A method, system, device and storage medium for chemical phase division of lacustrine shale

Abstract

The present invention provides a method, system, equipment and storage medium for chemical phase division of lacustrine mud shale, which belongs to the field of petroleum exploration and development geology. Element data is obtained by collecting lacustrine mud shale samples, and the element data is processed to remove trace elements that are greatly affected by terrigenous debris. The principal component analysis (PCA) method is used to screen the features that have a greater impact on the chemical phase division to construct a feature vector, and the clustering algorithm is used to perform cluster analysis on the feature vector to obtain the chemical phase type. The chemical phase prediction model is trained using the random forest algorithm to automatically and efficiently perform the chemical phase division of lacustrine mud shale, and finally the chemical phase division results are applied to the exploration and development of shale oil and gas to identify and evaluate the oil and gas resource potential in lacustrine mud shale.

Description

Technical Field

[0001] The invention belongs to the field of petroleum exploration and development geology, and in particular relates to a method, system, equipment and storage medium for chemical phase division of lacustrine shale. Background Art

[0002] As global energy demand continues to grow, shale oil has become an important unconventional energy resource. Due to its sensitivity to climate change, lacustrine shale usually shows more significant differences in mineral composition and lithology than marine shale, resulting in widespread heterogeneity in vertical and horizontal directions. The chemical phase division of shale originated from the study of marine shale. By dividing the chemical phases of shale, we can understand the geological environment and provide direction for oil and gas exploration.

[0003] Traditional chemical phase division methods rely on expert experience and qualitative analysis, and it is difficult to ensure the consistency and accuracy of the results; the manual analysis process is cumbersome, time-consuming, and difficult to meet the needs of rapid analysis of large-scale samples. Existing chemical phase division methods are mainly aimed at marine mud shales, and there are limitations in direct application to lacustrine mud shales. In particular, lacustrine mud shales are easily affected by terrigenous debris, and some trace elements cannot be used to identify chemical phases. Therefore, the promotion and application of marine mud shale chemical phase division and identification methods in the field of lacustrine mud shales still lacks pertinence and reliability, and a systematic understanding of the chemical phases of lacustrine mud shales and targeted methods and technologies need to be formed. Summary of the invention

[0004] In order to solve the problem of chemical phase division of lacustrine shale, the present invention provides a method, system, equipment and storage medium for chemical phase division of lacustrine shale.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A method for chemical phase division of lacustrine shale comprises the following steps:

[0007] Obtaining element data of the core sample, the element data including the concentration value of each element in the core sample; obtaining the method detection limit concentration value of the element data by analyzing and calculating, assigning the method detection limit concentration value to the element whose concentration value is lower than the method detection limit concentration value, and excluding the element whose concentration value is missing; drawing a scatter plot between the remaining elements, calculating the correlation coefficient between the elements according to the scatter plot, excluding the elements affected by the debris flux according to the correlation coefficient, and obtaining an element data sample;

[0008] Performing principal component analysis on the element data sample, screening features that affect chemical phase division to construct feature vectors, performing cluster analysis on the feature vectors, and obtaining chemical phase types according to the cluster analysis results;

[0009] Using the element data sample as input and the chemical phase type as a label, training a random forest algorithm to obtain a chemical phase prediction model;

[0010] The lacustrine shale sample data to be tested is input into the chemical phase prediction model to perform chemical phase division to obtain a chemical phase type division result.

[0011] Preferably, the obtaining of element data of the core sample is specifically to perform element analysis on the core sample by an X-ray fluorescence spectrometer to obtain the element type and the concentrations of main elements and trace elements of the core sample.

[0012] Preferably, the unsupervised K-means cluster analysis is performed on the feature vectors to obtain the chemical phase type according to the cluster analysis results, specifically comprising the following steps:

[0013] The center points of K clusters are randomly initialized; the Euclidean distance from each element data to the center of all clusters is calculated, and the element data is assigned to the cluster with the nearest distance; the center point of each cluster is recalculated, that is, the mean of all element data in the current cluster is calculated to update the position of the center point; the above process of assigning and recalculating the center point is repeated until the position change of all cluster centers is less than the set convergence threshold, or the maximum number of iterations is reached; according to the iterative results, the data is divided into 5 non-overlapping groups; then supervised classification is performed based on significant geochemical trends, and further divided into several chemical phase types.

[0014] Preferably, before calculating the correlation coefficients between the elements, the method further includes calculating the mean value and standard deviation of the element concentration values, and identifying and excluding outliers exceeding the mean value plus four times the standard deviation.

[0015] The present invention also provides a lacustrine shale chemical phase division system, which specifically includes:

[0016] A data module is used to obtain element data of a core sample, wherein the element data includes the concentration value of each element in the core sample; obtain the method detection limit concentration value of the element data by analyzing and calculating, assign the method detection limit concentration value to the element whose concentration value is lower than the method detection limit concentration value, and exclude the element whose concentration value is missing; draw a scatter plot between the remaining elements, calculate the correlation coefficient between the elements according to the scatter plot, and exclude the elements affected by the debris flux according to the correlation coefficient to obtain an element data sample.

[0017] The type classification module is used to perform principal component analysis on the element data sample, screen the features that affect the chemical phase classification to construct feature vectors, perform cluster analysis on the feature vectors, and obtain the chemical phase type according to the cluster analysis results.

[0018] The model training module is used to take the element data sample as input and the chemical phase type as a label to train the random forest algorithm to obtain a chemical phase prediction model.

[0019] The chemical phase division module is used to input the lacustrine shale sample data to be tested into the chemical phase prediction model to perform chemical phase division and obtain the chemical phase type division result.

[0020] The present invention also provides a computer device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps described in the method for chemical phase division of lacustrine shale.

[0021] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is loaded by a processor, the steps described in the method for chemical phase division of lacustrine shale can be executed.

[0022] The method for chemical phase division of lacustrine shale provided by the present invention has the following beneficial effects:

[0023] The present invention obtains the element data of the core sample, excludes the missing elements through the method detection limit concentration value, and calculates the correlation coefficient between the elements to eliminate the elements that are greatly affected by terrigenous debris, thereby ensuring the data quality and overcoming the limitation of the existing marine mud shale chemical phase division method that does not consider the influence of terrigenous debris. The principal component analysis is used to screen the features that have a greater impact on the chemical phase division to construct a feature vector, and the clustering algorithm is used to divide the chemical phase type, establish a scientific chemical phase category for the lacustrine mud shale, and improve the accuracy of the chemical phase division. According to the chemical phase type and the element data sample, the random forest algorithm is used to obtain the chemical phase prediction model, which can automatically and efficiently perform the chemical phase division of the lacustrine mud shale and obtain a more accurate division result. Finally, the chemical phase division results are applied to the exploration and development of shale oil and gas to identify and evaluate the oil and gas resource potential in the lacustrine mud shale. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiment of the present invention and its design scheme, the following briefly introduces the drawings required for this embodiment. The drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 The present invention is a flowchart of a method for chemical phase division of lacustrine shale according to an embodiment of the present invention.

[0026] Figure 2 This is a schematic diagram of removing trace elements related to terrigenous debris according to an embodiment of the present invention, wherein: Figure 2 (A) is a scatter plot of Zr elements including Al elements. Figure 2 (B) is a scatter plot of Ti elements including Al elements. Figure 2 (C) is a schematic diagram of the Pearson correlation coefficients of 22 trace elements with Al, Ti and Zr.

[0027] Figure 3 The biplot is a principal component analysis (PCA) and K-means clustering result according to an embodiment of the present invention.

[0028] Figure 4 Schematic diagram of supervised classification of chemical phases based on significant geochemical trends in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the technical solution of the present invention and implement it, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the scope of protection of the present invention. Example

[0030] The present invention provides a method, system, device and storage medium for chemical phase division of lacustrine shale, such as Figure 1 The present invention is a flow chart of a method for chemical phase division of lacustrine shale, which specifically includes the following steps:

[0031] Step S1, sample collection and preparation. Collect core samples from a target lacustrine shale layer in a depression. Clean and level the samples, and record the geological stratum and depth information of the samples.

[0032] Step S2, geochemical analysis. Use a portable energy dispersive X-ray fluorescence spectrometer (pXRF) to perform elemental analysis on the core samples and measure the concentrations of major elements (such as Si, Al, Fe, Ca, K, Mg, etc.) and trace elements (such as Ti, Zr, V, Cr, Ni, Mo, etc.). Use a carbon and sulfur detector to measure the total organic carbon (TOC) content to provide basic data for subsequent chemical phase division.

[0033] Step S3, data preprocessing. The pXRF data were preprocessed to assign method detection limit (MDL) concentration values ​​to element data below the MDL and exclude samples with missing data. The mean and standard deviation of each element concentration value were calculated to identify and exclude outliers exceeding the mean plus four times the standard deviation (4σ). The Al element was used as the standard and correlation analysis with other elements was performed to ensure the integrity and accuracy of the data.

[0034] Step S4, feature selection and principal component analysis (PCA). First, a scatter plot is drawn by cross-plotting the Al element with elements related to terrigenous debris such as Zr and Ti, such as Figure 2 As shown. Using Pearson formula , calculate the Pearson correlation coefficients of Mg, Si, P, Ca, Ni, As, U, S, K, V, Cr, Mn, Fe, Cu, Zn, Pb, Sr, Mo, Ba with Al, Ti and Zr. According to the correlation coefficients of the elements, the trace elements with correlations greater than 0.6 with Al, Ti and Zr were screened out, and the data greatly affected by the debris flux were eliminated. Subsequently, PCA was used to analyze the screened data and extract the principal components to reduce the data dimension and capture significant changes.

[0035] Step S5, unsupervised and supervised cluster analysis. Perform cluster analysis on the PCA analysis results. The specific calculation process is as follows: First, randomly initialize the center points of K clusters. Then, calculate the Euclidean distance of each data point to the center of all clusters, and assign the data point to the cluster with the closest distance. Next, recalculate the center point of each cluster, that is, calculate the mean of all data points in the current cluster to update the position of the center point. Repeat the above process of assigning and recalculating the center point until the position change of all cluster centers is less than the set convergence threshold, or the maximum number of iterations is reached. Through this iterative process, the data is finally divided into 5 non-overlapping groups. Subsequently, supervised classification is performed based on significant geochemical trends, and it is further divided into 9 chemical phase types.

[0036] Step S6, chemical phase division and result verification.

[0037] In steps S4 and S5, the key features of the samples are extracted through feature selection and principal component analysis (PCA), and a preliminary classification basis is constructed through clustering. Supervised classification is performed based on significant geochemical trends, and the divided sample points are used as training sets. The chemical phase categories that have been determined are used as labels to train the random forest algorithm to obtain a chemical phase prediction model that can identify and predict the chemical phase categories of the samples.

[0038] After the model training is completed, the model is used to perform chemical phase division on new lacustrine shale samples. Finally, based on the preliminary verification step, the accuracy of the division results and the reliability of the model are evaluated to ensure the effectiveness of the model in practical applications. The rationality and scientificity of the division results are ensured through geological and geochemical verification. For example, the accuracy of chemical phase division is verified through thin section analysis and organic matter content determination.

[0039] Step S7, application and optimization. Apply the chemical phase division results to the exploration and development of shale oil and gas to provide a scientific basis and optimize the exploration strategy. Adjust and optimize the model parameters based on actual application feedback to improve the generalization ability and applicability of the model. The optimization process includes repeated training and verification of the model to ensure its application effect in different situations.

[0040] like Figure 2 The flowchart of the present invention for removing trace elements related to terrigenous debris is shown in FIG. Figure 2 (A) and Figure 2 (B) are scatter plots of Al, Zr and Ti, and schematic diagrams of Pearson correlation coefficients of Mg, Si, P, Ca, Ni, As, U, S, K, V, Cr, Mn, Fe, Cu, Zn, Pb, Sr, Mo, Ba with Al, Ti and Zr. Figure 2 (C).

[0041] Figure 3 Biplot of the principal component analysis (PCA) and K-means clustering results, showing the projection of the PCA scores (filled circles) and PCA loadings (the vector of each element) onto PC-1, PC-2, and PC-3.

[0042] Figure 4 Schematic diagram of supervised classification of chemical phases based on significant geochemical trends, including schematic diagram of chemical phase aggregation morphology of Ca, Si and S elements.

[0043] The present invention realizes the automatic and efficient division of the chemical phases of lacustrine mud shale, greatly improves the accuracy and reliability of the division results, reduces the influence of human subjective factors, and provides important technical support for the exploration and development of shale oil and gas resources.

[0044] The present invention also includes a lacustrine shale chemical phase division system, specifically:

[0045] The data module is used to obtain the element data of the core sample, which includes the concentration value of each element in the core sample; the method detection limit concentration value of the element data is obtained by analysis and calculation, the method detection limit concentration value is assigned to the elements with concentration values ​​lower than the method detection limit concentration value, and the elements with missing concentration values ​​are excluded; a scatter plot is drawn between the remaining elements, and the correlation coefficient between the elements is calculated based on the scatter plot. The elements affected by the debris flux are eliminated based on the correlation coefficient to obtain the element data sample.

[0046] The type classification module is used to perform principal component analysis on element data samples, screen the features that affect chemical phase classification to construct feature vectors, perform cluster analysis on the feature vectors, and obtain the chemical phase type based on the cluster analysis results.

[0047] The model training module is used to take element data samples as input and chemical phase types as labels, train the random forest algorithm, and obtain a chemical phase prediction model.

[0048] The chemical phase division module is used to input the lacustrine shale sample data to be tested into the chemical phase prediction model to perform chemical phase division and obtain the chemical phase type division result.

[0049] Each module in the above-mentioned lacustrine shale chemical phase division method system can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0050] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps in an embodiment of a method for chemical phase division of lacustrine shale. The specific implementation method can be found in the method embodiment, which will not be described in detail here.

[0051] Furthermore, the present invention also provides a non-temporary computer-readable storage medium containing instructions, on which a computer program is stored. For example, a memory containing instructions, the instructions can be executed by a processor of a computer device to complete the above method. For example, a non-temporary computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device. When the computer program is executed by the processor, the steps in an embodiment of a method for chemical phase division of lacustrine shale can be implemented. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0052] It should be understood by those skilled in the art that embodiments of the present invention may provide methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented 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.

[0053] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0054] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0056] It should be pointed out that the specific implementation methods described above can enable those skilled in the art to understand the invention more comprehensively, but do not limit the invention in any way. Therefore, although the invention has been described in detail in this specification and embodiments, those skilled in the art should understand that the invention can still be modified or replaced by equivalents; and all technical solutions and improvements that do not deviate from the spirit and scope of the invention are included in the protection scope of the patent for the invention. Any figure mark in the claims should not be regarded as limiting the claims involved. Any simple change or equivalent replacement of the technical solution that can be obviously obtained by any technician familiar with the field within the technical scope disclosed in the present invention belongs to the protection scope of the present invention.

Claims

1. A method for chemical phase division of lacustrine shale, characterized in that: The following steps are involved: Obtaining element data of the core sample, the element data including concentration values ​​of main elements and trace elements in the core sample; obtaining a method detection limit concentration value of the element data by analyzing and calculating, assigning the method detection limit concentration value to elements with concentration values ​​lower than the method detection limit concentration value, and excluding elements with missing concentration values; Draw a scatter plot between the main element Al and the terrigenous debris-related elements Zr and Ti, and calculate the correlation coefficients between Mg, Si, P, Ca, Ni, As, U, S, K, V, Cr, Mn, Fe, Cu, Zn, Pb, Sr, Mo, Ba and Al, Ti and Zr based on the scatter plot. Eliminate the elements affected by the debris flux based on the correlation coefficients to obtain element data samples; Performing principal component analysis on the element data sample, screening features that affect chemical phase division to construct feature vectors, performing unsupervised K-means cluster analysis on the feature vectors, and obtaining chemical phase types according to the cluster analysis results; Using the element data sample as input and the chemical phase type as a label, training a random forest algorithm to obtain a chemical phase prediction model; The lacustrine shale sample data to be tested is input into the chemical phase prediction model to perform chemical phase division to obtain a chemical phase type division result.

2. The method for chemical phase division of lacustrine shale according to claim 1, characterized in that: The obtaining of element data of the core sample specifically involves performing element analysis on the core sample by using an X-ray fluorescence spectrometer.

3. The method for chemical phase division of lacustrine shale according to claim 1, characterized in that: The cluster analysis of the characteristic vectors is performed to obtain the chemical phase type according to the cluster analysis results, specifically comprising the following steps: The center points of K clusters are randomly initialized; the Euclidean distance from each element data to the center of all clusters is calculated, and the element data is assigned to the cluster with the nearest distance; the center point of each cluster is recalculated, that is, the mean of all element data in the current cluster is calculated to update the position of the center point; the above process of assigning and recalculating the center point is repeated until the position change of all cluster centers is less than the set convergence threshold, or the maximum number of iterations is reached; according to the iterative results, the data is divided into 5 non-overlapping groups; then supervised classification is performed based on significant geochemical trends, and further divided into several chemical phase types.

4. The method for chemical phase division of lacustrine shale according to claim 1, characterized in that: Before calculating the correlation coefficients between the elements, it also includes identifying and excluding outliers that exceed the mean plus four times the standard deviation by calculating the mean and standard deviation of the element concentration values.

5. A chemical phase division system for lacustrine shale, characterized in that: include: A data module, used to obtain element data of the core sample, wherein the element data includes concentration values ​​of major elements and trace elements; Obtaining the method detection limit concentration value of the element data by analyzing and calculating, assigning the method detection limit concentration value to the elements whose concentration value is lower than the method detection limit concentration value, and excluding the elements whose concentration value is missing; Draw a scatter plot between the main element Al and the terrigenous debris-related elements Zr and Ti, and calculate the correlation coefficients between Mg, Si, P, Ca, Ni, As, U, S, K, V, Cr, Mn, Fe, Cu, Zn, Pb, Sr, Mo, Ba and Al, Ti and Zr based on the scatter plot. Eliminate the elements affected by the debris flux based on the correlation coefficients to obtain element data samples; A type classification module is used to perform principal component analysis on the element data sample, screen the features that affect the chemical phase classification to construct a feature vector, perform cluster analysis on the feature vector, and obtain the chemical phase type according to the cluster analysis results; A model training module, used to take the element data sample as input and the chemical phase type as a label, train a random forest algorithm, and obtain a chemical phase prediction model; The chemical phase division module is used to input the lacustrine shale sample data to be tested into the chemical phase prediction model to perform chemical phase division and obtain the chemical phase type division result.

6. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is loaded into a processor, the computer program can execute the steps of the method according to any one of claims 1 to 4.

Images