Formation porosity prediction method and device, storage medium and electronic equipment
By constructing a machine learning method based on the XGBoost regression model, and using dielectric constant and resistivity curves to predict formation porosity, this method solves the problems of low automation and significant human influence in existing technologies, and achieves efficient and accurate prediction of formation porosity.
Patent Information
- Application Number
- CN202410603660.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-15
- Publication Date
- 2025-11-18
AI Technical Summary
Existing well logging interpretation technologies have low automation levels in low signal-to-noise ratio, low resolution, and heterogeneous complex reservoirs, and are greatly affected by human factors, making it difficult to accurately identify fluid properties. In particular, the identification rate is low in low-porosity, low-permeability lithological complex reservoirs and low-resistivity oil layers, which cannot meet production requirements.
Using machine learning methods, an XGBoost regression model was constructed based on the dielectric constant and resistivity curves measured by a high-frequency dielectric logging instrument. Through data preprocessing and evaluation strategies, formation porosity was predicted.
It improves the accuracy and efficiency of formation porosity prediction, and the model calculation results are accurate. It is suitable for reservoir parameter prediction and has good application prospects.
Smart Images
Figure CN120974445A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of oil well logging technology, and in particular to a formation porosity prediction method, apparatus, storage medium, and electronic equipment. Background Technology
[0002] The purpose of the background description provided herein is to give an overall background to this application. The statements in this section are merely to provide background information relevant to this application and do not necessarily constitute prior art.
[0003] Well logging interpretation typically faces challenges such as low signal-to-noise ratio, low resolution, heterogeneity, and nonlinearity. Conventional well logging interpretation often relies on professional knowledge and regional experience to extract hidden information from well logging data, calculate geological parameters such as porosity (which directly affects the amount of oil and gas reserves), and manually determine different well logging interpretation conclusions. These methods are often extremely inefficient and prone to errors. Therefore, seeking new reservoir logging interpretation technologies has become a key issue that urgently needs to be addressed in current exploration.
[0004] Fluid property identification is one of the core contents of well logging interpretation. Traditional fluid methods such as the chart method and the overlay method are still widely used in the field, but these methods have a low degree of automation and are greatly affected by human factors. In particular, the identification rate is low in complex reservoirs with low porosity and low permeability and low resistivity oil layers, which can hardly meet the production requirements.
[0005] In view of the above problems, in order to deeply explore the intrinsic relationship between multi-source logging data, gas logging data and fluid information, and with the development of logging technology, it is necessary to propose a new method for predicting formation porosity in order to achieve accurate formation evaluation. Summary of the Invention
[0006] To address the aforementioned issues, this application proposes a method, apparatus, storage medium, and electronic device for predicting formation porosity.
[0007] A first aspect of this application provides a method for predicting formation porosity, the method comprising:
[0008] Construct training samples and preprocess the training samples to obtain preprocessed sample data;
[0009] The pre-processed sample data is used to train the preset regression model to obtain the trained preset regression model.
[0010] Based on the dielectric constant and resistivity curves of the target formation, the porosity of the target formation is determined using the trained preset regression model.
[0011] Furthermore, the training samples include:
[0012] a dielectric constant, a resistivity curve, and a porosity; wherein the dielectric constant and the resistivity curve are taken as training data, and the porosity is taken as a label.
[0013] Further, the training sample is preprocessed by normalizing the data, wherein the expression of the normalization comprises:
[0014]
[0015] wherein x represents an input curve data sample, represents normalized curve data, min(x (n) ) represents the minimum value of the sample, and max(x (n) ) represents the maximum value of the sample.
[0016] Further, the preset regression model comprises:
[0017] an XGBoost regression model.
[0018] Further, it further comprises:
[0019] The porosity of the target formation is evaluated by a preset evaluation strategy to determine the accuracy of the prediction result.
[0020] Further, the preset evaluation strategy comprises:
[0021] The degree of change of the data points is evaluated by a mean square error evaluation model, the volatility of the data is evaluated by a root mean square error evaluation model, and the closeness of the prediction result to the true data set is evaluated by a mean absolute error evaluation model; wherein the mean square error evaluation model comprises:
[0022]
[0023] The root mean square error evaluation model comprises:
[0024]
[0025] The mean absolute error evaluation model comprises:
[0026]
[0027] wherein m is the number of test samples, y i is the true value in the test sample, is the predicted value in the test sample.
[0028] The second aspect of the present application provides a formation porosity prediction device, the device comprises:
[0029] The construction module is configured to construct a training sample and pre-process the training sample to obtain pre-processed sample data.
[0030] The training module is configured to train a preset regression model according to the pre-processed sample data to obtain a trained preset regression model.
[0031] The prediction module is configured to determine the porosity of the target formation according to the dielectric constant and resistivity curves of the target formation by using the trained preset regression model.
[0032] Further, the method further comprises:
[0033] The evaluation module is configured to evaluate the porosity of the target formation by using a preset evaluation strategy to determine the accuracy of the prediction result.
[0034] In a third aspect, the present application provides a computer readable storage medium storing a computer program, which can be executed by one or more processors to implement the steps of the method described above.
[0035] In a fourth aspect, the present application provides an electronic device comprising a memory and one or more processors, wherein the memory stores a computer program, and the memory and the one or more processors are communicatively connected, and the computer program is executed by the one or more processors to implement the steps of the method described above.
[0036] Compared with the prior art, the technical scheme of the present application has the following advantages or beneficial effects:
[0037] According to the high-frequency electromagnetic wave dielectric constant and resistivity measured by the high-frequency dielectric logging instrument, the nonlinear relationship between the dielectric constant and resistivity curves and the porosity is used, the machine learning method is used, the regression model is constructed by processing the actual data, and the formation porosity information is accurately predicted, which can effectively evaluate the formation saturation information, has the superiority of prediction, the model calculation result is accurate, and has a good application prospect in the direction of reservoir parameter prediction. BRIEF DESCRIPTION OF DRAWINGS
[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present application, and those skilled in the art can obtain other drawings according to the provided drawings without creative labor.
[0039] It should be noted that only parts related to the present disclosure are shown in the drawings for the convenience of description. The drawings accompanying the specification of the present application are used to provide further understanding of the present application, the schematic embodiments and the description thereof are used to explain the present application, and do not constitute improper limitation on the present application. In the drawings:
[0040] Figure 1 A flowchart of a formation porosity prediction method provided by an embodiment of the present application is shown in
[0041] Figure 2 A prediction result schematic diagram of the formation porosity prediction method provided by an embodiment of the present application is shown in
[0042] Figure 3 A flowchart of another formation porosity prediction method provided by an embodiment of the present application is shown in DETAILED DESCRIPTION
[0043] The embodiments of the present application will be described in detail below with reference to the drawings and embodiments, so that how the present application applies technical means to solve technical problems and achieves corresponding technical effects can be fully understood and implemented. The embodiments of the present application and each feature in the embodiments can be combined with each other on the premise of no conflict, and the formed technical solutions are all within the protection scope of the present application.
[0044] It should be clear that the following described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.
[0045] One of the purposes of the present application is to establish a dielectric constant-based formation porosity prediction method. Based on the dielectric constant and resistivity curves obtained by the existing high-frequency dielectric logging instrument, the XGBoost method in the machine learning method is used to train the actual logging data, a regression model is constructed, and the formation porosity is predicted.
[0046] Embodiment one
[0047] The present embodiment provides a formation porosity prediction method, Figure 1 A flowchart of a formation porosity prediction method provided by an embodiment of the present application is shown in Figure 1 The method disclosed by the present embodiment includes the following steps:
[0048] Step 110, constructing a training sample and preprocessing the training sample to obtain preprocessed sample data.
[0049] In some embodiments, the training sample includes:
[0050] dielectric constant, resistivity curve and porosity; wherein the dielectric constant and the resistivity curve are taken as training data, and the porosity is taken as a label.
[0051] As an example, first, collect the data of multiple wells based on the high-frequency dielectric logging instrument, take the measured dielectric constant and resistivity curve as the characteristic variable, and take the porosity as the label, and arrange into a data sample set.
[0052] Wherein, the sample set includes 2 input variables: dielectric constant and resistivity curve, and one output is porosity. The experiment is based on leave-one-out method for training, and the sample set is divided into training set and test set, the training set is training data, the model is trained, and the test set is used as test data to test the performance of the model.
[0053] In some embodiments, the training sample is preprocessed by normalizing the data, wherein the expression of the normalization includes:
[0054]
[0055] Wherein, x represents the input curve data sample, represents the normalized curve data, min(x (n) ) represents the minimum value of the sample, and max(x (n) ) represents the maximum value of the sample.
[0056] As an example, in the logging data processing, data preprocessing is an important step, which can help us reduce the noise and uncertainty in the data, and improve the quality and accuracy of the data. In this embodiment, the data preprocessing method is to normalize the data, which can be specifically referred to the expression of the normalization described above. After normalization, the correlation of the curve is not changed, the influence of different curves with different dimensions and orders of magnitude is solved, and the calculation accuracy is improved.
[0057] Step 120, training a preset regression model according to the obtained preprocessed sample data, to obtain a trained preset regression model.
[0058] In some embodiments, the preset regression model includes:
[0059] XGBoost regression model.
[0060] XGBoost is an optimized distributed gradient boosting library, aiming at high efficiency, flexibility and portability. XGBoost is a tool for large-scale parallel boosting trees, which is currently the fastest and best open source boosting tree toolkit, more than 10 times faster than common toolkits. In the field of data science, a large number of Kaggle contestants use XGBoost for data mining competitions, and it is a must-have weapon for major data science competitions. In the industrial field of large-scale data, the distributed version of XGBoost has wide portability, supporting running on Kubernetes, Hadoop, SGE, MPI, Dask and other distributed environments, so that it can well solve the problem of large-scale data in the industrial field.
[0061] The basic idea of XGBoost is to use the second-order Taylor expansion of the loss function as its substitute function, and solve its minimization (derivative is 0) to determine the best split point of the regression tree and the leaf node output value (this point is different from the cart regression tree). In addition, XGBoost fully considers the regularization problem by introducing the number of sub-trees and the leaf node value of the sub-tree in the loss function, which can effectively avoid overfitting. In terms of efficiency, XGBoost uses unique approximate regression tree split point estimation and sub-node parallelization, combined with the characteristics of second-order convergence, which greatly improves the modeling efficiency compared with general GBDT.
[0062] Step 130, according to the dielectric constant and resistivity curve of the target formation, the porosity of the target formation is determined by the trained preset regression model.
[0063] The porosity result determined by the formation porosity prediction method disclosed in the embodiment can be referred to Figure 2 .
[0064] In some embodiments, further comprising:
[0065] Step 140, evaluating the porosity of the target formation by a preset evaluation strategy to determine the accuracy of the prediction result.
[0066] In some embodiments, the preset evaluation strategy comprises:
[0067] The degree of change of the data points is evaluated by the mean square error evaluation model, the volatility of the data is evaluated by the root mean square error evaluation model, and the closeness of the prediction result to the true data set is evaluated by the mean absolute error evaluation model; wherein the mean square error evaluation model comprises:
[0068]
[0069] The root mean square error evaluation model comprises:
[0070]
[0071] The mean absolute error evaluation model comprises:
[0072]
[0073] Wherein, m is the number of test samples, y i is the true value in the test sample, is the predicted value in the test sample.
[0074] The XGBoost method model belongs to a kind of regression model, can use mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) as the evaluation standard of model.MSE refers to the difference between parameter estimate and parameter true value Expectation, can be used to evaluate the degree of change of data point, the smaller the MSE value, the more accurate the model prediction result.RMSE is used to measure the volatility of data, the smaller the RMSE value, the stronger the generalization ability and stability of model.MAE is the absolute value of the difference between the predicted value of each sample and the true value, then sum and average value are obtained.It is used to evaluate the closeness of prediction result and real data set, and the smaller the value, the better the fitting effect.
[0075] In order to facilitate the understanding of the technical scheme of the present application, reference can be made to Figure 3 , Figure 3 The flow chart of another formation porosity prediction method provided by the embodiment of the present application.
[0076] The formation porosity prediction method disclosed in the embodiment constructs XGBoost model prediction process, which is accurate and outstanding in effect;The regression method disclosed in the embodiment has fast training speed, and the generalization ability of prediction model is strong;The method disclosed in the embodiment is simple and easy to use, suitable for the business needs of well logging interpretation, and has low implementation cost, and has wide popularization value.
[0077] Embodiment two
[0078] The embodiment provides a formation porosity prediction device. The device embodiment can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiment, please refer to the method embodiments of the present application. The device disclosed in the embodiment comprises:
[0079] The construction module is used for constructing training samples and pre-processing the training samples to obtain pre-processed sample data;
[0080] a training module configured to train a preset regression model according to the obtained preprocessed sample data, and obtain a trained preset regression model;
[0081] a prediction module configured to determine the porosity of the target formation according to the dielectric constant and resistivity curves of the target formation and the trained preset regression model.
[0082] In some embodiments, the method further comprises:
[0083] an evaluation module configured to evaluate the porosity of the target formation according to a preset evaluation strategy, to determine the accuracy of the prediction result.
[0084] In some embodiments, the training sample comprises:
[0085] a dielectric constant, a resistivity curve, and a porosity; wherein the dielectric constant and the resistivity curve are used as training data, and the porosity is used as a label.
[0086] In some embodiments, the training sample is preprocessed by normalization of data, wherein the expression of normalization comprises:
[0087]
[0088] wherein x represents the input curve data sample, represents the normalized curve data, min(x (n) ) represents the minimum value of the sample, and max(x (n) ) represents the maximum value of the sample.
[0089] In some embodiments, the preset regression model comprises:
[0090] an XGBoost regression model.
[0091] In some embodiments, the preset evaluation strategy comprises:
[0092] evaluating the degree of change of data points by a mean square error evaluation model, evaluating the volatility of data by a root mean square error evaluation model, and evaluating the closeness of the prediction result to the real data set by a mean absolute error evaluation model; wherein the mean square error evaluation model comprises:
[0093]
[0094] the root mean square error evaluation model comprises:
[0095]
[0096] the mean absolute error evaluation model comprises:
[0097]
[0098] wherein m is the number of test samples, y i is the true value in the test sample, is the predicted value in the test sample.
[0099] Those skilled in the art can understand that the structure shown in the embodiment does not constitute a limitation on the device of the present application, and can include more or fewer modules / cells than the figure, or combine certain modules / cells, or different module / cell arrangement.
[0100] Those skilled in the art should understand that the modules or steps of the present application described above can be realized by a general computing device, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Alternatively, they can be realized by program codes executable by a computing device, so that they can be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described can be executed in an order different from here, or they can be made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module.
[0101] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of each module in the formation porosity prediction device can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.
[0102] Embodiment Three
[0103] The embodiment provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the method steps in the foregoing method embodiments, which will not be repeated here.
[0104] The computer-readable storage medium can also include, or be, alone, a computer program, a data file, a data structure, etc., or a combination thereof. The computer-readable storage medium or the computer program can be specifically designed and understood by those skilled in the computer software field, or can be known and available to those skilled in the computer software field. Examples of the computer-readable storage medium include: magnetic media, such as a hard disk, a floppy disk, and a magnetic tape; optical media, such as a CD ROM disk and a DVD; a magneto-optical medium, such as an optical disk; and a hardware device specifically configured to store and execute a computer program, such as a read-only memory (ROM), a random access memory (RAM), a flash memory, or a server, an app application store, etc. Examples of the computer program include machine code (e.g., code generated by a compiler) and a file containing high-level code that can be executed by a computer by using an interpreter. The described hardware device can be configured to function as one or more software modules to perform the above-described operations and methods, and vice versa. In addition, the computer-readable storage medium can be distributed in a networked computer system, and the program code or computer program can be stored and executed in a distributed manner.
[0105] Embodiment Four
[0106] The embodiment provides a computer program product. The computer program product includes a computer program or instructions that, when executed by a processor, implement all or part of the steps of the methods in the foregoing method embodiments, which are not repeated here.
[0107] Further, the computer program product can include one or more computer-executable components that, when executed by a processor, are configured to perform one or more embodiments described herein; the computer program product can also include a computer program tangibly embodied on a computer-readable medium, the computer program including instructions for performing any of the methods of the embodiments described herein. In such embodiments, the computer program can be downloaded from a network, and installed, and / or downloaded from a removable medium, and installed.
[0108] Embodiment Five
[0109] The embodiment provides an electronic device, which can include one or more processors, a memory, a multimedia component, an input / output (I / O) interface, and a communication component.
[0110] The one or more processors are configured to perform all or part of the steps in the foregoing method embodiments. The memory is configured to store various types of data, which can include, for example, instructions of any application program or method in the electronic device, and application-related data.
[0111] The one or more processors can be implemented with an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor or other electronic devices implementing the above methods.
[0112] The memory can be implemented with any type of volatile or non-volatile storage devices or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage devices, flash memory, magnetic disks, or optical disks.
[0113] The multimedia component can include a screen, which can be a touch screen, and an audio component for outputting and / or inputting audio signals. For example, the audio component can include a microphone for receiving external audio signals. The received audio signals can be further stored in the memory or transmitted through the communication component. The audio component also includes at least one speaker for outputting audio signals.
[0114] The I / O interface provides an interface between the one or more processors and other interface modules, which can be a keyboard, a mouse, a button, etc. These buttons can be virtual buttons or physical buttons.
[0115] The communication component is configured to perform wired or wireless communication between the electronic device and other devices. The wired communication includes communication through a network port, a serial port, etc. The wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, 5G, or a combination of one or more of them.
[0116] It should also be understood that the methods and apparatuses disclosed in the embodiments provided herein can be implemented in other ways. The above-described method and apparatus embodiments are merely illustrative, and the flowcharts and block diagrams in the drawings show possible implementation architectures, functions, and operations of the methods and apparatuses according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a computer program segment, or a part of a computer program, which includes one or more computer programs for implementing a specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the blocks can occur in a different order from that noted in the drawings, and in fact, they can be executed substantially in parallel, or in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and a combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or by a combination of dedicated hardware and computer programs.
[0117] In this application, the terms "comprise", "contain", or any other variant thereof are intended to cover a non-exclusive inclusion, so that processes, methods, articles, or devices that comprise a list of elements do not only include those elements, but also include other elements that are not expressly listed, or further include elements inherent in such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, device or equipment comprising the element; if there is a description of "first", "second", etc., it is only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the sequence of indicated technical features; in the description of the present application, unless otherwise specified, the meaning of the term "a plurality of" or "a plurality" is at least two; if there is a description of a server, it should be noted that the server can be a stand-alone physical server or terminal, or a server cluster composed of multiple physical servers, or a cloud server capable of providing cloud server, cloud database, cloud storage and CDN and other basic cloud computing services; if there is a description of intelligent terminal or mobile device in the present application, it should be noted that the intelligent terminal or mobile device can be a mobile phone, tablet computer, smart watch, netbook, wearable electronic device, personal digital assistant (PDA), augmented reality technology device (AR), virtual reality device (VR), smart television, smart sound, personal computer (PC) and the like, but is not limited thereto, and the specific form of the intelligent terminal or mobile device is not specially limited in the present application.
[0118] Finally, it should be noted that in the description of the present application, the description of the terms "one embodiment", "some embodiments", "example", "one example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0119] Although the embodiments of the present application have been shown and described above, it is understood that all the above-described embodiments are exemplary only, the contents described are merely adopted for the purpose of facilitating the understanding of the present application, and are not intended to limit the present application. Any person skilled in the art to which the present application belongs can make any modification and change in the form and details without departing from the spirit and scope of the present application, but the protection scope of the present application shall be subject to the scope defined by the appended claims.
Claims
1. A method for predicting formation porosity, characterized in that, The method includes: Construct training samples and preprocess the training samples to obtain preprocessed sample data; The pre-processed sample data is used to train the preset regression model to obtain the trained preset regression model. Based on the dielectric constant and resistivity curves of the target formation, the porosity of the target formation is determined using the trained preset regression model.
2. The formation porosity prediction method according to claim 1, characterized in that, The training samples include: Dielectric constant, resistivity curve, and porosity; wherein the dielectric constant and the resistivity curve are used as training data, and the porosity is used as a label.
3. The formation porosity prediction method according to claim 1, characterized in that, The training samples are preprocessed by normalizing the data, wherein the normalization expression includes: Where x represents the input curve data sample, This represents the normalized curve data, min(x) (n) ) represents the minimum value of the sample, max(x) (n) ) represents the maximum value of the sample.
4. The formation porosity prediction method according to claim 1, characterized in that, The preset regression model includes: XGBoost regression model.
5. The formation porosity prediction method according to claim 1, characterized in that, Also includes: The porosity of the target formation is evaluated using a preset evaluation strategy to determine the accuracy of the prediction results.
6. The formation porosity prediction method according to claim 5, characterized in that, The preset evaluation strategy includes: The mean square error (MSE) evaluation model evaluates the degree of change in data points, the root mean square error (RMSE) evaluation model evaluates the volatility of the data, and the mean absolute error (MAE) evaluation model assesses the closeness of the predicted results to the actual dataset. The MSE evaluation model includes: The root mean square error evaluation model includes: The mean absolute error evaluation model includes: Where m is the number of test samples, y i To be the true value in the test sample, These are the predicted values from the test samples.
7. A formation porosity prediction device, characterized in that, include: The construction module is used to construct training samples and preprocess the training samples to obtain preprocessed sample data; The training module is used to train the preset regression model based on the obtained preprocessed sample data to obtain the trained preset regression model. The prediction module is used to determine the porosity of the target formation based on the dielectric constant and resistivity curve of the target formation using the trained preset regression model.
8. The formation porosity prediction device according to claim 7, characterized in that, Also includes: The evaluation module is used to evaluate the porosity of the target formation using a preset evaluation strategy in order to determine the accuracy of the prediction results.
9. A computer-readable storage medium, characterized in that, The computer program stored in the computer-readable storage medium, when executed by one or more processors, implements the formation porosity prediction method as described in any one of claims 1 to 6.
10. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the formation porosity prediction method as described in any one of claims 1 to 6.