A method, apparatus, equipment and medium for detecting connectivity of stacked reservoirs

Abstract

This application discloses a method, apparatus, device, and medium for detecting the connectivity of stacked reservoirs. The method includes: using the reservoir connectivity coefficients of exploited wells as labels for corresponding historical attribute parameters, and generating training samples based on the historical attribute parameters and labels; the reservoir connectivity coefficients reflect the reservoir connectivity between a first historical reservoir and a second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially stacked; training a connectivity detection model based on the training samples to obtain a connectivity detection model, and then using the connectivity detection model to detect the connectivity of the first target reservoir and the second target reservoir. This technical solution provides a model with connectivity detection capabilities, which can accurately determine the connectivity coefficients between stacked reservoirs. These connectivity coefficients can provide theoretical guidance for dynamic analysis, development deployment, and adjustment of stacked reservoirs.

Description

Technical Field

[0001] This invention relates to the field of oil and gas exploration technology, and in particular to a method, apparatus, equipment and medium for detecting the connectivity of superimposed reservoirs. Background Technology

[0002] Sandstone buried hill superimposed oil reservoirs consist of sandstone directly overlying a buried hill without a stable mudstone interlayer. The sandstone and buried hill are vertically connected and interfere with each other. In actual production, the pressure, daily oil production, and other indicators of oil wells producing in the sandstone reservoir are affected by those of wells producing in the buried hill reservoir, and vice versa. How to conduct connectivity analysis for superimposed oil reservoirs is a technical problem that urgently needs to be solved by those skilled in the art.

[0003] Current technical solutions only conduct dynamic analysis on reservoirs with single reservoirs. For superimposed reservoirs, the interference between the two types of reservoirs cannot be avoided, thus making it impossible to obtain accurate connectivity analysis results. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for detecting the connectivity of stacked reservoirs, which can accurately determine the connectivity coefficients between stacked reservoirs, providing theoretical guidance for dynamic analysis, development deployment, and adjustment of stacked oil reservoirs.

[0005] According to one aspect of the present invention, a method for detecting the connectivity of a stacked reservoir is provided, the method comprising:

[0006] The reservoir connectivity coefficient of the exploited well is used as the label of the corresponding historical attribute parameter, and training samples are generated based on the historical attribute parameter and the label; the reservoir connectivity coefficient reflects the reservoir connectivity between the first historical reservoir and the second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially superimposed.

[0007] The connectivity detection model is trained based on the training samples to obtain the connectivity detection model, and then connectivity detection is performed on the first target reservoir and the second target reservoir based on the connectivity detection model.

[0008] According to another aspect of the present invention, a connectivity detection device for a stacked reservoir is provided, comprising:

[0009] The training sample generation module is used to use the reservoir connectivity coefficient of the exploited well as the label of the corresponding historical attribute parameter, and to generate training samples based on the historical attribute parameter and the label; the reservoir connectivity coefficient reflects the reservoir connectivity between the first historical reservoir and the second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially superimposed.

[0010] The connectivity detection model determination module is used to train the connectivity detection model to be trained based on the training samples to obtain the connectivity detection model, and to perform connectivity detection on the first target reservoir and the second target reservoir based on the connectivity detection model.

[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0012] At least one processor; and

[0013] A memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the connectivity detection method for stacked reservoirs according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the connectivity detection method for stacked reservoirs according to any embodiment of the present invention.

[0016] The technical solution of this application includes: using the reservoir connectivity coefficient of an exploited well as a label for a corresponding historical attribute parameter, and generating training samples based on the historical attribute parameter and the label; the reservoir connectivity coefficient reflects the reservoir connectivity between a first historical reservoir and a second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially superimposed; training a connectivity detection model to be trained based on the training samples to obtain a connectivity detection model, and then performing connectivity detection on the first target reservoir and the second target reservoir based on the connectivity detection model. This technical solution uses the reservoir connectivity coefficient as a label for a corresponding historical attribute parameter to generate training samples, resulting in a model with connectivity detection capabilities. Based on this model, the connectivity coefficient between superimposed reservoirs can be accurately determined, and this connectivity coefficient can provide theoretical guidance for dynamic analysis, development deployment, and adjustment of superimposed reservoirs.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a connectivity detection method for a stacked reservoir according to Embodiment 1 of this application;

[0020] Figure 2 This is a flowchart of a connectivity detection method for a stacked reservoir according to Embodiment 2 of this application;

[0021] Figure 3(a) is a cross plot of predicted and actual values ​​of the corresponding multiple linear regression algorithm provided in Embodiment 2 of this application;

[0022] Figure 3(b) is a cross-plot of predicted and actual values ​​according to the random forest algorithm provided in Embodiment 2 of this application;

[0023] Figure 3(c) is a cross-plot of the predicted and actual values ​​of the corresponding BP neural network algorithm provided in Embodiment 2 of this application;

[0024] Figure 3(d) is a cross plot of the predicted and actual values ​​of XGBoost according to Embodiment 2 of this application;

[0025] Figure 4(a) is a cross plot of predicted and actual values ​​of the corresponding multiple linear regression algorithm provided in Embodiment 2 of this application;

[0026] Figure 4(b) is a cross-plot of predicted and actual values ​​according to the random forest algorithm provided in Embodiment 2 of this application;

[0027] Figure 4(c) is a cross-plot of the predicted and actual values ​​of the corresponding BP neural network algorithm provided in Embodiment 2 of this application;

[0028] Figure 4(d) is a cross plot of the predicted and actual values ​​of XGBoost according to Embodiment 2 of this application;

[0029] Figure 5 This is a schematic diagram of the structure of a connectivity detection device for a stacked reservoir according to Embodiment 3 of this application;

[0030] Figure 6 This is a schematic diagram of the structure of an electronic device that implements a connectivity detection method for a stacked reservoir according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1 This application provides a flowchart of a connectivity detection method for stacked reservoirs according to Embodiment 1. This embodiment is applicable to analyzing the connectivity of stacked reservoirs. The method can be executed by a connectivity detection device for stacked reservoirs, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0035] S110, the reservoir connectivity coefficient of the exploited well is used as the label of the corresponding historical attribute parameter, and training samples are generated according to the historical attribute parameter and the label; the reservoir connectivity coefficient reflects the reservoir connectivity between the first historical reservoir and the second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially superimposed.

[0036] In this embodiment, the reservoir connectivity coefficient reflects the connectivity between the first historical reservoir and the second historical reservoir. There can be two reservoir connectivity coefficients, for example, reflecting the connectivity from the first historical reservoir to the second historical reservoir, and the connectivity from the second historical reservoir to the first historical reservoir, respectively. Historical attribute parameters refer to the attribute parameters of the first historical reservoir and the second historical reservoir. These historical attribute parameters are used to train the connectivity detection model. For example, historical attribute parameters may include porosity, permeability, reservoir thickness, and recovery rate.

[0037] In this embodiment, the historical attribute parameters reflect the physical and / or chemical properties of the first and second historical reservoirs, and the reservoir connectivity coefficient reflects the connectivity between the first and second historical reservoirs. Therefore, the reservoir connectivity coefficient is used as a label for the historical attribute parameters to generate training samples. After obtaining the connectivity detection model based on the training samples, the model can detect the connectivity of the two stacked reservoirs, and the detection results are relatively accurate.

[0038] It should be noted that the terms "first historical reservoir," "second historical reservoir," and "historical attribute parameters" refer to the names of the reservoirs and sample data used in the training samples. The subsequent terms "first target reservoir" and "second target reservoir" refer to the names of the two stacked reservoirs to be detected, and the target attribute parameters refer to the attribute parameters of these two stacked reservoirs.

[0039] Stacked reservoirs refer to two different reservoirs, one of which is located above the other, with no stable mudstone barrier between them. For stacked reservoirs, connectivity needs to consider the physical properties of the two reservoirs as well as the interference from wells producing in the two reservoirs.

[0040] S120, the connectivity detection model to be trained is trained based on the training samples to obtain a connectivity detection model, and connectivity detection is performed on the first target reservoir and the second target reservoir based on the connectivity detection model.

[0041] Specifically, after establishing the connectivity detection model to be trained, the model is trained based on the training samples to obtain the trained connectivity detection model. Further, target attribute parameters of the first and second target reservoirs are obtained, and these parameters are input into the trained connectivity detection model to obtain the connectivity detection results for the first and second target reservoirs.

[0042] The technical solution of this application includes: using the reservoir connectivity coefficient of an exploited well as a label for a corresponding historical attribute parameter, and generating training samples based on the historical attribute parameter and the label; the reservoir connectivity coefficient reflects the reservoir connectivity between a first historical reservoir and a second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially superimposed; training a connectivity detection model to be trained based on the training samples to obtain a connectivity detection model, and then performing connectivity detection on the first target reservoir and the second target reservoir based on the connectivity detection model. This technical solution uses the reservoir connectivity coefficient as a label for a corresponding historical attribute parameter to generate training samples, resulting in a model with connectivity detection capabilities. Based on this model, the connectivity coefficient between superimposed reservoirs can be accurately determined, and this connectivity coefficient can provide theoretical guidance for dynamic analysis, development deployment, and adjustment of superimposed reservoirs.

[0043] Example 2

[0044] Figure 2 This is a flowchart of a connectivity detection method for a stacked reservoir provided in Embodiment 2 of this application. This embodiment is an optimization based on the above embodiment.

[0045] In this embodiment of the application, for example, the first historical reservoir is a sandstone reservoir and the second historical reservoir is a buried hill reservoir; correspondingly, the first target reservoir and the second target reservoir are also a sandstone reservoir and a buried hill reservoir, respectively. This setting allows for model training based on the attribute parameters of the sandstone reservoir and the buried hill reservoir, and then the connectivity between the superimposed sandstone reservoir and the buried hill reservoir can be identified based on the trained model, making the connectivity detection results more accurate.

[0046] like Figure 2 As shown, the method in this embodiment of the application specifically includes the following steps:

[0047] S210, the first and second sand potential connectivity coefficients of the exploited wells are used as labels for the corresponding historical attribute parameters, and training samples are generated based on the historical attribute parameters and the labels; the first and second historical reservoirs are spatially superimposed.

[0048] In this embodiment of the application, optionally, the first historical reservoir is a sandstone reservoir and the second historical reservoir is a buried hill reservoir; correspondingly, the reservoir connectivity coefficient includes: the first sandstone-buried hill connectivity coefficient and the second sandstone-buried hill connectivity coefficient. The historical attribute parameters are the attribute parameters of the first historical reservoir and the second historical reservoir.

[0049] The first sandstone connectivity coefficient reflects the connectivity of oil and gas from buried hill reservoirs into sandstone reservoirs. The second sandstone connectivity coefficient reflects the connectivity of oil and gas from sandstone reservoirs into buried hill reservoirs.

[0050] In this embodiment of the application, the ratio of the first oil and gas flow rate to the oil and gas production of the sandstone reservoir is determined as the first sandstone-buried hill connectivity coefficient; the first oil and gas flow rate is the flow from the buried hill reservoir into the sandstone reservoir.

[0051] The first sand-submerged connectivity coefficient is determined using the following formula:

[0052]

[0053] Where f1 is the first sand-dwelling connectivity coefficient, Q 潜山流入砂层 Q represents the first oil and gas flow rate. 砂 This represents the oil and gas production of sandstone reservoirs.

[0054] In this embodiment of the application, the ratio of the second oil and gas flow rate to the oil and gas production of the buried hill reservoir is determined as the second sand-buried hill connectivity coefficient; the second oil and gas flow rate is the flow from the sandstone reservoir into the buried hill reservoir.

[0055] The second sand subsurface connectivity coefficient is determined using the following formula:

[0056]

[0057] f2 is the second sand-potential connectivity coefficient, Q 砂层流入潜山 Q represents the second oil and gas flow rate. 潜 This refers to the oil and gas production of buried hill reservoirs.

[0058] It should be noted that the units for the first and second oil and gas flow rates are m³. 3 / s, the unit for oil and gas production is also m. 3 / s.

[0059] In this embodiment of the application, the optional historical attribute parameters include at least one of the following: sand layer porosity (SPO), buried hill matrix porosity (BMPO), buried hill fracture porosity (BFPO), sandstone permeability (SPE), buried hill matrix permeability (BMPE), buried hill fracture permeability (BFPE), sandstone thickness (ST), buried hill thickness (BT), well spacing (WP), number of fractures (FN), sand layer recovery rate (SFR), and buried hill recovery rate (BFR).

[0060] In this embodiment of the application, the method may optionally further include: preprocessing historical attribute parameters; the preprocessing includes at least one of the following: outlier handling, missing value handling, and standardization.

[0061] Specifically, outlier detection is performed on basic attribute parameters based on the interquartile range (ICM) and Z-score methods. If an outlier is found, it can be deleted.

[0062] For example, regarding outlier handling, data that exceeds a reasonable range can generally be considered outliers. Besides a given range, IQR and Z-score methods can also be used for detection.

[0063] If a missing value is detected in the historical attribute parameters, the historical attribute parameter corresponding to the missing value is deleted, or the missing value is interpolated.

[0064] For example, regarding missing value handling, records with missing values ​​can be directly deleted or imputed. Common imputation methods include mean imputation, median imputation, mode imputation, linear imputation, previous value imputation, and next value imputation.

[0065] Furthermore, each training sample is standardized, such as through normalization.

[0066] For example, standardization can accelerate gradient descent, eliminate the influence of units and scales between features, and speed up model learning. Therefore, standardization can, to some extent, help the model learn better. Commonly used standardization methods include Min-max, Z-score, absolute value, and robustness.

[0067] S220, the connectivity detection model to be trained is trained based on the training samples to obtain a connectivity detection model, and connectivity detection is performed on the first target reservoir and the second target reservoir based on the connectivity detection model.

[0068] In this embodiment of the application, optionally, the method further includes: training the connectivity detection model to be trained based on at least one of the following regression algorithms to obtain the connectivity detection model; the regression algorithms include: multiple linear regression, random forest regression, BP neural network regression and XGBoost regression.

[0069] Specifically, multiple linear regression, random forest regression, BP neural network regression, and XGBoost regression can be used as regression algorithms to train the model, resulting in multiple connectivity detection models. Each model can then be evaluated to determine the final connectivity detection model.

[0070] In this embodiment, optionally, grid search is used to optimize the hyperparameters of the machine learning model. Table 1 shows the results of the grid search for optimized hyperparameters. The grid search method creates a grid of possible values ​​for the hyperparameters. Each iteration tries combinations of hyperparameters in a specific order, fits the model on each possible combination of hyperparameters, records the model's performance, and finally returns the best model with the optimal hyperparameters.

[0071] Table 1 Results of Optimized Hyperparameters in Grid Search

[0072]

[0073]

[0074] In this embodiment of the application, optionally, the method further includes: during the training process of the connectivity detection model, evaluating the generalization ability of the model using a generalization ability evaluation index to obtain an evaluation result; the generalization ability evaluation index includes at least one of the following: mean absolute error, root mean square error, and coefficient of determination; and determining the regression algorithm used by the connectivity detection model based on the evaluation result.

[0075] The Mean Absolute Error (MAE) is defined as follows:

[0076]

[0077] Where n is the number of samples in the test set, y i ′ is the predicted value, y i This is the actual value.

[0078] The root mean absolute error (RMSE) is defined as follows:

[0079]

[0080] Coefficient of Determination (R²) 2 The definition of ) is:

[0081]

[0082] in, This is the average of the true values.

[0083] Specifically, the generalization ability of the model is evaluated using a generalization ability assessment index to obtain the evaluation results. Based on the evaluation results, the final connectivity detection model is determined among the models corresponding to each regression algorithm.

[0084] For example, Figure 3 shows the cross plot of predicted and actual values ​​for the test set of the first sand-potential connectivity coefficient. Figure 3(a) shows the cross plot of predicted and actual values ​​for the corresponding multiple linear regression algorithm. Figure 3(b) shows the cross plot of predicted and actual values ​​for the corresponding random forest algorithm. Figure 3(c) shows the cross plot of predicted and actual values ​​for the corresponding BP neural network algorithm. Figure 3(d) shows the cross plot of predicted and actual values ​​for the corresponding XGBoost algorithm.

[0085] Table 2 shows the evaluation results of various model evaluation indicators, i.e., generalization ability evaluation indicators, for the test set of the first sand potential connectivity coefficient.

[0086] Table 2. Model Evaluation Indicators for the First Sandy Subsurface Connectivity Coefficient Test Set

[0087]

[0088] As shown in Figure 3 and Table 2, for fitting the first sand potential connectivity coefficient, the four algorithms do not exhibit significant overfitting and show good prediction accuracy and generalization performance. Among them, the Random Forest and XGBoost models have similar performance and are better than the other two algorithms.

[0089] For example, the intersection of the true and predicted values ​​of the second sand-potential connectivity coefficient is shown in Figure 4. Figure 4(a) is the intersection of predicted and true values ​​for the corresponding multiple linear regression algorithm. Figure 4(b) is the intersection of predicted and true values ​​for the corresponding random forest algorithm. Figure 4(c) is the intersection of predicted and true values ​​for the corresponding BP neural network algorithm. Figure 4(d) is the intersection of predicted and true values ​​for the corresponding XGBoost algorithm. Furthermore, the mean absolute error, root mean square error, and coefficient of determination of the corresponding training and prediction sets are shown in Table 3.

[0090] Table 3. Model Evaluation Indicators for the Second Sandy Subsurface Connectivity Coefficient Test Set

[0091]

[0092]

[0093] As shown in Figure 4 and Table 3, all four algorithms perform relatively well in fitting the second sand potential connectivity coefficient. Among them, the random forest model has a more serious overfitting problem, while the BP neural network model shows outstanding prediction accuracy and generalization performance. The other three algorithms have similar results.

[0094] In this embodiment of the application, optionally, after obtaining the connectivity detection model, the method further includes: obtaining target attribute parameters of the first target reservoir and the second target reservoir; inputting the target attribute parameters into the connectivity detection model to obtain connectivity detection results.

[0095] Among them, the first target reservoir and the second target reservoir are the sandstone reservoir and the buried hill reservoir to be tested, respectively.

[0096] The technical solution of this application includes: using the first and second sandstone connectivity coefficients of already produced wells as labels for corresponding historical attribute parameters, and generating training samples based on the historical attribute parameters and the labels; the first and second historical reservoirs are spatially superimposed; training the connectivity detection model to be trained based on the training samples to obtain a connectivity detection model, and performing connectivity detection on the first and second target reservoirs based on the connectivity detection model. This technical solution, based on this model, can accurately determine the connectivity coefficients between superimposed sandstone reservoirs and buried hill reservoirs. These connectivity coefficients can provide theoretical guidance for dynamic analysis, development deployment, and adjustment of superimposed reservoirs; they can also quantitatively characterize the connectivity relationship between sandstone and buried hill reservoirs, reflecting the degree of interference between production wells in the two types of reservoirs.

[0097] Example 3

[0098] Figure 5 This is a schematic diagram of a connectivity detection device for a stacked reservoir provided in Embodiment 3 of this application. This device can execute the connectivity detection method for stacked reservoirs provided in any embodiment of this invention, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 5 As shown, the device includes:

[0099] The training sample generation module 310 is used to use the reservoir connectivity coefficient of the exploited well as the label of the corresponding historical attribute parameter, and generate training samples based on the historical attribute parameter and the label; the reservoir connectivity coefficient reflects the reservoir connectivity between the first historical reservoir and the second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially superimposed.

[0100] The connectivity detection model determination module 320 is used to train the connectivity detection model to be trained based on the training samples to obtain the connectivity detection model, and to perform connectivity detection on the first target reservoir and the second target reservoir based on the connectivity detection model.

[0101] The technical solution of this application includes: a training sample generation module, used to use the reservoir connectivity coefficient of the exploited well as the label of the corresponding historical attribute parameter, and to generate training samples based on the historical attribute parameter and the label; the reservoir connectivity coefficient reflects the reservoir connectivity between the first historical reservoir and the second historical reservoir of the exploited well; the first historical reservoir and the second historical reservoir are spatially superimposed; and a connectivity detection model determination module, used to train the connectivity detection model to be trained based on the training samples to obtain a connectivity detection model, and to perform connectivity detection on the first target reservoir and the second target reservoir based on the connectivity detection model. This technical solution uses the reservoir connectivity coefficient as the label of the corresponding historical attribute parameter to generate training samples, obtaining a model with connectivity detection capability. Based on this model, the connectivity coefficient between superimposed reservoirs can be accurately determined, and this connectivity coefficient can provide theoretical guidance for dynamic analysis, development deployment, and adjustment of superimposed reservoirs.

[0102] Optionally, the first historical reservoir is a sandstone reservoir, and the second historical reservoir is a buried hill reservoir;

[0103] Accordingly, the reservoir connectivity coefficient includes: the first sand-potential connectivity coefficient and the second sand-potential connectivity coefficient;

[0104] Accordingly, the ratio of the first oil and gas flow rate to the oil and gas production of the sandstone reservoir is determined as the first sandstone-buried hill connectivity coefficient; the first oil and gas flow rate is the flow from the buried hill reservoir into the sandstone reservoir.

[0105] The ratio of the second oil and gas flow rate to the oil and gas production of the buried hill reservoir is determined as the second sand-buried hill connectivity coefficient; the second oil and gas flow rate is the flow from the sandstone reservoir into the buried hill reservoir.

[0106] Optional, historical attribute parameters include at least one of the following: sand layer porosity, buried hill matrix porosity, buried hill fracture porosity, sandstone permeability, buried hill matrix permeability, buried hill fracture permeability, sandstone thickness, buried hill thickness, well spacing, number of fractures, sand layer recovery rate, and buried hill layer recovery rate.

[0107] Optionally, the device further includes:

[0108] The preprocessing module is used to preprocess historical attribute parameters; the preprocessing includes at least one of the following: outlier handling, missing value handling, and standardization.

[0109] Optionally, the apparatus further includes: a model training module based on a regression algorithm, used to train the connectivity detection model to be trained based on at least one of the following regression algorithms to obtain a connectivity detection model;

[0110] The regression algorithm includes:

[0111] Multiple linear regression, random forest regression, backpropagation (BP) neural network regression, and XGBoost regression.

[0112] Optionally, the device further includes:

[0113] The evaluation result determination module is used to evaluate the generalization ability of the connectivity detection model during the training process and obtain the evaluation result; the generalization ability evaluation index includes at least one of the following: mean absolute error, root mean square error and coefficient of determination.

[0114] The regression algorithm determination module is used to determine the regression algorithm used by the connectivity detection model based on the evaluation results.

[0115] Optionally, the device further includes:

[0116] The target attribute parameter acquisition module is used to acquire the target attribute parameters of the first target reservoir and the second target reservoir.

[0117] The connectivity detection result determination module is used to input the target attribute parameters into the connectivity detection model to obtain the connectivity detection result.

[0118] The connectivity detection device for stacked reservoirs provided in this application embodiment can execute the connectivity detection method for stacked reservoirs provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0119] Example 4

[0120] Figure 6 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. 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, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0121] like Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0122] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0123] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the connectivity detection method for stacked reservoirs.

[0124] In some embodiments, the connectivity detection method for the stacked reservoir can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the connectivity detection method for the stacked reservoir described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the connectivity detection method for the stacked reservoir by any other suitable means (e.g., by means of firmware).

[0125] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] Computer programs used to implement 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 device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0127] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0128] To provide 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 pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide 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 sound input, voice input, or tactile input).

[0129] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0130] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the 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 cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0131] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0132] The specific embodiments described above do not constitute a limitation on the scope of protection of this 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 principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting the connectivity of stacked reservoirs, characterized in that, include: The reservoir connectivity coefficient of the exploited wells is used as the label of the corresponding historical attribute parameter, and training samples are generated based on the historical attribute parameter and the label. The reservoir connectivity coefficient reflects the reservoir connectivity between the first and second historical reservoirs of the exploited well; the first and second historical reservoirs are spatially superimposed. The connectivity detection model is trained based on the training samples to obtain a connectivity detection model, and connectivity detection is performed on the first target reservoir and the second target reservoir based on the connectivity detection model. The first historical reservoir is a sandstone reservoir, and the second historical reservoir is a buried hill reservoir. Accordingly, the reservoir connectivity coefficient includes: the first sand-potential connectivity coefficient and the second sand-potential connectivity coefficient; Accordingly, the ratio of the first oil and gas flow rate to the oil and gas production of the sandstone reservoir is determined as the first sandstone-buried hill connectivity coefficient; the first oil and gas flow rate is the flow from the buried hill reservoir into the sandstone reservoir. The ratio of the second oil and gas flow rate to the oil and gas production of the buried hill reservoir is determined as the second sandstone-buried hill connectivity coefficient; the second oil and gas flow rate is the flow rate from the sandstone reservoir into the buried hill reservoir. The historical attribute parameters include at least one of the following: sand layer porosity, buried hill matrix porosity, buried hill fracture porosity, sandstone permeability, buried hill matrix permeability, buried hill fracture permeability, sandstone thickness, buried hill thickness, well spacing, number of fractures, sand layer recovery rate, and buried hill layer recovery rate. The method further includes: The connectivity detection model is trained based on at least one of the following regression algorithms to obtain the connectivity detection model; The regression algorithm includes: Multiple linear regression, random forest regression, backpropagation (BP) neural network regression, and XGBoost regression; The method further includes: During the training process of the connectivity detection model, the generalization ability evaluation index is used to evaluate the generalization ability of the model and obtain the evaluation result; the generalization ability evaluation index includes at least one of the following: mean absolute error, root mean square error and coefficient of determination. Based on the evaluation results, the regression algorithm used in the connectivity detection model is determined; After obtaining the connectivity detection model, the method further includes: Obtain the target attribute parameters of the first and second target reservoirs; The target attribute parameters are input into the connectivity detection model to obtain the connectivity detection results.

2. The method according to claim 1, characterized in that, The method further includes: The historical attribute parameters are preprocessed; the preprocessing includes at least one of the following: outlier handling, missing value handling, and standardization.

3. A connectivity detection device for a stacked reservoir, characterized in that, include: The training sample generation module is used to use the reservoir connectivity coefficient of the exploited wells as the label of the corresponding historical attribute parameter, and generate training samples based on the historical attribute parameter and the label. The reservoir connectivity coefficient reflects the reservoir connectivity between the first and second historical reservoirs of the exploited well; the first and second historical reservoirs are spatially superimposed. The connectivity detection model determination module is used to train the connectivity detection model to be trained based on the training samples to obtain the connectivity detection model, so as to perform connectivity detection on the first target reservoir and the second target reservoir based on the connectivity detection model. The first historical reservoir is a sandstone reservoir, and the second historical reservoir is a buried hill reservoir. Accordingly, the reservoir connectivity coefficient includes: the first sand-potential connectivity coefficient and the second sand-potential connectivity coefficient; Accordingly, the ratio of the first oil and gas flow rate to the oil and gas production of the sandstone reservoir is determined as the first sandstone-buried hill connectivity coefficient; the first oil and gas flow rate is the flow from the buried hill reservoir into the sandstone reservoir. The ratio of the second oil and gas flow rate to the oil and gas production of the buried hill reservoir is determined as the second sandstone-buried hill connectivity coefficient; the second oil and gas flow rate is the flow rate from the sandstone reservoir into the buried hill reservoir. The historical attribute parameters include at least one of the following: sand layer porosity, buried hill matrix porosity, buried hill fracture porosity, sandstone permeability, buried hill matrix permeability, buried hill fracture permeability, sandstone thickness, buried hill thickness, well spacing, number of fractures, sand layer recovery rate, and buried hill layer recovery rate. The connectivity detection model determination module is further used for: The connectivity detection model is trained based on at least one of the following regression algorithms to obtain the connectivity detection model; The regression algorithm includes: Multiple linear regression, random forest regression, backpropagation (BP) neural network regression, and XGBoost regression; The connectivity detection model determination module is specifically used for: During the training process of the connectivity detection model, the generalization ability evaluation index is used to evaluate the generalization ability of the model and obtain the evaluation result; the generalization ability evaluation index includes at least one of the following: mean absolute error, root mean square error and coefficient of determination. Based on the evaluation results, the regression algorithm used in the connectivity detection model is determined; The parameter acquisition module is used for: Obtain the target attribute parameters of the first and second target reservoirs; The target attribute parameters are input into the connectivity detection model to obtain the connectivity detection results.

4. 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 that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the connectivity detection method for the stacked reservoir as described in any one of claims 1-2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the connectivity detection method for the stacked reservoir as described in any one of claims 1-2.

Images