Reservoir fluid type identification method, device, equipment and medium

Abstract

The embodiment of the invention provides a reservoir fluid type identification method and device, equipment and a medium. The method comprises the steps that logging data and spatial information obtained by logging a target position of a reservoir are obtained, then the logging data and the spatial information are input into a pre-obtained fluid type recognition model for recognition processing, and the fluid type of the target position is obtained, the fluid type identification model is obtained by training based on an AdaBoost-random forest algorithm. According to the method, the dependence on physical sampling and manual interpretation is reduced, the identification method capable of intelligently, rapidly and effectively identifying the reservoir fluid type is developed, and the effect of efficiently identifying the reservoir fluid type is achieved.

Description

Technical Field

[0001] The present application relates to the field of oil and gas exploration and production, and in particular to a method, device, equipment and medium for identifying reservoir fluid types. Background Art

[0002] Natural gas hydrates and oil are both important energy resources, and their development and utilization have attracted widespread attention from energy scientists and industry worldwide. Seismic exploration and well logging data analysis techniques can identify the types of fluids (oil, gas, and water) in reservoirs, providing key information for the discovery and development of oil and gas reservoirs. Accurately identifying the fluid types in reservoirs is a key step in assessing their economic value and development feasibility during the exploration and development of natural gas hydrates and oil.

[0003] Traditional reservoir fluid identification technology requires physical sampling and manual interpretation of new wells to identify the reservoir fluid type. Existing technologies lack a method that can intelligently, quickly, and effectively identify reservoir fluid types. Summary of the Invention

[0004] The embodiments of the present application provide a method, apparatus, device, and medium for identifying reservoir fluid types, which are used to train a model using limited historical data and use the model to intelligently, quickly, and effectively identify reservoir fluid types, thereby reducing reliance on physical sampling and manual interpretation during the identification process.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying a reservoir fluid type, comprising:

[0006] Acquiring well logging data and spatial information obtained by logging a target location of a reservoir;

[0007] Inputting the well logging data and the spatial information into a pre-acquired fluid type identification model for identification processing to obtain the fluid type at the target location;

[0008] The fluid type recognition model is obtained by training based on the AdaBoost-Random Forest algorithm.

[0009] In a possible implementation, the spatial information includes well logging location information and well logging depth of the target location; the well logging location information includes the longitude and latitude of the well logging location.

[0010] In a possible implementation, before inputting the well logging data and the spatial information into a pre-acquired fluid type identification model for identification processing, the method further includes:

[0011] Acquire a historical well logging data set and a historical fluid type set, wherein the historical well logging data set includes well logging data obtained from multiple well logging operations at different locations in different reservoirs and spatial information of each well logging operation, and the historical fluid type set includes fluid types analyzed from each well logging operation at different locations corresponding to the historical well logging data set;

[0012] Based on the historical well logging data set and the historical fluid type set, a sample set is obtained, wherein the sample set includes a plurality of samples, each sample includes a set of well logging data, spatial information corresponding to the well logging data, and a fluid type;

[0013] Constructing an initial fluid type recognition model based on the AdaBoost-Random Forest algorithm;

[0014] Based on the sample set, the initial fluid type recognition model is trained to obtain the fluid type recognition model.

[0015] In a possible implementation, the performing model training on the initial fluid type recognition model based on the sample set to obtain the fluid type recognition model includes:

[0016] Divide the sample set into a training set and a validation set according to a preset ratio;

[0017] Training the initial fluid type recognition model according to the training set, adjusting the model hyperparameters, and obtaining a trained fluid type recognition model;

[0018] The trained fluid type recognition model is subjected to model verification based on the verification set to obtain the fluid type recognition model.

[0019] In a possible implementation, obtaining a historical well logging data set and a historical fluid type set includes:

[0020] Based on the exploration data of the drilled intervals or single wells, multiple well logging data and the spatial information of each well logging are obtained;

[0021] Based on the test production data and core sampling analysis results of each test production at different locations, the fluid type corresponding to each well logging is determined to obtain the historical fluid type set;

[0022] Preprocessing the plurality of well logging data to obtain a plurality of processed well logging data;

[0023] The processed multiple well logging data and the spatial information of each well logging are standardized to obtain the historical well logging data set.

[0024] In one possible implementation, the preprocessing includes the following steps:

[0025] cleaning erroneous data and placeholders in the plurality of well logging data;

[0026] removing abnormal data from the plurality of well logging data;

[0027] Missing values ​​in the plurality of well logging data are supplemented by using other well logging data within a preset depth range.

[0028] In one possible implementation, the method further includes:

[0029] Based on the well logging data and spatial information of the target location, and the fluid type of the target location, the fluid type identification model is optimized to obtain a new fluid type identification model.

[0030] In a second aspect, an embodiment of the present application provides a device for identifying a reservoir fluid type, comprising:

[0031] The first acquisition module is used to acquire the well logging data and spatial information obtained by logging the target location of the reservoir;

[0032] Identification module: Input the logging data and the spatial information into a pre-acquired fluid type identification model for identification processing to obtain the fluid type at the target location; wherein the fluid type identification model is trained based on the AdaBoost-Random Forest algorithm.

[0033] In a third aspect, an embodiment of the present application provides a device for identifying a reservoir fluid type, comprising: a memory, a processor;

[0034] The memory stores computer-executable instructions;

[0035] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementations of the first aspect.

[0037] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0038] The reservoir fluid type identification method, apparatus, equipment, and medium provided in the embodiments of the present application obtain the logging data and spatial information obtained by logging the target location of the reservoir in advance, and input the logging data and the spatial information into a pre-acquired fluid type identification model trained based on the AdaBoost-random forest algorithm for identification processing to obtain the fluid type of the target location. The technical means achieves the effect of using limited historical data to train the model and use the model to intelligently, quickly and effectively identify the reservoir fluid type, thereby reducing the reliance on physical sampling and manual interpretation during the identification process. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] Figure 1 This is a flow chart of Example 1 of the method for identifying reservoir fluid types provided in this application;

[0041] Figure 2 This is a flow chart of Example 2 of the method for identifying reservoir fluid types provided in this application;

[0042] Figure 3 This is a flow chart of Example 3 of the method for identifying reservoir fluid types provided in this application;

[0043] Figure 4 This is a flow chart of Example 4 of the method for identifying reservoir fluid types provided in this application;

[0044] Figure 5 The comparison results of the actual and predicted layer labels after model verification in Example 5 of the reservoir fluid type identification method provided in this application;

[0045] Figure 6 This is the confusion matrix comparison classification result after model verification in Example 5 of the reservoir fluid type identification method provided in this application.

[0046] Figure 7 The comparison result of the actual and predicted layer labels after the new well logging data is predicted in the fifth embodiment of the method for identifying the reservoir fluid type provided by this application;

[0047] Figure 8 This is the comparison and classification result of the confusion matrix after model verification after prediction of new logging data in Example 5 of the reservoir fluid type identification method provided in this application.

[0048] Figure 9 A schematic diagram of the structure of the device for identifying the reservoir fluid type provided in this application;

[0049] Figure 10This is a schematic diagram of the structure of the reservoir fluid type identification device provided in this application.

[0050] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0051] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0052] First, let’s explain the terms involved in this application:

[0053] Cross-Validation (CV) is a common method used in machine learning to build models and validate model parameters. It's generally used to evaluate the performance of a machine learning model and can also be used for hyperparameter tuning. The basic idea behind this method is to split the original dataset into smaller subsets. These subsets are used as training and test sets to train and test the model, thereby evaluating its performance.

[0054] Well logging data: Well logging data is a crucial component of oil and gas exploration and development, recording the physical properties of the rocks and fluids within the wellbore. This data is obtained through well logging technology, which utilizes various physical methods (such as electrical, acoustic, nuclear, and chemical) to measure various wellbore parameters, such as resistivity, wellbore diameter, natural gamma ray, acoustic transit time, density, neutrons, and spontaneous potential. This data is crucial for understanding subsurface rock properties, identifying oil and gas reservoirs, assessing oil and gas reserves, and developing subsequent development plans.

[0055] In order to clearly understand the technical solution of the present application, the solution of the prior art is introduced in detail below.

[0056] Natural gas hydrates are a potential energy source found in marine sediments and permafrost on land. Petroleum, on the other hand, is one of the world's most important energy and chemical raw materials. Their development and utilization has garnered widespread attention from energy scientists and industry worldwide. In the exploration and development of natural gas hydrates, accurately identifying the fluid type within the reservoir is a key step in assessing its economic value and development feasibility.

[0057] Traditional fluid identification technologies mostly rely on drilling sampling and field testing. These methods are not only costly but also have certain risks in technical implementation, such as the possibility of damaging the reservoir structure or changing the original fluid distribution. Existing logging interpretation methods, such as sonic logging and resistivity logging, often rely on experienced geologists for data analysis and interpretation. This is not only time-consuming, but its accuracy depends largely on personal experience and subjective judgment. In complex geological conditions such as high-salinity environments and areas with mixed fluids, the accuracy of traditional logging technology and data interpretation methods will be greatly reduced. In addition, these methods often lack sufficient flexibility and adaptability when dealing with rapidly changing geological environments.

[0058] Based on the description of existing reservoir fluid type identification methods in the background technology above, these methods lack the ability to effectively integrate multiple well logging data to quickly and efficiently identify fluids in today's rapidly developing artificial intelligence technology, limiting their application in rapid decision-making scenarios. Furthermore, especially in the early stages of oil and gas exploration, the existing technology lacks a fluid type identification method that uses limited historical data to train a model and then use this model to intelligently, quickly and effectively identify reservoir fluid types.

[0059] The present application provides a method for identifying reservoir fluid types, which obtains the fluid type of the target location by inputting the logging data and spatial information of the reservoir target location into a fluid type identification model trained based on the AdaBoost-Random Forest algorithm. The present application uses spatial information as input data, so that the constructed model can not only perform efficient identification, but also has the ability to determine the fluid type in combination with spatial information. Because obtaining a large amount of high-quality fluid types from historical logging data is often time-consuming and labor-intensive, the present application adopts a machine learning algorithm based on AdaBoost-Random Forest in the process of fluid identification, wherein the random forest algorithm used can not only process high-dimensional data and suppress overfitting, but also achieve efficient identification with less training data; and the integrated learning strategy of AdaBoost further enhances the adaptability and stability of the model under variable geological conditions. It solves the technical problems in the prior art that the reservoir fluid identification process is time-consuming and labor-intensive, has a large influence of subjective factors, and lacks a method that can intelligently, quickly and effectively identify reservoir fluid types.

[0060] The reservoir fluid type identification method provided in this application can be applied to the exploration of fluids such as natural gas hydrates and oil exploration, and is suitable for rapid decision-making scenarios. This is especially true in the early stages of exploration, when only a few key wells are selected for drilling to initially obtain basic reservoir geological information and fluid signatures. Therefore, the available historical data is limited. In such cases, the reservoir fluid type identification method provided in this application can be used for efficient identification. The historical data includes logging data for drilled intervals or individual wells, as well as the fluid type and spatial information corresponding to the logging data.

[0061] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0062] Figure 1 This is a flow chart of Example 1 of the method for identifying reservoir fluid types provided in this application, as shown in FIG. Figure 1 As shown, the method includes:

[0063] S101: Acquire well logging data and spatial information obtained by logging a target location of a reservoir.

[0064] In this solution, it should be understood that, in practice, to identify the fluid type in a particular reservoir, explorers must perform well logging. During this logging process, the number of wells and their locations are determined based on information such as the geological structure and exploration objectives. When logging a single well, logging can be performed at different depths, thereby obtaining logging data and spatial information for multiple target locations corresponding to the well. During the identification process, the logging data and spatial information for these multiple target locations can be input into a pre-trained model for reservoir fluid identification, ultimately obtaining multiple fluid types corresponding to these multiple target locations.

[0065] In this step, if you want to identify the fluid type at a target location in the reservoir, you need to log the target location in the reservoir in advance. By logging the well corresponding to the target location, you can obtain the logging data of the target location and the spatial information corresponding to the logging data.

[0066] Optionally, the logging method used can be resistivity logging, caliper logging, natural gamma logging, acoustic time difference logging, density logging, neutron logging, natural potential logging, etc., and the logging data obtained can also correspond to resistivity, caliper, natural gamma ray, acoustic time difference, density, neutron ray, natural potential, etc.

[0067] In the specific implementation of this solution, it should be understood that well logging data is a set of curves showing the variation of measured data with well depth. For example, spontaneous potential logging uses a spontaneous potential logging tool to measure the variation of spontaneous potential in a well with well depth. The measured curve is called a spontaneous potential curve. Therefore, each location in the reservoir corresponds to a set of well logging data, including values ​​corresponding to that location, such as resistivity, wellbore diameter, natural gamma ray, acoustic transit time, density, neutron radiation, and spontaneous potential.

[0068] Optionally, the spatial information obtained by logging a target location of the reservoir includes logging location information and logging depth of the target location, wherein the logging location information further includes the longitude and latitude of the logging location.

[0069] In the specific implementation of this solution, it should be understood that in order to better capture the spatial distribution characteristics of the reservoir, it is necessary to obtain the logging location information of the target location. When performing well logging operations on the well corresponding to the target location, the location of the well is the logging location information of the target location, including the longitude and latitude of the logging location. In addition, to explore the sedimentary patterns of the reservoir at the target location as it changes with depth, it is necessary to obtain the logging depth of the target location, where the logging depth is the corresponding well depth.

[0070] S102: Input the well logging data and spatial information into a pre-acquired fluid type recognition model for recognition processing to obtain the fluid type at the target location, wherein the fluid type recognition model is trained based on the AdaBoost-Random Forest algorithm.

[0071] In this step, the previously acquired well logging data and spatial information corresponding to the target location are used as input data, and this input data is input into the fluid type recognition model trained based on the AdaBoost-Random Forest algorithm. After the fluid type recognition model recognizes the input data, the fluid type of the target location in the reservoir can be automatically obtained.

[0072] Optionally, the fluid type that can be identified by the fluid type identification model may include: oil, water, gas, hydrate or other fluids. The fluid type can be determined according to actual exploration conditions, and this solution does not impose any restrictions on this.

[0073] In the specific implementation of this solution, it should be understood that the data input to the fluid type identification model is generally logging data from a new well corresponding to the target reservoir. By inputting this new well logging data, the model can identify the fluid type at multiple locations in the reservoir corresponding to the well in real time, helping geological engineers make more accurate resource assessments and production decisions.

[0074] In the specific application implementation of this solution, it should be understood that the AdaBoost-Random Forest algorithm used in this solution effectively improves the generalization ability and prediction accuracy of the model. The random forest algorithm can process high-dimensional data and suppress overfitting, while the integrated learning strategy of AdaBoost further enhances the adaptability and stability of the model under variable geological conditions. Therefore, the fluid type identification model trained by this algorithm can quickly and effectively respond to complex and variable geological conditions, has flexibility and stability, and is suitable for applications in rapid decision-making scenarios. Furthermore, the fluid type identification technology of this solution can support geological engineers in making accurate resource assessments and mining decisions, which will greatly improve the economic benefits and efficiency of natural gas hydrate and oil reservoir exploration and development, and benefit the sustainable development of resources.

[0075] The reservoir fluid type identification method provided in this embodiment uses pre-acquired well logging data and spatial information corresponding to the target location as input to a fluid type identification model trained using the AdaBoost-Random Forest algorithm. The model then rapidly identifies the fluid type at the target location. This solution uses the AdaBoost-Random Forest algorithm to train the fluid type identification model and incorporates spatial information from well logging into the model. This allows the constructed model to not only perform efficient identification but also incorporates spatial information to determine fluid type. This enables intelligent, rapid, and effective identification of fluids in a variety of complex geological conditions, optimizing resource assessment and mining decision-making processes.

[0076] Figure 2 This is a flow chart of Example 2 of the method for identifying reservoir fluid types provided in this application, as shown in FIG. Figure 2 As shown, before inputting the well logging data and spatial information into the pre-acquired fluid type identification model for identification processing, the method further includes:

[0077] S201: Acquire a historical well logging data set and a historical fluid type set.

[0078] In this solution, before inputting the well logging data and spatial information of the target location into a pre-acquired fluid type recognition model for identification, the model must be trained to obtain a fluid type recognition model. The training data used includes a historical well logging data set and a historical fluid type set. After a sample set is determined based on the historical well logging data set and the historical fluid type set, the model is trained using this sample data to obtain a fluid type recognition model.

[0079] In this step, the historical logging data set obtained includes logging data obtained from multiple well logging operations at different locations in different reservoirs, as well as spatial information from each logging operation. This spatial information includes the longitude, latitude, and depth of each logging location. The historical fluid type set obtained includes the fluid type analyzed from each logging operation at different locations corresponding to the historical logging data set.

[0080] It should be understood that the fluid type at a certain location is determined based on the test production data obtained from the test production at that location and the core sampling analysis results.

[0081] S202: Acquire a sample set based on a historical well logging data set and a historical fluid type set, wherein the sample set includes multiple samples, and each sample includes a set of well logging data, spatial information corresponding to the well logging data, and fluid type.

[0082] In this step, it is necessary to collect data from all wells, including the historical logging data set and historical fluid type set collected in step S201, and obtain a sample set for model training based on the data of these wells. Specifically, each sample includes a set of logging data, spatial information corresponding to the logging data, and fluid type.

[0083] S203: Constructing an initial fluid type recognition model based on the AdaBoost-Random Forest algorithm.

[0084] In this step, a preliminary fluid type recognition model is constructed using the AdaBoost-Random Forest algorithm. It should be understood that the AdaBoost algorithm is an ensemble learning method that aims to create a strong learner by combining multiple weak learners. In this solution, the performance of the fluid recognition model is enhanced by combining AdaBoost with Random Forest.

[0085] S204: Divide the sample set into a training set and a validation set according to a preset ratio.

[0086] In this solution, the initial fluid type recognition model should be trained based on the sample set to obtain a fluid type recognition model.

[0087] In this step, the sample set is divided into a training set and a validation set according to a preset ratio. The preset ratio can be determined based on the actual training situation and is not limited in this solution. For example, if the preset ratio is set to 7:3, 70% of the sample set is randomly used as the training set and 30% of the sample set is used as the validation set, which can be expressed by the following formula:

[0088] W train , W test =split(W,train_size=0.7)

[0089] In the above formula, W is the sample set, W train is the sample set, W test For the test set.

[0090] S205: Training the initial fluid type recognition model according to the training set, adjusting the model hyperparameters, and obtaining a trained fluid type recognition model.

[0091] In a specific application, training the initial fluid type recognition model based on the training set may include:

[0092] (1) Initialize the sample weights according to the training set (X1, Y1)(X2, Y2), ..., (X N ,Y N ), assigning the same weight to each sample, which can be expressed as:

[0093]

[0094] Where w i represents the weight of the i-th sample, and N represents the total number of samples in the training set.

[0095] (2) Start iterative training, the total number of iterations is M.

[0096] A. According to the sample weight w i (m) Train the weak learner, where the weak learner is a random forest classifier. The sample weight in each iteration is w i (m) Represents, where m represents the number of iterations, m=1,2,......,M.

[0097] B. After one iteration of training, calculate the weighted error rate of all weak learners. Specifically, according to the accuracy of the prediction output of a certain weak learner for all samples, determine the weighted error rate of the weak learner after this round of training. The weighted error rate of the tth weak learner ∈ t The calculation formula is:

[0098]

[0099] Where h t (X i ) represents the predicted output of the t-th weak learner for the i-th sample; Is an indicator function, such as the weak learner's prediction error for the sample Output 1, otherwise Output 0.

[0100] C. Calculate the weights of all weak learners. Specifically, according to the weighted error rate of the t-th weak learner, determine the weight of the t-th weak learner. The weight of the t-th weak learner α t The calculation formula is as follows:

[0101]

[0102] D. Update the weight of the sample in the training set corresponding to the weak learner according to the current weight of the weak learner, the actual output of the sample, and the predicted output of the weak learner for the sample. The new weight of the i-th sample The calculation formula is as follows:

[0103]

[0104] After calculating the new weights of all samples in the training set corresponding to the t-th weak learner using the above formula, the sample weights are normalized to ensure that the sum of the sample weights in the training set is 1, completing the update of the sample weights in the training set corresponding to the t-th weak learner. Following this method, the sample weights in the training set corresponding to all weak learners are updated.

[0105] (3) After M rounds of iterative training, the prediction models of all weak learners are combined according to the final weights of each weak learner to obtain the strong learner model H(x). The basic form of this model can be expressed as:

[0106]

[0107] Where h t (x) is the prediction of the tth weak learner for the input data x, where the weak learner is a random forest classifier, R represents the number of numbers, and d represents the depth of the tree.

[0108] Through the above steps, the model training of the initial fluid type recognition model can be completed.

[0109] Optionally, in the process of adjusting the model hyperparameters, the optimal hyperparameter combination can be found through methods such as cross-validation, grid search, and Bayesian optimization to optimize the model's prediction accuracy and generalization ability. The number and type of hyperparameters are determined by the hyperparameters involved in the model, and are not limited in this case. For example, the representative hyperparameters of the random forest model are the number of trees and the depth of the trees. The process of adjusting the model hyperparameters can be expressed by the following formula:

[0110] (R * ,d * )=argmin R,d CVerror(W train ,R,d)

[0111] In the above formula, R* is the optimal number of trees, d * is the optimal tree depth.

[0112] According to the optimal hyperparameters found above, after training on the training set, the trained fluid type recognition model H can be obtained. * (x), expressed as follows:

[0113]

[0114] In this step, the initial fluid type recognition model is trained according to the training set to obtain the fluid recognition model H(x). Then, the hyperparameters such as the number and depth of trees in the model are automatically adjusted by cross-validation and other methods to obtain the trained fluid type recognition model H * (x).

[0115] S206: Performing model verification on the trained fluid type recognition model based on the verification set to obtain a fluid type recognition model.

[0116] In this step, the sample data on the validation set is needed to verify the trained fluid type recognition model and evaluate the model performance. The specific formula can be expressed as follows:

[0117]

[0118] In the above formula, N correct Represents the correct number of validations on the validation set after validation, N test is the total number of validation sets.

[0119] Optionally, before performing model validation on the trained fluid type recognition model, the performance of the AdaBoost-Random Forest model may be evaluated using evaluation methods such as cross-validation to ensure that the model has high accuracy and stability.

[0120] The reservoir fluid type identification method provided in this embodiment uses a sample set obtained from a collection of historical well logging data and a collection of historical fluid types. This sample set is then used to construct a fluid type identification model based on the AdaBoost-Random Forest algorithm. This solution effectively enhances the model's generalization and prediction accuracy, effectively expanding its applicability in complex geological conditions.

[0121] Figure 3 This is a flow chart of Example 3 of the method for identifying reservoir fluid types provided in this application, as shown in FIG. Figure 2 As shown, a historical well logging data set and a historical fluid type set are obtained, including:

[0122] S301: Acquire multiple well logging data and spatial information of each well logging according to the exploration data of the drilled interval or the drilled single well;

[0123] In this step, the exploration data of the drilled layer or the drilled single well include but are not limited to resistivity, acoustic wave time difference, density, neutron and other logging data, test production data and core sampling analysis results. Based on the acquired exploration data, multiple logging data and spatial information of each logging can be obtained.

[0124] S302: Based on the test production data and coring analysis results of each test production at different locations, determine the fluid type corresponding to each well logging and obtain a historical fluid type set;

[0125] In this step, based on the test production data of each test production at different locations and the core analysis results in the acquired exploration data, after laboratory processing and expert experience analysis, the fluid type corresponding to each well logging can be obtained, and then a historical fluid type set can be obtained.

[0126] S303: Pre-processing the plurality of well logging data to obtain a plurality of processed well logging data.

[0127] Optionally, the step of preprocessing the plurality of well logging data may include: data cleaning, removing outliers, and correcting missing values. In a specific implementation, the preprocessing may be performed by the following steps:

[0128] A. Cleaning erroneous data and placeholders in the plurality of well logging data.

[0129] Optionally, the error data and placeholders may include: -999, -9999, -99999, -9999, -999.25, 0. In a specific application, the error data and placeholders in multiple well logging data may be replaced with null values ​​to represent missing data, thereby cleaning the well logging data. This can be expressed as follows:

[0130] X i =Nan,X i ∈{-999,-9999,-99999,-999.25,0}

[0131] Where, X i Represents multiple logging data, including resistivity, wellbore diameter, natural gamma, acoustic wave transit time, density, neutron, natural potential, etc.

[0132] B. removing abnormal data from the plurality of well logging data;

[0133] Optionally, abnormal data includes: negative values ​​in well logging data other than self-potential data and extreme values ​​in all well logging data. In a specific application, for all negative values ​​other than self-potential data, the abnormal data can be removed by replacing the negative values ​​with null values, which can be expressed as follows:

[0134] X i =Nan,(X i <0),(X i <0)

[0135] Among them, X i The logging data cannot be the natural potential curve.

[0136] For all the extreme values ​​in the well logging data, the standard deviation method is used to eliminate outliers. Specifically, the mean μ and standard deviation δ of the corresponding curve of each well logging data are calculated first, and then the conditional judgment is used to mark the values ​​exceeding the mean ± 2 times the standard deviation as null values, which can be expressed as the following formula:

[0137] X i =Nan,(X i -μ>2δ)

[0138] C. Fill missing values ​​in multiple well logging data with other well logging data within a preset depth range.

[0139] For example, the average value of other logging data within 10 m above and below the depth of the missing value can be used to supplement and correct the missing value to complete the data processing, which can be expressed by the following formula:

[0140] X i =average(X i [Depth i -10, Depth i +10]),(X i =Nan)

[0141] Where, Depth i The well logging depths for missing values ​​in multiple well logging data.

[0142] In the specific implementation of this solution, it should be understood that after preprocessing multiple well logging data, the logging depth information can be incorporated by sorting all the logging data in the historical well logging data set by depth sequence. This allows subsequent training to retain certain information about sedimentary patterns that vary with depth. After incorporating the logging depth information using this method, the spatial information for each well logging location only includes the longitude and latitude of each logging location. The longitude and latitude of each logging location can be represented by spatial coordinates (x, y).

[0143] S304: performing standardization processing on the processed multiple well logging data and the spatial information of each well logging to obtain the historical well logging data set.

[0144] Optionally, the Z-score method can be used to normalize the preprocessed multiple logging data and the spatial information of each logging. The specific normalization formula is as follows:

[0145]

[0146] Where X is multiple well logging data or the spatial coordinates corresponding to the well logging data, X standardized is the standardized logging data or the spatial coordinate corresponding to the logging data, μ is the average value of the curve corresponding to the logging data, and σ is the standard deviation of the curve corresponding to the logging data.

[0147] In the specific application implementation of this solution, it should be understood that by obtaining the spatial information of each well logging, it is possible to have the ability to determine the fluid type in combination with the spatial information, and to better capture the spatial distribution characteristics of the hydrate reservoir.

[0148] The reservoir fluid type identification method provided in this embodiment utilizes exploration data from drilled intervals or individual wells to obtain multiple well logging data sets and spatial information from each well logging event. The fluid type corresponding to each well logging event is then determined, resulting in a historical fluid type set. The multiple well logging data sets are then preprocessed and standardized to obtain a historical well logging data set. This preprocessing of the multiple well logging data improves the accuracy of the logging data in the historical well logging data set, thereby improving the accuracy of the model. Furthermore, the aforementioned standardization eliminates dimensionality effects and improves algorithm performance, ensuring that data quality meets model training requirements.

[0149] Figure 4 This is a flow chart of Example 4 of the method for identifying reservoir fluid types provided in this application, as shown in FIG. Figure 4 As shown, after the well logging data and spatial information of the target position of the reservoir are input into the pre-acquired fluid type identification model for identification processing to obtain the fluid type of the target position, the method further includes:

[0150] Based on the well logging data and spatial information of the target location, as well as the fluid type at the target location, the fluid type identification model can be optimized to obtain a new fluid type identification model, which specifically includes the following steps:

[0151] S401: acquiring new historical logging data based on the well logging data and spatial information of the target location, and acquiring new historical fluid types according to the fluid type of the target location.

[0152] In this scheme, the newly acquired well logging data and spatial information of the target location, as well as the fluid type at the target location, can be used to update and optimize the AdaBoost-Random Forest model through an incremental learning method, so that the model can continuously learn and adapt to new data.

[0153] In this step, the newly acquired well logging data and spatial information of the target location, as well as the fluid type of the target location, are also subjected to the preprocessing and standardization processing described in Example 3 to obtain new historical well logging data and new historical fluid types.

[0154] S402: Acquire a new sample set based on new historical logging data and new historical fluid types.

[0155] In the specific implementation of this solution, it should be understood that the target object of well logging using the well logging method is the well corresponding to a certain reservoir, rather than a specific location within the reservoir. Therefore, the well logging data and spatial information input into the model are the well logging data and spatial information of multiple target locations. Therefore, the new sample set can include the well logging data and spatial information of multiple target locations, as well as the fluid types of the target locations. Thus, the sample set can include multiple samples, each of which includes a set of well logging data, spatial information corresponding to the well logging data, and fluid type. The new sample set is represented by W new express.

[0156] S403: Based on the new sample set, the fluid type recognition model is trained to obtain a new fluid type recognition model.

[0157] In this step, the new sample set needs to be divided into a new training set W according to the preset ratio. new,train And the new validation set W new,test The fluid type recognition model is trained to obtain a new fluid type recognition model, comprising the following steps:

[0158] A. Train the fluid type recognition model based on the new training set. Update the weights of the existing weak classifiers according to the impact of the new training set on the error rate. This can be expressed as follows:

[0159]

[0160] Where, α t is the original weight of the existing t-th weak classifier, α' t is the new weight of the existing t-th weak classifier, and γ is an adjustment factor that can dynamically adjust the weight according to the error rate of the new sample.

[0161] B. Generally speaking, the new training set has new features or patterns that the previous model has not captured well. Therefore, this step requires adding a new classifier, which is expressed as follows:

[0162] h new = RandomForest(W new )

[0163] α new =calculate_weight(h new ,W new )

[0164] In the above formula, h new is the new weak trainer, α new is the weight of the new weak classifier.

[0165] C. Add the new weak trainer and its weight to the existing fluid type recognition model, which can be expressed as follows:

[0166]

[0167] In the above formula, M'(x) represents the updated fluid type identification model

[0168] D. Perform model validation on the updated fluid type recognition model to obtain a new fluid type recognition model. Specifically, it is necessary to use sample data on the new validation set to validate the updated fluid type recognition model and evaluate the model performance. It can be expressed by the following formula:

[0169]

[0170] In the above formula, N correct_new Represents the correct number of validations on the new validation set after validation, N test_new is the total number of new validation sets.

[0171] Optionally, the validation set used for validation may also be the sum of the original validation set and the new validation set.

[0172] In the reservoir fluid type identification method provided in this embodiment, the fluid type identification model is optimized based on the well logging data and spatial information at the target location, as well as the fluid type at the target location, thereby obtaining a new fluid type identification model. This solution adopts an incremental learning approach, which updates the model optimization method as new data is received, allowing the model to continuously learn and adapt to new data environments without requiring the entire optimization process to be trained from scratch. Furthermore, this feature enables the model to be continuously optimized over time, maintaining its predictive accuracy and adaptability under new geological conditions, effectively improving the model's application scope and sustained performance under complex geological conditions.

[0173] The following is a specific embodiment 5 of this solution, in which the reservoir fluid type identification method of the present invention is used to identify several typical hydrate drilling wells in the Shenhu Sea Area of ​​my country.

[0174] After the fluid type recognition model is obtained through training based on the AdaBoost-Random Forest model, the trained fluid type recognition model is subjected to model verification based on the verification set. Figure 5 The comparison result of the actual and predicted layer labels after model verification, wherein the layer label is the fluid type of the target location described in other embodiments. Figure 5 As shown in the figure, the predicted layer labels on the validation set are basically consistent with the actual layer labels, and the accuracy of the validation set is as high as 0.99. Figure 6 The confusion matrix after model validation is used to compare the classification results, such as Figure 6 As shown in the figure, the confusion matrix shows that only three data labels are wrong in the classification prediction, which meets the accuracy requirements. New well prediction can be carried out based on this training model.

[0175] Based on the well logging data, the W11 well natural gas hydrate reservoir fluid type identification and prediction outside the training set were carried out. Figure 7 This is the comparison result between the actual and predicted layer labels after the new logging data is predicted, such as Figure 7 As shown in the figure, the actual classification results are represented by solid points, and the recognition prediction results are represented by the symbol '×'. It can be seen that the actual classification results are basically consistent with the prediction results, and the prediction accuracy reaches above 0.947. Figure 8 To compare the classification results after the confusion matrix of the model validation after prediction of new logging data, e.g. Figure 8 As shown in Figure 3, the W11 well prediction confusion matrix compared with the classification results shows that the classification accuracy is high.

[0176] Through the specific embodiments provided above, it can be seen that the reservoir fluid identification method provided in this application can accurately identify and predict the type of natural gas hydrate reservoir fluid, has stronger applicability and practicality than previous methods, and has certain industrial application value.

[0177] Figure 9 A schematic diagram of the structure of the device for identifying the reservoir fluid type provided in this application, such as Figure 9 As shown, the reservoir fluid type identification device 50 provided in this embodiment includes:

[0178] The first acquisition module 501 is used to acquire well logging data and spatial information obtained by logging a target location of a reservoir;

[0179] The identification module 502 is used to input the logging data and the spatial information into a pre-acquired fluid type identification model for identification processing to obtain the fluid type at the target location, wherein the fluid type identification model is trained based on the AdaBoost-Random Forest algorithm.

[0180] The reservoir fluid type identification device provided in this embodiment is used to implement the technical solution in any of the aforementioned method embodiments. Its implementation principles and technical effects are similar and will not be described in detail here.

[0181] In a possible implementation, the spatial information includes well logging location information and a logging depth for logging the target location; the well logging location information includes the longitude and latitude of the logging location.

[0182] Based on the above-mentioned reservoir fluid type identification device 50, in a specific embodiment, before inputting the well logging data and the spatial information into the pre-acquired fluid type identification model for identification processing, the reservoir fluid type identification device 50 may further include:

[0183] A second acquisition module 503 is configured to acquire a historical well logging data set and a historical fluid type set, wherein the historical well logging data set includes well logging data obtained from multiple well logging operations at different locations in different reservoirs and spatial information of each well logging operation, and the historical fluid type set includes fluid types analyzed from each well logging operation at different locations corresponding to the historical well logging data set;

[0184] A processing module 504 is configured to obtain a sample set based on the historical well logging data set and the historical fluid type set, wherein the sample set includes a plurality of samples, each sample including a set of well logging data, spatial information corresponding to the well logging data, and a fluid type;

[0185] A construction module 505 is used to construct an initial fluid type recognition model based on the AdaBoost-Random Forest algorithm;

[0186] The training module 506 is configured to perform model training on the initial fluid type recognition model based on the sample set to obtain the fluid type recognition model.

[0187] In a specific embodiment, in order to perform model training on the initial fluid type recognition model based on the sample set to obtain the fluid type recognition model, the training module 506 is specifically configured to:

[0188] Divide the sample set into a training set and a validation set according to a preset ratio;

[0189] Training the initial fluid type recognition model according to the training set, adjusting the model hyperparameters, and obtaining a trained fluid type recognition model;

[0190] The trained fluid type recognition model is subjected to model verification based on the verification set to obtain the fluid type recognition model.

[0191] In a specific embodiment, to obtain a historical well logging data set and a historical fluid type set, the second acquisition module 503 is specifically configured to:

[0192] Based on the exploration data of the drilled intervals or single wells, multiple well logging data and the spatial information of each well logging are obtained;

[0193] Based on the test production data and core sampling analysis results of each test production at different locations, the fluid type corresponding to each well logging is determined to obtain the historical fluid type set;

[0194] Preprocessing the plurality of well logging data to obtain processed plurality of well logging data, wherein the preprocessing includes the following processing steps:

[0195] cleaning erroneous data and placeholders in the plurality of well logging data;

[0196] removing abnormal data from the plurality of well logging data;

[0197] Missing values ​​in the plurality of well logging data are supplemented by using other well logging data within a preset depth range.

[0198] The processed multiple well logging data and the spatial information of each well logging are standardized to obtain the historical well logging data set.

[0199] Based on the above-mentioned reservoir fluid type identification device 50, in a specific embodiment, the reservoir fluid type identification device 50 may further include:

[0200] The updating module 507 is configured to optimize the fluid type identification model based on the well logging data and spatial information of the target location and the fluid type of the target location to obtain a new fluid type identification model.

[0201] The reservoir fluid type identification device 50 provided in any of the aforementioned embodiments can execute the method provided in the aforementioned method embodiment, and its implementation principle and technical effects are similar, which will not be described in detail in this embodiment.

[0202] Figure 10 This is a schematic diagram of the structure of the device for identifying the reservoir fluid type provided in this application. Figure 10As shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the electronic device 60 further includes a communication component 603. The processor 601, the memory 602 and the communication component 603 are connected via a bus 604.

[0203] During the specific implementation process, at least one processor 601 executes the computer-executable instructions stored in the memory 602, so that the at least one processor 601 performs the above method.

[0204] The specific implementation process of the processor 601 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0205] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0206] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0207] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0208] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0209] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0210] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0211] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0212] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0213] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0214] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0215] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0216] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0217] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A method for identifying reservoir fluid type, characterized in that: include: Acquire logging data and spatial information obtained by logging a target location of a reservoir; Inputting the logging data and the spatial information into a pre-acquired fluid type recognition model for recognition processing to obtain the fluid type at the target location; Wherein, the fluid type recognition model is obtained by training based on the AdaBoost-Random Forest algorithm.

2. The method according to claim 1, characterized in that: The spatial information includes the well logging location information and the well logging depth for logging the target location; the well logging location information includes the longitude and latitude of the well logging location.

3. The method according to claim 1 or 2, characterized in that: Before inputting the logging data and the spatial information into a pre-acquired fluid type recognition model for recognition processing, the method further includes: Acquire a historical well logging data set and a historical fluid type set, wherein the historical well logging data set includes well logging data obtained by multiple well loggings at different locations of different reservoirs and spatial information of each well logging, and the historical fluid type set includes fluid types analyzed by each well logging at different locations corresponding to the historical well logging data set; Based on the historical well logging data set and the historical fluid type set, a sample set is obtained, wherein the sample set includes a plurality of samples, each sample includes a set of well logging data, spatial information corresponding to the well logging data, and a fluid type; Constructing an initial fluid type recognition model based on the AdaBoost-Random Forest algorithm; Based on the sample set, the initial fluid type recognition model is trained to obtain the fluid type recognition model.

4. The method according to claim 3, characterized in that The step of training the initial fluid type recognition model based on the sample set to obtain the fluid type recognition model includes: Dividing the sample set into a training set and a validation set according to a preset ratio; Training the initial fluid type recognition model according to the training set, adjusting the model hyperparameters, and obtaining a trained fluid type recognition model; The trained fluid type recognition model is validated based on the validation set to obtain the fluid type recognition model.

5. The method according to claim 3, characterized in that: The obtaining of a historical well logging data set and a historical fluid type set includes: Based on the exploration data of the drilled layer section or the drilled single well, multiple well logging data and the spatial information of each well logging are obtained; According to the test production data and coring analysis results of each test production at different locations, the fluid type corresponding to each well logging is determined to obtain the historical fluid type set; Preprocessing the plurality of well logging data to obtain a plurality of processed well logging data; The processed multiple well logging data and the spatial information of each well logging are standardized to obtain the historical well logging data set.

6. The method according to claim 5, characterized in that Preprocessing includes the following processing steps: Cleaning erroneous data and placeholders in the plurality of well logging data; removing abnormal data from the plurality of well logging data; The missing values ​​in the plurality of well logging data are supplemented by other well logging data within a preset depth range.

7. The method according to claim 1 or 2, characterized in that: The method further comprises: Based on the logging data and spatial information of the target location, and the fluid type of the target location, the fluid type identification model is optimized to obtain a new fluid type identification model.

8. A device for identifying reservoir fluid type, characterized in that: include: The first acquisition module: acquires the logging data and spatial information obtained by logging the target position of the reservoir; Identification module: input the logging data and the spatial information into a pre-acquired fluid type identification model for identification processing to obtain the fluid type of the target location, wherein the fluid type identification model is trained based on the AdaBoost-Random Forest algorithm.

9. A device for identifying reservoir fluid type, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images