CN117909933B - A rock drillability prediction method based on support vector machine regression model - Google Patents
A rock drillability prediction method based on support vector machine regression model Download PDFInfo
- Publication number
- CN117909933B CN117909933B CN202410091823.3A CN202410091823A CN117909933B CN 117909933 B CN117909933 B CN 117909933B CN 202410091823 A CN202410091823 A CN 202410091823A CN 117909933 B CN117909933 B CN 117909933B
- Authority
- CN
- China
- Prior art keywords
- rock
- support vector
- regression model
- vector machine
- drillability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000011435 rock Substances 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 34
- 239000002245 particle Substances 0.000 claims abstract description 33
- 238000013139 quantization Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims description 12
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005553 drilling Methods 0.000 abstract description 14
- 239000013598 vector Substances 0.000 abstract description 11
- 238000005520 cutting process Methods 0.000 abstract description 4
- 239000013078 crystal Substances 0.000 abstract description 3
- 229910052500 inorganic mineral Inorganic materials 0.000 description 11
- 239000011707 mineral Substances 0.000 description 11
- 239000007789 gas Substances 0.000 description 7
- 230000010287 polarization Effects 0.000 description 4
- 239000012530 fluid Substances 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000006703 hydration reaction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Earth Drilling (AREA)
Abstract
The invention discloses a rock drillability prediction method based on a support vector machine regression model, which comprises the steps of obtaining a microscopic structure quantization index value of rock particles, constructing the support vector machine regression model, initializing, training the support vector machine regression model through the microscopic structure quantization index value of the rock particles after penalty coefficients and gamma coefficients of the support vector machine regression model are determined, obtaining a prediction model, obtaining a microscopic structure quantization value of the rock particles of an oil-gas well, inputting the microscopic structure quantization index value into the prediction model, and predicting the rock drillability level value of the oil-gas well. The method for predicting the drillability of the oil-gas well rock based on the crystal structure and mineralogy characteristics of the rock cuttings can be used for predicting the drillability of the rock based on the crystal structure and mineralogy characteristics of the rock cuttings, and the method for predicting the drillability of the oil-gas well rock established by using the support vector regression model not only can improve the prediction precision of the model, but also can solve the problem of rapidly predicting the drillability of the rock by using the underground rock cuttings, and provides a direction for the while-drilling prediction of the drillability of the rock of the whole well section.
Description
Technical Field
The invention belongs to the technical field of rock mechanics of petroleum and natural gas drilling engineering, and particularly relates to a rock drillability prediction method based on a support vector machine regression model.
Background
Rock drillability has been the parameter of greatest concern to bit design engineers in oil and gas drilling engineering. The most commonly used methods for obtaining the drillability of the rock are a laboratory micro-drilling test method and a sound wave time difference prediction method, but the laboratory micro-drilling method has the problems of difficult underground coring and high drilling cost, and the drillability of the whole well section is extremely difficult to obtain. The acoustic time difference prediction method firstly establishes a large number of databases to search rules statistically, and secondly cannot reveal the influence mechanism of acoustic time differences of different lithologies on drillability. However, the drillability of rock can severely impact the life of the drill bit, the drilling cycle and the cost of drilling, and lengthening the drilling cycle can also result in hydration reactions of the drilling fluid with the well Zhou Yandan, affecting the stability of the wellbore. Therefore, accurate prediction of rock drillability is of great significance in the aspect of speed increasing and efficiency improving of safe drilling, and a method for predicting the rock drillability of an oil and gas well based on a support vector machine regression model is needed to establish a set of reliable models for rapidly and accurately predicting the rock drillability based on underground rock cuttings, and finally rapid rock drillability while drilling is achieved.
Disclosure of Invention
The invention aims to provide a rock drillability prediction method based on a support vector machine regression model, so as to solve the problems in the prior art.
In order to achieve the above object, the present invention provides a rock drillability prediction method based on a support vector machine regression model, comprising:
acquiring a mesostructure quantization index value of the rock particles;
Constructing a support vector machine regression model and initializing;
After penalty coefficients and gamma coefficients of a support vector machine regression model are determined, training the support vector machine regression model through the mesostructure quantization index values of the rock particles to obtain a prediction model;
And obtaining a quantitative value of the microstructure of the oil-gas well rock particles, inputting the quantitative value into the prediction model, and predicting the drillability level value of the oil-gas well rock.
Optionally, the process of obtaining the fine structure quantization index value of the rock particles comprises the steps of collecting literature data, obtaining the fine structure quantization index value according to analysis of the literature data, carrying out contour division on the rock particle image to obtain absolute positions of a plurality of points of the boundary of the rock particles in the image, and calculating geometric parameters of corresponding contours based on the absolute positions of the plurality of points to obtain the fine structure quantization index value.
Optionally, the rock particle image is profiled based on the optical characteristics of each rock particle type.
Optionally, the mesostructure quantization index includes, but is not limited to, length, area, perimeter, roundness, angle factor, aspect ratio, mesostructure coefficient.
Optionally, the model initialization is performed by normalizing and normalizing the input data of the support vector machine regression model.
Optionally, the process of determining the penalty coefficient and the gamma coefficient of the support vector machine regression model includes:
And predefining the parameter range, determining the punishment coefficient and the gamma coefficient by adopting an exhaustion method, training and testing the model under the coefficient combination of each pair of punishment coefficient and gamma coefficient, and selecting the coefficient combination with the optimal test result as the punishment coefficient and the gamma coefficient of the support vector machine regression model.
Optionally, a gaussian kernel function is used as the kernel function of the prediction model.
The invention has the technical effects that:
According to the method, rock drillability can be predicted based on the crystal structure and mineralogy characteristics of rock scraps, the prediction accuracy of the model can be improved by using the oil-gas well rock drillability prediction method established by the support vector regression model, the problem of rapidly predicting the rock drillability by using underground rock scraps can be solved, powerful support is provided for predicting the deep well ultra-deep well rock drillability, and the direction is provided for predicting the whole-well-section rock drillability while drilling. The method reduces the cost of acquiring the rock drillability, solves the problem of difficult prediction of the rock drillability of the deep well and the ultra-deep well by utilizing the rock scraps discharged by the drilling fluid, improves the prediction precision of the rock drillability and simultaneously avoids the occurrence of overfitting of a model.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a flow chart of a rock drillability prediction method based on a support vector machine regression model in an embodiment of the invention;
FIG. 2 is a flow chart of determining penalty coefficients and gamma coefficients in an embodiment of the invention;
FIG. 3 is a schematic diagram of the importance of different mesoscopic coefficients of structure to rock drillability in an embodiment of the invention;
FIG. 4 is a graph showing the comparison of predicted and actual values of rock drillability in an embodiment of the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Example 1
As shown in fig. 1-4, in this embodiment, a rock drillability prediction method based on a support vector machine regression model is provided, including:
The method comprises the steps of obtaining a quantitative index of a microstructure of the rock, initializing a support vector regression model, determining a Gaussian kernel function, determining a punishment coefficient and a gamma coefficient, training and testing the model, and forming a rock drillability prediction method based on the support vector machine regression model.
Specifically, the acquisition of the quantitative index of the microstructure of the rock comprises defining the quantitative index of the microstructure, dividing the outline of the mineral particles according to the optical characteristics of the mineral, summarizing all outline information of the mineral particles, calculating the geometric parameters of the corresponding outline, and programming and calculating to obtain the quantitative index of the microstructure.
The optical characteristics of the minerals refer to that images of the same mineral are different under the condition of single polarization and different angle orthogonal polarization, according to the characteristics, the single polarization and orthogonal polarization images of one mineral can be compared to distinguish the actual outline of the mineral, then the image J software is used for surrounding particles of the mineral by using the mark points, and then adjacent mark points are connected to form a closed curve, so that the outline of the particles is obtained.
Specifically, the support vector regression model initialization includes normalization processing of the quantitative index of the microstructure, and normalization processing of the data.
In particular, determining the gaussian kernel function includes mapping the input parameters to high latitude, thereby enabling it to process non-linearly separable samples. The complex relation between samples can be effectively captured by using the Gaussian kernel function, and the fitting capacity and generalization capacity of the model are improved. The expression of the gaussian kernel function is as follows:
Where κ (x i,xj) represents the output value of the gaussian kernel, x i,xj represents the eigenvector of the input sample, |x i-xj||2 represents the square of the modular length of the eigenvector difference, σ represents the bandwidth of the gaussian kernel.
Specifically, determining the penalty coefficient and the gamma coefficient includes changing the penalty coefficient to determine a proper relaxation factor, determining a lower limit of model prediction accuracy, debugging out a proper gamma coefficient, and improving generalization capability of the kernel function.
Specifically, the model training and testing includes importing Jupyter programs with data, dividing 70% of the data into training sets, dividing 30% of the data into testing sets, and setting penalty coefficients and Gamma to obtain the accuracy of the training sets and the testing sets. And obtaining a prediction model according to the training and testing results.
Specifically, the rock drillability prediction method based on the support vector machine regression model comprises the steps of establishing the support vector machine regression model taking a microscopic structure of particles as an input parameter and taking a rock drillability level value as an output parameter.
In this embodiment, the rock drillability prediction method based on the support vector machine regression model mainly includes the steps of obtaining a quantitative index of a microstructure of a rock, initializing the support vector regression model, determining a Gaussian kernel function, determining a penalty coefficient and a gamma coefficient, training and testing the model, and forming the rock drillability prediction method based on the support vector machine regression model.
In the embodiment, proper micro-structure quantization indexes mainly comprise length, area, perimeter, roundness, angle factors, length-width ratio, micro-structure coefficients and the like, absolute positions of mark points on each mineral boundary are obtained through image processing, geometric dimensions are calculated according to the absolute positions of the mark points on the mineral boundary, micro-structure quantization index values are calculated according to a calculation model of each micro-structure quantization index through matlab programming, a support vector regression model is initialized, input data are normalized, kernel functions, penalty coefficients and gamma coefficients are determined, wherein the kernel functions are Gaussian kernel functions, the penalty coefficients determine interval sizes and classification accuracy, the gamma coefficients influence the Gaussian action range corresponding to support vectors so as to influence the generalization capability of the kernel functions, and an oil-gas well rock drillability prediction method based on the support vector machine regression model is formed through the training and testing phases of the model.
The length, area, circumference refer to classical geometric features, the roundness refers to "the ratio of the object area a to the circular area with the same circumference P", e.g. the roundness SF can be calculated using this formulaWherein P is perimeter, A is object area, angle factor is AF 1, which can be calculated according to the following two formulas, wherein x 1 is the number that the angle between the longest axis of the particle and the direction is 0-10 degrees, x 2 is the number that the angle between the longest axis of the particle and the direction is 10-20 degrees, and the like, and x 9 is the number that the angle between the longest axis of the particle and the direction is 80-90 degrees.
AF 1 = ANGLE FACTOR/5 aspect ratio refers to the ratio of the longest axis to the shortest axis of the particle.
The mesoscopic structural coefficient TC refers toWhere TC is the mesoscopic structure factor, AW is the mineral fill factor, N 0、N1 is the number of particles with aspect ratio (Feret definition) below and above the preset value (typically 2), the arithmetic average of the discriminable (DISCRIMINATED) shape factors of all particles of SF 0, the arithmetic average of the discriminable (DISCRIMINATED) aspect ratios of all particles of AR 1, and the angle factor of AF 1 particles, respectively.
As shown in fig. 2, fig. 2 is a flow of determining penalty coefficients and gamma coefficients.
In this embodiment, the ranges of penalty coefficients and gamma coefficients are predefined first, then the penalty coefficients and gamma coefficients are determined by using an exhaustion method, then the performance of the combination of the coefficients is cross-validated, the score condition of the training set and the test set of each pair of penalty coefficients and gamma coefficient combinations is calculated by using a Mean Square Error (MSE), the superiority of each pair of penalty coefficients and gamma coefficient combinations is evaluated, the smaller the MSE is, the better the score is, the penalty coefficients and gamma coefficients at this time are the preferred combinations, and the preferred parameter combination is used as the penalty coefficients and gamma coefficient stage of the model.
Where N is the number of samples, y p,i is the predicted drillability, and y t,i is the actual drillability.
As shown in fig. 3, fig. 3 shows the importance of different mesoscopic structural coefficients to rock drillability, the importance being obtained by using the lagrangian multiplier a i, the larger the lagrangian multiplier the higher the corresponding importance.
In this example, the angle factor, mesoscopic structure factor, aspect ratio and roundness have the greatest impact on rock drillability and the area, particle homogeneity and compaction have the least impact on rock drillability.
The Lagrangian function of the original problem is as follows:
Y(w,b,ζ,α,β)=Y1+Y2-Y3-Y4
Where Y 1 is the average norm of the model, Y 2 is the penalty factor, Y 3 is the constraint function of the model output and the actual label, Y 4 is the constraint function of the relaxation variable, w is the weight vector, b is the intercept, ζ is the relaxation variable vector, and α i and β i are Lagrangian multiplier vectors.
Solving a Lagrangian function, maximizing the Lagrangian function, solving a dual problem, solving partial derivatives of a weight vector, an intercept and a relaxation variable, enabling the partial derivatives to be equal to zero, and obtaining a Lagrangian multiplier, wherein the larger the Lagrangian multiplier is, the higher the importance degree is, and when the influence of a i and beta i on output parameters is inconsistent, a i is used as a judgment basis.
As shown in fig. 4, fig. 4 is a comparison of predicted and actual values of rock drillability.
In the embodiment, the predicted drillability and the actually measured drillability show better correlation, so that the oil-gas well rock drillability prediction method based on the support vector machine regression model has better popularization prospect.
The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims (3)
1. The rock drillability prediction method based on the support vector machine regression model is characterized by comprising the following steps of:
acquiring a mesostructure quantization index value of the rock particles;
the process for obtaining the microscopic structure quantization index value of the rock particles comprises the steps of collecting literature data, analyzing and obtaining the microscopic structure quantization index value according to the literature data, carrying out contour division on the rock particle image to obtain absolute positions of a plurality of points of the boundary of the rock particles in the image, and calculating geometric parameters of corresponding contours based on the absolute positions of the plurality of points to obtain the microscopic structure quantization index value;
performing contour division on the rock particle image based on the optical characteristics of each rock particle belonging type;
the mesostructure quantization index includes, but is not limited to, length, area, circumference, roundness, angle factor, aspect ratio, mesostructure coefficient;
Constructing a support vector machine regression model and initializing;
After penalty coefficients and gamma coefficients of a support vector machine regression model are determined, training the support vector machine regression model through the mesostructure quantization index values of the rock particles to obtain a prediction model;
the process of determining the penalty coefficients and gamma coefficients of the support vector machine regression model includes:
Predefining parameter ranges, determining punishment coefficients and gamma coefficients by adopting an exhaustion method, training and testing a model under the coefficient combination of each pair of punishment coefficients and gamma coefficients, and selecting the coefficient combination with the optimal test result as the punishment coefficients and gamma coefficients of the support vector machine regression model;
And obtaining a quantitative value of the microstructure of the oil-gas well rock particles, inputting the quantitative value into the prediction model, and predicting the drillability level value of the oil-gas well rock.
2. The method for predicting rock drillability based on the support vector machine regression model of claim 1 wherein,
And carrying out model initialization by carrying out standardization and normalization processing on the input data of the support vector machine regression model.
3. The method for predicting rock drillability based on the support vector machine regression model of claim 1 wherein,
And adopting a Gaussian kernel function as a kernel function of the prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410091823.3A CN117909933B (en) | 2024-01-23 | 2024-01-23 | A rock drillability prediction method based on support vector machine regression model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410091823.3A CN117909933B (en) | 2024-01-23 | 2024-01-23 | A rock drillability prediction method based on support vector machine regression model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117909933A CN117909933A (en) | 2024-04-19 |
| CN117909933B true CN117909933B (en) | 2024-12-10 |
Family
ID=90690723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410091823.3A Active CN117909933B (en) | 2024-01-23 | 2024-01-23 | A rock drillability prediction method based on support vector machine regression model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117909933B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809518A (en) * | 2015-04-29 | 2015-07-29 | 重庆大学 | A prediction method of rock burst acoustic emission based on support vector machine |
| CN115407046A (en) * | 2022-08-05 | 2022-11-29 | 西南石油大学 | Comprehensive characterization method of abrasiveness based on rock mesostructure and equivalent quartz content |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9128203B2 (en) * | 2011-09-28 | 2015-09-08 | Saudi Arabian Oil Company | Reservoir properties prediction with least square support vector machine |
| US11066917B2 (en) * | 2018-05-10 | 2021-07-20 | Baker Hughes Holdings Llc | Earth-boring tool rate of penetration and wear prediction system and related methods |
| AU2020101854A4 (en) * | 2020-08-17 | 2020-09-24 | China Communications Construction Co., Ltd. | A method for predicting concrete durability based on data mining and artificial intelligence algorithm |
| CN112230283B (en) * | 2020-10-12 | 2021-08-10 | 北京中恒利华石油技术研究所 | Seismic porosity prediction method based on logging curve support vector machine modeling |
| CN113378998B (en) * | 2021-07-12 | 2022-07-22 | 西南石油大学 | Stratum lithology while-drilling identification method based on machine learning |
| CN114091333B (en) * | 2021-11-18 | 2024-12-06 | 电子科技大学长三角研究院(湖州) | An artificial intelligence prediction method for shale gas content based on machine learning |
| CN116342967A (en) * | 2023-03-31 | 2023-06-27 | 西南石油大学 | Drillability intelligent prediction method based on rock mesoscopic structural parameters |
-
2024
- 2024-01-23 CN CN202410091823.3A patent/CN117909933B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809518A (en) * | 2015-04-29 | 2015-07-29 | 重庆大学 | A prediction method of rock burst acoustic emission based on support vector machine |
| CN115407046A (en) * | 2022-08-05 | 2022-11-29 | 西南石油大学 | Comprehensive characterization method of abrasiveness based on rock mesostructure and equivalent quartz content |
Non-Patent Citations (1)
| Title |
|---|
| 基于最小二乘支持向量机的岩石可钻性研究;谢祥俊 等;西南石油大学学报(自然科学版);20100228;第145-148页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117909933A (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110674841B (en) | Logging curve identification method based on clustering algorithm | |
| WO2017084454A1 (en) | Stratum component optimization determination method and device | |
| CN115662533B (en) | Construction geochemistry combination anomaly identification method for hidden ore detection | |
| Zhihong et al. | Evaluation of granular particle roundness using digital image processing and computational geometry | |
| CN106066493A (en) | Bayes's petrofacies method of discrimination and device | |
| CN110006568B (en) | Method and system for acquiring three-dimensional ground stress by using rock core | |
| CN105760673A (en) | Fluvial facies reservoir earthquake sensitive parameter template analysis method | |
| Bagheri et al. | Reservoir rock permeability prediction using SVR based on radial basis function kernel | |
| Shi et al. | Data-driven multi-stage sampling strategy for a three-dimensional geological domain using weighted centroidal voronoi tessellation and IC-XGBoost3D | |
| CN110568495B (en) | Rayleigh wave multi-mode dispersion curve inversion method based on generalized objective function | |
| CN116927771A (en) | A method, device, equipment and medium for predicting total organic carbon data of shale reservoirs | |
| CN117909933B (en) | A rock drillability prediction method based on support vector machine regression model | |
| CN119443418A (en) | A multi-dimensional fusion prospecting prediction method based on multi-source data | |
| CN114818493A (en) | A method for quantitative evaluation of the integrity of tunnel rock mass | |
| Hou et al. | Identification of carbonate sedimentary facies from well logs with machine learning | |
| Schopmans et al. | Neural networks trained on synthetically generated crystals can extract structural information from ICSD powder X-ray diffractograms | |
| CN110717528A (en) | Support vector machine-based sedimentary microfacies identification method using conventional logging information | |
| Li et al. | A rapid updating method to predict grade heterogeneity at smaller scales | |
| CN113627640A (en) | Productivity well testing prediction method and system for fracture-cavity type oil reservoir oil and gas well | |
| CN117743978A (en) | Rock mass integrity identification method based on gradient lifting decision tree and while-drilling parameters | |
| CN111582292A (en) | Interlayer identification method and device | |
| Shao et al. | Carbonate log interpretation models based on machine learning techniques | |
| CN113534283B (en) | Quantitative evaluation method for ore-forming element characteristics of sandstone-type uranium ores | |
| CN113419278B (en) | Well-seismic joint multi-target simultaneous inversion method based on state space model and support vector regression | |
| CN116931069A (en) | Underground fluid prediction method, equipment and medium considering geologic body weight |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |