Geologic facies quality index-based lithofacies identification method, apparatus and device, and medium

Abstract

The embodiment of the invention discloses a lithofacies identification method and device based on a geological facies quality index, equipment and a medium, and relates to the technical field of geological exploration. The method comprises the following steps: determining a quality index of the geological facies according to reservoir physical properties of the geological facies; classifying the geological facies according to the numerical value of the quality index of each geological facies to obtain a plurality of lithofacies categories; determining the plurality of lithofacies categories as label contents, labeling the logging data to obtain training data, and training the lithofacies recognition model based on the training data to obtain a trained lithofacies recognition model; the trained lithofacies identification model is used for identifying the lithofacies type of the to-be-researched area. According to the technical scheme, the geologic facies are divided into the lithofacies categories, then the lithofacies categories serve as the labels of the logging data to train the lithofacies recognition model, the number of categories needing to be recognized by the model is reduced, the model recognition accuracy is improved, and the data size needed by model training is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of geological exploration, and particularly relates to a lithofacies identification method, device, equipment and medium based on a geological facies quality index. Background Art

[0002] Lithology identification is closely related to oil and gas reservoir evaluation, and the accuracy of lithology identification affects the accuracy of subsequent reservoir evaluation. Lithology identification can be carried out through an artificial intelligence model, such as constructing a model through algorithms such as support vector machines, neural networks, and gradient boosting decision trees and then performing lithology identification.

[0003] In the current solutions for identifying reservoir lithology through an artificial intelligence model, due to the large number of types of reservoir lithology, the training samples and computing resources required for training the model are relatively large. Summary of the Invention

[0004] The present invention provides a lithofacies identification method, device, equipment and medium based on a geological facies quality index, which can divide geological facies into lithofacies and then train a lithofacies identification model, reducing the number of categories that the model needs to identify, and reducing the number of samples and computing resources required for training on the premise of keeping the accuracy of the trained model unchanged.

[0005] According to one aspect of the present invention, there is provided a lithofacies identification method based on a geological facies quality index, the method comprising:

[0006] Determining a quality index of a geological facies according to the reservoir physical properties of the geological facies; the magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies;

[0007] Classifying the geological facies according to the numerical magnitudes of the quality indices of the respective geological facies to obtain a plurality of lithofacies categories; each lithofacies category includes at least one geological facies;

[0008] Determining the plurality of lithofacies categories as label contents, performing a tagging process on logging data to obtain training data, and training a lithofacies identification model based on the training data to obtain a trained lithofacies identification model; the trained lithofacies identification model is used to identify the lithofacies type of a region to be studied.

[0009] According to another aspect of the present invention, there is provided a lithofacies identification device based on a geological facies quality index, comprising:

[0010] A quality index determination module, configured to determine a quality index of a geological facies according to the reservoir physical properties of the geological facies; the magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies;

[0011] A lithofacies category determination module, configured to classify geological facies according to the numerical values of the quality indices of each geological facies, so as to obtain multiple lithofacies categories; each lithofacies category includes at least one geological facies;

[0012] A model training module, configured to determine the multiple lithofacies categories as label content, perform label processing on logging data to obtain training data, and train a lithofacies recognition model based on the training data to obtain a trained lithofacies recognition model; the trained lithofacies recognition model is used to identify the lithofacies types in the area to be studied.

[0013] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the lithofacies recognition method based on the geological facies quality index according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to implement the lithofacies recognition method based on the geological facies quality index according to any embodiment of the present invention when executed by a processor.

[0018] The technical solution of the embodiments of the present application includes: determining the quality index of a geological facies according to the reservoir physical properties of the geological facies; the magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies; classifying the geological facies according to the numerical values of the quality indices of each geological facies to obtain multiple lithofacies categories; each lithofacies category includes at least one geological facies; determining the multiple lithofacies categories as label content, performing label processing on logging data to obtain training data, and training a lithofacies recognition model based on the training data to obtain a trained lithofacies recognition model; the trained lithofacies recognition model is used to identify the lithofacies types in the area to be studied. By dividing geological facies into lithofacies categories and then using the lithofacies categories as labels for logging data to train the lithofacies recognition model, this technical solution reduces the number of types that the model needs to identify, improves the accuracy of model recognition, and reduces the number of samples and the computing resources required for model training.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flow chart of a lithofacies identification method based on geological facies quality index provided in accordance with the first embodiment of the present application;

[0022] Figure 2 This is a flow chart of a lithofacies identification method based on geological facies quality index provided in Example 2 of the present application;

[0023] Figure 3 This is a schematic diagram of dividing small layers at the lower half of the vertical depth scale of 1:400 provided in Example 2 of the present application;

[0024] Figure 4 This is a schematic diagram of constructing a random forest well logging lithofacies identification model according to Example 2 of the present application;

[0025] Figure 5 This is a structural schematic diagram of a lithofacies identification device based on geological facies quality index provided in accordance with the third embodiment of the present application;

[0026] Figure 6 It is a structural schematic diagram of an electronic device for implementing a lithofacies identification method based on geological facies quality index according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", "target", etc. in the description, claims and the above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 The present application provides a flowchart of a lithofacies identification method based on a geological facies quality index for Embodiment 1 of the present application. The embodiments of the present application are applicable to the situation of identifying the lithofacies of a reservoir. This method can be executed by a lithofacies identification device based on a geological facies quality index. The lithofacies identification device based on a geological facies quality index can be implemented in the form of hardware and / or software, and the lithofacies identification device based on a geological facies quality index can be configured in an electronic device with data processing capabilities. As Figure 1 shown, the method includes:

[0031] S110, determine the quality index of the geological facies according to the reservoir physical properties of the geological facies.

[0032] Among them, the geological facies reflects the attributes of the reservoir. The geological facies can be lithology, and the geological facies includes but is not limited to: carbonate rock geological facies, sandstone geological facies, etc. The reservoir physical properties are the physical properties of the reservoir corresponding to the geological facies. The reservoir physical properties can be: porosity, permeability, pore throat tortuosity, etc. The magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies. For example, if the quality index of the reservoir sample of geological facies A is greater than that of the reservoir sample of geological facies B, then the possibility of the reservoir corresponding to geological facies A storing oil and gas is greater than that of the reservoir corresponding to geological facies B.

[0033] Specifically, obtain the reservoir physical properties such as porosity and permeability of the core slices of a certain section after drilling, and input the reservoir physical properties into the quality index calculation formula of the corresponding geological facies to obtain the quality index of the geological facies. For example, drill wells in the area to be studied to obtain three wells S1, S2, and S3. Take cores from the M section in S1, S2, and S3 to obtain core slices. Determine the rock type of the core slices as the geological facies of this section, and determine the quality index of the geological facies according to the following formula:

[0034]

[0035] Among them, GI is the geological facies quality index; a is the lithology constraint factor; R is the reservoir rating; Fs is the pore throat shape factor; ε is the pore throat tortuosity; Sgv is the specific surface area of particles; φe is the effective porosity.

[0036] It should be noted that the quality index of each geological facies can be calculated according to the above formula. For example, if the geological facies is carbonate rock geological facies, the quality index of carbonate rock geological facies is determined according to the following formula:

[0037]

[0038] Among them, GI is the quality index of carbonate rock geological facies; a is the lithology constraint factor; R is the reservoir rating of carbonate rock; Fs is the pore throat shape factor of carbonate rock core thin section; ε is the pore throat tortuosity of carbonate rock core thin section; Sgv is the specific surface area of particles of carbonate rock core thin section; φ e is the effective porosity of carbonate rock core thin section.

[0039] S120. According to the numerical values of the quality indices of each geological facies, classify the geological facies to obtain multiple lithofacies categories.

[0040] Among them, each lithofacies category includes at least one geological facies; the number of lithofacies categories is less than the number of geological facies.

[0041] Specifically, after obtaining the quality indices of each geological facies, since the quality indices of geological facies with similar reservoir properties are usually close, the geological facies can be classified according to the magnitude of the quality index. The geological facies classified into one category are determined as one lithofacies. In this way, the obtained lithofacies are all geological facies with similar reservoir properties, which is convenient for subsequent identification of lithofacies through the model. In a feasible solution, the number of lithofacies can be set in advance. After dividing the number of geological facies by the number of lithofacies, the number of geological facies included in each lithofacies is obtained. Then, according to the magnitude of the quality index, each geological facies is sequentially divided into the corresponding lithofacies to obtain multiple lithofacies categories. In another feasible solution, clustering processing can be performed on the quality indices. The geological facies clustered into one category have relatively close attributes, and the geological facies clustered into one category can be determined as one lithofacies category.

[0042] S130. Determine the multiple lithofacies categories as label content, perform label processing on the logging data to obtain training data, and train the lithofacies identification model based on the training data to obtain a trained lithofacies identification model.

[0043] Among them, the trained lithofacies identification model is used to identify the lithofacies type of the area to be studied.

[0044] Specifically, after obtaining the lithofacies categories, since each lithofacies category is composed of geological facies with similar reservoir properties and the geological facies under each lithofacies category have approximate characteristics, the lithofacies categories can be used as labels to tag the logging data. The tagged logging data is used as training data to train the lithofacies recognition model, and the trained lithofacies recognition model is obtained. Since the lithofacies recognition model only needs to identify lithofacies categories rather than geological facies (lithology), the number of labels it needs to identify is greatly reduced, and the trained lithofacies recognition model can be obtained with only a small number of training samples and less computing resources.

[0045] In an embodiment of the present application, optionally, the method further includes: obtaining logging curves of the area to be studied; inputting the logging curves into the trained lithofacies recognition model to obtain the lithofacies types of the area to be studied.

[0046] Specifically, after obtaining the trained lithofacies recognition model, the logging curves of the area to be studied can be obtained and input into the trained lithofacies recognition model. The trained lithofacies recognition model can output the lithofacies types of the area to be studied. Since the lithofacies types include at least one geological facies, the geological facies included in the lithofacies types can also be determined as the reservoir identification results of the area to be studied.

[0047] The technical solution of the embodiment of the present application includes: determining the quality index of the geological facies according to the reservoir physical properties of the geological facies; the size of the quality index reflects the pros and cons of the oil and gas reservoir performance of the geological facies; classifying the geological facies according to the numerical values of the quality indices of each geological facies to obtain multiple lithofacies categories; each lithofacies category includes at least one geological facies; determining the multiple lithofacies categories as label content, tagging the logging data to obtain training data, and training the lithofacies recognition model based on the training data to obtain the trained lithofacies recognition model; the trained lithofacies recognition model is used to identify the lithofacies types of the area to be studied. By dividing the geological facies into lithofacies categories and then using the lithofacies categories as labels for the logging data to train the lithofacies recognition model, this technical solution reduces the number of types that the model needs to identify, improves the accuracy of model recognition, and reduces the number of samples and computing resources required for model training.

[0048] Embodiment 2

[0049] Figure 2 FIG. is a flowchart of a lithofacies recognition method based on the quality index of geological facies provided by Embodiment 2 of the present application. The embodiment of the present application is optimized based on the above embodiment.

[0050] As Figure 2 shown, the method of the embodiment of the present application specifically includes the following steps:

[0051] S210. Determine the quality index of each geological facies according to the reservoir physical properties of the geological facies. The magnitude of the quality index reflects the quality of the oil and gas accumulation performance of the geological facies.

[0052] S220. Sort the quality indices of each geological facies to obtain the sorted quality indices.

[0053] Exemplarily, the quality indices of each geological facies can be sorted from largest to smallest to obtain the sorted quality indices. Among the sorted quality indices, the value of the quality index at the first position is the largest, and the value of the quality index at the last position is the smallest.

[0054] S230. Divide the sorted quality indices according to a preset division method to obtain multiple groups of quality indices.

[0055] In the embodiments of the present application, optionally, divide the sorted quality indices according to a preset division method to obtain multiple groups of quality indices, including: starting from the first position of the sorted quality indices, determine a preset number of consecutive quality indices as a group of quality indices; starting from the first position of the remaining sorted quality indices, determine a preset number of consecutive quality indices as another group of quality indices, until all quality indices are grouped to obtain multiple groups of quality indices.

[0056] Among them, the preset number can be determined according to the actual situation, and the embodiments of the present application do not limit this. Exemplarily, the preset number is 3. Specifically, among the sorted quality indices, starting from the first position, determine the first preset number of quality indices as a group of quality indices, and in the sorted order, sequentially determine a preset number of quality indices as a group of quality indices until all quality indices are grouped to obtain multiple groups of quality indices.

[0057] Exemplarily, there are 15 sorted quality indices from largest to smallest. Determine the 1st - 3rd quality indices as the first group of quality indices, determine the 4th - 6th quality indices as the second group of quality indices... to obtain five groups of quality indices. Each group of quality indices of the geological facies corresponds to a lithofacies category, as shown in Table 1. Table 1 shows the average quality index values of 5 lithofacies in 3 wells. Among them, the first group of quality indices corresponds to Class I, the second group of quality indices corresponds to Class II... the fifth group of quality indices corresponds to Class V. The average quality index value of Class I lithofacies in Well S1 is 8.49.

[0058] Table 1

[0059]

[0060] In an embodiment of the present application, optionally, the sorted quality indices are divided according to a preset division method to obtain multiple groups of quality indices, including: adding an auxiliary flag to the first sorted quality index; traversing the sorted quality indices. If the difference between the currently traversed quality index and the next quality index is greater than a preset threshold, the quality indices from the quality index with the auxiliary flag to the currently traversed quality index are determined as a group of quality indices, and the auxiliary flag is moved to the next quality index; if the currently traversed quality index is the last quality index, the quality indices from the quality index with the auxiliary flag to the last quality index are determined as a group of quality indices.

[0061] Among them, the auxiliary flag is used to mark the first position of a group of quality indices. After adding the auxiliary flag to the first sorted quality index, starting from the first quality index, traverse the sorted quality indices. If the difference between the currently traversed quality index and the next quality index is greater than a preset threshold, there is a certain difference in the reservoir performance between the geological facies corresponding to the currently traversed quality index and the geological facies corresponding to the next quality index. These two geological facies can be divided into two groups so that they are divided into different lithofacies. Determine all the quality indices between the quality index with the auxiliary flag and the currently traversed quality index as a group of quality indices, and move the auxiliary flag to the next quality index to determine the next quality index as the first position of a new group of quality indices until the traversal ends, obtaining multiple groups of quality indices. It should be noted that if the currently traversed quality index is the last quality index, there is no next quality index at this time, and the quality indices from the quality index with the auxiliary flag to the last quality index can be determined as a group of quality indices.

[0062] With this setting in this solution, when the difference between two adjacent quality indices is less than the preset threshold, these two quality indices are divided into the same group; otherwise, they are divided into different groups. Such a setting makes the reservoir performances of the geological facies corresponding to the quality indices in the same group relatively close, and the reservoir performances of the geological facies corresponding to the quality indices in different groups have a certain difference, making the reservoir performances of the same lithofacies determined subsequently relatively close, and the reservoir performances of different lithofacies have a certain difference.

[0063] S240. Determine the geological facies corresponding to each group of quality indices as a lithofacies category.

[0064] Exemplarily, if a group of quality indices are respectively the quality indices corresponding to geological facies A, the quality indices corresponding to geological facies B, and the quality indices corresponding to geological facies C, then geological facies A, geological facies B, and geological facies C are determined as a lithofacies.

[0065] S250. Perform sub-layer division on the logging data to obtain the sub-logging data corresponding to each divided layer segment.

[0066] Among them, well logging data can reflect the porosity and permeability information of the reservoir. Exemplarily, five types of well logging data with high correlations with porosity and permeability are determined by the grey correlation method, namely: natural gamma, acoustic travel time, compensated neutron, deep induction resistivity, and microspherically focused resistivity well logging data. (It should be noted that the sub-well logging data in the embodiments of the present application is a certain section of the complete well logging data)

[0067] Specifically, after determining that the types of well logging data are natural gamma, acoustic travel time, compensated neutron, deep induction resistivity, and microspherically focused resistivity well logging data, corresponding seismic well logging is performed on the formation to obtain well logging curves. Since the natural gamma well logging curve can intuitively reflect the changes in the formation, taking the natural gamma well logging curve as an example, small layer division is carried out: the changes in the curve with well depth in terms of morphology, amplitude, and contact relationship can be comprehensively analyzed to divide the underground into small layers and obtain formations with the same lithology.

[0068] In the embodiments of the present application, optionally, small layer division is performed on the well logging data to obtain the sub-well logging data corresponding to each divided layer segment, including: extracting the wave peaks of the well logging curve; among the extracted wave peaks, the well logging data corresponding to the wave peaks that meet the wave peak similarity condition is determined as the sub-well logging data belonging to the same divided layer segment.

[0069] Exemplarily, when performing small layer division, the natural gamma image can be analyzed to extract the wave peaks contained in the curve, the types of the extracted wave peaks are evaluated according to the existing high, medium, and low amplitude definitions and common morphological classification features such as bell-shaped and box-shaped, and the depths where the wave peaks that are continuous in vertical depth and similar in amplitude and morphology are divided into the same lithology in combination with the continuous relationship of each wave type in vertical depth. The formation depth corresponding to each lithology is a divided layer segment, and the well logging data measured at the formation depths corresponding to the same lithology is the sub-well logging data corresponding to the same divided layer segment.

[0070] With this setting of the present solution, the formation of the research area can be accurately divided to obtain the formations corresponding to the same divided layer segment, and then the sub-well logging data corresponding to each divided layer segment can be determined.

[0071] Exemplarily, Figure 3 It is a schematic diagram of small layer division with the vertical depth scale set to 1:400 for the lower half.

[0072] S260, determine the lithofacies category corresponding to the divided layer segment as the label of the sub-well logging data corresponding to this divided layer segment.

[0073] Specifically, after drilling, rock samples of each divided layer segment can be obtained, and the geological facies (this geological facies is the lithology) of the rock samples of the divided layer segment measured through experiments can be obtained, and the lithofacies corresponding to this geological facies is determined as the label of the sub-well logging data corresponding to this divided layer segment.

[0074] S270. Train the lithofacies identification model based on the training data to obtain the trained lithofacies identification model; the trained lithofacies identification model is used to identify the lithofacies types in the area to be studied.

[0075] Specifically, determine the sub-logging data and the corresponding labels as the training data, and train the lithofacies identification model based on the training data to obtain the trained lithofacies identification model. The trained lithofacies identification model is used to process the logging data in the area to be studied and output the lithofacies types in the area to be studied.

[0076] Exemplarily, the lithofacies identification model is a model constructed based on random forest. In the embodiment of the present application, random forest is selected to construct the final lithofacies identification model. Starting from three formation factors of radioactivity, electrical property, and pore characteristics, the number of decisions of the random forest can be set to 3. Take the logging data as the training data, and take the lithofacies category corresponding to the logging data as the output label. Considering that the number of samples in the logging data set may be small, the maximum depth of the random forest is not limited in the embodiment of the present application. The embodiment of the present application uses the precision rate P to evaluate the prediction results of the lithofacies identification model. Figure 4 It is a schematic diagram for constructing a random forest logging lithofacies identification model. As shown in the figure, the number of decision trees of the model is 3. In a specific example, the 3 decision trees process the electrical method characteristics, pore characteristics, and radioactivity characteristics respectively.

[0077] In the technical solution of the embodiment of the present application, by dividing the quality index and determining the lithofacies category according to the geological facies corresponding to the divided quality index, there are certain differences in the reservoir performance among the obtained lithofacies categories, and the reservoir performance of the same lithofacies category is relatively close. Since the lithofacies category is the label during the training of the lithofacies identification model, the types of results that the lithofacies identification model needs to identify are reduced compared with directly identifying the geological facies, and the differences in characteristics among the identified results are relatively obvious, greatly improving the identification accuracy of the lithofacies identification model.

[0078] Exemplarily, the lithofacies identification model according to the embodiment of the present application is actually applied, and the obtained results are as follows:

[0079] 1. Verification of lithofacies of single-well same-layer data:

[0080] Perform lithofacies identification on 40 data of the same layer of a single well. The identification results of 36 data are correct, and the identification accuracy rate reaches 90%. It shows that the accuracy of using the random forest classification method to identify lithofacies in a single well is high.

[0081] 2. Core well verification:

[0082] By adopting the above lithofacies identification model, the M section with coring data in Well S1 is selected for lithofacies identification. The selected section length is 20 m, and the length of the misidentified section is 2 m. The identification accuracy rate can reach 90%.

[0083] 3. Verification of the correlation between porosity and permeability:

[0084] Similar pore structures should exist in the same type of lithofacies. After the lithofacies division of the uncored wells is completed and compared with the unclassified data, the correlation between porosity and permeability of the data classified into 5 types of lithofacies has increased by more than 15%, indicating that the lithofacies identification effect of the model is good.

[0085] Embodiment 3

[0086] Figure 5 The following is a schematic structural diagram of a lithofacies identification device provided in Embodiment 3 of the present application. This device can execute the lithofacies identification method based on the geological facies quality index provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. As Figure 5 shown, the device includes:

[0087] A quality index determination module 310, configured to determine the quality index of the geological facies according to the reservoir physical properties of the geological facies; the magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies;

[0088] A lithofacies category determination module 320, configured to classify the geological facies according to the numerical values of the quality indices of the geological facies to obtain multiple lithofacies categories; each lithofacies category includes at least one geological facies;

[0089] A model training module 330, configured to determine the multiple lithofacies categories as label content, perform label processing on well logging data to obtain training data, and train a lithofacies identification model based on the training data to obtain a trained lithofacies identification model; the trained lithofacies identification model is used to identify the lithofacies type of the area to be studied.

[0090] The technical solution of the embodiment of the present application includes: a quality index determination module 310, configured to determine the quality index of a geological facies according to the reservoir physical properties of the geological facies; the magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies; a lithofacies category determination module 320, configured to classify the geological facies according to the numerical magnitude of the quality index of each geological facies, and obtain multiple lithofacies categories; each lithofacies category includes at least one geological facies; a model training module 330, configured to determine the multiple lithofacies categories as label content, perform label processing on well logging data to obtain training data, and train a lithofacies recognition model based on the training data to obtain a trained lithofacies recognition model; the trained lithofacies recognition model is used to identify the lithofacies type of the area to be studied. This technical solution divides the geological facies into lithofacies categories, and then uses the lithofacies categories as labels for well logging data to train the lithofacies recognition model, reducing the number of types that the model needs to identify, improving the accuracy of model recognition, and reducing the number of samples and the required computing resources for model training.

[0091] In the embodiment of the present application, optionally, the lithofacies category determination module 320 includes:

[0092] A quality index sorting unit, configured to sort the quality indexes of each geological facies to obtain sorted quality indexes;

[0093] A quality index grouping unit, configured to divide the sorted quality indexes according to a preset division method to obtain multiple groups of quality indexes;

[0094] A lithofacies category determination unit, configured to determine the geological facies corresponding to each group of quality indexes as a lithofacies category.

[0095] In the embodiment of the present application, optionally, the quality index grouping unit includes:

[0096] A first group of quality index determination sub-unit, configured to start from the first of the sorted quality indexes and determine a preset number of consecutive quality indexes as a group of quality indexes;

[0097] A quality index grouping sub-unit, configured to start from the first of the remaining sorted quality indexes and determine a preset number of consecutive quality indexes as another group of quality indexes until all quality indexes are grouped to obtain multiple groups of quality indexes.

[0098] In the embodiment of the present application, optionally, the quality index grouping unit includes:

[0099] An auxiliary flag adding sub-unit, configured to add an auxiliary flag to the first quality index after sorting;

[0100] A quality index traversal unit for traversing the sorted quality indices. If the difference between the currently traversed quality index and the next quality index is greater than a preset threshold, the quality indices with an auxiliary flag up to the currently traversed quality index are determined as a group of quality indices, and the auxiliary flag is moved to the next quality index;

[0101] An end-of-traversal operation unit for, if the currently traversed quality index is the last quality index, determining the quality indices with an auxiliary flag up to the last quality index as a group of quality indices.

[0102] In an embodiment of the present application, optionally, the model training module 330 includes:

[0103] A small layer division unit for dividing well logging data into small layers to obtain sub-well logging data corresponding to each divided layer segment;

[0104] A label determination unit for determining the lithofacies category corresponding to the divided layer segment as the label of the sub-well logging data corresponding to the divided layer segment.

[0105] In an embodiment of the present application, optionally, the small layer division unit includes:

[0106] A wave peak extraction sub-unit for extracting wave peaks from well logging curves;

[0107] A divided layer segment attribution sub-unit for, among the extracted wave peaks, determining the well logging data corresponding to the wave peaks that meet the wave peak similarity condition as the sub-well logging data belonging to the same divided layer segment.

[0108] In an embodiment of the present application, optionally, the device further includes:

[0109] A well logging curve acquisition module for acquiring well logging curves of the area to be studied;

[0110] A lithofacies type determination module for inputting the well logging curves into the trained lithofacies identification model to obtain the lithofacies type of the area to be studied.

[0111] The lithofacies identification device based on geological facies quality index provided by the embodiment of the present application can execute the lithofacies identification method based on geological facies quality index provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0112] ]]Embodiment Four

[0113] Figure 6FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0114] As Figure 6 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0115] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0116] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the lithofacies identification method based on the geological facies quality index.

[0117] In some embodiments, the lithofacies identification method based on the geological facies quality index may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the lithofacies identification method based on the geological facies quality index described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the lithofacies identification method based on the geological facies quality index by any other suitable means (e.g., by means of firmware).

[0118] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0120] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0123] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0124] It should be understood that various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0125] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A lithofacies identification method based on a geological facies quality index, characterized in that, Including: Determine the quality index of the geological facies according to the reservoir physical properties of the geological facies; the magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies; Classify the geological facies according to the numerical values of the quality indexes of each geological facies to obtain multiple lithofacies categories; Each lithofacies category includes at least one geological facies; Determine the multiple lithofacies categories as tag content, perform tag processing on the logging data to obtain training data, and train the lithofacies recognition model based on the training data to obtain the trained lithofacies recognition model; the trained lithofacies recognition model is used to identify the lithofacies types in the area to be studied.

2. The method according to claim 1, wherein Classify the geological facies according to the numerical values of the quality indexes of each geological facies to obtain multiple lithofacies categories, including: Sort the quality indexes of each geological facies to obtain the sorted quality indexes; Divide the sorted quality indexes according to a preset division method to obtain multiple groups of quality indexes; Determine the geological facies corresponding to each group of quality indexes as a lithofacies category.

3. The method according to claim 2, wherein Divide the sorted quality indexes according to a preset division method to obtain multiple groups of quality indexes, including: Starting from the first of the sorted quality indexes, determine a preset number of consecutive quality indexes as a group of quality indexes; Starting from the first of the remaining sorted quality indexes, determine a preset number of consecutive quality indexes as another group of quality indexes until all quality indexes are grouped to obtain multiple groups of quality indexes.

4. The method according to claim 2, characterized in that, Divide the sorted quality indexes according to a preset division method to obtain multiple groups of quality indexes, including: Add an auxiliary flag to the first quality index after sorting; Traverse the sorted quality indexes. If the difference between the currently traversed quality index and the next quality index is greater than a preset threshold, then determine the quality index with the auxiliary flag to the currently traversed quality index as the same group of quality indexes, and move the auxiliary flag to the next quality index; If the currently traversed quality index is the last quality index, then determine the quality index with the auxiliary flag to the last quality index as the same group of quality indexes.

5. The method according to claim 1, wherein Perform tag processing on the logging data to obtain training data, including: Perform sub-layer division on the logging data to obtain the sub-logging data corresponding to each divided layer segment; Determine the lithofacies category corresponding to the divided layer segment as the tag of the sub-logging data corresponding to the divided layer segment.

6. The method according to claim 5, wherein Perform sub-layer division on the logging data to obtain the sub-logging data corresponding to each divided layer segment, including: Extract the wave peaks of the logging curves; Among the extracted wave peaks, determine the logging data corresponding to the wave peaks that meet the wave peak similarity condition as the sub-logging data belonging to the same divided layer segment.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the logging curves of the area to be studied; Input the logging curves into the trained lithofacies recognition model to obtain the lithofacies types in the area to be studied.

8. A lithofacies identification device based on a geological facies quality index, characterized in that Including: A quality index determination module for determining the quality index of the geological facies according to the reservoir physical properties of the geological facies; the magnitude of the quality index reflects the pros and cons of the oil and gas accumulation performance of the geological facies; A lithofacies category determination module for classifying the geological facies according to the numerical values of the quality indexes of each geological facies to obtain multiple lithofacies categories; Each lithofacies category includes at least one geological facies; A model training module, configured to determine the multiple lithofacies categories as label content, perform label processing on logging data to obtain training data, and train a lithofacies identification model based on the training data to obtain a trained lithofacies identification model; the trained lithofacies identification model is used to identify the lithofacies types in the area to be studied.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the lithofacies identification method based on the geological facies quality index according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the lithofacies identification method based on the geological facies quality index according to any one of claims 1-7 is implemented.

Images