Stratum resistivity reconstruction and mud invasion degree quantitative evaluation method and related equipment
By utilizing neural network algorithms and sensitive parameter analysis in a saline-muddy environment, the resistivity of the original formation was reconstructed and the degree of mud invasion was quantitatively evaluated. This solved the problem of resistivity logging data distortion caused by saline-muddy invasion and improved the accuracy and interpretability of logging data.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA NAT PETROLEUM CORP
- Filing Date
- 2024-10-17
- Publication Date
- 2026-04-17
AI Technical Summary
In existing technologies, the intrusion of salt and cement mud leads to distortion of resistivity logging data, making it difficult to accurately obtain the original formation resistivity and determine the degree of mud intrusion, thus affecting oil and gas reservoir evaluation and fluid identification.
Using logging-while-drilling data based on reservoir sections, sensitive parameters are selected by setting a correlation coefficient threshold. A prediction model is established using a neural network learning algorithm to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data. The degree of mud invasion is quantitatively characterized by the invasion index.
It effectively reduced the impact of salt and cement slurry intrusion on resistivity logging, improved the accuracy and reliability of data, provided a more accurate basis for geological interpretation and reservoir evaluation, and improved exploration and development efficiency.
Smart Images
Figure CN121881014A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of formation resistivity reconstruction and quantitative evaluation of mud invasion degree, and related equipment. Background Technology
[0002] Resistivity is a crucial logging data point for stratigraphic lithology classification, oil and gas reservoir identification, and fluid saturation assessment, playing a vital role in oil and gas exploration and development. With continuous advancements in science and technology, resistivity logging methods have made rapid progress, evolving from traditional conventional electrode logging to array logging with varying depths and vertical resolutions. Resistivity logging instruments have also evolved from cable-based to drilling-while-drilling (WDD) logging, finding wide application in complex and unconventional oil and gas environments.
[0003] Water-based drilling mud has the advantages of low cost and less environmental pollution, making it the most common type of mud used in drilling operations. Water-based mud is relatively inexpensive to produce, has good solubility, and causes less environmental pollution. In reservoirs such as argillaceous sandstone, to ensure wellbore stability, organic salts and other chemicals are often added to improve the conductivity of the mud, making its resistivity significantly lower than that of formation water; this type of mud is called salt-mud mud. The use of salt-mud mud presents challenges for resistivity logging. Due to the intrusion of mud filtrate, the resistivity obtained from logging is significantly lower than the true resistivity of the reservoir, causing significant difficulties in fluid identification and saturation calculation. Previous researchers have used multi-parameter invasion models and data processing to obtain the resistivity of the flushed zone, the resistivity of the undisturbed formation, and the invasion depth, achieving some application results. However, due to the lack of verification with drilling resistivity data, the authenticity and reliability of the inversion results deserve further scrutiny. In other words, existing technologies face technical problems such as difficulty in obtaining the resistivity of the undisturbed formation and difficulty in determining the degree of invasion. Summary of the Invention
[0004] To address the problems existing in the prior art, this invention provides a method and related equipment for reconstructing formation resistivity and quantitatively evaluating the degree of mud invasion, thereby solving technical problems such as the difficulty in obtaining the resistivity of undisturbed formations and the difficulty in judging the degree of invasion in the prior art.
[0005] To achieve the above objectives, the present invention provides the following technical solution: A method for reconstructing formation resistivity and quantitatively evaluating the degree of mud invasion includes the following steps: Based on the logging-while-drilling data of the reservoir section, a preset correlation coefficient threshold is set, and logging data with a correlation coefficient greater than the threshold is selected as sensitive parameters; A prediction model is established based on the aforementioned sensitive parameters and neural network learning algorithm. The prediction model is used to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data, and the converted phase resistivity is used as the original formation resistivity. Based on the difference between the converted phase resistivity and the resistivity measured by cable logging, an invasion index is obtained, which is used as a quantitative characterization of the degree of mud invasion.
[0006] Furthermore, the logging-while-drilling data includes phase resistivity and natural gamma, compensated density, compensated acoustic wave, compensated neutron, spontaneous potential and microsphere focused resistivity; The reservoir section is a region with a clay content of less than 40%.
[0007] Furthermore, the correlation coefficient threshold is greater than 0.6.
[0008] Furthermore, the neural network learning algorithm is a BP neural network structure, which includes three layers: an input layer, a hidden layer, and an output layer.
[0009] Furthermore, the input data of the prediction model is normalized to obtain standardized sensitive logging data. The normalization process is as follows:
[0010] In the formula: y * This represents the standardized sensitive logging data, y i This represents the sensitive logging data input, y iave represents the average value of the input sensitive logging data, and s represents the standard deviation of the input sensitive logging data.
[0011] Furthermore, the prediction model is as follows:
[0012]
[0013] In the formula: n is the number of training samples, m is the type of input sensitivity parameter corresponding to each sample, and X input Here are the input parameters for the neural network: GR is the natural gamma ray logging curve, DEN is the density logging curve, CNL is the compensated neutron logging curve, AC is the sonic transit time logging curve, and Y... output Here, RPLH represents the depth resistivity logging curve during drilling, and T represents the matrix transpose.
[0014] Furthermore, the intrusion index is:
[0015] In the formula: This represents the phase resistivity after conversion; Represents the resistivity of cable logging. This indicates the invasiveness index.
[0016] Furthermore, the resistivity of the cable logging includes dual-induction / lateral resistivity or array-induction / lateral resistivity.
[0017] A system for quantitatively evaluating formation resistivity reconstruction and mud invasion degree includes: The initialization unit is configured as follows: For logging-while-drilling data based on reservoir sections, a preset correlation coefficient threshold is used, and logging data with a correlation coefficient greater than the threshold is selected as sensitive parameters. The prediction unit is configured as follows: The prediction model is used to establish a prediction model based on the sensitive parameters and the neural network learning algorithm. The prediction model is used to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data, and to use the converted phase resistivity as the original formation resistivity. The output unit is configured as follows: The invasion index is obtained based on the difference between the converted phase resistivity and the resistivity measured by wireline logging, and the invasion index is used as a quantitative characterization of the degree of mud invasion.
[0018] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the formation resistivity reconstruction and mud invasion quantitative evaluation method as described above.
[0019] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for reconstructing formation resistivity and quantitatively evaluating the degree of mud intrusion.
[0020] Compared with the prior art, the present invention has the following beneficial technical effects: This invention provides a method and related equipment for reconstructing formation resistivity and quantitatively evaluating the degree of mud invasion. The method includes the following steps: based on logging-while-drilling data of the reservoir section, a preset correlation coefficient threshold is established, and logging data exceeding the threshold are selected as sensitive parameters; a prediction model is established based on the sensitive parameters and a neural network learning algorithm; the prediction model is used to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data, and the converted phase resistivity is used as the original formation resistivity; based on the difference between the converted phase resistivity and the resistivity measured by wireline logging, an invasion index is obtained, and the invasion index is used as a quantitative representation of the degree of mud invasion. This application, based on sensitive parameter analysis, uses a neural network learning algorithm to establish a prediction model to reconstruct the original formation resistivity, and defines an invasion index based on the comparison between the reconstructed resistivity and the measured wireline logging resistivity, thereby achieving a quantitative representation of the degree of invasion. This application can effectively solve the impact of salt and mud mud invasion on resistivity logging, providing a foundation for research on reservoir evaluation and fluid identification in salt and mud mud environments.
[0021] Furthermore, by pre-setting correlation coefficient thresholds to screen sensitive parameters and using neural network learning algorithms to establish a prediction model, the effective conversion of phase resistivity in conventional logging data to phase resistivity in logging-while-drilling data was achieved. This process effectively reduced the impact of salt and cement slurry intrusion on resistivity logging data, improving the accuracy and reliability of the data.
[0022] Furthermore, based on the training results of the neural network prediction model, the transformed phase resistivity can be used as an approximation of the original formation resistivity, thus achieving the reconstruction of the original formation resistivity. This is of great significance for subsequent geological interpretation and reservoir evaluation.
[0023] Furthermore, by comparing the difference between the reconstructed original formation resistivity and the resistivity measured by wireline logging, an invasion index was defined as a quantitative characterization of the degree of mud invasion. This index provides a quantitative basis for assessing the impact of mud invasion on formation resistivity, and helps to more accurately understand formation property changes and fluid distribution.
[0024] Furthermore, this invention is applicable to saline-muddy environments, and by solving the problem of resistivity logging data distortion caused by saline-muddy intrusion, it provides more accurate and reliable basic data support for well logging reservoir evaluation and fluid identification studies. This helps improve exploration and development efficiency and reduce decision-making risks.
[0025] Furthermore, by introducing neural network learning algorithms and sensitive parameter analysis techniques, this method not only improves the processing and analysis capabilities of well logging data but also enhances its interpretability. This enables geologists to more accurately understand subsurface geological structures, reservoir characteristics, and fluid distribution patterns.
[0026] Furthermore, the implementation of this invention relies on advanced neural network learning algorithms and data processing technologies, which helps to promote the development of logging technology towards intelligence. By continuously optimizing and improving the prediction model algorithm, the processing accuracy and interpretation efficiency of logging data can be further improved, providing stronger technical support for oil and gas exploration and development. Attached Figure Description
[0027] Figure 1 A flowchart of a method for reconstructing formation resistivity and quantitatively evaluating the degree of mud invasion according to an embodiment of the present invention is shown; Figure 2(a) shows a single-factor analysis of natural gamma and logging-while-drilling phase resistivity in an embodiment of the present invention; Figure 2(b) shows a single-factor analysis diagram of the compensating acoustic wave and the phase resistivity of logging while drilling in an embodiment of the present invention; Figure 2(c) shows a single-factor analysis of the compensation density and logging-while-drilling phase resistivity in an embodiment of the present invention; Figure 2(d) shows a single-factor analysis of the compensating neutron and logging-while-drilling phase resistivity in an embodiment of the present invention; Figure 3 The diagram shows a BP neural network architecture for modeling and predicting phase resistivity and conventional logging curves in a drilling embodiment of the present invention. Figure 4 The diagram shows the predicted phase resistivity of a well obtained from a drilling logging-while-drilling test according to an embodiment of the present invention. Detailed Implementation
[0028] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.
[0029] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0030] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0031] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0032] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0033] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.
[0034] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0035] To address the difficulties in obtaining undisturbed formation resistivity and determining the degree of invasion, this patent proposes a method for reconstructing undisturbed formation resistivity and quantitatively evaluating the degree of mud invasion. This method can define an invasion index to quantitatively characterize the degree of mud invasion, effectively solving the impact of saline mud invasion on resistivity logging, and providing a foundation for research on well logging reservoir evaluation and fluid identification in saline mud environments.
[0036] Figure 1 This disclosure illustrates a method for reconstructing formation resistivity and quantitatively evaluating the degree of mud invasion, as shown in the embodiments of this disclosure. Figure 1 As shown, it includes the following steps: Step S1: Based on the logging-while-drilling data of the reservoir section, a correlation coefficient threshold is preset, and logging data with a correlation coefficient greater than the threshold are selected as sensitive parameters; Preferably, in this embodiment of the disclosure, the logging-while-drilling data includes phase resistivity and natural gamma, compensated density, compensated acoustic wave, compensated neutron, spontaneous potential and microsphere focused resistivity; The reservoir section is a region with a clay content of less than 40%.
[0037] Furthermore, the correlation coefficient threshold is greater than 0.6. Specifically, the process for calculating the correlation coefficient threshold is as follows: A single-factor correlation analysis was used to establish a cross-plot with conventional logging data as the abscissa and logging-while-drilling phase resistivity as the ordinate, and the correlation coefficient threshold R was obtained. Specifically, taking a water-bearing section of a well as an example, the logging-while-drilling phase resistivity curves showed good correlation with curves of natural gamma, compensated acoustic wave, compensated neutron, and compensated density, with correlation coefficients all greater than 0.6. Therefore, the sensitive input parameters were determined to be natural gamma, compensated acoustic wave, compensated neutron, and compensated density. Figure 2(a) shows the single-factor analysis diagram of natural gamma and logging-while-drilling phase resistivity in this embodiment of the present disclosure, Figure 2(b) shows the single-factor analysis diagram of compensated acoustic wave and logging-while-drilling phase resistivity in this embodiment of the present disclosure, Figure 2(c) shows the single-factor analysis diagram of compensated density and logging-while-drilling phase resistivity in this embodiment of the present disclosure, and Figure 2(d) shows the single-factor analysis diagram of compensated neutron and logging-while-drilling phase resistivity in this embodiment of the present disclosure.
[0038] Specifically, the natural gamma logging is mainly used to classify lithology because different rocks have different contents of radioactive elements. For example, mudstone is usually rich in radioactive elements, while sandstone and limestone are relatively less so. The compensated sonic logging uses a specially designed probe to eliminate the influence of wellbore irregularities and mud on the measurement results, thereby more accurately reflecting the true situation of the formation. Compensated sonic logging is mainly used to measure the sound wave propagation velocity of the formation, and then calculate the formation's porosity, permeability and other physical parameters. The compensated neutron logging uses a neutron source to emit neutrons into the formation and measures the secondary gamma rays generated after hydrogen interacts with neutrons in the formation. Since hydrogen in the formation is mainly found in pore water and hydrocarbon fluids, compensated neutron logging can indirectly reflect the fluid content of the formation. The compensated density logging uses a radioactive isotope source, such as cesium-137, to measure the bulk density of the formation by the scattering effect of gamma rays generated after interacting with formation materials. The compensation technology is also used to eliminate the influence of wellbore and mud and improve measurement accuracy.
[0039] It should be further noted that the aforementioned univariate correlation analysis is a basic and commonly used method in statistics to study whether a linear relationship exists between two variables, and the strength and direction of such a relationship. In some publicly available embodiments, the Pearson correlation coefficient is used as the indicator to measure the degree of linear correlation between two variables.
[0040] Step S2: Establish a prediction model based on the aforementioned sensitive parameters and neural network learning algorithm; the prediction model is used to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data, and use the converted phase resistivity as the original formation resistivity. Figure 4 This diagram shows the predicted phase resistivity of a well obtained from logging while drilling, according to an embodiment of this disclosure. In this embodiment of the disclosure, the neural network learning algorithm is a BP neural network structure, which includes three layers: an input layer, a hidden layer, and an output layer; specifically, as follows... Figure 3 As shown, the input layer has 4 layers, the hidden layer has 3 layers, and the output layer has 1 layer. Those skilled in the art can adjust these layers according to the actual application effect.
[0041] It should be noted that the BP neural network mentioned above is a multi-layer feedforward neural network based on the gradient descent algorithm. This network model is inspired by the structure of neurons in the human brain and consists of a large number of neurons, or nodes or units, connected by weights. These neurons are distributed in the input layer, hidden layer and output layer.
[0042] More specifically, the prediction model is:
[0043]
[0044] In the formula: n is the number of training samples, m is the type of input sensitivity parameter corresponding to each sample, and X input Here are the input parameters for the neural network: GR is the natural gamma ray logging curve, DEN is the density logging curve, CNL is the compensated neutron logging curve, AC is the sonic transit time logging curve, and Y... output Here, RPLH represents the depth resistivity logging curve during drilling, and T represents the matrix transpose.
[0045] Furthermore, in some disclosed embodiments, the input data of the prediction model is normalized to obtain standardized sensitive logging data. The normalization process is as follows:
[0046] In the formula: y * This represents the standardized sensitive logging data, y i This represents the sensitive logging data input, y iave represents the average value of the input sensitive logging data, and s represents the standard deviation of the input sensitive logging data.
[0047] Step S3: Based on the difference between the converted phase resistivity and the resistivity measured by cable logging, the invasion index is obtained, and the invasion index is used as a quantitative characterization of the degree of mud invasion.
[0048] Specifically, the intrusion index is:
[0049] In the formula: This represents the phase resistivity after conversion; Represents the resistivity of cable logging. This indicates the invasiveness index.
[0050] Furthermore, the resistivity measured by the cable logging includes dual-induction / lateral resistivity or array-induction / lateral resistivity. Specifically, the dual-induction logging consists of two types of induction logging with different detection depths, mainly including deep induction logging and medium induction logging. Deep induction logging has a larger detection depth and mainly reflects the size of eddies and formation conductivity in undisturbed formations; medium induction logging has a shallower detection depth and mainly reflects the size of eddies and their conductivity in flushed zones. This method infers the resistivity and other electrical parameters of the formation by measuring changes in the electromagnetic field, thereby determining the lithology and hydrocarbon content of the formation. Lateral logging is a resistivity logging method that infers the resistivity of the formation by measuring the lateral flow of current in the formation. It is mainly used to determine parameters such as lithology, porosity, and hydrocarbon saturation of the formation. Array induction logging is an advanced form of induction logging technology, which uses multiple focusing coil systems combined together, including a main electrode, multiple pairs of monitoring electrodes, and shielding electrodes. This logging method can obtain richer information about the formation's electrical properties by simultaneously measuring the induced electromotive force components at multiple different depths. The array lateral logging is similar to array induction logging, also employing a combination of multiple electrodes to infer formation resistivity and other electrical parameters by measuring the lateral flow of current within the formation.
[0051] It should be noted that, for saline-cement slurries, the predicted logging-while-drilling phase resistivity is generally greater than or equal to the resistivity measured by wireline logging, and the intrusion index is also important. The larger the value, the greater the impact of salt and cement slurry intrusion on resistivity, and the higher the degree of intrusion.
[0052] This disclosure also provides a system for quantitatively evaluating formation resistivity reconstruction and mud invasion, including: The initialization unit is configured as follows: For logging-while-drilling data based on reservoir sections, a preset correlation coefficient threshold is used, and logging data with a correlation coefficient greater than the threshold is selected as sensitive parameters. The prediction unit is configured as follows: The prediction model is used to establish a prediction model based on the sensitive parameters and the neural network learning algorithm. The prediction model is used to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data, and to use the converted phase resistivity as the original formation resistivity. The output unit is configured as follows: The invasion index is obtained based on the difference between the converted phase resistivity and the resistivity measured by wireline logging, and the invasion index is used as a quantitative characterization of the degree of mud invasion.
[0053] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of the methods for reconstructing formation resistivity and quantitatively evaluating the degree of mud intrusion.
[0054] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the methods for reconstructing formation resistivity and quantitatively evaluating the degree of mud intrusion described in the above embodiments.
[0055] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0056] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0057] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0058] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0059] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.
[0060] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.
Claims
1. A method for reconstructing formation resistivity and quantitatively evaluating the degree of mud invasion, characterized in that, Includes the following steps: Based on the logging-while-drilling data of the reservoir section, a preset correlation coefficient threshold is set, and logging data with a correlation coefficient greater than the threshold is selected as sensitive parameters; A prediction model is established based on the aforementioned sensitive parameters and neural network learning algorithm. The prediction model is used to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data, and the converted phase resistivity is used as the original formation resistivity. Based on the difference between the converted phase resistivity and the resistivity measured by cable logging, an invasion index is obtained, which is used as a quantitative characterization of the degree of mud invasion.
2. The formation resistivity reconstruction and mud invasion quantitative evaluation method of claim 1, wherein, The logging-while-drilling data includes phase resistivity and natural gamma, compensated density, compensated acoustic wave, compensated neutron, spontaneous potential, and microsphere focused resistivity. The reservoir section is a region with a clay content of less than 40%.
3. The formation resistivity reconstruction and mud invasion quantitative evaluation method of claim 1, wherein, The correlation coefficient threshold is greater than 0.
6.
4. The formation resistivity reconstruction and mud invasion quantitative evaluation method of claim 1, wherein, The neural network learning algorithm is a BP neural network structure, which includes three layers: an input layer, a hidden layer, and an output layer.
5. The method of claim 1, wherein, The input data of the prediction model is normalized to obtain standardized sensitive logging data. The normalization process is as follows: In the formula: y * This represents the standardized sensitive logging data, y i This represents the sensitive logging data input, y iave represents the average value of the input sensitive logging data, and s represents the standard deviation of the input sensitive logging data.
6. The formation resistivity reconstruction and mud invasion quantitative evaluation method of claim 1, wherein, The prediction model is as follows: In the formula: n is the number of training samples, m is the type of input sensitivity parameter corresponding to each sample, and X input Here are the input parameters for the neural network: GR is the natural gamma ray logging curve, DEN is the density logging curve, CNL is the compensated neutron logging curve, AC is the sonic transit time logging curve, and Y... output Here, RPLH represents the depth resistivity logging curve during drilling, and T represents the matrix transpose.
7. The method of claim 1, wherein, The intrusion index is: where: represents the phase resistivity after conversion; represents the resistivity of the wireline logging, represents the invasion index.
8. The method of claim 1, wherein, The resistivity of the cable logging includes dual-induction / lateral resistivity or array-induction / lateral resistivity.
9. A system for formation resistivity reconstruction and quantitative mud invasion evaluation, characterized in that, include: The initialization unit is configured as follows: For logging-while-drilling data based on reservoir sections, a preset correlation coefficient threshold is used, and logging data with a correlation coefficient greater than the threshold is selected as sensitive parameters. The prediction unit is configured as follows: The prediction model is used to establish a prediction model based on the sensitive parameters and the neural network learning algorithm. The prediction model is used to convert the phase resistivity in conventional logging data into the phase resistivity in logging-while-drilling data, and to use the converted phase resistivity as the original formation resistivity. The output unit is configured as follows: The invasion index is obtained based on the difference between the converted phase resistivity and the resistivity measured by wireline logging, and the invasion index is used as a quantitative characterization of the degree of mud invasion.
10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the formation resistivity reconstruction and mud invasion degree quantitative evaluation method as described in any one of claims 1-8. 11.A computer readable storage medium, storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the formation resistivity reconstruction and mud invasion degree quantitative evaluation method as described in any one of claims 1-8.