CN111079783B - Method for identifying stratum lithology parameters based on multi-core ensemble learning - Google Patents
Method for identifying stratum lithology parameters based on multi-core ensemble learning Download PDFInfo
- Publication number
- CN111079783B CN111079783B CN201911094176.7A CN201911094176A CN111079783B CN 111079783 B CN111079783 B CN 111079783B CN 201911094176 A CN201911094176 A CN 201911094176A CN 111079783 B CN111079783 B CN 111079783B
- Authority
- CN
- China
- Prior art keywords
- lithology
- sample set
- training
- samples
- classifier
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
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)
- Geophysics And Detection Of Objects (AREA)
- Investigation Of Foundation Soil And Reinforcement Of Foundation Soil By Compacting Or Drainage (AREA)
Abstract
The invention relates to the technical field of reservoir lithology identification, in particular to a method for identifying stratum lithology parameters based on multi-core ensemble learning. The method comprises the following steps: dividing different sample sets according to the logging parameter characteristics; dividing a training sample set and a test sample set; aiming at the lithological parameter characteristics, establishing a strong classifier, respectively judging the test samples in the test sample set, and obtaining the lithological parameters by adopting an averaging method; establishing a strong classifier aiming at lithologic parameter characteristics according to the prediction result and reconstructed sample data; forming a strong classifier by using the strong classifier; judging the sample, and determining the final stratum lithology category by adopting a voting mode; and (4) adopting an absolute majority voting method, if the half number of votes marked by a certain lithology is judged to be the lithology, and if not, refusing to predict. The invention applies the characteristic of a multi-core ensemble learning algorithm, combines a plurality of classifiers, minimizes the classification error rate, improves the utilization rate of logging data and has high judgment accuracy.
Description
Technical Field
The invention relates to the technical field of reservoir lithology identification, in particular to a method for identifying stratum lithology parameters based on multi-core ensemble learning.
Background
Reservoir lithology identification is an important link in reservoir evaluation work, a development scheme can be formulated only after actual conditions of a stratum are accurately known, high and stable yield of an oil field is promoted, a coring method, a cross plot method and a statistical analysis method are conventionally used in the lithology identification process, so that not only is the workload large, but also the identification accuracy is influenced by professional knowledge and human factors. The relation between the logging parameters and the lithology is complex, the identification result is influenced by various logging methods, the accuracy of identifying different lithologies is unstable by utilizing single-core learning, different kernel functions are selected to obtain different identification results, and therefore correct lithology identification is obtained, the logging parameters and the kernel functions are carefully discussed and analyzed, and the lithology is identified as detailed as possible.
Hao Xia and Steven Hoi creatively put forward a multi-core Integrated learning framework (MKBoost), and the idea of AdaBoost is applied to multi-core learning, so that the complex optimization problem is ingeniously avoided, and the algorithm efficiency is greatly improved.
The prior art discloses an automatic rock lithology identification and classification method in a deep learning mode, which is used for analyzing rock lithology in geological engineering. By establishing the automatic recognition and classification model of the rock image, the geological condition in the engineering can be automatically and intelligently analyzed.
However, in actual production, the existing method mainly utilizes a deep learning method to identify the lithology of the stratum, and a multi-core ensemble learning method is not utilized to distinguish the lithology parameters and the lithology type temporarily.
Disclosure of Invention
Technical problem to be solved
The invention provides a method for identifying stratum lithology parameters based on multi-core ensemble learning, which aims to overcome the defects of low utilization rate of logging data, low judgment accuracy and the like caused by identifying stratum lithology by using a deep learning method in the prior art.
(II) technical scheme
In order to solve the problems, the invention provides a stratum lithology prediction method based on multi-core ensemble learning, which comprises the following steps of:
s1, dividing M different sample sets according to logging parameter characteristics,
S 1 ={(x 11 ,y 11 ),(x 12 ,y 12 ),…,(x 1n ,y 1n )};
S 2 ={(x 21 ,y 21 ),(x 22 ,y 22 ),…,(x 2n ,y 2n )};…;
S m ={(x m1 ,y m1 ),(x m2 ,y m2 ),…,(x mn ,y mn )}
S2, aiming at the predicted lithological parameter characteristics, under the condition that the same proportion is kept, dividing each sample set into training sample sets according to a certain proportion mtrain And a test sample set S mtest The number of samples in the training sample set is n mtrain The number of samples in the test sample set is n mtest ;
S3, aiming at lithologic parameter characteristics, establishing a strong classifier H j (x),j=1~L f Co-building L f A strong classifier;
s4, utilizing the strong classifiers H of the multiple categories produced above j (x),j=1~L f Respectively judging the test samples in the test sample set, and obtaining lithology parameters by adopting an averaging method;
step S5, comparing the prediction result with y in step S1 m2 Reconstruction of sample data, S 2m ={(z1,y1),(z2,y2),...,(zn,yn)}S 2m ={(z 1 ,y 1 ),(z 2 ,y 2 ),…,(z n ,y n )}
Wherein z is n =H(x mn ),y n =y mn ;
S6, aiming at lithological parameter characteristics, establishing a strong classifier H j (x),j=1~L p Co-building L p A strong classifier;
s7, taking the predicted lithology parameters as input data and utilizing a strong classifier H j (x),j=L f +1~2L f Composition strong classifier H (x):
s8, judging the sample, and determining the final stratum lithology type in a voting mode; h i Will be from the lithology label set c 1 ,c 2 ,…,c n A flag is predicted, identifying the predicted output of H (x) at sample x as an N-vectorWherein h is i j (x) Is h i Marking of lithology c j An output of (d);
and S9, adopting an absolute majority voting method, if the number of the marked votes of a certain lithology is more than half, predicting the lithology, and if not, refusing to predict.
Preferably, the logging parameter vector x in step S1 m The method specifically comprises the following steps: acoustic time difference, neutron porosity, resistivity, permeability, natural gamma, natural resistivity, compensated neutrons.
Preferably, the lithology parameter vector y described in step S1 m1 Length L of f =3, specifically including: permeability, porosity, water saturation, lithology class parameter vector y m2 Length L of p =6, specifically including: shale, sandstone, mudstone, siltstone, argillaceous sandstone, argillaceous siltstone.
Preferably, the number M of sample sets in step S1 is equal to y m1 Length L of f 。
Preferably, the number of samples in the training sample set is 70% of the total number of samples in the sample set, and the number of samples in the testing sample set is 30% of the total number of samples.
Preferably, the strong classifier establishing method described in step S3 includes:
s31, setting training times T and carrying out training sample set S mtrain Each sample is assigned with an initialization weight D t T is the number of times of the current training,
step S33, according to weight distribution D of training samples t From a training sample set S mtrain Extracting the obtained samples to form a training set L;
step S34, training by using a base learning algorithm and using a training set L to generate a weak classifier h t ;
Step S35, using the weak classifier h generated in step S33 t For training sample set S mtrain Is predicted, the weak classifier h is calculated t Error rate of (e) t ,Wherein y is i Is a training sample set S mtrain Sample of (1), f t j (x i ) Using a weak classifier h t The obtained prediction results, i =1 to S mtain J denotes the jth kernel function k j (·,·);
Step S36, selecting classification error rateMinimum weak classifier f t j As the t-th classification base classifier, andas a classification error rate epsilon t :
Step S37, calculating the weak classifier h t Weight of a t ,And updates the weight distribution of the training sample set,wherein Z t Is normalizationThe factor(s) is (are),increasing the number of cycles T = T +1, if T < T, proceeding to step S32, and if k = T, proceeding to step S38;
step S38, the above steps S31 to S35, collectively generate T weak classifiers, each having a weight a t To form a strong classifier H (x),
preferably, the kernel function in step S32 is a linear kernel, a polynomial kernel, a gaussian kernel, a laplacian kernel, or a Sigmoid kernel.
(III) advantageous effects
The method for identifying the formation lithology parameters based on the multi-core ensemble learning provided by the invention applies the characteristics of the multi-core ensemble learning algorithm, combines a plurality of classifiers, minimizes the classification error rate, and has the remarkable characteristics of improving the utilization rate of logging data, high judgment accuracy and the like.
Drawings
FIG. 1 is a flowchart of a method for identifying formation lithology parameters based on multi-core ensemble learning according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the drawings and examples.
As shown in fig. 1, an embodiment of the present invention provides a method for identifying formation lithology parameters based on multi-core ensemble learning, which specifically includes:
s1, dividing M different sample sets according to logging parameter characteristics,
S 1 ={(x 11 ,y 11 ),(x 12 ,y 12 ),…,(x 1n ,y 1n )};
S 2 ={(x 21 ,y 21 ),(x 22 ,y 22 ),…,(x 2n ,y 2n )};…;
S m ={(x m1 ,y m1 ),(x m2 ,y m2 ),…,(x mn ,y mn )}
S2, aiming at the predicted lithological parameter characteristics, under the condition that the same proportion is kept, dividing each sample set into training sample sets according to a certain proportion mtrain And a test sample set S mtest The number of samples in the training sample set is n mtrain The number of samples in the test sample set is n mtest ;
S3, aiming at lithologic parameter characteristics, establishing a strong classifier H j (x),j=1~L f Co-building L f A strong classifier;
s4, utilizing the strong classifiers H of the multiple categories produced above j (x),j=1~L f Respectively judging the test samples in the test sample set, and obtaining lithology parameters by adopting an averaging method;
step S5, comparing the prediction result with y in step S1 m2 Reconstruction of sample data, S 2m ={(z1,y1),(z2,y2),...,(zn,yn)}S 2m ={(z 1 ,y 1 ),(z 2 ,y 2 ),…,(z n ,y n )}
Wherein z is n =H(x mn ),y n =y mn ;
S6, aiming at lithologic parameter characteristics, establishing a strong classifier H j (x),j=1~L p Co-building L p A strong classifier;
s7, taking the predicted lithology parameters as input data and utilizing a strong classifier H j (x),j=L f +1~2L f Composition strong classifier H (x):
s8, judging the sample, and determining the final stratum lithology category by voting;H i Will be from the lithology label set c 1 ,c 2 ,…,c n A flag is predicted, identifying the predicted output of H (x) at sample x as an N-vectorWhereinIs h i Marking of lithology c j An output of (d);
and S9, adopting an absolute majority voting method, if the number of the marked votes of a certain lithology is more than half, predicting the lithology, and if not, refusing to predict.
Wherein, the logging parameter vector x in the step S1 m The method specifically comprises the following steps: acoustic time difference, neutron porosity, resistivity, permeability, natural gamma, natural resistivity, compensated neutrons.
Lithology parameter vector y described in step S1 m1 Length L of f =3, specifically including: permeability, porosity, water saturation, lithology class parameter vector y m2 Length L of p =6, specifically including: shale, sandstone, mudstone, siltstone, argillaceous sandstone, argillaceous siltstone.
Wherein the number M of the sample sets in the step S1 is equal to y m1 Length L of f 。
The number of samples in the training sample set is 70% of the total number of samples in the sample set, and the number of samples in the testing sample set is 30% of the total number of samples.
The strong classifier establishing method in step S3 includes:
s31, setting training times T and carrying out training sample set S mtrain Each sample is assigned with an initialization weight D t T is the number of times of the current training,
Step S33, according to weight distribution D of training samples t From a training sample set S mtrain Extracting the obtained samples to form a training set L;
step S34, training by using a base learning algorithm and using a training set L to generate a weak classifier h t ;
Step S35, using the weak classifier h generated in step S33 t For training sample set S mtrain Is predicted, the weak classifier h is calculated t Error rate of (e) t ,Wherein y is i Is a training sample set S mtrain Sample of (1), f t j (x i ) Using a weak classifier h t The obtained prediction results, i =1 to S mtain J denotes the jth kernel function k j (·,·);
Step S36, selecting classification error rateMinimum weak classifier f t j As the t-th classification base classifier, andas a classification error rate epsilon t :
Step S37, calculating the weak classifier h t Weight of a t ,And updates the weight distribution of the training sample set,wherein Z t Is a normalization factor that is a function of,increasing the cycle number T = T +1, if T < T, proceeding to step S32, and if k = T, proceeding to step S38;
step S38, the above steps S31 to S35, collectively generate T weak classifiers, each having a weight a t To form a strong classifier H (x),
the kernel function in step S32 is a linear kernel, a polynomial kernel, a gaussian kernel, a laplacian kernel, or a Sigmoid kernel.
According to the technical scheme, a plurality of weak classifiers with differences are established through a base learning algorithm, the lithological parameters of the test sample are judged respectively, the prediction results with the differences are obtained, and the strong classifiers are formed and used for judging the lithological character of the stratum. The method has the remarkable characteristics of improving the utilization rate of logging data, having high judgment accuracy and the like.
The method for identifying the formation lithology parameters based on the multi-core ensemble learning fully applies the characteristics of the multi-core ensemble learning algorithm, combines a plurality of classifiers and minimizes the classification error rate. In the method, a plurality of weak classifiers with differences are established through a base learning algorithm, the lithology parameters are judged first, prediction results with differences are obtained, strong classifiers are formed, the prediction results are used as input data, single lithology type judgment is carried out on samples again, and the purpose of predicting the lithology parameters and the lithology types is achieved.
The above embodiments are only for illustrating the invention and are not to be construed as limiting the invention, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention, therefore, all equivalent technical solutions also belong to the scope of the invention, and the scope of the invention is defined by the claims.
Claims (6)
1. A method for identifying stratum lithology parameters based on multi-core ensemble learning is characterized by comprising the following steps:
s1, dividing M different sample sets according to logging parameter characteristics,
S 1 ={(x 11 ,y 11 ),(x 12 ,y 12 ),L,(x 1n ,y 1n )};
S 2 ={(x 21 ,y 21 ),(x 22 ,y 22 ),L,(x 2n ,y 2n )};L;
S m ={(x m1 ,y m1 ),(x m2 ,y m2 ),L,(x mn ,y mn )}
S2, aiming at the predicted lithological parameter characteristics, under the condition that the same proportion is kept, dividing each sample set into training sample sets according to a certain proportion mtrain And a test sample set S mtest The number of samples in the training sample set is n mtrain The number of samples in the test sample set is n mtest ;
S3, aiming at lithologic parameter characteristics, establishing a strong classifier H j (x),j=1~L f Co-building L f The strong classifier specifically comprises: s31, setting training times T and carrying out training sample set S mtrain Each sample is assigned with an initialization weight D t T is the number of times of the current training,
Step S33, according to weight distribution D of training samples t From a training sample set S mtrain Extracting the obtained samples to form a training set L;
step S34, training by using a base learning algorithm and using a training set L to generate a weak classifier h t ;
Step S35, using the weak classifier h generated in step S33 t For training sample set S mtrain Is predicted, the weak classifier h is calculated t Error rate of (e) t ,Wherein y is i Is a training sample set S mtrain Sample of (1), f t j (x i ) Using a weak classifier h t The obtained prediction results, i =1 to S mtain J denotes the jth kernel function k j (·,·);
Step S36, selecting classification error rateMinimum weak classifier f t j As the t-th classification base classifier, andas a classification error rate
Step S37, calculating the weak classifier h t Weight of a t ,And updates the weight distribution of the training sample set,wherein Z t Is a normalization factor that is a function of,increasing the cycle number T = T +1, if T < T, proceeding to step S32, and if k = T, proceeding to step S38;
step S38, the above steps S31 to S35, collectively generate T weak classifiers, each having a weight a t To form a strong classifier H (x),
step S4, utilizing the strong classifiers H of the multiple categories produced in the above way j (x),j=1~L f Respectively judging the test samples in the test sample set, and obtaining lithology parameters by adopting an averaging method;
step S5, the prediction result and y in the step S1 m2 Reconstruction of sample data, S 2m ={(z1,y1),(z2,y2),...,(zn,yn)}S 2m ={(z 1 ,y 1 ),(z 2 ,y 2 ),L,(z n ,y n )}
Wherein z is n =H(x mn ),y n =y mn ;
S6, aiming at lithological parameter characteristics, establishing a strong classifier H j (x),j=1~L p Co-building L p A strong classifier;
s7, taking the predicted lithology parameters as input data and utilizing a strong classifier H j (x),j=L f +1~2L f Composition strong classifier H (x):
step S8, pairJudging the sample, and determining the final stratum lithology category by adopting a voting mode; h i Will be from the lithology label set c 1 ,c 2 ,L,c n A flag is predicted, identifying the predicted output of H (x) at sample x as an N-vectorWhereinIs h i Marking of lithology c j An output of (d);
and S9, adopting an absolute majority voting method, if the number of the marked votes of a certain lithology is more than half, predicting the lithology, and if not, refusing to predict.
2. The method of claim 1, wherein the logging parameter vector x in step S1 m The method specifically comprises the following steps: acoustic time difference, neutron porosity, resistivity, permeability, natural gamma, natural resistivity, compensated neutrons.
3. The method of claim 1, wherein the lithology parameter vector y of step S1 m1 Length L of f =3, including in particular: permeability, porosity, water saturation, lithology class parameter vector y m2 Length L of p =6, specifically including: shale, sandstone, mudstone, siltstone, argillaceous sandstone, argillaceous siltstone.
4. The method of claim 3, wherein the number of sample sets M in step S1 is equal to y m1 Length L of f 。
5. The method of claim 1, wherein the number of samples in the training sample set is 70% of the total number of samples in the sample set, and the number of samples in the testing sample set is 30% of the total number of samples.
6. The method of claim 1, wherein the kernel function in step S32 is a linear kernel, a polynomial kernel, a gaussian kernel, a laplacian kernel, or a Sigmoid kernel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911094176.7A CN111079783B (en) | 2019-11-11 | 2019-11-11 | Method for identifying stratum lithology parameters based on multi-core ensemble learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911094176.7A CN111079783B (en) | 2019-11-11 | 2019-11-11 | Method for identifying stratum lithology parameters based on multi-core ensemble learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111079783A CN111079783A (en) | 2020-04-28 |
CN111079783B true CN111079783B (en) | 2022-11-08 |
Family
ID=70310830
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911094176.7A Active CN111079783B (en) | 2019-11-11 | 2019-11-11 | Method for identifying stratum lithology parameters based on multi-core ensemble learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111079783B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111596354B (en) * | 2020-05-11 | 2021-06-04 | 同济大学 | Seismic reservoir prediction method considering space constraint under machine learning framework |
CN111723949A (en) * | 2020-06-24 | 2020-09-29 | 中国石油大学(华东) | Porosity prediction method based on selective ensemble learning |
CN113033637B (en) * | 2021-03-16 | 2022-11-22 | 电子科技大学 | Integrated learning lithofacies prediction method based on rock physical sample enhancement |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101482926A (en) * | 2009-02-19 | 2009-07-15 | 北京大学 | Extensible self-adapting multi-core classification method |
CN105388531A (en) * | 2015-10-19 | 2016-03-09 | 成都理工大学 | Lithology identification method based on support vector regression machine and Kernel Fisher discriminant analysis |
CN108961468A (en) * | 2018-06-27 | 2018-12-07 | 大连海事大学 | A kind of ship power system method for diagnosing faults based on integrated study |
CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012243180A (en) * | 2011-05-23 | 2012-12-10 | Sony Corp | Learning device, method and program |
US10839510B2 (en) * | 2015-08-19 | 2020-11-17 | Colorado Seminary, Which Owns And Operates The University Of Denver | Methods and systems for human tissue analysis using shearlet transforms |
-
2019
- 2019-11-11 CN CN201911094176.7A patent/CN111079783B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101482926A (en) * | 2009-02-19 | 2009-07-15 | 北京大学 | Extensible self-adapting multi-core classification method |
CN105388531A (en) * | 2015-10-19 | 2016-03-09 | 成都理工大学 | Lithology identification method based on support vector regression machine and Kernel Fisher discriminant analysis |
CN108961468A (en) * | 2018-06-27 | 2018-12-07 | 大连海事大学 | A kind of ship power system method for diagnosing faults based on integrated study |
CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
Non-Patent Citations (1)
Title |
---|
秦研博."多核核函数方法在储层岩性识别中的应用".《中国优秀硕士学位论文全文数据库(电子期刊)》.2018, * |
Also Published As
Publication number | Publication date |
---|---|
CN111079783A (en) | 2020-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111079783B (en) | Method for identifying stratum lithology parameters based on multi-core ensemble learning | |
CN110674841B (en) | Logging curve identification method based on clustering algorithm | |
CN112989708B (en) | Well logging lithology identification method and system based on LSTM neural network | |
CN111783825A (en) | Well logging lithology identification method based on convolutional neural network learning | |
CN109919184A (en) | A kind of more well complex lithology intelligent identification Methods and system based on log data | |
CN109345007B (en) | Advantageous reservoir development area prediction method based on XGboost feature selection | |
US20090276157A1 (en) | System and method for interpretation of well data | |
WO2019232224A1 (en) | Systems and methods for special core analysis sample selection and assessment | |
Thomas et al. | Automated lithology extraction from core photographs | |
CN110263835A (en) | Rock category automatic identifying method based on deep learning and Bayesian network | |
CN111160389A (en) | Lithology identification method based on fusion of VGG | |
Brown et al. | Machine learning on Crays to optimize petrophysical workflows in oil and gas exploration | |
CN111027249B (en) | Machine learning-based inter-well connectivity evaluation method | |
CN105986819B (en) | The method and apparatus with integrated interpretation are automatically processed for well-log information | |
CN115587191A (en) | Coal mine vein tendency reasoning system | |
CN114359617A (en) | Method for identifying lithology of rock based on lightweight convolutional neural network | |
CN116540316B (en) | Geological Soil Layer Testing Method Based on SVM Classification Algorithm and Clustering Algorithm | |
CN117473305A (en) | Method and system for predicting reservoir parameters enhanced by neighbor information | |
CN111626377A (en) | Lithofacies identification method, device, equipment and storage medium | |
CN115809411A (en) | Improved decision tree lithology identification method based on logging data | |
US20230145880A1 (en) | Method for predicting geological features from images of geologic cores using a deep learning segmentation process | |
CN114581666A (en) | Intelligent rock sample identification method and system based on image deep learning | |
CN115204277A (en) | Asymptotic optimal lithology prediction method based on multi-threshold quantitative output observation | |
CN112612935A (en) | Complete logging data acquisition method based on self-reasoning model | |
CN113720952A (en) | Method, device, equipment and medium for generating chart for reservoir interpretation and evaluation |
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 |