formula are sensitive logging curve, microelectrode amplitude difference, and sandstone thickness, the obtained Fisher discriminant formula is shown in the table below.

[0208] Among them, the vertical accumulation body and the siltation layer are located inside the sand body of the braided flow sand island, and there is no parameter of sandstone thickness.

[0209] Table 2 Discriminant formula 1

[0210]

[0211] 2. When the parameters of the Fisher discriminant formula are sensitive logging curves, dual-induction invasion factors, sandstone thickness and other logging curves, the obtained Fisher discriminant formula is shown in the table below.

[0212] Among them, other logging curves are logging curves whose correlation does not reach the target threshold, but the recognition accuracy can be improved after the logging curve is introduced into the Fisher discriminant formula, so it can be introduced into the Fisher discriminant formula. The other logging curves selected here are neutron curves and density curves.

[0213] Table 3 Discriminant formula 2

[0214]

[0215] The logging characteristic information of the core well, the dual-sensing invasion factor, the sandstone thickness and the characteristic information corresponding to other logging curves were substituted into the discrimination formula to obtain the recognition result. The recognition result was compared with the actual configuration unit corresponding to the logging characteristic information, and the return judgment accuracy of the scheme was 94%.

[0216] 3. When the parameters of the Fisher discriminant formula are sensitive logging curve, array induction invasion factor, and sandstone thickness, the obtained Fisher discriminant formula is shown in the table below.

[0217] Table 4 Discriminant formula three

[0218]

[0219] The logging characteristic information of the coring well, the array sensing invasion factor, and the sandstone thickness were substituted into the discrimination formula to obtain the recognition result. The recognition result was compared with the configuration unit corresponding to the actual logging characteristic information, and the return judgment accuracy of the scheme was 77%.

[0220] Step 4: Obtain logging characteristic information of a single well.

[0221] The well logging characteristic information of a single well in the address area is obtained. The well logging characteristic information of a single well is measured when the single well is drilled.

[0222] The resistivity logging parameter corresponding to the single well is calculated, and the resistivity logging parameter is at least one of a microelectrode amplitude difference, a dual induction intrusion factor, and an array induction intrusion factor.

[0223] Get the sandstone thickness corresponding to the unit.

[0224] Step 5: Identify the configuration unit corresponding to the logging characteristic information of the single well based on the Fisher discriminant formula.

[0225] Substitute the corresponding formula parameters into the Fisher discriminant formula to obtain the calculation results of the corresponding 5 configuration units. The largest calculation result of the 5 configuration units obtained is the configuration unit corresponding to the parameter.

[0226] For example, according to the discriminant formula 1, there are natural potential 1, microelectrode amplitude difference 1, acoustic wave time difference 2, resistivity 12, and sandstone thickness 5; substituting into the Fisher discriminant formula, the corresponding calculation results are -636.354, -629.251, -653.814, 91.627, and 92.539, respectively. Therefore, the configuration unit corresponding to the logging characteristic information is the siltation layer.

[0227] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0228] Please refer to Fig.10 , which shows a structural block diagram of a single well configuration identification device provided by an exemplary embodiment of the present application. The device has the function of implementing the above-mentioned single well configuration identification method example, and the function can be implemented by hardware or by hardware executing corresponding software. Fig.10 As shown, the device 500 may include: a first acquisition module 510 , a second acquisition module 520 , a construction module 530 , a third acquisition module 540 and an identification module 550 .

[0229] A first acquisition module 510 is used to acquire a plurality of candidate configuration units corresponding to a geological region, wherein the geological region includes core wells and single wells;

[0230] A second acquisition module 520 is used to acquire well logging characteristic information of the coring well and a configuration unit corresponding to the well logging characteristic information, wherein the well logging characteristic information is characteristic information whose correlation with the plurality of candidate configuration units is better than a target threshold;

[0231] A construction module 530, configured to construct a Fisher discriminant formula corresponding to each configuration unit based on the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information;

[0232] A third acquisition module 540 is used to acquire the logging characteristic information of the single well;

[0233] The identification module 550 is used to identify the configuration unit corresponding to the logging characteristic information of the single well based on the Fisher discriminant formula.

[0234] In some embodiments, the construction module 530 includes: a projection submodule, a construction submodule, and a solution submodule.

[0235] A projection submodule, used for projecting the logging characteristic information of the coring well to a target projection direction, wherein the target projection direction is a projection direction that maximizes the variance of the mean of the logging characteristic information corresponding to each of the configuration units after projection and minimizes the variance of the logging characteristic information corresponding to the same configuration unit after projection;

[0236] A construction submodule, used for constructing a conditional formula, wherein the conditional formula is a ratio of the variance of the mean of the well logging characteristic information corresponding to each of the configuration units after projection to the variance of the well logging characteristic information corresponding to the same configuration unit after projection;

[0237] The solving submodule is used to solve the formula coefficient of the discriminant formula that makes the conditional formula obtain the maximum value by using the logging characteristic information of the coring well and the configuration unit corresponding to the logging characteristic information as formula parameters, so as to obtain the Fisher discriminant formula.

[0238] In some embodiments, the solution submodule includes: a first construction unit, a first solution unit, and a first calculation unit.

[0239] A first construction unit is used to construct n discriminant formulas with the natural potential as a first parameter, the resistivity as a second parameter, the acoustic time difference as a third parameter, and the configuration unit corresponding to the logging characteristic information as a fourth parameter, wherein one side of each of the discriminant formulas is the fourth parameter, and the other side is the sum of the product of the first coefficient and the first parameter plus the product of the second coefficient and the second parameter plus the product of the third coefficient and the third parameter plus a first constant;

[0240] a first solving unit, used for substituting the first parameter, the second parameter, the third parameter and the fourth parameter into a discriminant formula, and solving the first coefficient, the second coefficient, the third coefficient and the first constant respectively corresponding to n discriminant formulas that make the conditional formula obtain a maximum value;

[0241] The first calculation unit is used to substitute the first coefficient, the second coefficient, the third coefficient and the first constant into the n discriminant formulas to obtain the Fisher discriminant formula.

[0242] In some embodiments, the solution submodule includes: a second construction unit, a second solution unit, and a second calculation unit.

[0243] a second construction unit, for constructing n discriminant formulas with the k logging characteristic information as k parameters, the resistivity logging parameter as a fifth parameter, and the configuration unit corresponding to the logging characteristic information as a fourth parameter, wherein one side of each of the discriminant formulas is the fourth parameter, and the other side is the sum of a first sum value, a second sum value, and a second constant, wherein the first sum value is a cumulative sum of products of the k parameters and unknown coefficients corresponding to the k parameters, and the second sum value is a product of a fifth coefficient and the fifth parameter;

[0244] A second solving unit is used to substitute the k parameters, the fifth parameter and the fourth parameter into the discriminant formula, and solve the unknown coefficients corresponding to the k parameters, the fifth coefficient and the second constant respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value;

[0245] The second calculation unit is used to substitute the unknown coefficients corresponding to the k parameters, the fifth coefficient and the second constant into the n discriminant formulas to obtain the Fisher discriminant formula.

[0246] In some embodiments, the solution submodule includes: a third construction unit, a third solution unit, and a third calculation unit.

[0247] a third construction unit, for constructing n discriminant formulas with the k logging characteristic information as k parameters, the sandstone thickness as a sixth parameter, and the configuration unit corresponding to the logging characteristic information as a fourth parameter, wherein one side of each of the discriminant formulas is the fourth parameter, and the other side is a third sum value, a sum of the fourth sum value and a third constant, the third sum value is a cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, and the fourth sum value is a product of the sixth coefficient and the sixth parameter;

[0248] A third solving unit is used to substitute the k parameters, the sixth parameter and the fourth parameter into the discriminant formula, and solve the unknown coefficients corresponding to the k parameters, the sixth coefficient and the third constant respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value;

[0249] The third calculation unit is used to substitute the unknown coefficients corresponding to the k parameters, the sixth coefficient and the third constant into the n discriminant formulas to obtain the Fisher discriminant formula.

[0250] In some embodiments, the solution submodule includes: a fourth construction unit, a fourth solution unit, and a fourth calculation unit.

[0251] a fourth construction unit, for constructing n discriminant formulas with the k logging characteristic information as k parameters, the resistivity logging parameter as a fifth parameter, the sandstone thickness as a sixth parameter, and the configuration unit corresponding to the logging characteristic information as a fourth parameter, wherein one side of each of the discriminant formulas is the fourth parameter, and the other side is the sum of a fifth sum value, a sixth sum value, a seventh sum value and a fourth constant, the fifth sum value being the cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, the sixth sum value being the product of the fifth coefficient and the fifth parameter, and the seventh sum value being the product of the sixth coefficient and the sixth parameter;

[0252] a fourth solving unit, used for substituting the k parameters, the fifth parameter, the sixth parameter and the fourth parameter into the discriminant formula, and solving the unknown coefficients corresponding to the k parameters, the fifth coefficient, the sixth coefficient and the fourth constant respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value;

[0253] The fourth calculation unit is used to substitute the unknown coefficients corresponding to the k parameters, the fifth coefficient, the sixth coefficient and the fourth constant into the n discriminant formulas to obtain the Fisher discriminant formula.

[0254] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0255] Please refer to Fig.11 , which shows a structural block diagram of a server provided in one embodiment of the present application. The server can be used to implement the single well configuration identification method provided in the above embodiment. Specifically:

[0256] The server 600 includes a central processing unit (CPU) 601, a system memory 604 including a random access memory (RAM) 602 and a read-only memory (ROM) 603, and a system bus 605 connecting the system memory 604 and the central processing unit 601. The computer device 600 also includes a basic input / output system (I / O system) 606 for facilitating information transmission between various components in the computer device, and a large-capacity storage device 607 for storing an operating system 613, application programs 614, and other program modules 615.

[0257] The basic input / output system 606 includes a display 608 for displaying information and an input device 609 such as a mouse and a keyboard for user inputting information. The display 608 and the input device 609 are connected to the central processing unit 601 through an input / output controller 610 connected to the system bus 605. The basic input / output system 606 may also include an input / output controller 610 for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 610 also provides output to a display screen, a printer, or other types of output devices.

[0258] The mass storage device 607 is connected to the central processing unit 601 via a mass storage controller (not shown) connected to the system bus 605. The mass storage device 607 and its associated computer-readable storage medium provide non-volatile storage for the server 600. That is, the mass storage device 607 may include a computer-readable storage medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0259] Without loss of generality, the computer-readable storage medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable storage instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, Erasable Programmable Read Only Memory (EPROM), Electronically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other solid-state storage technology, CD-ROM, Digital Versatile Disc (DVD) or other optical storage, cassette, tape, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that the computer storage medium is not limited to the above. The above-mentioned system memory 604 and mass storage device 607 can be collectively referred to as memory.

[0260] The memory stores one or more programs, and the one or more programs are configured to be executed by one or more central processing units 601. The one or more programs contain instructions for implementing the above-mentioned method embodiments. The central processing unit 601 executes the one or more programs to implement the methods provided by the above-mentioned method embodiments.

[0261] According to various embodiments of the present application, the server 600 can also be connected to a remote server on the network through a network such as the Internet. That is, the server 600 can be connected to the network 612 through a network interface unit 611 connected to the system bus 605, or the network interface unit 611 can be used to connect to other types of networks or remote server systems (not shown).

[0262] The memory also includes one or more programs, which are stored in the memory and include steps executed by the server in the method provided in the embodiment of the present application.

[0263] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the single well configuration identification method described above is implemented.

[0264] In an exemplary embodiment, a computer program product is also provided. When the computer program product is executed by a processor, it is used to implement the above-mentioned single well configuration identification method.

[0265] It should be understood that the "multiple" mentioned in this article refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. In addition, the step numbers described in this article only illustrate a possible execution sequence between the steps. In some other embodiments, the above steps may not be executed in the order of the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in the opposite order to the diagram. The embodiments of the present application are not limited to this.

[0266] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A single well configuration identification method, characterized in that: The method comprises: Acquire a plurality of candidate configuration units corresponding to a geological region, wherein the geological region includes core wells and single wells; Acquire well logging characteristic information of the coring well and a configuration unit corresponding to the well logging characteristic information, wherein the well logging characteristic information is characteristic information whose correlation with the plurality of candidate configuration units is better than a target threshold; Based on the well logging characteristic information of the coring well and the configuration units corresponding to the well logging characteristic information, constructing a Fisher discriminant formula corresponding to each of the configuration units; Acquiring logging characteristic information of the single well; The configuration unit corresponding to the logging characteristic information of the single well is identified based on the Fisher discriminant formula.

2. The method according to claim 1, characterized in that The method of constructing a Fisher discriminant formula corresponding to each configuration unit based on the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information comprises: Projecting the logging characteristic information of the coring well to a target projection direction, wherein the target projection direction is a projection direction that maximizes the variance of the mean of the logging characteristic information corresponding to each of the configuration units after projection and minimizes the variance of the logging characteristic information corresponding to the same configuration unit after projection; Constructing a conditional formula, wherein the conditional formula is a ratio of the variance of the mean of the well logging characteristic information corresponding to each of the configuration units after projection to the variance of the well logging characteristic information corresponding to the same configuration unit after projection; The Fisher discriminant formula is obtained by taking the logging characteristic information of the coring well and the configuration unit corresponding to the logging characteristic information as formula parameters and solving the formula coefficient of the discriminant formula that makes the conditional formula obtain the maximum value.

3. The method according to claim 2, characterized in that The logging characteristic information of the coring well is at least one of natural potential, resistivity and acoustic time difference; the plurality of candidate configuration units are i configuration units, i being a positive integer; The method uses the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information as formula parameters, solves the formula coefficient of the discriminant formula that makes the conditional formula obtain the maximum value, and obtains the Fisher discriminant formula, including: Taking the natural potential as the first parameter, the resistivity as the second parameter, the acoustic time difference as the third parameter, and the configuration unit corresponding to the logging characteristic information as the fourth parameter, n discriminant formulas are constructed, one side of each of the discriminant formulas is the fourth parameter, and the other side is the sum of the product of the first coefficient and the first parameter plus the product of the second coefficient and the second parameter plus the product of the third coefficient and the third parameter plus the first constant; Substituting the first parameter, the second parameter, the third parameter and the fourth parameter into a discriminant formula, and solving the first coefficient, the second coefficient, the third coefficient and the first constant respectively corresponding to n discriminant formulas that make the conditional formula obtain a maximum value; Substituting the first coefficient, the second coefficient, the third coefficient and the first constant into the n discriminant formulas to obtain the Fisher discriminant formula; Wherein, n is a positive integer not greater than i.

4. The method according to claim 2, characterized in that: The formula parameters also include resistivity logging parameters, which are logging parameters calculated based on at least two resistivity logging feature information; the multiple candidate configuration units are i configuration units, i is a positive integer; The method uses the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information as formula parameters, solves the formula coefficient of the discriminant formula that makes the conditional formula obtain the maximum value, and obtains the Fisher discriminant formula, including: Taking the k logging characteristic information as k parameters, the resistivity logging parameter as the fifth parameter, and the configuration unit corresponding to the logging characteristic information as the fourth parameter, n discriminant formulas are constructed, one side of each of the discriminant formulas is the fourth parameter, and the other side is the sum of a first sum value, a second sum value, and a second constant, the first sum value is the cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, and the second sum value is the product of the fifth coefficient and the fifth parameter; Substituting the k parameters, the fifth parameter and the fourth parameter into the discriminant formula, solving the unknown coefficients corresponding to the k parameters, the fifth coefficient and the second constant respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value; Substituting the unknown coefficients corresponding to the k parameters, the fifth coefficient and the second constant into the n discriminant formulas to obtain the Fisher discriminant formula; Wherein, n is a positive integer not greater than i, and k is a positive integer.

5. The method according to claim 2, characterized in that: The formula parameters also include sandstone thickness; the plurality of candidate configuration units are i configuration units, i being a positive integer; The method uses the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information as formula parameters, solves the formula coefficient of the discriminant formula that makes the conditional formula obtain the maximum value, and obtains the Fisher discriminant formula, including: Taking the k logging characteristic information as k parameters, the sandstone thickness as the sixth parameter, and the configuration unit corresponding to the logging characteristic information as the fourth parameter, n discriminant formulas are constructed, one side of each of the discriminant formulas is the fourth parameter, and the other side is the sum of the third sum value, the fourth sum value and the third constant, the third sum value is the cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, and the fourth sum value is the product of the sixth coefficient and the sixth parameter; Substituting the k parameters, the sixth parameter and the fourth parameter into the discriminant formula, solving the unknown coefficients corresponding to the k parameters, the sixth coefficient and the third constant respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value; Substituting the unknown coefficients corresponding to the k parameters, the sixth coefficient and the third constant into the n discriminant formulas to obtain the Fisher discriminant formula; Wherein, n is a positive integer not greater than i, and k is a positive integer.

6. The method according to claim 2, characterized in that The formula parameters also include resistivity logging parameters and sandstone thickness; the plurality of candidate configuration units are i configuration units, i being a positive integer; The method uses the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information as formula parameters, solves the formula coefficient of the discriminant formula that makes the conditional formula obtain the maximum value, and obtains the Fisher discriminant formula, including: Taking the k logging characteristic information as k parameters, the resistivity logging parameter as the fifth parameter, the sandstone thickness as the sixth parameter, and the configuration unit corresponding to the logging characteristic information as the fourth parameter, n discriminant formulas are constructed, one side of each of the discriminant formulas is the fourth parameter, and the other side is the sum of the fifth sum value, the sixth sum value, the seventh sum value and the fourth constant, the fifth sum value is the cumulative sum of the products of the k parameters and the unknown coefficients corresponding to the k parameters, the sixth sum value is the product of the fifth coefficient and the fifth parameter, and the seventh sum value is the product of the sixth coefficient and the sixth parameter; Substituting the k parameters, the fifth parameter, the sixth parameter and the fourth parameter into the discriminant formula, solving the unknown coefficients corresponding to the k parameters, the fifth coefficient, the sixth coefficient and the fourth constant respectively corresponding to the n discriminant formulas that make the conditional formula obtain the maximum value; Substituting the unknown coefficients corresponding to the k parameters, the fifth coefficient, the sixth coefficient and the fourth constant into the n discriminant formulas to obtain the Fisher discriminant formula; Wherein, n is a positive integer not greater than i, and k is a positive integer.

7. A single well configuration identification device, characterized in that: The device comprises: A first acquisition module is used to acquire a plurality of candidate configuration units corresponding to a geological region, wherein the geological region includes a core well and a single well; A second acquisition module is used to acquire well logging characteristic information of the coring well and a configuration unit corresponding to the well logging characteristic information, wherein the well logging characteristic information is characteristic information whose correlation with the plurality of candidate configuration units is better than a target threshold; A construction module, used to construct a Fisher discriminant formula corresponding to each configuration unit based on the well logging characteristic information of the coring well and the configuration unit corresponding to the well logging characteristic information; A third acquisition module is used to acquire the logging characteristic information of the single well; An identification module is used to identify the configuration unit corresponding to the logging characteristic information of the single well based on the Fisher discriminant formula.

8. A computer device, characterized in that: The computer device includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the single well configuration identification method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the single well configuration identification method as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, which is stored in a computer-readable storage medium; the computer program is read and executed from the computer-readable storage medium by a processor of a computer device, so that the computer device executes the single well configuration identification method as described in any one of claims 1 to 6.

Images