Methods, systems, electronic devices, and storage media for evaluating effectiveness of sandstone reservoirs

Abstract

The present application belongs to the field of geophysical well logging, and particularly relates to a method, system, electronic device and storage medium for evaluating the effectiveness of a sandstone reservoir, aiming to solve the problem that there is no established method for evaluating the effectiveness of a reservoir. The present application comprises: taking standard well logging data with a correlation parameter greater than a threshold value as training data; performing model training on each type of training data and a historical reservoir pore structure parameter related thereto; assigning a weight to each training model based on the accuracy of each training model; inputting current well logging data into each training model corresponding to a reservoir pore structure parameter to obtain a predicted value of each pore structure parameter; and calculating each pore structure parameter based on the predicted value of each pore structure parameter and the weight of the corresponding training model. A conventional pore structure comprehensive index and a reservoir macroscopic porosity-permeability index are constructed based on each pore structure parameter, and then evaluated. The present application guides oilfield exploration and development, and improves oil production.

Description

Technical Field

[0001] This invention belongs to the field of geophysical logging, and specifically relates to a method, system, electronic device and storage medium for evaluating the effectiveness of sandstone reservoirs. Background Technology

[0002] There are many methods for reservoir effectiveness evaluation, which can be broadly categorized into two main types. The first type is based on conventional logging and core analysis data. After analyzing the main controlling factors of reservoir effectiveness, two or more parameters are selected, and cross-plot analysis is used to establish a reservoir effectiveness evaluation method. The second type is based on imaging logging technologies such as nuclear magnetic resonance (NMR), electrical imaging, and array acoustic logging. Analysis of the main controlling factors of reservoir effectiveness reveals that the quality of the reservoir's pore structure is one of the main controlling factors. Therefore, the key to reservoir effectiveness evaluation is the assessment of the reservoir's pore structure. Parameters such as the geometric mean of T2 and the proportion of different pore components obtained from NMR logging can effectively classify the pore structure of the reservoir. Therefore, NMR logging has the best application effect in reservoir effectiveness evaluation. However, NMR logging is more expensive than conventional logging, so it is only used in key wells and key intervals, making this method unsuitable for well sections without NMR logging. Current methods for evaluating reservoir effectiveness based on conventional data generally combine rock physical analysis with conventional logging data, applying regression or machine learning algorithms to calculate parameters related to reservoir effectiveness, and establishing effectiveness evaluation methods through cross-plot analysis. Traditional conventional reservoir effectiveness evaluation typically employs statistical regression and machine algorithms to predict mercury injection porosimetry pore structure parameters. Based on this, it combines reservoir quality-related parameters such as porosity and permeability to establish effectiveness evaluation methods. The key parameter evaluation of pore structure mainly involves establishing a regression relationship between logging curves and reservoir pore structure parameters such as displacement pressure and mean radius obtained from core experiments. In most cases, this relationship is linear and univariate. However, in real-world environments, reservoir conditions are complex and highly heterogeneous, and the relationship between logging curves and reservoir pore structure parameters is often non-linear. Traditional methods struggle to integrate more geological information to fully reflect the relationship between logging curves and reservoir pore structure parameters, resulting in prediction models with poor accuracy and limited adaptability. Therefore, there is an urgent need for a new method and technology to establish a nonlinear predictive relationship between well logging curves and reservoir pore structure parameters under specific geological conditions, and to further adapt to the requirements of exploration and development of complex reservoir oil and gas fields.

[0003] With the development of computer big data technology, non-traditional mathematical machine learning techniques are increasingly being applied in reservoir parameter prediction and reservoir productivity prediction. Random Forest (RF) is an ensemble learning algorithm based on decision trees. Its core principles are Bagging and the random subspace method. Given an input sample, RF averages the predictions from multiple decision trees to obtain the final result. It can perform nonlinear inversion and has excellent prediction performance for high-dimensional features. Furthermore, RF is simple to operate, easy to implement, less prone to overfitting, and computationally efficient. KNN regression predicts continuous data labels by calculating the average of the K nearest neighbors. SVM's basic idea is to map the sample space to a feature space of a certain dimension using a kernel function, finding the optimal classification surface of the original sample in the feature space, and obtaining a linear or nonlinear relationship between the input variables and the output result—essentially, finding an SVM for pattern classification. SVR regression is an important application branch of SVM, mainly achieving linear regression by constructing a linear decision function in a high-dimensional space after increasing the dimensionality. By introducing a kernel function, both dimensionality can be increased while controlling overfitting. Kernel functions can replace linear terms in linear equations, making the original linear algorithm "nonlinear" and enabling nonlinear regression. There are many types of kernel functions, such as linear kernels, polynomial kernels, Sigmoid kernels, and radial basis function (RBF) kernels.

[0004] However, there is currently no method to calculate reservoir pore structure parameters using intelligent algorithms that combine classification and regression based on conventional logging data, in order to characterize the quality of reservoir pore structure and establish a reservoir effectiveness evaluation method. This would help improve the accuracy of reservoir effectiveness evaluation. Summary of the Invention

[0005] To address the aforementioned problems in existing technologies—namely, the lack of a method for calculating reservoir pore structure parameters using intelligent algorithms combining classification and regression based on conventional well logging data—to characterize the quality of reservoir pore structure and thus establish a reservoir effectiveness evaluation method, this invention provides a method for evaluating the effectiveness of sandstone reservoirs. The method includes:

[0006] Correlation analysis was performed between each type of standard logging data and each historical pore structure parameter to obtain correlation parameters. Standard logging data with correlation parameters greater than the threshold were used as training data.

[0007] The training data of various types and their related historical reservoir pore structure parameters are used to train the model, so as to obtain the training model of each reservoir pore structure parameter and the accuracy of the training model.

[0008] Weights are assigned to the training models based on their accuracy. The current logging data is input into the training models corresponding to the pore structure parameters of each reservoir to obtain the predicted values ​​of each pore structure parameter. The pore structure parameters are then calculated based on the predicted values ​​of each pore structure parameter and the weights of the corresponding training models.

[0009] A comprehensive index of conventional pore structure and a macroscopic porosity-permeability index of reservoir are constructed based on various pore structure parameters, and an evaluation is performed based on the comprehensive index of conventional pore structure and the macroscopic porosity-permeability index of reservoir.

[0010] In a preferred embodiment, the standard logging data includes gamma, resistivity, acoustic waves, density, and neutrons.

[0011] In a preferred embodiment, the pore structure parameters include reservoir pore structure, porosity, permeability, and clay content.

[0012] In a preferred embodiment, the pore structure parameters are calculated based on the predicted values ​​of each pore structure parameter and the corresponding weights of the training model, including:

[0013] For the current pore structure parameters: Z=q1.z1+q2.z2+···+qn.zn;

[0014] Where Z represents the current pore structure parameter value, z1 represents the predicted value output by the first training model for the current pore structure parameter value, q1 represents the accuracy of the first training model for the current pore structure parameter value, z2 represents the predicted value output by the second training model for the current pore structure parameter value, q2 represents the accuracy of the second training model for the current pore structure parameter value, zn represents the predicted value output by the nth training model for the current pore structure parameter value, and qn represents the accuracy of the nth training model for the current pore structure parameter value.

[0015] In a preferred embodiment, the comprehensive index of the conventional pore structure is: CQI = Cpsf·Φ·K / Vsh;

[0016] Wherein, CQI is the comprehensive index of conventional pore structure; Cpsf is the reservoir pore structure parameter calculated by the combined model; Φ is the effective porosity of the reservoir; K is the reservoir permeability; and Vsh is the clay content.

[0017] In a preferred embodiment, the reservoir macroporous permeability index is: EPI = Φ·(logK);

[0018] Wherein, EPI is the macroscopic porosity index; Φ is the effective porosity of the reservoir; and K is the reservoir permeability.

[0019] A second aspect of the invention provides a system for evaluating the effectiveness of sandstone reservoirs, the system comprising:

[0020] The correlation analysis module is used to perform correlation analysis between each type of standard logging data and each historical pore structure parameter to obtain correlation parameters. Standard logging data with correlation parameters greater than the threshold are used as training data.

[0021] The parameter training module is used to train models using various types of training data and their associated historical reservoir pore structure parameters, to obtain various training models for each reservoir pore structure parameter and the accuracy of the training models.

[0022] The parameter calculation module is used to assign weights to the training models based on the accuracy of each training model. It inputs the current logging data into the training model corresponding to each reservoir pore structure parameter to obtain the predicted value of each pore structure parameter. Based on the predicted value of each pore structure parameter and the weight of the corresponding training model, the pore structure parameter is calculated.

[0023] The index construction module is used to construct a comprehensive index of conventional pore structure and a macroscopic porosity-permeability index of reservoir based on various pore structure parameters, and to evaluate the reservoir based on the comprehensive index of conventional pore structure and the macroscopic porosity-permeability index of reservoir.

[0024] A third aspect of the invention provides an electronic device comprising: at least one processor; and a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by the processor for implementing the aforementioned method for evaluating the effectiveness of sandstone reservoirs.

[0025] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions for execution by the computer to implement the above-described method for evaluating the effectiveness of sandstone reservoirs.

[0026] The beneficial effects of this invention are:

[0027] (1) This invention provides a method for evaluating the effectiveness of sandstone reservoirs using a combined intelligent model. By constructing an intelligent learning framework of classification and regression, and utilizing the response relationship between conventional logging data and nuclear magnetic resonance pore structure characteristic parameters, a method for calculating conventional pore structure parameters based on big data analysis of logging is established. By predicting reservoir pore structure parameters, the influence of missing logging data on the quantitative evaluation of reservoir pore structure quality is compensated. Furthermore, based on parameters such as conventional pore structure, porosity, permeability, and clay content, a comprehensive index of conventional pore structure and a macro-pore-permeability index are constructed to form a reservoir effectiveness evaluation method and standard, providing technical support for oil testing, layer selection, and exploration discovery.

[0028] (2) This invention constructs a complete intelligent calculation system for conventional reservoir pore structure parameters (Cpsf), which can improve the quality of input data and realize the calculation of reservoir pore structure parameters (Cpsf) quickly and accurately. Based on conventional pore structure parameters, porosity, permeability, clay content and other parameters, a comprehensive index of conventional pore structure and a macro-pore-permeability index are constructed to form a reservoir effectiveness evaluation method and standard, which solves the problem of difficulty in reservoir effectiveness evaluation due to the lack of nuclear magnetic logging.

[0029] (3) This invention guides oilfield exploration and development, increases oil production, saves exploration and development costs, and improves economic benefits. Attached Figure Description

[0030] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0031] Figure 1 This is a schematic diagram of a method for evaluating the effectiveness of sandstone reservoirs according to an embodiment of the present invention;

[0032] Figure 2 This is a schematic diagram of standard well logging data according to an embodiment of the present invention;

[0033] Figure 3 This is a schematic diagram illustrating the correlation analysis between each type of standard logging data and each historical pore structure parameter in an embodiment of the present invention;

[0034] Figure 4 It is the relative error of the pore structure parameters obtained based on the training model in this embodiment of the invention;

[0035] Figure 5 This is a comparison chart of the predicted values ​​of pore structure parameters and the geometric mean of NMR T2 in an embodiment of the present invention;

[0036] Figure 6 This is a classification and evaluation chart of the comprehensive index of conventional reservoir pore structure according to an embodiment of the present invention;

[0037] Figure 7 This is a diagram showing the reservoir effectiveness evaluation results of Well C in this embodiment of the invention;

[0038] Figure 8 This is a schematic diagram of the structure of a computer system used to implement the methods, systems, and devices of this application. Detailed Implementation

[0039] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0040] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0041] This invention provides a method for evaluating the effectiveness of sandstone reservoirs, the method comprising:

[0042] Correlation analysis was performed between each type of standard logging data and each historical pore structure parameter to obtain correlation parameters. Standard logging data with correlation parameters greater than the threshold were used as training data.

[0043] The training data of various types and their related historical reservoir pore structure parameters are used to train the model, so as to obtain the training model of each reservoir pore structure parameter and the accuracy of the training model.

[0044] Weights are assigned to the training models based on their accuracy. The current logging data is input into the training models corresponding to the pore structure parameters of each reservoir to obtain the predicted values ​​of each pore structure parameter. The pore structure parameters are then calculated based on the predicted values ​​of each pore structure parameter and the weights of the corresponding training models.

[0045] A comprehensive index of conventional pore structure and a macroscopic porosity-permeability index of reservoir are constructed based on various pore structure parameters, and an evaluation is performed based on the comprehensive index of conventional pore structure and the macroscopic porosity-permeability index of reservoir.

[0046] To more clearly explain the method for evaluating the effectiveness of sandstone reservoirs according to the present invention, the following is in conjunction with... Figure 1 The steps in the embodiments of the present invention will be described in detail below.

[0047] The method for evaluating the effectiveness of sandstone reservoirs according to the first embodiment of the present invention is described in detail below:

[0048] Correlation analysis was performed between each type of standard logging data and each historical pore structure parameter to obtain correlation parameters. Standard logging data with correlation parameters greater than the threshold were used as training data.

[0049] In this embodiment, the standard logging data is obtained by first standardizing the logging data curves, such as... Figure 2As shown, this standardization aims to ensure a uniform scale for logging information across the entire oilfield, enabling quantitative comparability of logging data across different wells and improving interpretation accuracy. Standardizing and preprocessing logging data before training a machine learning model effectively enhances the model's predictive power and accuracy. Secondly, it involves removing enlarged well sections. In mudstone layers and certain loose rock formations, wellbore collapse often occurs due to drilling mud soaking and scouring, resulting in an actual well diameter larger than the drill bit diameter, leading to enlarged well diameter. This enlarged diameter significantly impacts conventional logging curve values, greatly affecting the extrapolation capability of machine learning models during training. For logging data, the data volume is relatively small, and small sample sizes are more sensitive to outliers and contaminated data. The correlation between reservoir NMR pore structure parameters (T2 geometric mean) and logging data in enlarged well sections is poor (contaminated data). Therefore, before model training, it is necessary to remove the influence of contaminated data such as enlarged well sections to improve model prediction accuracy.

[0050] In this embodiment of the invention, standard logging data includes gamma, resistivity, acoustic waves, density, and neutrons.

[0051] In this embodiment, correlation and sensitivity analysis of standard logging data are performed to obtain a correlation analysis diagram between the input conventional logging curve and the nuclear magnetic resonance pore structure parameter (T2 geometric mean), as shown below. Figure 3 As shown, the correlation between the conventional curves and the label data, namely the NMR pore structure parameters (T2 geometric mean), can be intuitively displayed, providing a reference for the optimal selection of feature inputs.

[0052] In this embodiment, sensitivity analysis is performed on standard logging data. Small weighting coefficients result in the smallest error, indicating low sensitivity; for example, well diameter is a low-sensitivity curve. Large weighting coefficients result in the smallest error, indicating high sensitivity; for example, DEN, CNL, AC, and resistivity are high-sensitivity curves. Through correlation and sensitivity analysis, the optimal feature input curves can be selected for model training, resulting in the optimal model.

[0053] The training data of various types and their related historical reservoir pore structure parameters are used to train the model, so as to obtain the training model of each reservoir pore structure parameter and the accuracy of the training model.

[0054] In this embodiment, the reservoir porosity structure parameter regression training module first extracts conventional logging data and NMR porosity structure parameter (T2 geometric mean) data from well data with NMR logging data to construct a training set. Conventional logging data includes, but is not limited to, gamma, resistivity, acoustic, density, and neutron measurements. The NMR porosity structure parameter data is the NMR T2 geometric mean extracted from well data with NMR logging data. Then, machine learning regression methods such as SVR, KNN, and RF are used to train the training set to obtain a reservoir porosity structure parameter regression model. Simultaneously, the training weights of individual regression models are calculated using the prediction accuracy of the regression models on the training set.

[0055] Weights are assigned to the training models based on their accuracy. The current logging data is input into the training models corresponding to the pore structure parameters of each reservoir to obtain the predicted values ​​of each pore structure parameter. The pore structure parameters are then calculated based on the predicted values ​​of each pore structure parameter and the weights of the corresponding training models.

[0056] In this embodiment of the invention, the pore structure parameters include reservoir pore structure, porosity, permeability, and clay content.

[0057] In the intelligent prediction module for pore structure parameters across the entire well section, the data cleaning and preprocessing module first standardizes the data from different wells across the entire well section and filters out enlarged well sections to maintain the consistency and standardization of the multi-well logging data. Then, three trained SVR, KNN, and RF reservoir pore structure parameter prediction models are used to predict reservoir pore structure parameters on the conventional curves of the well data, obtaining and recording the three predicted reservoir pore structure parameters. Next, the combined model prediction results are calculated using the weights of the three models and the prediction results through a combined model formula to obtain the conventional pore structure parameters predicted by the combined model.

[0058] In this embodiment, the pore structure parameters are calculated based on the predicted values ​​of each pore structure parameter and the corresponding weights of the training model, including:

[0059] For the current pore structure parameters: Z=q1.z1+q2.z2+···+qn.zn;

[0060] Where Z represents the current pore structure parameter value, z1 represents the predicted value output by the first training model for the current pore structure parameter value, q1 represents the accuracy of the first training model for the current pore structure parameter value, z2 represents the predicted value output by the second training model for the current pore structure parameter value, q2 represents the accuracy of the second training model for the current pore structure parameter value, zn represents the predicted value output by the nth training model for the current pore structure parameter value, and qn represents the accuracy of the nth training model for the current pore structure parameter value.

[0061] A comprehensive index of conventional pore structure and a macroscopic porosity-permeability index of reservoir are constructed based on various pore structure parameters, and an evaluation is performed based on the comprehensive index of conventional pore structure and the macroscopic porosity-permeability index of reservoir.

[0062] In this embodiment, the comprehensive index of the conventional pore structure is: CQI = Cpsf·Φ·K / Vsh;

[0063] Wherein, CQI is the comprehensive index of conventional pore structure; Cpsf is the reservoir pore structure parameter calculated by the combined model; Φ is the effective porosity of the reservoir; K is the reservoir permeability; and Vsh is the clay content.

[0064] In this embodiment, the reservoir macroscopic porosity-permeability index is: EPI = Φ·(logK);

[0065] Wherein, EPI is the macroscopic porosity index; Φ is the effective porosity of the reservoir; and K is the reservoir permeability.

[0066] Although the steps in the above embodiments are described in the above order, those skilled in the art will understand that in order to achieve the effect of this embodiment, different steps do not need to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple variations are all within the protection scope of this invention.

[0067] In embodiments of the present invention, the data cleaning and preprocessing steps include functions such as multi-well data standardization and well diameter expansion screening, which are used to improve the quality of input data, construct training sets, and achieve the purpose of improving model accuracy.

[0068] The pore structure parameter regression training steps involve training three regression models, SVR, KNN, and RF, to obtain the pore structure parameter regression model. At the same time, the weights of the three regression models SVR, KNN, and RF in the combined model are calculated.

[0069] The combined model for predicting pore structure parameters across the entire well section includes data cleaning and preprocessing, pore structure parameter (Cpsf) calculation, and combined calculation functions, which are used to automatically calculate the pore structure parameter (Cpsf) values ​​across the entire well section.

[0070] The steps for evaluating the effectiveness of reservoir control by pore structure aim to establish reservoir classification and evaluation standards by constructing the Conventional Pore Structure Comprehensive Index (CQI) and the Macroscopic Porosity-Permeability Index (EPI).

[0071] To fully illustrate the method for evaluating the effectiveness of sandstone reservoirs according to the present invention, an example is also provided for specific explanation:

[0072] This study utilizes a combination of well logging data, production data, and testing data from an oilfield in northern my country to evaluate reservoir effectiveness using a combined intelligent model. The input well logging data includes natural gamma ray logging (GR), acoustic logging (AC), density logging (DEN), neutron logging (CNL), resistivity logging (M2RX), shale content (SH), and porosity (POR). Nuclear magnetic resonance (NMR) data is represented by T2 geometric mean (T2LM). Training and testing datasets are constructed by combining these well logging and T2LM data. Table 1 shows some of the training data constructed based on the well logging and testing data.

[0073] The constructed training dataset was input into the data cleaning and preprocessing steps. Data standardization and diameter expansion filtering were performed. The preprocessed data was then used to train three regression models: SVR, KNN, and RF, resulting in a regression model for conventional pore structure parameters. The weights of the three regression models (SVR, KNN, and RF) in the combined model were calculated as q1 = 0.45, q2 = 0.25, and q3 = 0.3, respectively. The weights and the prediction results of the individual regression models were input into the combined prediction model to obtain the combined prediction results. The prediction results of the individual models and the combined model were compared with the T2LM values ​​from nuclear magnetic resonance logging for error analysis. The results showed that the average relative error of the combined model was 5.5%. The relative error of the combined prediction results is shown in the figure below. Figure 4 As shown, the average relative errors of the three regression models, SVR, KNN, and RF, were 6.5%, 7.5%, and 7.15%, respectively. The combined model significantly improved the accuracy of the prediction results, and the predicted pore structure parameters (Cpsf) were closer to the T2LM obtained from nuclear magnetic resonance logging.

[0074] Using data cleaning and preprocessing steps and a trained reservoir pore structure parameter regression model, pore structure parameter values ​​were predicted for data from more than 10 wells in the study area, yielding pore structure parameter values ​​(Cpsf) for these wells. Figure 5 A graph is plotted to show the predicted results of the T2 geometric mean of the nuclear magnetic resonance (NMR) pore structure parameter and the conventional pore structure parameter. From left to right, the graph represents natural gamma, depth, sonic transit time, neutron, density, deep resistivity, clay content, porosity, and pore structure parameter. The Cpsf curve in the rightmost channel is the conventional pore structure parameter curve predicted using this method, and the T2LM curve is the T2 geometric mean curve from the NMR logging of this well. The predicted Cpsf and T2LM are basically consistent in size and shape, indicating that the algorithm for predicting pore structure parameters based on conventional logging data through classification and regression combination has good generalization ability and can effectively compensate for the difficulty in evaluating reservoir pore structure due to the lack of NMR logging.

[0075] Finally, based on logging, production, and testing data from more than 10 wells in the study area, a comprehensive conventional pore structure index (CQI) and a macroporous permeability index (EPI) were constructed. According to the reservoir productivity classification standard for the study area, reservoir grading and evaluation standards were established using the reservoir EPI and CQI, resulting in a reservoir grading and evaluation chart, as shown below. Figure 6 As shown in the figure, Class I reservoirs are high-yield reservoirs with a yield of more than 20 cubic meters per meter; Class II reservoirs are medium-to-high-yield reservoirs with a yield of 5-20 cubic meters per meter; Class III reservoirs are medium-yield reservoirs with a yield of 2-5 cubic meters per meter; and Class IV reservoirs are low-yield reservoirs with a yield of less than 2 cubic meters per meter.

[0076] The established comprehensive index-based evaluation method for conventional reservoir pore structure was applied to well C in the study area. Figure 7 This is the logging results for reservoir effectiveness evaluation in Well C. In the figure, line 8 shows the conventional reservoir pore structure parameters calculated using a combined machine learning algorithm; line 9 shows the macroscopic porosity-permeability index; and line 10 shows the conventional pore structure evaluation index. For the macroscopic porosity-permeability index, pink areas indicate reservoirs of types I, II, III, and IV; light green areas indicate types II, III, and IV; and gray areas indicate type V (dry layer). For the conventional pore structure evaluation index, red areas indicate types I and II; purple areas indicate type II; green areas indicate type III; light blue indicates type IV; and yellow indicates dry. The 128th layer in this well (interval 5688.6–4691.2m) has good reservoir properties, with a porosity of approximately 18% and a resistivity of approximately 2 Ω·m, interpreted as an oil-bearing layer in logging. The macroscopic porosity index of this layer is greater than 40, and the conventional pore structure index of the reservoir is mostly greater than 12. According to the reservoir classification evaluation standard, this layer is a Class I reservoir. Post-perforation testing of this layer yielded a daily oil production of 50.68 tons, and the reservoir classification conclusion is in good agreement with the testing results.

[0077] A system for evaluating the effectiveness of sandstone reservoirs according to a second embodiment of the present invention, the system comprising:

[0078] The correlation analysis module is used to perform correlation analysis between each type of standard logging data and each historical pore structure parameter to obtain correlation parameters. Standard logging data with correlation parameters greater than the threshold are used as training data.

[0079] The parameter training module is used to train models using various types of training data and their associated historical reservoir pore structure parameters, to obtain various training models for each reservoir pore structure parameter and the accuracy of the training models.

[0080] The parameter calculation module is used to assign weights to the training models based on the accuracy of each training model. It inputs the current logging data into the training model corresponding to each reservoir pore structure parameter to obtain the predicted value of each pore structure parameter. Based on the predicted value of each pore structure parameter and the weight of the corresponding training model, the pore structure parameter is calculated.

[0081] The index construction module is used to construct a comprehensive index of conventional pore structure and a macroscopic porosity-permeability index of reservoir based on various pore structure parameters, and to evaluate the reservoir based on the comprehensive index of conventional pore structure and the macroscopic porosity-permeability index of reservoir.

[0082] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the system described above can be found in the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0083] It should be noted that the system for evaluating the effectiveness of sandstone reservoirs provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be merged into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the various modules or steps and are not considered as an improper limitation of the present invention.

[0084] An electronic device according to a third embodiment of the present invention includes:

[0085] At least one processor; and

[0086] A memory communicatively connected to at least one of the processors; wherein,

[0087] The memory stores instructions that can be executed by the processor to implement the above-described method for evaluating the effectiveness of sandstone reservoirs.

[0088] A fourth embodiment of the present invention provides a computer-readable storage medium storing computer instructions for execution by a computer to implement the above-described method for evaluating the effectiveness of sandstone reservoirs.

[0089] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the storage device and processing device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0090] Those skilled in the art will recognize that the modules and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. The programs corresponding to the software modules and method steps can be placed in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art. To clearly illustrate the interchangeability of electronic hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the invention.

[0091] The following is for reference. Figure 8 It shows a schematic diagram of the structure of a computer system for implementing the methods, systems, and devices of this application. Figure 8 The server shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0092] like Figure 8 As shown, the computer system includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in Read Only Memory (ROM) 602 or programs loaded from storage section 608 into Random Access Memory (RAM) 603. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0093] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0094] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0095] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The terms “first”, “second”, etc., are used to distinguish similar objects, not to describe or indicate a specific order or sequence.

[0098] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus / device.

[0099] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for evaluating the effectiveness of sandstone reservoirs, characterized in that, The method includes: Correlation analysis was performed between each type of standard logging data and each historical pore structure parameter to obtain correlation parameters. Standard logging data with correlation parameters greater than the threshold were used as training data. The training data of various types and their related historical reservoir pore structure parameters are used to train the model, so as to obtain the training model of each reservoir pore structure parameter and the accuracy of the training model. Weights are assigned to the training models based on their accuracy. The current logging data is input into the training models corresponding to the pore structure parameters of each reservoir to obtain the predicted values ​​of each pore structure parameter. The pore structure parameters are then calculated based on the predicted values ​​of each pore structure parameter and the weights of the corresponding training models. A comprehensive index of conventional pore structure and a macroscopic porosity-permeability index of reservoir are constructed based on various pore structure parameters, and an evaluation is performed based on the comprehensive index of conventional pore structure and the macroscopic porosity-permeability index of reservoir.

2. The method for evaluating the effectiveness of sandstone reservoirs according to claim 1, characterized in that, The standard logging data includes gamma, resistivity, acoustic waves, density, and neutrons.

3. The method for evaluating the effectiveness of sandstone reservoirs according to claim 1, characterized in that, The pore structure parameters include reservoir pore structure, porosity, permeability, and clay content.

4. The method for evaluating the effectiveness of sandstone reservoirs according to claim 1, characterized in that, The pore structure parameters are calculated based on the predicted values ​​of each pore structure parameter and the corresponding weights of the training model. For the current pore structure parameters: Z=q1.z1+q2.z2+···+qn.zn; Where Z represents the current pore structure parameter value, z1 represents the predicted value output by the first training model for the current pore structure parameter value, q1 represents the accuracy of the first training model for the current pore structure parameter value, z2 represents the predicted value output by the second training model for the current pore structure parameter value, q2 represents the accuracy of the second training model for the current pore structure parameter value, zn represents the predicted value output by the nth training model for the current pore structure parameter value, and qn represents the accuracy of the nth training model for the current pore structure parameter value.

5. The method for evaluating the effectiveness of sandstone reservoirs according to claim 4, characterized in that, The comprehensive index of the conventional pore structure is: CQI = Cpsf·Φ·K / Vsh; Wherein, CQI is the comprehensive index of conventional pore structure; Cpsf is the reservoir pore structure parameter calculated by the combined model; Φ is the effective porosity of the reservoir; K is the reservoir permeability; and Vsh is the clay content.

6. The method for evaluating the effectiveness of sandstone reservoirs according to claim 5, characterized in that, The macroscopic porosity and permeability index of the reservoir is: EPI = Φ·(logK); Wherein, EPI is the macroscopic porosity index; Φ is the effective porosity of the reservoir; and K is the reservoir permeability.

7. A system for evaluating the effectiveness of sandstone reservoirs, characterized in that, The system includes: The correlation analysis module is used to perform correlation analysis between each type of standard logging data and each historical pore structure parameter to obtain correlation parameters. Standard logging data with correlation parameters greater than the threshold are used as training data. The parameter training module is used to train models using various types of training data and their associated historical reservoir pore structure parameters, to obtain various training models for each reservoir pore structure parameter and the accuracy of the training models. The parameter calculation module is used to assign weights to the training models based on the accuracy of each training model. It inputs the current logging data into the training model corresponding to each reservoir pore structure parameter to obtain the predicted value of each pore structure parameter. Based on the predicted value of each pore structure parameter and the weight of the corresponding training model, the pore structure parameter is calculated. The index construction module is used to construct a comprehensive index of conventional pore structure and a macroscopic porosity-permeability index of reservoir based on various pore structure parameters, and to evaluate the reservoir based on the comprehensive index of conventional pore structure and the macroscopic porosity-permeability index of reservoir.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor to implement the method for evaluating the effectiveness of sandstone reservoirs as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are executed by the computer to implement the method for evaluating the effectiveness of sandstone reservoirs as described in any one of claims 1-6.

Images