Complex lithology identification method and device, electronic equipment and storage medium

Abstract

The invention provides a complex lithology identification method and apparatus, an electronic device and a storage medium. The complex lithology identification method comprises the steps of selecting sensitive logging data corresponding to a to-be-identified target reservoir; wherein the sensitive logging data is used for representing the lithology of the target reservoir; classifying the sensitive logging data according to the correlation between the sensitive logging data and preset calibration logging data; and identifying the lithology of the target reservoir according to the calibration logging data, the correlation coefficient among the plurality of sensitive logging data and the classified sensitive logging data. According to the method, aiming at complex lithology, the identification models of different lithology are established by analyzing the logging response rules and differences of different lithology, so that the lithology identification accuracy is improved.

Description

Technical Field

[0001] The present application belongs to the field of oil and natural gas exploration technology, in particular to the field of oil and gas geological research and geophysical logging technology, and specifically to a method and device for identifying complex lithology. Background Art

[0002] It is understandable that lithology identification is the basis of reservoir description, real-time drilling monitoring, reservoir parameter solution and reservoir evaluation. In the existing technology, there are roughly three types of methods for identifying reservoir lithology:

[0003] (1) Core sampling is carried out through drilling, and core observation and core analysis are performed to determine the lithology and mineral composition. This method is intuitive and effective in identifying lithology. However, its disadvantages are that the cost of coring is high and the coring section is very limited.

[0004] (2) Rock cuttings logging can be used to identify lithology, but rock cuttings logging generally describes lithology every 1 or 2 meters, and the description is not precise and has deviations. At the same time, there is a certain lag in identifying lithology, and the accuracy of identification is greatly affected by the quality of logging data.

[0005] (3) Using electrical imaging logging data to identify lithology. Electrical imaging logging can image the downhole formation and identify the lithology. However, imaging logging is expensive, data is limited, and core calibration of the imaging logging map is required before manual identification of the lithology. In other words, imaging logging to identify lithology is expensive, time-consuming, labor-intensive, and unintelligent.

[0006] The above three methods are only effective for lithology identification of conventional reservoirs. When the object is a reservoir with complex lithology, the identification accuracy drops significantly. Therefore, how to quickly and accurately identify the lithology of a reservoir with complex lithology is an urgent problem to be solved. Summary of the Invention

[0007] One object of the present invention is to provide a method for identifying complex lithologies. The method analyzes the logging response patterns and differences of different lithologies to establish identification models for different lithologies, thereby improving the accuracy of lithology identification.

[0008] Another object of the present invention is to provide a device for identifying complex lithology. Another object of the present invention is to provide an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for identifying complex lithology are implemented. Another object of the present invention is to provide a readable medium storing the computer program, and when the processor executes the computer program, the steps of the above-mentioned method for identifying complex lithology are implemented.

[0009] In order to solve the technical problems in the background technology of this application, the present invention provides the following technical solutions:

[0010] In a first aspect, the present invention provides a method for identifying complex lithology, comprising:

[0011] Selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir;

[0012] Classifying the sensitive well logging data according to the correlation between the sensitive well logging data and preset calibration well logging data;

[0013] The lithology of the target reservoir is identified based on the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data.

[0014] In some embodiments of the present invention, selecting sensitive logging data corresponding to the target reservoir to be identified includes:

[0015] Determine the lithology of the target reservoir core and a plurality of conventional well logging data;

[0016] The sensitive logging data is preferably selected from the plurality of conventional logging data according to the lithology and the plurality of conventional logging data.

[0017] In some embodiments of the present invention, the calibration logging data is lithologic logging data; the lithologic logging data is natural gamma ray logging data, natural potential logging data, and caliper logging data.

[0018] In some embodiments of the present invention, classifying the sensitive logging data according to the correlation between the sensitive logging data and preset calibration logging data includes:

[0019] If the correlation between the sensitive well logging data and the calibrated well logging data is positive, classifying the sensitive well logging data into the first type of well logging data;

[0020] If the correlation between the sensitive well logging data and the calibrated well logging data is negative, the sensitive well logging data is classified as the second type of well logging data.

[0021] In some embodiments of the present invention, identifying the lithology of the target reservoir based on the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data includes:

[0022] constructing a first sub-model for lithology identification based on the first type of well logging data;

[0023] constructing a second sub-model for lithologic identification based on the second type of well logging data;

[0024] Constructing a lithology identification model according to the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model; wherein the first lithology identification sub-model and the second lithology identification sub-model play different roles in the lithology identification model;

[0025] The lithology of the target reservoir is identified according to the lithology identification model.

[0026] In some embodiments of the present invention, constructing a lithology identification model according to the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model includes:

[0027] Determine the first weight and the second weight of the first lithology identification sub-model and the second lithology identification sub-model in the lithology identification model respectively according to the correlation coefficient;

[0028] The lithology identification model is constructed according to the calibrated logging data, the first weight, the second weight, the first lithology identification sub-model, and the second lithology identification sub-model.

[0029] In some embodiments of the present invention, before classifying the sensitive well logging data according to the correlation between the sensitive well logging data and the preset calibration well logging data, the method further includes:

[0030] The sensitive logging data is normalized.

[0031] In a second aspect, the present invention provides a device for identifying complex lithology, the device comprising:

[0032] A sensitive logging data selection module is used to select sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir;

[0033] A sensitive well logging data classification module, configured to classify the sensitive well logging data according to a correlation between the sensitive well logging data and preset calibration well logging data;

[0034] The target reservoir lithology identification module is used to identify the lithology of the target reservoir based on the calibration logging data, the correlation coefficients among the multiple sensitive logging data, and the classified sensitive logging data.

[0035] In some embodiments of the present invention, the sensitive logging data selection module includes:

[0036] a lithology and conventional logging data determining unit, configured to determine the lithology of the core of the target reservoir and a plurality of conventional logging data;

[0037] The sensitive logging data selection unit is configured to select the sensitive logging data from the plurality of conventional logging data based on the lithology and the plurality of conventional logging data.

[0038] In some embodiments of the present invention, the calibration logging data is lithologic logging data; the lithologic logging data is natural gamma ray logging data, natural potential logging data, and caliper logging data.

[0039] In some embodiments of the present invention, the sensitive logging data classification module includes:

[0040] a first sensitive logging data classification unit, configured to classify the sensitive logging data into a first type of logging data if the correlation between the sensitive logging data and the calibration logging data is positively correlated;

[0041] The second sensitive logging data classification unit is configured to classify the sensitive logging data into the second type of logging data if the correlation between the sensitive logging data and the calibration logging data is negatively correlated.

[0042] In some embodiments of the present invention, the target reservoir lithology identification module includes:

[0043] A first sub-model building unit, configured to build a first sub-model for lithology identification based on the first type of well logging data;

[0044] A second sub-model construction unit is used to construct a second sub-model for lithology identification based on the second type of well logging data;

[0045] a lithology identification model construction unit, configured to construct a lithology identification model based on the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model; wherein the first lithology identification sub-model and the second lithology identification sub-model play different roles in the lithology identification model;

[0046] The target reservoir lithology identification unit is used to identify the lithology of the target reservoir according to the lithology identification model.

[0047] In some embodiments of the present invention, the lithology identification model building unit includes:

[0048] a weight determination unit, configured to determine a first weight and a second weight of the first lithology identification sub-model and the second lithology identification sub-model in the lithology identification model respectively according to the correlation coefficient;

[0049] The lithology identification model construction subunit is used to construct the lithology identification model according to the calibrated logging data, the first weight, the second weight, the first lithology identification submodel and the second lithology identification submodel.

[0050] In some embodiments of the present invention, a device for identifying complex lithology further includes:

[0051] The sensitive logging data normalization module is used to normalize the sensitive logging data.

[0052] In a third aspect, the present invention provides a computer program product comprising a computer program / instruction, which implements the steps of a method for identifying complex lithology when executed by a processor.

[0053] In a fourth aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a method for identifying complex lithology when executing the program.

[0054] In a fifth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of a method for identifying complex lithology when executed by a processor.

[0055] As can be seen from the above description, an embodiment of the present invention provides a method and device for identifying complex lithology. The corresponding complex lithology identification method includes: first, selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir; then, classifying the sensitive logging data based on the correlation between the sensitive logging data and preset calibration logging data; finally, identifying the lithology of the target reservoir based on the calibration logging data, the correlation coefficient between multiple sensitive logging data, and the classified sensitive logging data. Specifically, the present invention has the following beneficial effects:

[0056] (1) By combining core data with well logging, the advantages of conventional well logging data, such as large amount of information, easy processing, continuous data and systematic distribution, are utilized to solve the disadvantages of high coring cost and vertical discontinuity.

[0057] (2) By establishing a lithology identification model based on multiple logging curves, the influence of a single factor is eliminated, which can more comprehensively reflect the lithology information of the formation and help improve the accuracy of lithology identification.

[0058] (3) By combining core analysis data with logging data, multiple methods for identifying lithologic characteristics are combined, and the complementary information of multiple technologies is used to reflect the lithologic characteristics of the formation, it is beneficial to improve the accuracy of the lithologic identification results. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 A schematic flow chart of a method for identifying complex lithology in an embodiment of the present invention;

[0061] Figure 2 This is a flow chart of step 100 of a method for identifying complex lithology in an embodiment of the present invention;

[0062] Figure 3 This is a flow chart of step 200 of a complex lithology identification method according to an embodiment of the present invention;

[0063] Figure 4 This is a flow chart of step 300 of a complex lithology identification method according to an embodiment of the present invention;

[0064] Figure 5 This is a flow chart of step 303 of a complex lithology identification method in an embodiment of the present invention;

[0065] Figure 6 Another schematic flow chart of a complex lithology identification method according to an embodiment of the present invention;

[0066] Figure 7 This is a schematic flow chart of a method for identifying complex lithology in a first embodiment of the present invention;

[0067] Figure 8 1 is a relationship diagram of different lithologic logging curves (CNL-AC) in the first embodiment of the present invention;

[0068] Figure 9 GR-AC is a relationship diagram of different lithologic logging curves in the first embodiment of the present invention;

[0069] Figure 10 1 is a relationship diagram (RT-AC) of different lithologic logging curves in the first embodiment of the present invention;

[0070] Figure 11 This is a relationship diagram of different lithologic logging curves (DEN-AC) in the first embodiment of the present invention;

[0071] Figure 12 1 is a correlation diagram (CNL-GR) between two sensitive logging curves in the first embodiment of the present invention;

[0072] Figure 13 This is a correlation diagram (DEN-GR) between two sensitive logging curves in the first embodiment of the present invention;

[0073] Figure 14 This is a correlation diagram (DEN-CNL) between two sensitive logging curves in the first embodiment of the present invention;

[0074] Figure 15 Schematic diagram of the lithology identification model in the first embodiment of the present invention;

[0075] Figure 16 It is a relationship diagram (AC-GA) of different lithologic logging curves in the second specific embodiment of the present invention;

[0076] Figure 17 It is a relationship diagram of different lithologic logging curves (CNL-GA) in the second specific embodiment of the present invention;

[0077] Figure 18 This is a relationship diagram of different lithologic logging curves (DEN-GA) in the second embodiment of the present invention;

[0078] Figure 19 It is a relationship diagram (RT-GA) of different lithologic logging curves in the second specific embodiment of the present invention;

[0079] Figure 20 1 is a correlation diagram (AC-GR) between two sensitive logging curves in the second embodiment of the present invention;

[0080] Figure 21 1 is a correlation diagram (RT-GR) between two sensitive logging curves in the second embodiment of the present invention;

[0081] Figure 22 1 is a correlation diagram (RT-AC) between two sensitive logging curves in the second embodiment of the present invention;

[0082] Figure 23 This is a schematic diagram of the lithology identification model in the second specific embodiment of the present invention;

[0083] Figure 24 is a block diagram of a complex lithology identification device in an embodiment of the present invention;

[0084] Figure 25 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0086] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices. The embodiments in this application and the features described in the embodiments may be combined with each other unless there is a conflict. The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0088] The acquisition, storage, use, and processing of data in the technical solution of this application comply with relevant laws and regulations.

[0089] In existing technologies, complex lithology identification is a complex and diverse process. Using a single technology or method to identify lithology often presents challenges. In recent years, research has shifted from a single approach to a multi-technique approach. By combining core data with well logging, conventional logging data offers advantages such as high information volume, ease of processing, and continuous and systematic data distribution, addressing the high cost and vertical discontinuity of coring. Leveraging the complementary information from multiple technologies to reflect formation lithology characteristics improves the accuracy of lithology identification results.

[0090] Example 1:

[0091] Based on the above reasons, the embodiment of the present invention provides a specific implementation method of a complex lithology identification method, see Figure 1 , specifically including the following contents:

[0092] Step 100: Selecting sensitive well logging data corresponding to a target reservoir to be identified; wherein the sensitive well logging data is used to characterize the lithology of the target reservoir;

[0093] Step 200: classifying the sensitive logging data according to the correlation between the sensitive logging data and preset calibration logging data;

[0094] Step 300: Identify the lithology of the target reservoir based on the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data.

[0095] From the above description, it can be seen that an embodiment of the present invention provides a method for identifying complex lithology, including: first, selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir; then, classifying the sensitive logging data according to the correlation between the sensitive logging data and preset calibration logging data; finally, identifying the lithology of the target reservoir based on the calibration logging data, the correlation coefficient between multiple sensitive logging data, and the classified sensitive logging data.

[0096] The present invention establishes identification models of different lithologies by analyzing the logging response laws and differences of different lithologies, thereby improving the accuracy of lithology identification.

[0097] Example 2:

[0098] Regarding step 100 , it should be noted that for different lithologies, the corresponding sensitive logging data may be different, so it is necessary to optimize the sensitive logging data.

[0099] Regarding step 200, the correlation relationship here is that the sensitive well logging data and the preset calibration well logging data are positively correlated, and the sensitive well logging data and the preset calibration well logging data are negatively correlated. Furthermore, the positive correlation relationship means that as the sensitive well logging data increases, the preset calibration well logging data also increases. Correspondingly, the negative correlation relationship means that as the sensitive well logging data increases, the preset calibration well logging data decreases.

[0100] For step 300, based on the principle of data separation, a lithology identification model is constructed by calibrating the logging data, the correlation coefficients among multiple sensitive logging data, and the classified sensitive logging data. The lithology identification model is used to calculate the calibration value of the lithology of the target reservoir, and the lithology of the target reservoir is determined based on the calibration value.

[0101] In some embodiments of the present invention, see Figure 2 , step 100 includes:

[0102] Step 101: Determine the lithology of the core of the target reservoir and a plurality of conventional well logging data;

[0103] Preferably, the conventional logging data in step 101 includes 3 lithologic logging curves, 3 physical logging curves, and 3 electrical (oil content) logging curves, specifically:

[0104] 3 Lithologic logging curves include: natural gamma logging curve, caliper logging curve and natural potential logging curve.

[0105] Natural gamma ray log (GR):

[0106] Purpose: Natural gamma ray logging is a method of identifying and evaluating formation lithology by measuring the natural gamma rays emitted by formation rocks. These rays mainly come from radioactive elements in the rocks, such as potassium, uranium, and thorium.

[0107] Applications: Gamma-ray logging is often used to identify strata with high shale and clay mineral content, as these strata typically have high levels of natural radioactivity. By comparing changes in gamma-ray intensity, sedimentary environments, lithologic changes, and stratigraphic correlation can be distinguished.

[0108] Caliper Log:

[0109] Purpose: Caliper logging is a method of identifying the condition of a wellbore wall by measuring the diameter of the wellbore. It typically uses one or more spring devices or other mechanical devices to measure the distance between the wellbore wall and the logging instrument.

[0110] Applications: Caliper measurements reveal the stability of the wellbore wall, as well as the size and shape of the wellbore. This is crucial for assessing drilling problems (such as wellbore collapse and hole enlargement) and designing appropriate sealing operations. Caliper logging can also be used to identify lithology, fractures, cavities, and other geological anomalies.

[0111] Spontaneous potential logging curve (SP):

[0112] Purpose: Spontaneous potential logging records the natural potential difference between the formation and the drilling fluid. This potential difference is related to the formation lithology (especially conventional reservoirs (sand and mudstone reservoirs)), water conductivity (salinity), capillary effect, and other factors.

[0113] Application: SP logging is often used to identify permeable and impermeable strata, particularly the boundaries between aquifers and hydrocarbon reservoirs. The spontaneous potential curve typically exhibits distinct "fluctuations," and their shape and amplitude can be used to identify the lithology of the formation.

[0114] 3 Physical property logging curves include: neutron logging curve, density logging curve and sonic time difference logging curve.

[0115] Neutron Log:

[0116] Principle: Neutron logging involves firing high-speed neutrons into the formation and detecting the number of neutrons that are slowed down after colliding with atomic nuclei in the formation. Since water and hydrocarbons contain a large amount of hydrogen atoms, they can effectively slow down neutrons.

[0117] Applications: Neutron logging is primarily used to assess formation porosity. Because hydrogen atoms have the most significant effect on neutron slowing, neutron logging is particularly sensitive to changes in water saturation and hydrocarbon saturation. Neutron logging readings will be low in very dry rock, while high in formations containing water or hydrocarbons.

[0118] Density Log:

[0119] Principle: Density logging uses a gamma-ray source to emit gamma rays into the formation and measures the degree of scattering and absorption of the gamma rays in the formation. This data can be used to calculate the electron density of the formation and, in turn, the bulk density of the formation.

[0120] Applications: Density logs are commonly used to assess formation porosity and rock type. Rocks that are more porous or contain fluids typically have lower density log readings, while denser rocks, such as limestone or dolomite, typically have higher readings. Density logs can also help identify a rock's mineral composition.

[0121] Sonic Log:

[0122] Principle: Time-of-day logging evaluates the acoustic properties of rocks by measuring the time (time difference) required for sound waves (sonar pulses) to pass through a certain distance of formation.

[0123] Applications: Acoustic transit time logging is commonly used to assess formation porosity and rock elastic properties. In highly porous formations, acoustic wave propagation is typically slow, resulting in larger transit time values. In dense rock, acoustic wave propagation is faster, resulting in smaller transit time values. Furthermore, transit time data can be used to assess formation pressure and calibrate seismic data.

[0124] These three types of logs are often used in combination because they can verify and complement each other. For example, porosity assessment often combines data from neutron logs and density logs.

[0125] 3. Electrical (oil content) logging curves include: Deep Lateral Resistivity Log, Shallow Lateral Resistivity Log, and Microspherically Focused Resistivity Log (MSFL)

[0126] Deep lateral resistivity curve:

[0127] Principle: Deep lateral resistivity logging detects the electrical properties of formations far from the wellbore by transmitting current into the formation and measuring the resistivity at a certain depth.

[0128] Applications: Due to its high penetration capability, deep lateroresistivity logging can provide information on formation resistivity far from the wellbore. This is particularly important for assessing the true resistivity of the formation (without interference from wellbore effects) and identifying hydrocarbon zones. Higher resistivity generally indicates greater oil and gas saturation, as hydrocarbons are highly resistive.

[0129] Shallow lateral resistivity curve:

[0130] Principle: Similar to deep lateral logging, shallow lateral resistivity logging also obtains resistivity data by emitting current and measuring formation response, but its detection depth is shallower and mainly focuses on the formation near the wellbore.

[0131] Application: Shallow lateral resistivity logging is commonly used to evaluate formation electrical properties near the wellbore. It is particularly useful in assessing the formation's intrusion zone. The intrusion zone is the area around the wellbore where drilling fluid invasion has altered the original formation fluid saturation. Shallow lateral resistivity can reveal how this intrusion effect has affected the formation's electrical properties.

[0132] Microsphere resistivity curve:

[0133] Principle: Microsphere resistivity logging is a method specifically designed to measure the resistivity of formations near the wellbore where the effects of intrusion are minimal. MSFL achieves this through a concentrated current source and a dedicated measurement device.

[0134] Applications: MSFL provides resistivity information in formations near the wellbore, unaffected by drilling fluids. This type of log is often used to identify and assess the continuity of thin hydrocarbon zones and their formations. In wells with complex formation intrusion characteristics, MSFL data can be used to estimate true formation resistivity, enabling more accurate assessment of hydrocarbon saturation.

[0135] These three resistivity logging technologies can complement each other, providing formation electrical information from near the wellbore to far away from the wellbore, helping to comprehensively evaluate the properties of oil and gas reservoirs.

[0136] Step 102: Select the sensitive logging data from the plurality of conventional logging data based on the lithology and the plurality of conventional logging data.

[0137] Specifically, a logging response relationship identification chart for different lithologies is established, and sensitive logging data sensitive to different lithologies are selected based on the logging response relationship identification chart for different lithologies.

[0138] In some embodiments of the present invention, the calibration logging data is lithologic logging data; the lithologic logging data is natural gamma ray logging data, natural potential logging data, and caliper logging data.

[0139] In some embodiments of the present invention, see Figure 3 , step 200 includes:

[0140] Step 201: If the correlation between the sensitive well logging data and the calibrated well logging data is positive, classify the sensitive well logging data into the first type of well logging data;

[0141] Step 202: If the correlation between the sensitive well logging data and the calibrated well logging data is negative, classify the sensitive well logging data into the second type of well logging data.

[0142] For step 201 and step 202, the logging response characteristics and response differences of different lithologies are analyzed, and the cross-plots are identified based on the logging response relationships of different lithologies to obtain the following:

[0143] 1) The logging responses of different lithologies have their own response ranges. Although there is some overlap, the response ranges are clearly distinguished.

[0144] 2) The logging response relationship of different lithologies is obvious. The correlation between the logging curves of different lithologies and the calibration logging data is found. Based on the principle of data separation, if the sensitive logging curve is positively correlated with the calibration logging data, that is, the logging curve values ​​of different lithologies increase with the increase of calibration logging data, then the sensitive logging curve is classified as the first type of logging data; if the sensitive logging curve is negatively correlated with the calibration logging data, that is, the logging curve values ​​of different lithologies decrease with the increase of calibration logging data, then the sensitive logging curve is classified as the second type of logging data.

[0145] In some embodiments of the present invention, see Figure 4 , step 300 includes:

[0146] Step 301: constructing a first sub-model for lithology identification based on the first type of well logging data;

[0147] Here we take the calibration logging data as the natural gamma logging curve as an example, refer to formula (1), if the sensitive logging curve (sensitive logging data) Xx It is positively correlated with the natural gamma ray GR, that is, the logging curve value X of different lithologies x As the natural gamma increases, X x归一 As a molecule.

[0148]

[0149] Step 302: constructing a second sub-model for lithology identification based on the second type of well logging data;

[0150] Similar to step 301, if the sensitive logging curve X y It is inversely proportional to the natural gamma ray GR, that is, the logging curve value X of different lithologies y As the natural gamma increases, it decreases, so X y归一 As the denominator, x, y∈1, 2, ..., i. Note: The normalization in formula (1) refers to the result after normalizing the logging curve.

[0151] Step 303: constructing a lithology identification model based on the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model; wherein the first lithology identification sub-model and the second lithology identification sub-model play different roles in the lithology identification model;

[0152] Referring to formula (2), here we still take the calibration logging data as a natural gamma log curve as an example. The correlation coefficient in step 303 is used to determine A, B, and C in formula (2), that is, the weights of the calibration logging data, the first lithology identification sub-model, and the second lithology identification sub-model in the lithology identification model. It should be pointed out that, regardless of formula (1) or formula (2), the first lithology identification sub-model and the second lithology identification sub-model are located in different positions, one in the numerator and the other in the denominator. Therefore, the first lithology identification sub-model and the second lithology identification sub-model play different roles in the lithology identification model, which is also the reason for classifying sensitive logging data.

[0153]

[0154] Step 304: Identify the lithology of the target reservoir according to the lithology identification model.

[0155] In some embodiments of the present invention, see Figure 5 , step 303 includes:

[0156] Step 3031: determining the first weight and the second weight of the first lithology identification sub-model and the second lithology identification sub-model in the lithology identification model respectively according to the correlation coefficient;

[0157] Step 3032: Construct the lithology identification model according to the calibrated logging data, the first weight, the second weight, the first lithology identification sub-model, and the second lithology identification sub-model.

[0158] Specifically, find the relationship between sensitive logging data and obtain the correlation coefficient R1 2 、R2 2 …R n 2 , calculate sensitive logging data X i The average value of the corresponding correlation coefficients is calculated to find its proportion of R1 2 、R2 2 …R n 2 The corresponding proportion is used as the coefficient of the sub-model to establish the lithologic parameter Lith, that is, formula (3):

[0159]

[0160] Among them, X x归一 is the normalized value of sensitive logging data that is positively correlated with natural gamma ray GR, X y归一 is the normalized value of sensitive logging data that is inversely correlated with natural gamma ray GR.

[0161] In some embodiments of the present invention, see Figure 6 A complex lithology identification method further includes, before step 200:

[0162] Step 400: Normalize the sensitive logging data.

[0163] It is understood that the normalization in step 400 is used to make the logging data from different logging wells or different wellbores comparable. Since different logging equipment, different operating conditions, and different formation conditions may produce inconsistent logging curves, the normalization process can help identify formation characteristics and compare logging data between different wellbores. The main steps of normalization include:

[0164] Data cleaning: First, the data must be cleaned to remove any outliers or erroneous measurements to ensure data quality for subsequent processing.

[0165] Calibration correction: If possible, use the calibration information of the formation calibration well or logging instrument to correct the logging data to ensure that the measurement results between different equipment are comparable.

[0166] Baseline Correction: Determine the baseline of each well log curve and correct the curve so that all data are referenced to the same benchmark point or range.

[0167] Scaling: Adjusting the scale of a well log so that data from different wells are comparable over the same range. This may involve stretching or compressing the data range to match the scale of a reference well log.

[0168] Normalization: Normalize the data so that it falls within a uniform numerical range, such as 0 to 1 or -1 to 1. Common methods include minimum-maximum normalization and Z-score normalization (mean is 0 and standard deviation is 1).

[0169] Cross-plotting: After data normalization, different well logs can be plotted on the same graph for comparison, thereby identifying similarities and differences.

[0170] From the above description, it can be seen that an embodiment of the present invention provides a method for identifying complex lithology, including: first, selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir; then, classifying the sensitive logging data according to the correlation between the sensitive logging data and preset calibration logging data; finally, identifying the lithology of the target reservoir based on the calibration logging data, the correlation coefficient between multiple sensitive logging data, and the classified sensitive logging data.

[0171] The present invention establishes identification models of different lithologies by analyzing the logging response laws and differences of different lithologies, thereby improving the accuracy of lithology identification.

[0172] Example 3:

[0173] In a specific embodiment, the present invention also provides a specific embodiment of a method for identifying complex lithology by taking the Jialingjiang Formation in the Sichuan Basin as an example, see Figure 7 , specifically including the following steps. Specific implementation method one:

[0175] Step S1: calibrate conventional logging curve data based on core analysis data to find logging data that is sensitive to different lithologies.

[0176] Specifically, the lithology is determined using core analysis data, which is calibrated to the corresponding conventional logging profile. The conventional logging response data of different lithologies are statistically calculated, and the sensitive logging data of different lithologies are found. The conventional logging response data include: natural gamma ray (GR), acoustic transit time (AC), compensated density (DEN), compensated neutron (CNL) and resistivity (RT). A logging response relationship identification chart for different lithologies is established. Based on the logging response relationship identification chart for different lithologies, conventional logging data sensitive to different lithologies are selected.

[0177] Core analysis of the Jialingjiang Formation in the Sichuan Basin reveals that the lithology of the Jialingjiang Formation is primarily limestone, dolomite, gypsum, and mudstone. Calibrated to corresponding conventional logging profiles, the conventional logging response data for each lithology was statistically analyzed, along with sensitive logging data for each lithology, including natural gamma ray (GR), compensated density (DEN), and compensated neutron (CNL).

[0178] Step S2: normalize the sensitive logging curves.

[0179] Specifically, see formula (4):

[0180]

[0181] Among them, X i归一 is the normalized value of sensitive logging data, X i is the sensitive logging curve value; X i max is the maximum value of the sensitive logging curve in the processed well section; i is 1, 2,…, n, and n is the number of sensitive parameter curves.

[0182] Normalize the logging data with different lithologic sensitivity: get the lithologic parameter value GR for each depth section 归一、 DEN 归一 、CNL 归一 .

[0183] Step S3: Analyze the logging response patterns and differences of different lithologies to find the correlation between sensitive logging curves and natural gamma ray (GR).

[0184] The logging response characteristics and response differences of different lithologies are analyzed. According to the identification cross-plot of the logging response relationship of different lithologies, we can find that: 1) The logging responses of different lithologies have their own response ranges. Although there is some overlap, the response ranges are clearly distinguished. Figures 8 to 11 ) The logging response relationship of different lithologies is obvious. Find the correlation between the logging curves of different lithologies and natural gamma. Based on the principle of data separation, if the sensitive logging curve X x It is positively correlated with the natural gamma ray GR, that is, the logging curve value X of different lithologies x As the natural gamma increases, X x归一 As a numerator, if the sensitive logging curve X y It is inversely proportional to the natural gamma ray GR, that is, the logging curve value X of different lithologies y As the natural gamma increases, it decreases, so X y归一 As the denominator, x, y∈1,2,…,i, see Figures 12 to 14 .

[0185] Step S4: Based on the data separation principle, a lithology identification quantitative model Lith is established. The Lith value intervals of different lithologies are distributed differently, thereby quantitatively identifying the lithology.

[0186] Find the relationship between the two sensitive logging curves and get the correlation coefficient R1 2 、R2 2 …R n 2 , calculate the sensitive logging curve X i The average value of the corresponding correlation coefficients is calculated to find its proportion of R1 2 、R2 2 …R n 2 The corresponding proportion is used as the coefficient of the model to establish the lithology quantitative model Lith.

[0187] First, the conventional logging curve data is calibrated according to the core analysis data, and the logging data sensitive to different lithologies are found. The logging response patterns and differences of different lithologies are analyzed. Combined with the principle of data separation, if the sensitive curve is positively correlated with the natural gamma GR, it is used as the numerator. If the sensitive curve is negatively correlated with the natural gamma GR, it is used as the denominator. The relationship between the two sensitive logging curves is found, and the correlation coefficient R1 is obtained. 2 、R2 2 …R n 2 , and then calculate the sensitive logging curve X i The average value of the corresponding correlation coefficients is calculated to find its proportion of R1 2 、R2 2 …R n 2 The corresponding proportion is used as the coefficient of the model to establish the lithology quantitative model Lith.

[0188] Specifically, find the relationship between the natural gamma ray GR, compensated density DEN, and compensated neutron CN logging curves, and obtain the correlation coefficient R1 2 、R2 2 、R3 2 , where R1 2 =0.7664, R2 2 =0.8804, R3 2 =0.9045, R1 2 +R2 2 +R3 2 =2.5513, calculate the average value of the correlation coefficients corresponding to the natural gamma GR and get 0.8234, which accounts for R1 2 、R2 2 、R3 2The proportion of the sum is 0.32274, and the average value of the correlation coefficients corresponding to the compensation density DEN is calculated to be 0.89245, which accounts for R1 2 、R2 2 、R3 2 The proportion of the sum is 0.3498, and the correlation coefficients corresponding to the compensated neutron CNL are added to get 0.83545, which accounts for R1 2 、R2 2 、R3 2 The proportion of the sum is 0.32746, and the corresponding proportion is used as the coefficient of the model to establish the lithology quantitative model Lith( Figure 15 ),Right now

[0189]

[0190] Figure 15 It can be seen that each lithology has its own corresponding Lith value range, among which the Lith value of limestone is (0.04663, 0.07256), the Lith value of dolomite is (0.01369, 0.04663), the Lith value of gypsum is (0.01251, 0.01369), and the Lith value of mudstone is greater than 0.07256. At the same time, the lithology quantitatively identified by logging is very consistent with the results of core thin section analysis, which can effectively identify and divide the reservoir lithology. Specific implementation method 2:

[0192] Core analysis data from this layer indicates that the Yanchang Formation in the Ordos Basin is primarily composed of sandstone, siltstone, argillaceous sandstone, sandy mudstone, mudstone, and organic mudstone. Calibrated to corresponding conventional logging profiles, the conventional logging response data for each lithology was statistically analyzed, along with sensitive logging data for each lithology, including gamma ray (GR), acoustic transit time (AC), and resistivity (RT).

[0193] Normalize the logging data with different lithologic sensitivity: get the lithologic parameter value GR for each depth section 归一、 AC 归一 , RT 归一 .

[0194] The logging response characteristics and response differences of different lithologies are analyzed. According to the identification cross-plot of the logging response relationship of different lithologies, it is found that: 1) The logging responses of different lithologies have their own response intervals. Although there is some overlap, the response intervals are clearly distinguished ( Figures 16 to 19 ) ; 2) The resistivity RT is positively correlated with the natural gamma GR, that is, the resistivity RT of different lithologies increases with the increase of the natural gamma GR. 10 RT 归一As the numerator, the acoustic time difference AC is inversely proportional to the natural gamma GR, that is, the acoustic time difference AC of different lithologies decreases with the increase of natural gamma GR. 归一 As the denominator ( Figures 20 to 22 ).

[0195] Find the relationship between the natural gamma ray GR, resistivity RT, and acoustic time difference AC logging curves, and get the correlation coefficient R1 2 、R2 2 、R3 2 , where R1 2 =0.9283, R2 2 =0.6259, R3 2 =0.6412, R1 2 +R2 2 +R3 2 =2.1954, calculate the average value of the correlation coefficients corresponding to the natural gamma GR and get 0.7771, which accounts for R1 2 、R2 2 、R3 2 The proportion of the sum is 0.35397, and the average value of the correlation coefficients corresponding to the resistivity RT is 0.63355, which accounts for R1 2 、R2 2 、R3 2 The proportion of the sum is 0.28858, and the correlation coefficients corresponding to the acoustic time difference AC are added to get 0.78475, which accounts for R1 2 、R2 2 、R3 2 The proportion of the sum is 0.35745, and the corresponding proportion is used as the coefficient of the model to establish the lithology quantitative model Lith( Figure 23 ),Right now

[0196]

[0197] Figure 23 It can be seen that each lithology has its own corresponding Lith value range, among which the Lith value of sandstone is (0.60, 0.90), the Lith value of siltstone is (0.50, 0.60), the Lith value of muddy sandstone is (0.40, 0.50), the Lith value of sandy mudstone is (0.30, 0.40), the Lith value of mudstone is (0.20, 0.30), and the Lith value of organic mudstone is less than 0.20. At the same time, the lithology quantitatively identified by well logging is very consistent with the results of core thin section analysis, which can effectively identify and divide the reservoir lithology.

[0198] The specific embodiment of the present invention provides a method for quantitative identification of complex lithology logging. It includes: (1) calibrating conventional logging curve data based on core analysis data to find logging data that is sensitive to different lithologies; (2) normalizing the sensitive logging curves; (3) analyzing the logging response patterns and differences of different lithologies to find the correlation between sensitive logging curves and natural gamma ray (GR); (4) finding the relationship between the two sensitive logging curves to obtain the correlation coefficient R1 2 、R2 2 …R n 2 Then calculate the average value of the correlation coefficients corresponding to the sensitive logging curves and calculate its proportion of R1 2 、R2 2 …R n 2 The corresponding weight is used as the coefficient of the model to establish a quantitative model for lithology identification. Using conventional logging data and core analysis data to characterize lithology greatly reduces costs and improves the accuracy of quantitative lithology identification.

[0199] Example 4:

[0200] Based on the same inventive concept, the embodiments of the present application also provide a device for identifying complex lithology, which can be used to implement the methods described in the above embodiments, such as the following embodiments. Since the principle of solving the problem by the device for identifying complex lithology is similar to that of the method for identifying complex lithology, the implementation of the device for identifying complex lithology can refer to the implementation of the method for identifying complex lithology, and the repeated parts will not be repeated. As used below, the terms "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceived.

[0201] The embodiment of the present invention provides a specific implementation of a complex lithology identification device capable of implementing a complex lithology identification method, see Figure 24 , a complex lithology identification device includes:

[0202] The sensitive logging data selection module 10 is used to select sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir;

[0203] A sensitive well logging data classification module 20 is configured to classify the sensitive well logging data according to the correlation between the sensitive well logging data and preset calibration well logging data;

[0204] The target reservoir lithology identification module 30 is used to identify the lithology of the target reservoir based on the calibration logging data, the correlation coefficients among the multiple sensitive logging data, and the classified sensitive logging data.

[0205] In some embodiments of the present invention, the sensitive logging data selection module includes:

[0206] a lithology and conventional logging data determining unit, configured to determine the lithology of the core of the target reservoir and a plurality of conventional logging data;

[0207] The sensitive logging data selection unit is configured to select the sensitive logging data from the plurality of conventional logging data based on the lithology and the plurality of conventional logging data.

[0208] In some embodiments of the present invention, the calibration logging data is lithologic logging data; the lithologic logging data is natural gamma ray logging data, natural potential logging data, and caliper logging data.

[0209] In some embodiments of the present invention, the sensitive logging data classification module includes:

[0210] a first sensitive logging data classification unit, configured to classify the sensitive logging data into a first type of logging data if the correlation between the sensitive logging data and the calibration logging data is positively correlated;

[0211] The second sensitive logging data classification unit is configured to classify the sensitive logging data into the second type of logging data if the correlation between the sensitive logging data and the calibration logging data is negatively correlated.

[0212] In some embodiments of the present invention, the target reservoir lithology identification module includes:

[0213] A first sub-model building unit, configured to build a first sub-model for lithology identification based on the first type of well logging data;

[0214] A second sub-model construction unit is used to construct a second sub-model for lithology identification based on the second type of well logging data;

[0215] a lithology identification model construction unit, configured to construct a lithology identification model based on the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model; wherein the first lithology identification sub-model and the second lithology identification sub-model play different roles in the lithology identification model;

[0216] The target reservoir lithology identification unit is used to identify the lithology of the target reservoir according to the lithology identification model.

[0217] In some embodiments of the present invention, the lithology identification model building unit includes:

[0218] a weight determination unit, configured to determine a first weight and a second weight of the first lithology identification sub-model and the second lithology identification sub-model in the lithology identification model respectively according to the correlation coefficient;

[0219] The lithology identification model construction subunit is used to construct the lithology identification model according to the calibrated logging data, the first weight, the second weight, the first lithology identification submodel and the second lithology identification submodel.

[0220] In some embodiments of the present invention, a device for identifying complex lithology further includes:

[0221] The sensitive logging data normalization module is used to normalize the sensitive logging data.

[0222] As can be seen from the above description, an embodiment of the present invention provides a complex lithology identification device, including: a sensitive logging data selection module for selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir; a sensitive logging data classification module for classifying the sensitive logging data based on the correlation between the sensitive logging data and preset calibration logging data; and a target reservoir lithology identification module for identifying the lithology of the target reservoir based on the calibration logging data, the correlation coefficient between multiple sensitive logging data, and the classified sensitive logging data. Specifically, the present invention has the following beneficial effects:

[0223] (1) By combining core data with well logging, the advantages of conventional well logging data, such as large amount of information, easy processing, continuous data and systematic distribution, are utilized to solve the disadvantages of high coring cost and vertical discontinuity.

[0224] (2) By establishing a lithology identification model based on multiple logging curves, the influence of a single factor is eliminated, which can more comprehensively reflect the lithology information of the formation and help improve the accuracy of lithology identification.

[0225] (3) By combining core analysis data with logging data, multiple methods for identifying lithologic characteristics are combined, and the complementary information of multiple technologies is used to reflect the lithologic characteristics of the formation, it is beneficial to improve the accuracy of the lithologic identification results.

[0226] Embodiment 5:

[0227] The embodiment of the present application also provides a specific implementation of an electronic device capable of implementing all steps of a complex lithology identification method in the above embodiment, see Figure 25 , electronic equipment specifically includes the following:

[0228] Processor 1201, memory 1202, communications interface 1203, and bus 1204;

[0229] The processor 1201, the memory 1202, and the communication interface 1203 communicate with each other via the bus 1204; the communication interface 1203 is used to implement information transmission between the server device and the client device and other related devices;

[0230] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, all steps of the complex lithology identification method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0231] Selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir;

[0232] Classifying the sensitive well logging data according to the correlation between the sensitive well logging data and preset calibration well logging data;

[0233] The lithology of the target reservoir is identified based on the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data.

[0234] In some embodiments of the present invention, selecting sensitive logging data corresponding to the target reservoir to be identified includes:

[0235] Determine the lithology of the target reservoir core and a plurality of conventional well logging data;

[0236] The sensitive logging data is preferably selected from the plurality of conventional logging data according to the lithology and the plurality of conventional logging data.

[0237] In some embodiments of the present invention, the calibration logging data is lithologic logging data; the lithologic logging data is natural gamma ray logging data, natural potential logging data, and caliper logging data.

[0238] In some embodiments of the present invention, classifying the sensitive logging data according to the correlation between the sensitive logging data and preset calibration logging data includes:

[0239] If the correlation between the sensitive well logging data and the calibrated well logging data is positive, classifying the sensitive well logging data into the first type of well logging data;

[0240] If the correlation between the sensitive well logging data and the calibrated well logging data is negative, the sensitive well logging data is classified as the second type of well logging data.

[0241] In some embodiments of the present invention, identifying the lithology of the target reservoir based on the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data includes:

[0242] constructing a first sub-model for lithology identification based on the first type of well logging data;

[0243] constructing a second sub-model for lithologic identification based on the second type of well logging data;

[0244] Constructing a lithology identification model according to the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model; wherein the first lithology identification sub-model and the second lithology identification sub-model play different roles in the lithology identification model;

[0245] The lithology of the target reservoir is identified according to the lithology identification model.

[0246] In some embodiments of the present invention, constructing a lithology identification model according to the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model includes:

[0247] Determine the first weight and the second weight of the first lithology identification sub-model and the second lithology identification sub-model in the lithology identification model respectively according to the correlation coefficient;

[0248] The lithology identification model is constructed according to the calibrated logging data, the first weight, the second weight, the first lithology identification sub-model, and the second lithology identification sub-model.

[0249] In some embodiments of the present invention, before classifying the sensitive well logging data according to the correlation between the sensitive well logging data and the preset calibration well logging data, the method further includes:

[0250] The sensitive logging data is normalized.

[0251] Example 6:

[0252] The present application also provides a computer-readable storage medium capable of implementing all steps of the complex lithology identification method in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all steps of the complex lithology identification method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0253] Selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir;

[0254] Classifying the sensitive well logging data according to the correlation between the sensitive well logging data and preset calibration well logging data;

[0255] The lithology of the target reservoir is identified based on the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data.

[0256] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the hardware + program embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0257] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0258] Although the present application provides method operation steps such as embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative work. The order of steps listed in the embodiments is only one way of executing the steps among many steps and does not represent the only execution order. When an actual device or client product is executed, it can be executed in the order shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0259] For the convenience of description, the above devices are described in terms of functions divided into various modules. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0260] Those skilled in the art will also appreciate that, in addition to implementing the controller in pure computer-readable program code, it is entirely possible to implement the same functionality by logically programming the method steps in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, and the like. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered structures within the hardware component. Alternatively, the devices for implementing various functions can be considered both software modules implementing the method and structures within the hardware component.

[0261] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0262] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0263] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between the various embodiments can be referenced across them. Each embodiment focuses on the differences from the other embodiments. In particular, since the system embodiments are generally similar to the method embodiments, their description is relatively simple. For relevant parts, reference can be made to the description of the method embodiments. Throughout this specification, reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the embodiments in this specification. In this specification, the schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and integrate the different embodiments or examples, and features of different embodiments or examples, described in this specification, without conflict.

[0264] The above description is merely an example of the embodiments of this specification and is not intended to limit the embodiments of this specification. For those skilled in the art, various modifications and variations of the embodiments of this specification are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A method for identifying complex lithology, characterized in that: include: Selecting sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir; Classifying the sensitive well logging data according to the correlation between the sensitive well logging data and preset calibration well logging data; The lithology of the target reservoir is identified based on the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data.

2. The method for identifying complex lithology according to claim 1, characterized in that: The step of selecting sensitive logging data corresponding to the target reservoir to be identified includes: Determine the lithology of the target reservoir core and a plurality of conventional well logging data; The sensitive logging data is preferably selected from the plurality of conventional logging data according to the lithology and the plurality of conventional logging data.

3. The method for identifying complex lithology according to claim 1, characterized in that: The calibration logging data is lithologic logging data; the lithologic logging data is natural gamma ray logging data, natural potential logging data and caliper logging data.

4. The method for identifying complex lithology according to any one of claims 1 to 3, characterized in that: Classifying the sensitive logging data according to the correlation between the sensitive logging data and preset calibration logging data includes: If the correlation between the sensitive well logging data and the calibrated well logging data is positive, classifying the sensitive well logging data into the first type of well logging data; If the correlation between the sensitive well logging data and the calibrated well logging data is negative, the sensitive well logging data is classified as the second type of well logging data.

5. The method for identifying complex lithology according to claim 4, characterized in that: The identifying the lithology of the target reservoir according to the calibration logging data, the correlation coefficients among the plurality of sensitive logging data, and the classified sensitive logging data includes: constructing a first sub-model for lithology identification based on the first type of well logging data; constructing a second sub-model for lithologic identification based on the second type of well logging data; Constructing a lithology identification model according to the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model; wherein the first lithology identification sub-model and the second lithology identification sub-model play different roles in the lithology identification model; The lithology of the target reservoir is identified according to the lithology identification model.

6. The method for identifying complex lithology according to claim 5, characterized in that: Constructing a lithology identification model according to the calibrated logging data, the correlation coefficient, the first lithology identification sub-model, and the second lithology identification sub-model includes: Determine the first weight and the second weight of the first lithology identification sub-model and the second lithology identification sub-model in the lithology identification model respectively according to the correlation coefficient; The lithology identification model is constructed according to the calibrated logging data, the first weight, the second weight, the first lithology identification sub-model, and the second lithology identification sub-model.

7. The method for identifying complex lithology according to claim 1, characterized in that: Before classifying the sensitive well logging data according to the correlation between the sensitive well logging data and the preset calibration well logging data, the method further includes: The sensitive logging data is normalized.

8. A device for identifying complex lithology, characterized in that: include: A sensitive logging data selection module is used to select sensitive logging data corresponding to the target reservoir to be identified; wherein the sensitive logging data is used to characterize the lithology of the target reservoir; A sensitive well logging data classification module, configured to classify the sensitive well logging data according to a correlation between the sensitive well logging data and preset calibration well logging data; The target reservoir lithology identification module is used to identify the lithology of the target reservoir based on the calibration logging data, the correlation coefficients among the multiple sensitive logging data, and the classified sensitive logging data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the complex lithology identification method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying complex lithology according to any one of claims 1 to 7 are implemented.

Images