Lithofacies identification method, apparatus and device, and storage medium

Abstract

The invention discloses a lithofacies recognition method, device and equipment and a storage medium, and relates to the field of physical logging, and the method comprises the steps: determining lithofacies combination features and target probability distribution features according to lithofacies types, and analyzing the heterogeneous features of a target lithofacies structure through the lithofacies combination features; obtaining a target layer section logging curve, processing the target layer section logging curve to obtain a processed target layer section logging curve, and determining a target logging curve based on the processed target layer section logging curve and the lithofacies type; determining a first depth value and a second depth value to obtain a third depth value, and determining a target weight value by using the third depth value to obtain target layer data; establishing model training data based on the target layer data, training the initial lithofacies identification model by using the model training data to obtain a model prediction result, comparing the model prediction result with the target probability distribution characteristics and the target lithofacies structure heterogeneous characteristics, determining a target lithofacies identification model, and identifying the lithofacies by using the target lithofacies identification model. And identification of the complex lithofacies is realized.

Description

Technical Field

[0001] The present invention relates to the field of physical well logging, and in particular to a lithofacies identification method, device, equipment and storage medium. Background Art

[0002] Geophysical logging interpretation mainly interprets the characteristics of the formation through various logging instrument measurements, such as natural gamma, acoustic time difference, neutron density, resistivity, etc., to determine important parameters such as lithology, lithofacies, physical properties, and oil and gas content. At present, there are two main methods for geophysical logging lithofacies interpretation: one is conventional logging interpretation, which mainly relies on core observation and thin section analysis combined with logging qualitative and quantitative methods under the guidance of sedimentary models to carry out lithofacies interpretation. Most of these methods rely on the knowledge and experience of interpreters, and the interpretation progress is relatively slow and the accuracy is low; the second is logging lithofacies interpretation based on artificial intelligence algorithms, which mainly uses supervised, unsupervised or semi-supervised methods to carry out lithofacies intelligent interpretation. Although this method has been widely used in logging interpretation, most methods only consider the relationship between sample labels and logging response characteristics, lack the constraints of geological concepts or geological laws, and do not find the intrinsic connection between geological laws and artificial intelligence algorithms, making machine learning methods only a mathematical algorithm and lacking mechanistic understanding.

[0003] In summary, how to combine intelligent algorithms to identify complex lithofacies is a problem that needs to be solved urgently. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a lithofacies identification method, device, equipment and storage medium, which can be combined with intelligent algorithms to identify complex lithofacies. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a lithofacies identification method, comprising:

[0006] Obtaining the lithofacies type corresponding to the coring section based on the acquired core description data of the coring well, determining the lithofacies combination characteristics corresponding to the coring section according to the acquired lithofacies type corresponding to the coring section, determining the target probability distribution characteristics of the lithofacies in the vertical direction according to the lithofacies type corresponding to the coring section, and analyzing the heterogeneous characteristics of the target lithofacies structure using the lithofacies combination characteristics;

[0007] Acquire a target layer logging curve, perform normalization processing on the target layer logging curve to obtain a processed target layer logging curve, and then determine a target logging curve based on the processed target layer logging curve and lithofacies type;

[0008] Determine a first depth value of a target peak point and a second depth value of a target valley point corresponding to the target logging curve, obtain a third depth value of a target half-width point based on the first depth value and the second depth value, determine a corresponding target weight value using the third depth value of the target half-width point, and obtain target layer data between the target half-width points according to the target weight value;

[0009] Model training data is established based on the target layer data between the target half-width points, and the initial lithofacies identification model is trained using the model training data to obtain a model prediction result. The predicted probability distribution characteristics in the obtained model prediction result are compared with the target probability distribution characteristics, and the predicted lithofacies structure heterogeneity characteristics in the obtained model prediction result are compared with the target lithofacies structure heterogeneity characteristics. The target lithofacies identification model is determined based on the obtained comparison results, so as to complete lithofacies identification using the target lithofacies identification model.

[0010] Optionally, obtaining the lithofacies type corresponding to the coring section based on the acquired core description data of the coring well includes:

[0011] The lithology and bedding type of the coring section are determined based on the obtained core description data of the coring well, and the lithofacies type corresponding to the coring section is obtained according to the obtained lithology and bedding type of the coring section.

[0012] Optionally, determining the target probability distribution characteristics of the vertical lithofacies according to the lithofacies type corresponding to the coring section includes:

[0013] A preset number of coring segment data are obtained, corresponding lithofacies types and the number of lithofacies types are determined according to the corresponding coring segments, and target probability distribution characteristics of the vertical lithofacies are determined based on the preset number and the number of lithofacies types.

[0014] Optionally, the analyzing the heterogeneous characteristics of the target lithofacies structure by using the lithofacies combination characteristics includes:

[0015] The lithofacies density and lithofacies frequency in the lithofacies combination characteristics corresponding to the coring section are counted, and the heterogeneous characteristics of the target lithofacies structure are analyzed based on the lithofacies density and the lithofacies frequency.

[0016] Optionally, normalizing the target layer interval well logging curve to obtain a processed target layer interval well logging curve includes:

[0017] A numerical value satisfying a preset maximum value condition and a numerical value satisfying a preset minimum value condition in a target layer segment logging curve are obtained, and the target layer segment logging curve is normalized based on the numerical value satisfying the preset maximum value condition and the numerical value satisfying the preset minimum value condition to obtain a processed target layer segment logging curve.

[0018] Optionally, determining a target logging curve based on the processed target layer interval logging curve and lithofacies type includes:

[0019] The Pearson correlation coefficient analysis is used to perform sensitivity analysis between the coring section logging curve in the processed target layer logging curve and the lithofacies type and sensitivity analysis between the logging curves of each processed target layer to obtain the target logging curve.

[0020] Optionally, obtaining the target layer data between the target half-width points according to the target weight value includes:

[0021] The curve data between the target half-width points is determined according to the target weight value, and the target layer data between the target half-width points is determined based on the curve data between the target half-width points.

[0022] Optionally, establishing model training data based on the obtained target layer data between the target half-width points includes:

[0023] The target layer data between the target half-width points are used to determine data that meets the preset minimum sample layer unit, depth slice unit data is obtained by splicing the data that meets the preset minimum sample layer unit, and the average depth value of the depth slice unit data is determined to obtain model training data containing vertical information.

[0024] Optionally, the using the model training data to train the initial lithofacies identification model to obtain a model prediction result includes:

[0025] Based on the model training data, a current training set and a current validation set are determined, the target probability distribution characteristics and the current training set are input into the initial lithofacies identification model for iterative updating to obtain an iterative lithofacies identification model, and the depth slice data to be predicted is input into the iterative lithofacies identification model to obtain a model prediction result.

[0026] In a second aspect, the present application provides a lithofacies identification device, comprising:

[0027] A feature analysis module is used to obtain the lithofacies type corresponding to the coring section based on the obtained core description data of the coring well, determine the lithofacies combination characteristics corresponding to the coring section according to the acquired lithofacies type corresponding to the coring section, determine the target probability distribution characteristics of the lithofacies in the vertical direction according to the lithofacies type corresponding to the coring section, and analyze the heterogeneous characteristics of the target lithofacies structure using the lithofacies combination characteristics;

[0028] A well logging curve determination module is used to obtain a target layer interval well logging curve, normalize the target layer interval well logging curve to obtain a processed target layer interval well logging curve, and then determine the target well logging curve based on the processed target layer interval well logging curve and the lithofacies type;

[0029] A data acquisition module is used to determine a first depth value of a target peak point and a second depth value of a target valley point corresponding to the target logging curve, obtain a third depth value of a target half-width point based on the first depth value and the second depth value, determine a corresponding target weight value using the third depth value of the target half-width point, and obtain target layer data between the target half-width points according to the target weight value;

[0030] A lithofacies identification completion module is used to establish model training data based on the target layer data between the target half-width points, use the model training data to train the initial lithofacies identification model to obtain a model prediction result, compare the predicted probability distribution characteristics in the obtained model prediction result with the target probability distribution characteristics, and compare the predicted lithofacies structure heterogeneity characteristics in the obtained model prediction result with the target lithofacies structure heterogeneity characteristics, determine the target lithofacies identification model according to the obtained comparison results, so as to complete lithofacies identification using the target lithofacies identification model.

[0031] In a third aspect, the present application provides an electronic device, including:

[0032] Memory, used to store computer programs;

[0033] A processor is used to execute the computer program to implement the aforementioned lithofacies identification method.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the lithology identification method as described above is implemented.

[0035] In summary, the present application first obtains the lithofacies type corresponding to the coring section based on the acquired core description data of the coring well, determines the lithofacies combination characteristics corresponding to the coring section according to the acquired lithofacies type corresponding to the coring section, determines the target probability distribution characteristics of the lithofacies in the vertical direction according to the lithofacies type corresponding to the coring section, and uses the lithofacies combination characteristics to analyze the heterogeneous characteristics of the target lithofacies structure; obtains the target layer segment logging curve, normalizes the target layer segment logging curve to obtain the processed target layer segment logging curve, and then determines the target logging curve based on the processed target layer segment logging curve and the lithofacies type; determines the first depth value of the target peak point and the second depth value of the target valley point corresponding to the target logging curve, and based on the first depth value and the second depth value Obtain the third depth value of the target half-width point, determine the corresponding target weight value using the third depth value of the target half-width point, and obtain the target layer data between the target half-width points according to the target weight value; establish model training data based on the target layer data between the target half-width points, use the model training data to train the initial lithofacies recognition model to obtain model prediction results, compare the predicted probability distribution characteristics in the obtained model prediction results with the target probability distribution characteristics, and compare the predicted lithofacies structure heterogeneity characteristics in the obtained model prediction results with the target lithofacies structure heterogeneity characteristics, and determine the target lithofacies recognition model according to the obtained comparison results, so as to complete lithofacies recognition using the target lithofacies recognition model. As can be seen from the above, the present application first obtains the core description data of the coring well, and determines the lithofacies type corresponding to the coring section based on this. Based on the lithofacies type, further clarify the lithofacies combination characteristics corresponding to the coring section, and determine the target probability distribution characteristics of the vertical lithofacies, and then use the lithofacies combination characteristics to analyze the target lithofacies structure heterogeneity characteristics. Subsequently, the target layer logging curve is obtained and normalized to obtain the processed target layer logging curve. The target logging curve is determined based on the processed logging curve and the lithofacies type. The first depth value of the target peak point and the second depth value of the target valley point in the target logging curve are determined, and the third depth value of the target half-width point is obtained based on these two depth values. The corresponding target weight value is determined using the third depth value, and then the target layer data between the target half-width points is obtained according to the target weight value. Afterwards, model training data is established based on the obtained target layer data, and the initial lithofacies identification model is trained using the model training data to obtain the model prediction results. The predicted probability distribution characteristics in the model prediction results are compared with the previously determined target probability distribution characteristics, and the predicted lithofacies structure heterogeneity characteristics are also compared with the target lithofacies structure heterogeneity characteristics. Finally, the target lithofacies identification model is determined based on these comparison results, so that the target lithofacies identification model can be used to complete the lithofacies identification work in the future.In this way, according to the vertical development probability characteristics of different lithofacies in a single-layer lithofacies combination, the heterogeneous characteristics of the lithofacies structure and the corresponding logging response characteristics, the lithofacies slices of the vertical depth sequence are used in combination with the deep learning model for adaptive and detailed interpretation of the lithofacies. This can improve the interpretation accuracy of complex lithofacies and add the vertical development laws of the lithofacies, laying a good foundation for further sedimentary geological interpretation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] Figure 1 A flow chart of a lithofacies identification method disclosed in this application;

[0038] Figure 2 A target probability distribution characteristic statistical diagram of a previous lithofacies of a current lithofacies disclosed in this application;

[0039] Figure 3 A target probability distribution characteristic statistical diagram of the next lithofacies of a current lithofacies disclosed in this application;

[0040] Figure 4 A statistical diagram of the heterogeneous characteristics of lithofacies structure regarding lithofacies density disclosed in the present application;

[0041] Figure 5 A statistical diagram of the heterogeneous characteristics of lithofacies structure regarding lithofacies frequency disclosed in the present application;

[0042] Figure 6 A schematic diagram of sensitivity analysis between a coring section logging curve and lithofacies type disclosed in the present application;

[0043] Figure 7 A schematic diagram of sensitivity analysis between a coring section logging curve and a logging curve disclosed in the present application;

[0044] Figure 8 A schematic diagram of establishing a sample layer database based on a well logging curve disclosed in the present application;

[0045] Fig. 9 A schematic diagram of establishing a petrographic label library based on depth slices disclosed in the present application;

[0046] Fig.10 A schematic diagram of a bidirectional long short-term memory neural network model training disclosed in this application;

[0047] Fig.11 A schematic diagram of a single well lithofacies identification result disclosed in this application;

[0048] Fig.12 A flow chart of a specific lithofacies identification method disclosed in this application;

[0049] Fig.13 This is a schematic diagram of the structure of a lithofacies identification device disclosed in this application;

[0050] Fig.14 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0051] 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.

[0052] At present, there are two main methods for geophysical logging lithofacies interpretation: one is conventional logging interpretation method, which mainly relies on core observation and thin section analysis combined with logging qualitative and quantitative methods under the guidance of sedimentary models to carry out lithofacies interpretation. Most of these methods rely on the knowledge and experience of interpreters, and the interpretation progress is relatively slow and the accuracy is low; the second is logging lithofacies interpretation based on artificial intelligence algorithms, which mainly uses supervised, unsupervised or semi-supervised methods to carry out lithofacies intelligent interpretation. Although this method has been widely used in logging interpretation, most methods only consider the relationship between sample labels and logging response characteristics, lack the constraints of geological concepts or geological laws, and do not find the intrinsic connection between geological laws and artificial intelligence algorithms, so that machine learning methods are only a mathematical algorithm and lack mechanistic understanding. In order to solve the above technical problems, the present application discloses a lithofacies identification method, device, equipment and storage medium, which can be combined with intelligent algorithms to identify complex lithofacies.

[0053] See also Figure 1 As shown, the embodiment of the present invention discloses a lithofacies identification method, comprising:

[0054] Step S11, based on the acquired core description data of the coring well, obtain the lithofacies type corresponding to the coring section, determine the lithofacies combination characteristics corresponding to the coring section according to the acquired lithofacies type corresponding to the coring section, determine the target probability distribution characteristics of the lithofacies in the vertical direction according to the lithofacies type corresponding to the coring section, and use the lithofacies combination characteristics to analyze the heterogeneous characteristics of the target lithofacies structure.

[0055] In this embodiment, it is first necessary to determine the lithology and bedding type of the coring section based on the obtained core description data of the coring well, and obtain the lithofacies type corresponding to the coring section according to the obtained lithology and bedding type of the coring section. Specifically, the lithology and bedding type of the coring section is determined based on the core description data of the coring well in the study area, and the lithofacies type of the coring section as shown in Table 1 is further determined based on the determined lithology and bedding type of the coring section. For example, a specific lithofacies type code is obtained based on the lithology and bedding type, and then the lithofacies combination characteristics are summarized according to the different lithofacies types in the vertical direction inside the single-layer continuous coring section.

[0056] Table 1 #timg#

[0057] Furthermore, it is necessary to obtain a preset number of coring segment data, determine the corresponding lithofacies type and the number of lithofacies types according to the corresponding coring segment, and determine the target probability distribution characteristics of the vertical lithofacies based on the preset number and the number of lithofacies types. Specifically, the heat map is used to display the target probability distribution characteristics of the development of a certain lithofacies above and below the current lithofacies in the vertical direction, and the analysis is as follows: Figure 2 The target probability distribution characteristics of the previous lithofacies of the current lithofacies and the Figure 3 The next target lithofacies probability distribution characteristics of the current lithofacies are shown.

[0058] In a specific implementation, assuming that there are M single-layer coring segment data, a specific lithofacies is selected as the research object, and the target probability distribution characteristics of lithofacies development are statistically analyzed. The vertical lithofacies distribution of a single layer can be expressed as , n is the total number of lithofacies in a single-layer coring section, and the lithofacies type can be expressed as , assuming that any lithofacies type The number of occurrences in M ​​lithofacies combinations is N, and T is any lithofacies. The number of adjacent lithofacies above and below, then any lithofacies The probability P of this particular lithofacies appearing above and below is:

[0059] ;

[0060] Among them, P is the probability of a specific lithofacies; M is the number of coring data; N is the number of times any lithofacies type appears in the M lithofacies combination; T is the number of a specific lithofacies adjacent to any lithofacies.

[0061] Next, it is necessary to count the lithofacies density and lithofacies frequency in the lithofacies combination characteristics corresponding to the coring section, and analyze the heterogeneous characteristics of the target lithofacies structure based on the lithofacies density and lithofacies frequency. Figure 4 The lithofacies density shown, Figure 5The lithofacies frequency shown in the figure quantitatively analyzes the heterogeneous characteristics of the target lithofacies structure. Among them, lithofacies density is the thickness of a single lithofacies or a single layer; lithofacies frequency is the number of occurrences of a certain type of lithofacies within a single lithofacies combination.

[0062] Step S12, obtaining a target layer logging curve, normalizing the target layer logging curve to obtain a processed target layer logging curve, and then determining a target logging curve based on the processed target layer logging curve and the lithofacies type.

[0063] In this embodiment, it is first necessary to obtain the numerical value that meets the preset maximum value condition and the numerical value that meets the preset minimum value condition in the target layer segment logging curve, and perform normalization processing on the target layer segment logging curve based on the numerical value that meets the preset maximum value condition and the numerical value that meets the preset minimum value condition to obtain the processed target layer segment logging curve. Specifically, the target layer segment logging curve can be first extracted, and the target layer segment logging curve of each well can be standardized to unify the scale, and then the maximum value and minimum value of the logging curves of different target layer segments are respectively obtained, and the min-max normalization method is used according to the maximum value and minimum value of the logging curve of the target layer segment to realize the normalization processing of different curves, so that the response values ​​contained in the logging curve of each target layer segment are mapped to between [0-1], and the processed target layer segment logging curve is obtained.

[0064] Then, the Pearson correlation coefficient analysis is used to perform sensitivity analysis between the core section logging curve and the lithofacies type in the processed target layer logging curve and the sensitivity analysis between the logging curves of each processed target layer to obtain the target logging curve. Specifically, the Pearson correlation coefficient analysis is used to perform the following operations: Figure 6 The sensitivity analysis between the coring section logging curve and lithofacies type is shown in Figure 2. Figure 7 The sensitivity analysis between the coring section logging curve and the logging curve shown above shows that the logging curve with a high correlation coefficient with the lithofacies and a low correlation coefficient with each other is preferred as the target logging curve for model training. It should be understood that GR (Gamma Ray), AC (Acoustic Time), LLD (Laterolog-Deep) and PE (Photoelectric Absorption Index) can be selected as logging sensitive parameters, and the logging curves corresponding to these logging sensitive parameters can be obtained as target logging curves.

[0065] Step S13, determine the first depth value of the target peak point and the second depth value of the target valley point corresponding to the target logging curve, obtain the third depth value of the target half-width point based on the first depth value and the second depth value, use the third depth value of the target half-width point to determine the corresponding target weight value, and obtain the target layer data between the target half-width points according to the target weight value.

[0066] In this embodiment, after determining the target logging curve, the value of the logging curve is firstly derived using the natural logarithm function to obtain a point where the slope of the curve is positive, that is, , the slope of the curve is negative, that is , if the curve changes from rising to falling, the trend of its derivative changes from positive to negative, which is determined as the target peak point; if the curve changes from falling to rising, the trend of its derivative changes from negative to positive, which is determined as the target valley point. Figure 8 As shown, the local peak-to-valley value is determined by comparing the sizes of adjacent data points. Next, the first depth value of the target peak value and the second depth value of the target valley value are counted, and the average value between the target peak value and the target valley value is used as the depth value of the target half-width point.

[0067] Furthermore, after obtaining the depth value of the target half-width point, the curve data between the target half-width points is determined according to the target weight value, and the target layer data between the target half-width points is determined based on the curve data between the target half-width points. Specifically, the distance between the peak point within the range of two target half-width points and any depth point within the range is used as a weight parameter, and the weight value w is calculated using the inverse distance weighting method. i :

[0068] ;

[0069] in, Represents the weight value of any depth point i between the half-width points; It represents the depth value of any depth point i between the half-width points; H represents the peak point depth value between the half-width points.

[0070] Adjust the weights of different depths, and use the following formula to calculate the curve data between the target half-width points by weighted average to obtain the corresponding weighted average, that is, the target layer data between the target half-width points:

[0071] ;

[0072] in Represents the weighted average curve value of the layer data between the half-width points; Represents the weight value of any depth point i between the half-width points; Represents the curve value of any depth point i between the half-width points; n is the number of depth points.

[0073] Step S14, establishing model training data based on the target layer data between the target half-width points, using the model training data to train the initial lithofacies identification model to obtain a model prediction result, comparing the predicted probability distribution characteristics in the obtained model prediction result with the target probability distribution characteristics, and comparing the predicted lithofacies structure heterogeneity characteristics in the obtained model prediction result with the target lithofacies structure heterogeneity characteristics, determining the target lithofacies identification model according to the obtained comparison results, so as to complete lithofacies identification using the target lithofacies identification model.

[0074] In this embodiment, after determining the target layer data between each target half-width point, the target layer data between the target half-width points are used to determine the data that meets the preset minimum sample layer unit, and the depth slice unit data is obtained by splicing the data that meets the preset minimum sample layer unit, and the average depth value of the depth slice unit data is determined to obtain the model training data containing vertical information. Specifically, the target layer data determined by the target half-width point is used as the minimum sample layer unit, and the depth slice unit data is constructed by splicing these minimum sample layer unit data. During the depth slicing operation, each time along the vertical depth direction, I minimum sample layer unit data (I=1, 2, 3, ..., 10) are spliced ​​and combined in sequence. As the value changes, different depth slice unit data can be obtained. Using the thickness weighted average method, the curve mean corresponding to each depth slice unit data can be calculated. The final value depends on the accuracy required for model training. At the same time, by statistically analyzing the average thickness of the minimum sample layer unit, the thickness of the single-layer lithofacies combination, and the lithofacies density, etc., the reasonable range of the minimum sample layer unit can be determined, which has guiding significance for the training of the initial lithofacies recognition model. After counting the average depth value of the depth slice unit data, we get Fig. 9 The deep slice label library containing vertical information is shown in the figure, which is the model training data. In addition, for the task of identifying lithofacies units with probability distribution characteristics in the vertical direction, BiLSTM (Bidirectional LongShort-Term Memory) is selected as the initial lithofacies identification model. This neural network performs well in processing time series data and can effectively maintain long-term memory. In addition, a gating mechanism is introduced in its model, which can solve the problem of gradient disappearance and explosion, greatly reducing the time and difficulty required for model training, and providing strong support for model training.

[0075] Furthermore, after obtaining the model training data, the current training set and the current validation set can be determined based on the model training data, the target probability distribution characteristics and the current training set can be input into the initial lithofacies recognition model for iterative update to obtain an iterative lithofacies recognition model, and the depth slice data to be predicted can be input into the iterative lithofacies recognition model to obtain the model prediction result. Specifically, Fig.10 As shown, first, a depth slice sample label library with different I values ​​is used as the current training set and the current verification set. For example, 75% of the data in the depth slice label library can be randomly selected as the current training set, and 25% of the data can be used as the current verification set. Then, the target lithofacies probability distribution characteristics and the current training set data are input into the initial lithofacies identification model, and the model training is completed by adjusting the initial lithofacies identification model parameters. Then, the model is verified by the current verification set. The density and frequency of the predicted lithofacies in the lithofacies combination are continuously updated, and the errors of the frequency and density of the same lithofacies are calculated by coring the section to obtain the final result and model accuracy. At the same time, the I in the depth slice is adjusted to obtain new model training data, and the model is repeatedly trained using the new model training data to obtain the iterated lithofacies identification model. In addition, by continuously updating the label library and adjusting the model parameters, the optimal lithofacies label library can be obtained, and the number of combinations of the minimum sample layer unit I can also be determined. Next, the depth slice data to be predicted is input into the iterated lithofacies identification model, and the model framework is used to process the depth slice data to be predicted, and finally the following is obtained. Fig.11 The model prediction results are shown.

[0076] Finally, the predicted probability distribution characteristics of the vertical lithofacies in the prediction results of the statistical model are used to verify whether they match the target lithofacies probability distribution characteristics of the coring section. At the same time, based on the predicted lithofacies heterogeneity characteristics in the prediction results, it is verified whether the model matches the target lithofacies structural heterogeneity to obtain the corresponding comparison results. Based on the obtained lithofacies probability distribution characteristics and the comparison results of the lithofacies internal structural heterogeneity, the target lithofacies identification model is finally determined so that different lithofacies can be identified using the target lithofacies identification model.

[0077] As can be seen from the above, the embodiment of the present application first obtains the core description data of the coring well, and determines the lithofacies type corresponding to the coring section based on this. Based on the lithofacies type, the lithofacies combination characteristics corresponding to the coring section are further clarified, and the target probability distribution characteristics of the vertical lithofacies are determined, and then the lithofacies combination characteristics are used to analyze the heterogeneous characteristics of the target lithofacies structure. Subsequently, the target layer segment logging curve is obtained and normalized to obtain the processed target layer segment logging curve. The target logging curve is determined based on the processed logging curve and the lithofacies type. The first depth value of the target peak point and the second depth value of the target valley point in the target logging curve are determined, and the third depth value of the target half-width point is obtained based on these two depth values. The corresponding target weight value is determined using the third depth value, and then the target layer data between the target half-width points is obtained according to the target weight value. Afterwards, model training data is established based on the obtained target layer data, and the initial lithofacies recognition model is trained using the model training data to obtain the model prediction result. The predicted probability distribution characteristics in the model prediction results are compared with the previously determined target probability distribution characteristics, and the predicted lithofacies structural heterogeneity characteristics are also compared with the target lithofacies structural heterogeneity characteristics. Finally, the target lithofacies identification model is determined based on these comparison results, so that the target lithofacies identification model can be used to complete the lithofacies identification work in the future. In this way, according to the vertical development probability characteristics of different lithofacies in a single-layer lithofacies combination, the lithofacies structural heterogeneity characteristics and the corresponding logging response characteristics, the lithofacies slices of the vertical depth sequence are used, combined with the deep learning model for adaptive and fine interpretation of the lithofacies, which can improve the interpretation accuracy of complex lithofacies, and add the vertical lithofacies development law, laying a good foundation for further sedimentary geological interpretation.

[0078] Based on the above embodiment, it can be seen that the present application discloses a lithofacies identification method, which can be combined with an intelligent algorithm to identify complex lithofacies. Fig.12 As shown, the specific lithofacies identification method is explained in detail.

[0079] This application first determines the lithology and bedding type of the coring section based on the core description data of the coring wells in the study area, and then determines the lithofacies type of the coring section based on the determined lithology and bedding type of the coring section. Then, a thermal map is used to show the target probability distribution characteristics of a certain lithofacies developed above and below the current lithofacies in the vertical direction, and the target probability distribution characteristics of the previous lithofacies of the current lithofacies and the target lithofacies probability distribution characteristics of the next lithofacies of the current lithofacies are analyzed. At the same time, the different lithofacies densities and lithofacies frequencies within the lithofacies combination of the complete single-layer coring section are statistically analyzed to quantitatively analyze the heterogeneous characteristics of the target lithofacies structure.

[0080] Furthermore, after determining the target probability distribution characteristics and the heterogeneous characteristics of the target lithofacies structure, the target layer logging curve is extracted, and the target layer logging curve of each well is standardized to unify the scale. Then, the maximum and minimum values ​​of the logging curves of different target layers are obtained respectively. According to the maximum and minimum values ​​of the logging curves of the target layers, the min-max normalization method is used to realize the normalization of different curves, so that the response values ​​contained in the logging curves of each target layer are mapped to [0-1], and the processed target layer logging curve is obtained. After that, the sensitivity analysis between the coring section logging curve and the lithofacies type and the sensitivity analysis between the logging curves are carried out respectively by using the Pearson correlation coefficient analysis, and the target logging curve is determined according to the analysis results.

[0081] Next, after determining the target logging curve, first use the natural logarithm function to derive the value of the logging curve, determine the target peak point and the target valley point, and obtain the depth value of the target peak point and the target valley point, and obtain the depth value of the target half-width point based on the depth value of the target peak point and the target valley point. After obtaining the depth value of the target half-width point, determine the curve data between the target half-width points according to the target weight value, and determine the target layer data between the target half-width points based on the curve data between the target half-width points.

[0082] Finally, after determining the target layer data between each target half-width point, the target layer data determined by the target half-width point is used as the minimum sample layer unit, and the depth slice unit data is constructed by splicing these minimum sample layer unit data. After counting the average depth value of the depth slice unit data, a depth slice label library containing vertical information, i.e., model training data, is obtained. After obtaining the model training data, the depth slice sample label library with different target weight values ​​is used as the current training set and the current validation set, and the target lithofacies probability distribution characteristics and the current training set data are input into the initial lithofacies recognition model. The model training is completed by adjusting the parameters of the initial lithofacies recognition model to obtain the iterative lithofacies recognition model. Then, the depth slice data to be predicted is input into the iterative lithofacies recognition model, and the model framework is used to process the depth slice data to be predicted, and finally the corresponding model prediction results are obtained. The predicted probability distribution characteristics of the vertical lithofacies in the statistical model prediction results are used to verify whether they match the target lithofacies probability distribution characteristics of the coring section. At the same time, according to the predicted lithofacies heterogeneity characteristics in the prediction results, the model is verified to match the target lithofacies structural heterogeneity to obtain the corresponding comparison results. According to the obtained lithofacies probability distribution characteristics and the comparison results of the lithofacies internal structural heterogeneity, the target lithofacies identification model is finally determined.

[0083] This application comprehensively considers the vertical development characteristics of different lithofacies and the logging responses under the influence of these characteristics, and uses the learning advantages of neural networks for vertical sequences and their long-term memory characteristics to perform adaptive intelligent recognition of complex lithofacies, so as to achieve a detailed interpretation of the lithofacies.

[0084] See also Fig.13 As shown, an embodiment of the present invention discloses a lithology identification device, which may include:

[0085] The feature analysis module 11 is used to obtain the lithofacies type corresponding to the coring section based on the obtained core description data of the coring well, determine the lithofacies combination characteristics corresponding to the coring section according to the acquired lithofacies type corresponding to the coring section, determine the target probability distribution characteristics of the lithofacies in the vertical direction according to the lithofacies type corresponding to the coring section, and analyze the heterogeneous characteristics of the target lithofacies structure using the lithofacies combination characteristics;

[0086] The well logging curve determination module 12 is used to obtain the well logging curve of the target layer, normalize the well logging curve of the target layer to obtain the processed well logging curve of the target layer, and then determine the target well logging curve based on the processed well logging curve of the target layer and the lithofacies type;

[0087] A data acquisition module 13 is used to determine a first depth value of a target peak point and a second depth value of a target valley point corresponding to the target logging curve, obtain a third depth value of a target half-width point based on the first depth value and the second depth value, determine a corresponding target weight value using the third depth value of the target half-width point, and obtain target layer data between the target half-width points according to the target weight value;

[0088] The lithofacies identification completion module 14 is used to establish model training data based on the target layer data between the target half-width points, use the model training data to train the initial lithofacies identification model to obtain a model prediction result, compare the predicted probability distribution characteristics in the obtained model prediction result with the target probability distribution characteristics, and compare the predicted lithofacies structure heterogeneity characteristics in the obtained model prediction result with the target lithofacies structure heterogeneity characteristics, determine the target lithofacies identification model according to the obtained comparison results, so as to complete lithofacies identification using the target lithofacies identification model.

[0089] As can be seen from the above, the present application first obtains the core description data of the coring well, and determines the lithofacies type corresponding to the coring section based on this. Based on the lithofacies type, the lithofacies combination characteristics corresponding to the coring section are further clarified, and the target probability distribution characteristics of the vertical lithofacies are determined, and then the lithofacies combination characteristics are used to analyze the heterogeneous characteristics of the target lithofacies structure. Subsequently, the target layer segment logging curve is obtained and normalized to obtain the processed target layer segment logging curve. The target logging curve is determined based on the processed logging curve and the lithofacies type. The first depth value of the target peak point and the second depth value of the target valley point in the target logging curve are determined, and the third depth value of the target half-width point is obtained based on these two depth values. The corresponding target weight value is determined using the third depth value, and then the target layer data between the target half-width points is obtained according to the target weight value. Afterwards, model training data is established based on the obtained target layer data, and the initial lithofacies recognition model is trained using the model training data to obtain the model prediction results. The predicted probability distribution characteristics in the model prediction results are compared with the previously determined target probability distribution characteristics, and the predicted lithofacies structural heterogeneity characteristics are also compared with the target lithofacies structural heterogeneity characteristics. Finally, the target lithofacies identification model is determined based on these comparison results, so that the target lithofacies identification model can be used to complete the lithofacies identification work in the future. In this way, according to the vertical development probability characteristics of different lithofacies in a single-layer lithofacies combination, the lithofacies structural heterogeneity characteristics and the corresponding logging response characteristics, the lithofacies slices of the vertical depth sequence are used, combined with the deep learning model for adaptive and fine interpretation of the lithofacies, which can improve the interpretation accuracy of complex lithofacies, and add the vertical lithofacies development law, laying a good foundation for further sedimentary geological interpretation.

[0090] In some specific implementations, the feature analysis module 11 includes:

[0091] The lithofacies type acquisition unit is used to determine the lithology and bedding type of the coring section based on the acquired core description data of the coring well, and to acquire the lithofacies type corresponding to the coring section according to the obtained lithology and bedding type of the coring section.

[0092] In some specific implementations, the feature analysis module 11 includes:

[0093] The target probability distribution feature determination unit is used to obtain a preset number of coring segment data, determine the corresponding lithofacies type and the number of the lithofacies types according to the corresponding coring segment, and determine the target probability distribution feature of the vertical lithofacies based on the preset number and the number of the lithofacies types.

[0094] In some specific implementations, the feature analysis module 11 includes:

[0095] The target lithofacies structural heterogeneity characteristic determination unit is used to count the lithofacies density and lithofacies frequency in the lithofacies combination characteristics corresponding to the coring section, and analyze the target lithofacies structural heterogeneity characteristics based on the lithofacies density and the lithofacies frequency.

[0096] In some specific implementations, the logging curve determination module 12 includes:

[0097] The processed target layer segment logging curve acquisition unit is used to obtain the numerical value that meets the preset maximum value condition and the numerical value that meets the preset minimum value condition in the target layer segment logging curve, and normalize the target layer segment logging curve based on the numerical value that meets the preset maximum value condition and the numerical value that meets the preset minimum value condition to obtain the processed target layer segment logging curve.

[0098] In some specific implementations, the logging curve determination module 12 includes:

[0099] The target logging curve acquisition unit is used to perform sensitivity analysis between the coring section logging curve in the processed target layer logging curve and the lithofacies type and sensitivity analysis between the processed target layer logging curves by using Pearson correlation coefficient analysis to obtain the target logging curve.

[0100] In some specific implementations, the data acquisition module 13 includes:

[0101] The target layer data determining unit is used to determine the curve data between the target half-width points according to the target weight value, and determine the target layer data between the target half-width points based on the curve data between the target half-width points.

[0102] In some specific embodiments, the petrographic identification completion module 14 includes:

[0103] A model training data acquisition unit is used to use the target layer data between the target half-width points to determine the data that meets the preset minimum sample layer unit, obtain depth slice unit data by splicing the data that meets the preset minimum sample layer unit, and determine the average depth value of the depth slice unit data to obtain model training data containing vertical information.

[0104] In some specific embodiments, the petrographic identification completion module 14 includes:

[0105] A model prediction result acquisition unit is used to determine a current training set and a current validation set based on the model training data, input the target probability distribution characteristics and the current training set into the initial lithofacies identification model for iterative update to obtain an iterative lithofacies identification model, and input the depth slice data to be predicted into the iterative lithofacies identification model to obtain a model prediction result.

[0106] Furthermore, the present application also discloses an electronic device. Fig.14 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0107] Fig.14 The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the lithofacies identification method disclosed in any of the above embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0108] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0109] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0110] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, and can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the lithofacies identification method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks.

[0111] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned disclosed lithofacies identification method. The specific steps of the method may refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be described in detail here.

[0112] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0113] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0114] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0115] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0116] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A lithofacies identification method, characterized in that: include: Obtaining the lithofacies type corresponding to the coring section based on the acquired core description data of the coring well, determining the lithofacies combination characteristics corresponding to the coring section according to the acquired lithofacies type corresponding to the coring section, determining the target probability distribution characteristics of the lithofacies in the vertical direction according to the lithofacies type corresponding to the coring section, and analyzing the heterogeneous characteristics of the target lithofacies structure using the lithofacies combination characteristics; Acquire a target layer logging curve, perform normalization processing on the target layer logging curve to obtain a processed target layer logging curve, and then determine a target logging curve based on the processed target layer logging curve and lithofacies type; Determine a first depth value of a target peak point and a second depth value of a target valley point corresponding to the target logging curve, obtain a third depth value of a target half-width point based on the first depth value and the second depth value, determine a corresponding target weight value using the third depth value of the target half-width point, and obtain target layer data between the target half-width points according to the target weight value; Model training data is established based on the target layer data between the target half-width points, and the initial lithofacies identification model is trained using the model training data to obtain a model prediction result. The predicted probability distribution characteristics in the obtained model prediction result are compared with the target probability distribution characteristics, and the predicted lithofacies structure heterogeneity characteristics in the obtained model prediction result are compared with the target lithofacies structure heterogeneity characteristics. The target lithofacies identification model is determined based on the obtained comparison results, so as to complete lithofacies identification using the target lithofacies identification model.

2. The petrographic identification method according to claim 1, characterized in that: The method of obtaining the lithofacies type corresponding to the coring section based on the obtained core description data of the coring well includes: The lithology and bedding type of the coring section are determined based on the obtained core description data of the coring well, and the lithofacies type corresponding to the coring section is obtained according to the obtained lithology and bedding type of the coring section.

3. The petrographic identification method according to claim 1, characterized in that: Determining the target probability distribution characteristics of the vertical lithofacies according to the lithofacies type corresponding to the coring section includes: A preset number of coring segment data are obtained, corresponding lithofacies types and the number of lithofacies types are determined according to the corresponding coring segments, and target probability distribution characteristics of the vertical lithofacies are determined based on the preset number and the number of lithofacies types.

4. The petrographic identification method according to claim 1, characterized in that: The method of analyzing the heterogeneous characteristics of the target lithofacies structure by using the lithofacies combination characteristics includes: The lithofacies density and lithofacies frequency in the lithofacies combination characteristics corresponding to the coring section are counted, and the heterogeneous characteristics of the target lithofacies structure are analyzed based on the lithofacies density and the lithofacies frequency.

5. The petrographic identification method according to claim 1, characterized in that: The step of normalizing the target layer interval well logging curve to obtain a processed target layer interval well logging curve comprises: A numerical value satisfying a preset maximum value condition and a numerical value satisfying a preset minimum value condition in a target layer segment logging curve are obtained, and the target layer segment logging curve is normalized based on the numerical value satisfying the preset maximum value condition and the numerical value satisfying the preset minimum value condition to obtain a processed target layer segment logging curve.

6. The petrographic identification method according to claim 1, characterized in that: The determining of the target logging curve based on the processed target layer interval logging curve and lithofacies type comprises: The Pearson correlation coefficient analysis is used to perform sensitivity analysis between the coring section logging curve in the processed target layer logging curve and the lithofacies type and sensitivity analysis between the logging curves of each processed target layer to obtain the target logging curve.

7. The petrographic identification method according to claim 1, characterized in that: The step of obtaining the target layer data between the target half-width points according to the target weight value includes: The curve data between the target half-width points is determined according to the target weight value, and the target layer data between the target half-width points is determined based on the curve data between the target half-width points.

8. The petrographic identification method according to any one of claims 1 to 7, characterized in that: The step of establishing model training data based on the target layer data between the target half-width points obtained includes: The target layer data between the target half-width points are used to determine data that meets the preset minimum sample layer unit, depth slice unit data is obtained by splicing the data that meets the preset minimum sample layer unit, and the average depth value of the depth slice unit data is determined to obtain model training data containing vertical information.

9. The petrographic identification method according to claim 8, characterized in that: The method of using the model training data to train the initial lithofacies identification model to obtain a model prediction result includes: Based on the model training data, a current training set and a current validation set are determined, the target probability distribution characteristics and the current training set are input into the initial lithofacies identification model for iterative updating to obtain an iterative lithofacies identification model, and the depth slice data to be predicted is input into the iterative lithofacies identification model to obtain a model prediction result.

10. A lithofacies identification device, characterized in that: include: A feature analysis module is used to obtain the lithofacies type corresponding to the coring section based on the obtained core description data of the coring well, determine the lithofacies combination characteristics corresponding to the coring section according to the acquired lithofacies type corresponding to the coring section, determine the target probability distribution characteristics of the lithofacies in the vertical direction according to the lithofacies type corresponding to the coring section, and analyze the heterogeneous characteristics of the target lithofacies structure using the lithofacies combination characteristics; A well logging curve determination module is used to obtain a target layer interval well logging curve, normalize the target layer interval well logging curve to obtain a processed target layer interval well logging curve, and then determine the target well logging curve based on the processed target layer interval well logging curve and the lithofacies type; A data acquisition module is used to determine a first depth value of a target peak point and a second depth value of a target valley point corresponding to the target logging curve, obtain a third depth value of a target half-width point based on the first depth value and the second depth value, determine a corresponding target weight value using the third depth value of the target half-width point, and obtain target layer data between the target half-width points according to the target weight value; A lithofacies identification completion module is used to establish model training data based on the target layer data between the target half-width points, use the model training data to train the initial lithofacies identification model to obtain a model prediction result, compare the predicted probability distribution characteristics in the obtained model prediction result with the target probability distribution characteristics, and compare the predicted lithofacies structure heterogeneity characteristics in the obtained model prediction result with the target lithofacies structure heterogeneity characteristics, determine the target lithofacies identification model according to the obtained comparison results, so as to complete lithofacies identification using the target lithofacies identification model.

11. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the lithofacies identification method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the lithology identification method according to any one of claims 1 to 9 is implemented.

Images