Lithology prediction method and system and computer readable storage medium

Abstract

The invention relates to the technical field of oil and gas exploration and development, and discloses a lithology prediction method and system and a computer readable storage medium, and the method comprises the steps: calculating the time-frequency spectrum of a plurality of logging parameters of a cored well section, and taking the time-frequency spectrum of each logging parameter as a logging characterization parameter; calculating lithologic model parameters by using the logging characterization parameters; establishing a lithology prediction model according to the corresponding relationship between the lithology model parameters and the actual lithology of the coring well section; and performing lithology prediction on the lithology model parameters of the unidentified well section by using the lithology prediction model. The time-frequency spectrum data reflect the instantaneous change of the logging parameters in time and frequency, and the time-frequency spectrum of each logging parameter is used as the logging characterization parameter to calculate the lithologic model parameter, so that the lithologic identification precision is improved, the formation with a complex structure and large lithologic change amplitude can be quickly handled, the drilling period is saved, the sampling rate is improved, and the method is suitable for mass production. And the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas exploration and development, and in particular to a lithology prediction method, system and computer-readable storage medium. Background Art

[0002] my country is rich in unconventional oil and gas resources, with recoverable resources of about (890-1260)×108t oil and gas equivalent, which is about three times that of conventional oil and gas. As the domestic oil and gas exploration and development efforts continue to increase, the requirements for efficient development continue to increase, and it is necessary to gradually develop unconventional oil and gas and ultra-deep oil and gas reservoirs. Wellbore stability, drilling parameter optimization, and downhole risks are prominent. Accurate prediction of lithology can ensure safe and rapid drilling and effectively prevent downhole risks caused by lithology mutations.

[0003] Traditional lithology prediction methods are mostly based on core and cuttings logging at the drilling site. Due to inaccurate core descriptions and cuttings soaked in drilling fluid, the sampling rate is low and the recognition accuracy is limited. The method based on traditional wavelet transform analysis of logging data cannot take into account both the frequency and time of the original data at the same time, so the resolution is low and has lag. In addition, although the lithology prediction method based on the logging while drilling tool can meet the low latency requirements, it is restricted by the environment and has high maintenance costs. Therefore, it is urgent to innovate and develop lithology prediction methods with "high sampling rate, high precision, low cost, and low operational risk" to optimize drilling and completion plans. Summary of the invention

[0004] The present invention aims to provide a lithology prediction method, system and computer-readable storage medium for improving lithology prediction accuracy and reducing costs, thereby providing a basis for optimizing drilling and completion plans.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A lithology prediction method, comprising:

[0007] Calculate the time-frequency spectra of multiple logging parameters in the coring section, and use the time-frequency spectra of each logging parameter as logging characterization parameters;

[0008] Calculating lithology model parameters using the well logging characterization parameters;

[0009] Establishing a lithology prediction model according to the correspondence between the lithology model parameters and the actual lithology of the coring well section;

[0010] The lithology prediction model is used to predict the lithology of unidentified well sections.

[0011] Furthermore, the multiple logging parameters of the coring section include natural gamma ray GR, acoustic time difference AC, compensated neutron CNL, compensated density DEN, eight lateral conductivity CLL8 and deep induction conductivity CILD.

[0012] Furthermore, the time-frequency spectrum of any logging parameter of the coring section is calculated, including:

[0013] Get the data set s(t) of any logging parameter;

[0014] Perform EMD decomposition on the data set s(t) to obtain a linear combination and residual of n IMF components;

[0015]

[0016] Among them, h i (t) is the i-th IMF component, p n (t) is the residual after n iterations;

[0017] Perform Hilbert transform on each IMF component to obtain the time-frequency spectrum of each IMF component;

[0018]

[0019] Among them, w i (t) is the constant corresponding to the i-th IMF component;

[0020] The time-frequency spectra of all IMF components are added together to obtain the time-frequency spectra of the logging parameters.

[0021] Further, the calculating of lithology model parameters using the well logging characterization parameters includes:

[0022] Characterization of parameters using natural gamma logging GR , Acoustic Time Difference Logging Characterization Parameters I AC , Compensated neutron logging characterization parameters I CNL , Compensated density logging characterization parameters I DEN , Eight Lateral Conductivity Logging Characterization Parameters I CLL8 and deep induction conductivity logging characterization parameters I CILD A multivariate regression calculation is performed to obtain a first lithology model parameter A, a second lithology model parameter B and a third lithology model parameter C of the coring well section.

[0023] Furthermore, the first lithology model parameter A is used to characterize the rock organic matter content and the location of the sweet spot target;

[0024] A=b1I GR +b2I AC +lnI CNL +c1

[0025] The second lithology model parameter B is used to characterize the degree to which mud flushing is controlled by the porosity and permeability of the rock when the same type of mud is used, wherein the second lithology model parameter B is combined with the first lithology model parameter A to determine the formation lithology classification mode;

[0026] B=b3ln(I CLL8 +I CILD )+b4I GR +c2

[0027] The third lithology model parameter C is used to characterize the fracture and pore volume that may be encountered in the actual well section, wherein the third lithology model parameter C is combined with the first lithology model parameter A and the second lithology model parameter B to refine the lithology type;

[0028] C=b5lnI CNL +b6I DEN +c3

[0029] Among them, b1-b6 and c1-c3 are constants.

[0030] Furthermore, the lithology prediction model is established according to the correspondence between the lithology model parameters and the actual lithology of the coring section, including:

[0031] The first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C of the coring section are projected onto a plane using a Kriging interpolation method;

[0032] The lithology boundary is determined according to the actual lithology data of the coring section, and the lithology identification boundary line is determined according to the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C at the lithology boundary to establish a lithology prediction model.

[0033] Furthermore, the lithology prediction of the unidentified well section using the lithology prediction model includes:

[0034] Converting a plurality of logging parameters of the unidentified well section into corresponding first lithology model parameter A, second lithology model parameter B and third lithology model parameter C;

[0035] The first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C of the unidentified well section are input into the lithology prediction model to obtain a lithology prediction result.

[0036] Furthermore, the lithology that can be identified according to the lithology prediction model includes at least fine sandstone, siltstone, muddy siltstone, silty mudstone, mudstone and shale.

[0037] The present invention also provides a lithology prediction system, comprising:

[0038] A parameter calculation unit, used to calculate the time-frequency spectra of multiple logging parameters of the coring section, use the time-frequency spectra of various logging parameters as logging characterization parameters, and calculate the lithology model parameters using the logging characterization parameters;

[0039] A model building unit, used to build a lithology prediction model according to the correspondence between the lithology model parameters and the actual lithology of the coring well section;

[0040] The lithology prediction unit is used to perform lithology prediction on the unidentified well section using the lithology prediction model.

[0041] Based on the same inventive concept, the present invention also provides a computer storage medium, in which computer executable instructions are stored, and the computer executable instructions can implement the above-mentioned lithology prediction method when executed.

[0042] Technical effects and advantages of the present invention:

[0043] 1. Calculate the time-frequency spectrum of multiple logging parameters. The time-frequency spectrum data accurately reflects the instantaneous changes of logging parameters in time and frequency. The time-frequency spectrum of each logging parameter is used as the logging characterization parameter to improve the accuracy of lithology identification.

[0044] 2. The lithology prediction method provided by the present invention will not cause a decrease in recognition accuracy due to the different sensitivities of formation lithology in different regions to logging parameters;

[0045] 3. This lithology prediction method can quickly respond to formations with complex structures and large lithology variations, save drilling cycles, increase sampling rates, and reduce costs, providing a basis for optimizing drilling and completion plans.

[0046] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A schematic diagram of a process flow of a lithology prediction method provided by an embodiment of the present invention;

[0049] Figure 2 Schematic diagram of a fitting envelope curve in an embodiment of the present invention;

[0050] Figure 3 Schematic diagram of multiple regression of the first lithology model parameter A in an embodiment of the present invention;

[0051] Figure 4 Schematic diagram of multiple regression of the second lithology model parameter B in an embodiment of the present invention;

[0052] Figure 5 Schematic diagram of multiple regression of the third lithology model parameter C in the embodiment of the present invention;

[0053] Figure 6 is a schematic diagram of a lithology prediction model in an embodiment of the present invention;

[0054] Figure 7 A schematic diagram of a lithology prediction system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] To solve the deficiencies of the prior art, the present invention provides a lithology prediction method, such as Figure 1 As shown, the method comprises the following steps:

[0057] S1, calculating the time-frequency spectra of multiple logging parameters of the coring section, and using the time-frequency spectra of various logging parameters as logging characterization parameters;

[0058] S2, calculating lithology model parameters using the well logging characterization parameters;

[0059] S3, establishing a lithology prediction model according to the correspondence between the lithology model parameters and the actual lithology of the coring well section;

[0060] S4. Using the lithology prediction model to perform lithology prediction on the unidentified well section.

[0061] The core well is mainly used to drill underground cores for observation, identification, and analysis of experimental samples, so as to directly obtain information or parameters on the lithology, lithofacies, physical properties, oil-generating properties, oil-bearing properties, and other aspects of the formation. Well logging is the use of different logging methods to monitor the various physical parameters of the formation in real time, and the logging curve is used to reflect the changes in various physical properties of the reservoir with the depth of the wellbore. In the embodiment of the present invention, corresponding logging parameters are obtained based on multiple logging curves of known lithology formations in key wells with more coring, and the time-frequency spectrum of each logging parameter is calculated as a logging characterization parameter to characterize the characteristics of the logging curve. The linear combination of each logging characterization parameter obtained after multivariate regression is used as a lithology model parameter, and a lithology prediction model that uses model parameters to characterize the lithology is constructed based on the corresponding relationship between the lithology model parameters and the actual lithology of the coring section. The lithology prediction model can be used to predict the lithology of unidentified well sections. Since the time-frequency spectrum data accurately characterizes the instantaneous changes of logging parameters in time and frequency, the lithology identification accuracy is improved. The lithology prediction method provided according to the embodiment of the present invention can achieve high-precision and low-cost lithology prediction, providing a basis for optimizing drilling and completion plans.

[0062] In the embodiment of the present invention, corresponding logging parameters are obtained according to multiple logging curves of the coring section, including natural gamma GR logging curve, acoustic time difference AC logging curve, compensated neutron CNL logging curve, compensated density DEN logging curve, eight lateral conductivity CLL8 logging curve and deep induction conductivity CILD logging curve. Among them, the natural gamma GR logging curve reflects the change of the radiation intensity of the natural gamma ray of the rock formation along the well profile; the acoustic time difference AC logging curve is used to measure the acoustic characteristics of the rock formation, indicating the relationship between the acoustic wave velocity and the depth of the rock formation; the compensated neutron CNL logging curve reflects the porosity value of the rock formation under the condition of eliminating the influence of the wellbore and the formation; the compensated density DEN logging curve reflects the density value of the rock per unit volume, and the density value is measured by the radiation source emitting high-energy particles to the formation to bombard the atoms of the formation; the induction conductivity logging curve reflects the conductivity of the rock formation measured by the induction logging instrument.

[0063] Therefore, multiple logging parameters of the coring section are obtained, including natural gamma ray GR, acoustic time difference AC, compensated neutron CNL, compensated density DEN, eight lateral conductivity CLL8 and deep induction conductivity CILD.

[0064] According to a preferred embodiment, the time-frequency spectrum of each logging parameter is calculated using the HHT model. The HHT model is composed of empirical mode decomposition (EMD) and Hilbert transform. The original signal is decomposed into a series of intrinsic mode function (IMF) components by the EMD method, and then each IMF component is subjected to Hilbert transform processing to obtain the time-frequency relationship of each IMF component. The EMD method can stabilize the non-steady-state signal to obtain a series of signals of different time scales, that is, IMF components of different frequencies. The first IMF component represents the high-frequency part of the original data. As the decomposition deepens, the frequency of the IMF component becomes smaller and the period increases. The Hilbert transform is a time-frequency analysis method for non-steady-state signals, which takes the instantaneous frequency as the basic quantity and the intrinsic mode signal as the basic signal. The Hilbert spectrum is obtained after the IMF component is Hilbert transformed. The time-frequency distribution of the instantaneous frequency and instantaneous amplitude changes is obtained by performing Hilbert transform on each IMF component of the signal, and then the time-frequency spectrum of all IMF components is added to obtain the complete time-frequency spectrum of the original signal.

[0065] Specifically, the HHT model is used to calculate the time-frequency spectrum of any logging parameter, including the following steps:

[0066] Step 1, obtaining a data set s(t) of any logging parameter;

[0067] Step 2: Perform EMD decomposition on the data set s(t) to obtain the linear combination and residual of n IMF components;

[0068]

[0069] Among them, h i (t) is the i-th IMF component, p n (t) is the residual after n iterations;

[0070] Step 3, perform Hilbert transform on each IMF component to obtain the time-frequency spectrum of each IMF component;

[0071]

[0072] Among them, w i is the constant corresponding to the i-th IMF component;

[0073] Step 4: Add the time-frequency spectra of all IMF components to obtain the time-frequency spectra of the logging parameters.

[0074] Preferably, the step 2 described above of performing EMD decomposition on the data set s(t) specifically includes:

[0075] Step 20: Find all local extreme points from the data set s(t), such as Figure 2 As shown, the local maximum point is fitted into the upper envelope through the cubic spline logging curve, and the local minimum point is fitted into the lower envelope, and the average value a(t) of the upper envelope and the lower envelope is calculated. The envelope average value a(t) is subtracted from the data set s(t) to obtain the signal h(t) without low-frequency components, h(t) = s(t) - a(t);

[0076] Step 21, determine whether h(t) satisfies the IMF condition, that is, the number of extreme points is equal to the number of zero-crossing points or the difference is no more than one, and the average values ​​of the upper envelope and the lower envelope are zero;

[0077] If so, h(t) is taken as the first IMF component of s(t);

[0078] Otherwise, take h(t) as the data set and repeat step 20 until h1(t) satisfies the IMF condition;

[0079] Therefore, s(t) = h1(t) + p1(t);

[0080] Among them, h1(t) is the first IMF component of s(t), and p1(t) is the residual without high-frequency components;

[0081] Step 22: Using p1(t) as a data set, repeat steps 20 and 21 to obtain n IMF components, thereby decomposing s(t) into the sum of n IMF components and the residual.

[0082] Based on the above HHT model, the time-frequency spectrum I of natural gamma GR is calculated respectively. GR , time spectrum of acoustic time difference AC I AC , Time-frequency spectrum of compensated neutron CNL I CNL 、Time spectrum of compensation density DEN I DEN , time spectrum of the lateral conductivity CLL8 CLL8 , time-frequency spectrum of deep induced conductivity CILD CILD According to the embodiment of the present invention, the time-frequency spectrum data can characterize the instantaneous changes of the logging parameters in the time and frequency domains, and the time-frequency spectrum of each logging parameter is used as the characterization parameter of the corresponding logging curve, which is recorded as the logging characterization parameter. Therefore, the above I GR As the natural gamma logging characterization parameter, the above I AC As a characterization parameter of acoustic time difference logging, I CNL As a characterization parameter of compensated neutron logging, I DEN As a characterization parameter of compensated density logging, I CLL8 As the eight lateral conductivity logging characterization parameters, I CILD As a characterization parameter of deep induction conductivity logging.

[0083] Due to the phenomenon of cross-overlapping of logging values ​​of different lithologies, in the embodiment of the present invention, a suitable combination of logging characterization parameters is selected for multivariate regression, and several lithology model parameters are established as the basis for lithology discrimination of the coring section. During the multivariate regression calculation, some constants and natural logarithm operations are introduced to adjust the response amplitude of the logging characterization parameters, so that the cross-overlapping range of different lithologies is reduced, thereby distinguishing different lithologies.

[0084] Therefore, the method of calculating the lithology model parameters by using the logging characterization parameters includes: using the natural gamma logging characterization parameters I GR , Acoustic Time Difference Logging Characterization Parameters I AC , Compensated neutron logging characterization parameters I CNL , Compensated density logging characterization parameters I DEN , Eight Lateral Conductivity Logging Characterization Parameters I CLL8 and deep induction conductivity logging characterization parameters I CILD A multivariate regression calculation is performed to obtain a first lithology model parameter A, a second lithology model parameter B and a third lithology model parameter C of the coring well section.

[0085] See also Figure 3-Figure 5 , natural gamma logging characterization parameter I GR Used to determine the organic matter content, acoustic time difference logging characterization parameter I AC Used to correct the position of the sweet spot target, InI CNL is the compensated neutron logging characterization parameter I CNL The logarithm of I is usually used to predict pores and fractures in the case of irregular wellbore. GR ,I AC and InI CNL A ternary regression calculation is performed to obtain a first lithology model parameter A, which can indicate both the location of the sweet spot target in the actual well section and the level of organic matter content in the actual well section.

[0086] The expression of the first lithology model parameter A is:

[0087] A=b1I GR +b2I AC +lnI CNL +c1 formula (3)

[0088] Furthermore, the natural gamma logging characterization parameter I GR It is used to determine the organic matter content, and the eight lateral conductivity logging characterization parameters I CLL8 and deep induction conductivity logging characterization parameters I CILD , used to obtain the resistivity of different positions of the formation in imaging logging through dual induction logging, using I GR ,I CLL8 and ICILD Regression calculation is performed to obtain a second lithology model parameter B, which is used to characterize the degree to which mud flushing is controlled by the porosity and permeability of the rock when the same type of mud is used. The second lithology model parameter B is combined with the first lithology model parameter A to determine the formation lithology classification mode.

[0089] The expression of the second lithology model parameter B is:

[0090] B=b3 ln(I CLL8 +I CILD )+b4I GR +c2 formula (4)

[0091] Furthermore, the compensated density logging characterization parameter I DEN Characterizes the volume density of underground rocks and can be used to measure rock properties and porosity. CNL Used to predict pores and fractures in irregular wellbore conditions, using I DEN With InI CNL Correlation regression is performed to obtain a third lithology model parameter C, which is used to characterize the volume of fractures and pores that may be encountered in the actual well section and the enrichment of brittle minerals in the rock. The third lithology model parameter C is combined with the first lithology model parameter A and the second lithology model parameter B to refine the lithology type, thereby further distinguishing mudstone from shale.

[0092] The expression of the third lithology model parameter C is:

[0093] C=b5 lnI CNL +b6I DEN +c3 formula (5)

[0094] In the above formulas (3)-(5), b1-b6 and c1-c3 are all constants.

[0095] In an embodiment of the present invention, a lithology prediction model is established according to the correspondence between the first lithology model parameter A, the second lithology model parameter B, the third lithology model parameter C and the actual lithology of the coring section, specifically including: using the Kriging interpolation method to project the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C of the coring section onto a plane; determining the lithology boundary according to the actual lithology data of the coring section, and determining the lithology identification boundary line according to the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C at the lithology boundary, and establishing the lithology prediction model.

[0096] In the embodiment of the present invention, the Kriging model extrapolation method is used to predict unknown points. The principle of the Kriging model is to use the random variables of a random function at several known points in space to predict the random variables at unknown points in space. The application of the Kriging model in geology is mainly carried out through experimental variation functions. For different lag distances h, in γ * Mark each point (h,γ * (h)), connect the adjacent points with line segments in sequence to obtain the experimental variation function graph.

[0097] Experimental variogram γ * The expression of (h) is as follows:

[0098]

[0099] Among them, N(h) is the number of sample points, h is the lag distance, x i is the i sample data of the initial variable, Z(x i ) is x i The measured value of

[0100] Using the point pairs with a distance (x, y) on the two-dimensional grid plane, the above formula (6) is converted into:

[0101]

[0102] In the above formula (7), N is the number of point pairs (x, y); m,l ​​= 1, 2…, n.

[0103] According to an embodiment of the present invention, the point pairs with a distance of (x, y) and the number of point pairs N in the data set of any two lithology model parameters are input into formula (7) for calculation, and a variogram on a two-dimensional plane is obtained. This variogram is the prediction model of the two lithology model parameters. Then, the variogram is calculated for each pair with another lithology model parameter, and a prediction model based on the three lithology model parameters can be obtained.

[0104] For example, after calculating the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C according to the drilling and logging parameters of a certain section of a coring well (for example, the 3000-3001m section), the actual lithology data of the section is determined according to the core, core analysis data and cuttings logging data, and the model prediction is performed using the values ​​of the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C of the section, and the prediction is repeated according to the drilling and logging parameters of multiple sections of the coring well. At the same time, the lithology boundary is determined according to the actual lithology data of the coring section, and the lithology identification boundary line is determined by using the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C at different lithology boundaries to perform lithology division. For example, the model parameter values ​​at the well depth of lithology mutation and the well depth of interlayer (mudstone interlayer with sandstone interlayer or sandstone interlayer with mudstone interlayer) are used as the dividing points of different lithologies, and the prediction model is divided into multiple lithology identification areas, each of which represents a different lithology, and finally a lithology prediction model is obtained.

[0105] In the embodiment of the present invention, a prediction model using model parameters to characterize lithology is constructed based on the correlation between the first lithology model parameter A, the second lithology model parameter B, the third lithology model parameter C and the actual lithology of the well section. Preferably, Figure 6 As shown, the lithology prediction model is a triangular plane map, and the coordinate values ​​on the three side axes correspond to the values ​​of the three lithology model parameters, wherein the AC axis represents the value of the first lithology model parameter A, the AB axis represents the value of the second lithology model parameter B, and the CB axis represents the value of the third lithology model parameter C. The plane map is divided into identification areas of fine sandstone, siltstone, argillaceous siltstone, silty mudstone, mudstone and shale, wherein the boundary of each identification area is determined by the lithology model parameters at the actual lithology boundary in the coring section. The lithologies that can be identified according to the plane map include at least: fine sandstone, siltstone, argillaceous siltstone, silty mudstone, mudstone and shale.

[0106] Furthermore, the accuracy of the lithology prediction model can be verified based on the drilling data and logging data of adjacent coring wells. The three lithology model parameters are calculated using the logging data of a certain section of the adjacent coring wells. The obtained lithology model parameters are input into the lithology prediction model to obtain the lithology prediction results. The lithology prediction results are quantitatively compared with the coring results, and the consistency between the two is analyzed to verify the accuracy of the lithology prediction model.

[0107] In an embodiment of the present invention, when the lithology prediction model is used to predict the lithology of an unidentified well section, multiple logging parameters of the unidentified well section are converted into corresponding first lithology model parameters A, second lithology model parameters B and third lithology model parameters C, and then the first lithology model parameters A, second lithology model parameters B and third lithology model parameters C of the unidentified well section are input into the lithology prediction model to obtain the lithology prediction results.

[0108] Specifically, the logging parameters of the unidentified well section are obtained, including natural gamma GR, acoustic time difference AC, compensated neutron CNL, compensated density DEN, eight-way lateral conductivity CLL8 and deep induction conductivity CILD. The time-frequency spectrum of each logging parameter is calculated based on the above HHT model, and the time-frequency spectrum of each logging parameter is used as the logging characterization parameter. Then, the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C of the unidentified well section are calculated using the obtained logging characterization parameters, and the obtained lithology model parameters are put into the lithology prediction model. For example, the lithology model parameters are projected into the following example: Figure 6 On the plane map shown, the lithology of the unidentified well section is determined based on the lithology identification area of ​​the projected point.

[0109] The lithology prediction method provided by the embodiment of the present invention calculates the time-frequency spectrum of the logging parameters and uses the time-frequency spectrum of each logging parameter as the logging characterization parameter. The time-frequency spectrum data accurately reflects the instantaneous changes of the logging parameters in time and frequency, thereby improving the lithology identification accuracy. At the same time, the lithology prediction method will not cause a decrease in identification accuracy due to the different sensitivities of the lithology of formations in different regions to various logging parameters. It can quickly respond to formations with complex structures and large lithology changes, save drilling cycles, improve sampling rates, and reduce costs, thereby providing a basis for optimizing drilling and completion plans.

[0110] like Figure 7 As shown, the second embodiment of the present invention further provides a lithology prediction system, which includes:

[0111] A parameter calculation unit, used to calculate the time-frequency spectra of multiple logging parameters of the coring section, use the time-frequency spectra of various logging parameters as logging characterization parameters, and calculate the lithology model parameters using the logging characterization parameters;

[0112] A model building unit, used to build a lithology prediction model according to the correspondence between the lithology model parameters and the actual lithology of the coring well section;

[0113] The lithology prediction unit is used to perform lithology prediction on the unidentified well section using the lithology prediction model.

[0114] The lithology prediction system provided in an embodiment of the present invention can identify at least the following lithologies according to the lithology prediction model: fine sandstone, siltstone, muddy siltstone, silty mudstone, mudstone and shale, thereby achieving high-precision, high-sampling-rate and low-cost lithology prediction and providing a basis for optimizing drilling and completion plans.

[0115] Regarding the system in the above embodiment, the specific manner in which each unit module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0116] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can implement the aforementioned lithology prediction method when executed.

[0117] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0118] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional modules in the various embodiments of the present invention may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0119] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0120] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0121] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not used to limit the present invention. Although the present invention is described in detail with reference to the above embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the above embodiments, or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A lithology prediction method, characterized in that: The method comprises: Calculate the time-frequency spectra of multiple logging parameters of the coring section, and use the time-frequency spectra of various logging parameters as logging characterization parameters; Calculating lithology model parameters using the well logging characterization parameters; Establishing a lithology prediction model according to the correspondence between the lithology model parameters and the actual lithology of the coring well section; The lithology prediction model is used to predict the lithology of unidentified well sections.

2. The method according to claim 1, characterized in that: The multiple logging parameters of the coring section include natural gamma ray GR, acoustic time difference AC, compensated neutron CNL, compensated density DEN, eight lateral conductivity CLL8 and deep induction conductivity CILD.

3. The method according to claim 1, characterized in that Calculate the time-frequency spectrum of any logging parameter in the coring section, including: Get the data set s(t) of any logging parameter; Perform EMD decomposition on the data set s(t) to obtain a linear combination and residual of n IMF components; Among them, h i (t) is the i-th IMF component, p n (t) is the residual after n iterations; Perform Hilbert transform on each IMF component to obtain the time-frequency spectrum of each IMF component; Among them, w i (t) is the constant corresponding to the i-th IMF component; The time-frequency spectra of all IMF components are added together to obtain the time-frequency spectra of the logging parameters.

4. The method according to claim 2, characterized in that: The method of calculating the lithology model parameters by using the well logging characterization parameters comprises: Characterization of parameters using natural gamma logging GR , Acoustic Time Difference Logging Characterization Parameters I AC , Compensated neutron logging characterization parameters I CNL , Compensated density logging characterization parameters I DEN , Eight Lateral Conductivity Logging Characterization Parameters I CLL8 and deep induction conductivity logging characterization parameters I CILD A multivariate regression calculation is performed to obtain a first lithology model parameter A, a second lithology model parameter B and a third lithology model parameter C of the coring well section.

5. The method according to claim 4, characterized in that The first lithology model parameter A is used to characterize the rock organic matter content and the location of the sweet spot target; A=b1I GR +b2I AC +lnI CNL +c1 The second lithology model parameter B is used to characterize the degree to which mud flushing is controlled by the porosity and permeability of the rock when the same type of mud is used, wherein the second lithology model parameter B is combined with the first lithology model parameter A to determine the formation lithology classification mode; B=b3ln(I CLL8 +I CILD )+b4I GR +c2 The third lithology model parameter C is used to characterize the fracture and pore volume that may be encountered in the actual well section, wherein the third lithology model parameter C is combined with the first lithology model parameter A and the second lithology model parameter B to refine the lithology type; C=b5lnI CNL +b6I DEN +c3 Among them, b1-b6 and c1-c3 are constants.

6. The method according to claim 4, characterized in that The step of establishing a lithology prediction model based on the correspondence between the lithology model parameters and the actual lithology of the coring well section comprises: The first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C of the coring section are projected onto a plane using a Kriging interpolation method; The lithology boundary is determined according to the actual lithology data of the coring section, and the lithology identification boundary line is determined according to the first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C at the lithology boundary to establish a lithology prediction model.

7. The method according to claim 6, characterized in that The method of using the lithology prediction model to predict the lithology of the unidentified well section includes: Converting a plurality of logging parameters of the unidentified well section into corresponding first lithology model parameter A, second lithology model parameter B and third lithology model parameter C; The first lithology model parameter A, the second lithology model parameter B and the third lithology model parameter C of the unidentified well section are input into the lithology prediction model to obtain a lithology prediction result.

8. The method according to any one of claims 1 to 7, characterized in that: The lithologies that can be identified according to the lithology prediction model include at least fine sandstone, siltstone, muddy siltstone, silty mudstone, mudstone and shale.

9. A lithology prediction system, characterized in that: The system comprises: A parameter calculation unit, used to calculate the time-frequency spectra of multiple logging parameters of the coring section, use the time-frequency spectra of various logging parameters as logging characterization parameters, and calculate the lithology model parameters using the logging characterization parameters; A model building unit, used to build a lithology prediction model according to the correspondence between the lithology model parameters and the actual lithology of the coring well section; The lithology prediction unit is used to perform lithology prediction on the unidentified well section using the lithology prediction model.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed, the lithology prediction method according to any one of claims 1 to 8 is implemented.

Images