CN114482995B - Fine determination method for clay content of fine sediment - Google Patents
Fine determination method for clay content of fine sediment Download PDFInfo
- Publication number
- CN114482995B CN114482995B CN202210233604.5A CN202210233604A CN114482995B CN 114482995 B CN114482995 B CN 114482995B CN 202210233604 A CN202210233604 A CN 202210233604A CN 114482995 B CN114482995 B CN 114482995B
- Authority
- CN
- China
- Prior art keywords
- content
- clay content
- data
- logging
- core
- 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
- 239000004927 clay Substances 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000013049 sediment Substances 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 17
- 230000008021 deposition Effects 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000007689 inspection Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 17
- 238000002474 experimental method Methods 0.000 claims description 14
- 239000004576 sand Substances 0.000 claims description 12
- 239000011435 rock Substances 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 238000003921 particle size analysis Methods 0.000 claims description 4
- 230000006698 induction Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 3
- 239000002245 particle Substances 0.000 description 9
- 238000011156 evaluation Methods 0.000 description 5
- 239000010419 fine particle Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000704 physical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 239000000945 filler Substances 0.000 description 2
- 238000005755 formation reaction Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000011362 coarse particle Substances 0.000 description 1
- 239000007771 core particle Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B49/00—Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B2200/00—Special features related to earth drilling for obtaining oil, gas or water
- E21B2200/20—Computer models or simulations, e.g. for reservoirs under production, drill bits
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention aims to provide a fine determination method for the clay content of fine sediment, which is characterized in that firstly, a single well sediment microphase section is divided based on reservoir sediment characteristics and logging curve combination characteristics. And secondly, according to the experimental results of core analysis, granularity and the like, calibrating the sediment microphase clay contents of different types with different granularity values. And after the core is subjected to deep homing, logging characteristic parameters are extracted according to logging response characteristics of different types of sedimentary microphase strata, and a training data set and a checking data set are established. And training the training set by adopting an LSTM neural network method, and establishing a clay content calculation model. And then, carrying out model inspection by using an inspection set, and popularizing and applying after meeting the precision requirement. Practice proves that the method can accurately calculate the clay content of the fine sediment low-resistance reservoir under the complex deposition environment, lays an important foundation for calculating the porosity, saturation and other reservoir parameters of the reservoir, and has wide application and popularization prospects.
Description
Technical Field
The invention relates to the field of geophysical exploration, belongs to a logging data processing and evaluating technology, and particularly relates to a fine determination method for the clay content of fine sediment, which is a fine calculation method for the clay content based on a machine learning algorithm based on granularity experimental analysis and sediment microphase division, and is suitable for calculating clay content parameters of fine sediment stratum of Wenchang oilfield groups similar to Zhujiang Kou basin.
Background
Fine-grained sedimentary formations in weak hydrodynamic environments tend to develop low-resistivity hydrocarbon reservoirs, a more typical example being the southern-ocean and northern-ocean bead basin Wenchang oilfield group. A large number of low-resistance oil layers with resistivity close to 1 omega.m are widely developed in a Zhujiang group in a shallow sea land canopy environment in the area, and the Zhujiang group has the characteristics of fine granularity, high clay content and high irreducible water saturation, and greatly increases the difficulty of accurate evaluation of reservoir parameters and fluid identification. It is well known that for argillaceous sandstone formations, accurate argillaceous content calculation models are critical to solving for other reservoir parameters. At present, the calculation model of the clay content is more, the calculation method is relatively mature, and three types are mainly included. One is to calculate the clay content one by using a single log capable of reacting to the clay content by using an empirical formula to quantify the clay content, and then combine the calculated results to obtain a final result (Wang Xiaoguang, 2017; yongshihe, 1996; yuan Yidong, 2017; zhang Shaofang, 2016). For example, patent CN202110513391.7 (yanglin et al, 2021) discloses a method for determining the shale content using a natural Gamma (GR) curve. Patent CN202011282762.7 (Wang Meng, 2020) is divided into different types according to the gamma value of the stratum, a plurality of argillaceous content curves are calculated by using a natural Gamma (GR) curve, and the argillaceous content is finally obtained by combining after evaluating the levels of the curves. Patent CN201811138450.1 (Wang Zhenhua, 2018) discloses a model for calculating the argillaceous index after weighting the SP and GR curves. The second class is based on three-porosity logs (sonic, neutron, density) and calculates the shale content by a two-by-two intersection method (Xiao, 2019; meng Fanxiao, 2019; zhang Demei, 2011). And three types are that a plurality of logging curves closely related to the clay content are selected, and the clay content is predicted by adopting a multiple regression or BP neural network method. As patent CN201911286140.9 (Li Binglong, 2019) discloses a neural network based method of clay content prediction, which focuses on proceeding for different log types. The first and second methods give satisfactory results when the correlation between the clay content and the log is good, but have not been ideal in the application of clay content calculation in the fine-grained sediment reservoirs of the Wenchang oilfield group. Through core data inspection, the precision of the multiple regression method and the BP neural network method is improved, but the requirements of on-site fine evaluation can not be met. The main reasons are that (1) the rock particles are fine, the content of gap filler is high, and the relationship between the clay content and single curves such as GR curves is complex; (2) Rock slice and granularity analysis data show that rocks of different sedimentary microphase types have different lithology characteristics, and a unified argillaceous content model is difficult to build; (3) The above model does not take into account specific features and differences of different sedimentary microphase reservoirs.
Disclosure of Invention
In order to overcome the defects of the method for calculating the shale content in practical application, the invention aims to provide a fine determination method for the shale content of fine sediment, which is based on a granularity analysis experiment, and is used for calibrating the shale content of a fine sediment core under the control of a sediment microphase. According to the method, the time sequence of the stratum deposit sequence, the clay content and the depth sequence relation of the logging curve are considered, and an LSTM neural network algorithm with obvious advantages on the sequence modeling problem is used, so that the effect of solving fine particle deposits with complex relation between the clay content and the natural gamma curve is good.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
a fine determination method of the clay content of fine-grained sediment, comprising the steps of:
Step one: microphase type division is deposited. And under the large background of regional deposition, the type of the deposition microphase is divided according to the combined characteristics of the logging curves by taking the deposition phase as a basis and combining the data such as core analysis, logging and the like.
Step two: particle size experiments were performed. And carrying out a granularity analysis experiment on the rock core of the research area by using a screening method and other means, wherein the obtained granularity experiment data (phi value) is used for calibrating the parameters of the clay content.
Step three: the core depth for the particle size analysis experiment was reset to the logging depth.
Step four: and (5) making core argillaceous content label data. Because the clastic rock of different sedimentary microphase types has different granularity, the clay content parameters can be classified and finely calibrated according to the sedimentary microphase types by using granularity analysis data, and the calibrated data are combined to obtain core clay content label data.
Step five: and extracting characteristic parameters representing the clay content. And extracting logging characteristic parameters representing the shale content of the core by adopting a dimension reduction method such as a principal component analysis method. The logging characteristic parameter curves of the analysis and research area for representing the clay content comprise natural Gamma (GR), natural potential (SP), compensation Neutron (CNL), compensation sound wave (AC) and deep induction resistivity (Rt).
Step six: a training data set and a test data set are established. And (3) combining the label data of the shale content of the core obtained in the step (IV) and the logging characteristic parameters obtained in the step (V) into a label database, wherein 80% of the label data are used as model training data, and the rest 20% of the label data are used as model test data.
Step seven: and (5) establishing a muddy content calculation model by using an LSTM neural network algorithm. Considering the time sequence of stratum deposit sequence, the clay content and the depth sequence relation of logging curve, the invention uses LSTM neural network algorithm with long-term memory function to build clay content fine model.
Step eight: the LSTM neural network model is examined using the test dataset. And step seven, the clay content model is used for testing a data set to calculate clay content, then the clay content of the core of the data set is used for carrying out effect test on a calculation result, and if the effect is good, the model can be considered to be popularized and applied.
Step nine: and calculating the clay content. And step eight, the LSTM neural network model established through inspection is popularized and applied to calculation of the clay content of each single well in the zone, clay content parameters are obtained, and a foundation is laid for calculation of reservoir parameters such as porosity, oil saturation and the like.
The invention firstly divides a single well deposition microphase section based on reservoir deposition characteristics and logging curve combination characteristics. And secondly, according to core slices, granularity and physical property experimental results, calibrating the clay content of different types of sedimentary microphase with different granularity (phi) values. After the core is reset, characteristic parameters are extracted according to logging response characteristics of different types of sedimentary microphase strata, and a training data set and a checking data set are established. And training the training set by adopting an LSTM neural network method, and establishing a clay content calculation model. And then, carrying out model inspection by using an inspection set, and popularizing and applying after meeting the precision requirement. Practice proves that the method can accurately calculate the clay content of the fine sediment reservoir under the complex deposition environment, lays an important foundation for calculating other parameters such as the porosity, the oil saturation and the like of the reservoir, and has wide application and popularization prospects.
The beneficial effects of the invention are as follows:
Based on geological researches such as basic experiments of core slices, granularity and the like, the rock of different sedimentary microphase types is considered to have different lithology characteristics, and the differences of reservoir parameters such as clay content, porosity, permeability and the like are obvious. And (5) calibrating the quality content of different types of deposited microphase mud by using different granularity (phi) values. The method solves the problem that the clay content cannot be finely calibrated by taking the uniform granularity (phi) value as the clay standard under the background of fine-grain low-resistance deposition. In addition, the rock particles of the fine-grained sedimentary stratum are fine, the content of the gap filler is high, the typical multi-parameter nonlinear mapping problem is solved between logging parameters such as the clay content and GR, the acoustic, electrical and nuclear physical properties of the stratum in different sedimentary periods are reflected by the clay content, the time sequence characteristics are provided, the depth sequence characteristics are represented on the logging curve, the LSTM neural network algorithm can search nonlinear relations among various different parameters from data, and the method is very suitable for solving the nonlinear reservoir parameter logging evaluation problem. Therefore, the method for calculating and solving the clay content by using the LSTM cyclic neural network combines the processing advantages of the LSTM cyclic neural network on the serialized structure data, not only can fully utilize the response characteristics of various logging parameters on different stratum, but also can get rid of the limitation of linear prediction of the traditional empirical formula and intersection graph analysis.
Drawings
The shallow sea mud granularity probability graph of the embodiment of fig. 1;
the basket particle size probability graph of the embodiment of fig. 2;
The shoreface sand dam granularity probability plot of the embodiment of fig. 3;
FIG. 4 is a LSTM model diagram;
Fig. 5 is a flow chart of the present invention.
Detailed Description
The specific technical scheme of the invention is described by combining the embodiments.
As shown in fig. 1, a fine determination method of the clay content of fine-grained sediment, comprising the steps of:
step one: deposited microphase partitioning
And under the large background of regional deposition, the type of the deposition microphase is divided according to the combined characteristics of the logging curve by taking the deposition phase as a basis and combining core analysis and logging data. The Wenchang oilfield group Zhujiang group is used for receiving the source sea phase sediment from the northwest direction. According to the characteristics of the core, the slice, the logging and the electrical combination, three sedimentary microphases of shallow sea sand, shoreface sand dams and shallow sea mud are divided, wherein the reservoir layer is mainly made of shallow sea sand and the lithology is mainly made of argillaceous siltstone.
(1) And (3) performing sand-polishing: the hydrodynamic environment is relatively calm, and has sufficient material source supply, the lithology is mainly composed of argillaceous siltstone, the lithology is well selected, and the natural gamma curve of well logging is expressed as a low-amplitude tooth form, so that the method is an advantageous reservoir phase zone of the oil field.
(2) Shallow sea mud: shallow sea mud is typically distributed on the seafloor, reflecting a quiet hydrodynamic environment, lithology being mudstone and silty mudstone, and the natural gamma curve of the well logging appears as high values.
(3) Shoreface sand dams: the granularity is thicker, the hydrodynamic force is stronger, and the water body is shallower. The natural gamma curve of the well logging is in a high-amplitude box shape or a funnel shape, is smooth or micro-toothed, and gradually changes from top to bottom.
Step two: particle size experiments were conducted
Particle size analysis experiments are carried out on the core of the research area to obtain accurate experimental data (phi value), and the experimental data are analyzed and arranged for calibrating the clay content, as shown in table 1.
Table 1 core particle size experiment table
Step three: the core depth for the particle size analysis experiment was reset to the logging depth.
Step four: making core shale content label data
The classification statistics are carried out according to experimental data and physical property test data of three different sediment microphases of shallow sea mud, sand mats and shoreface sand dams in a research area, and the larger difference of the granularity of the different sediment microphases is found, as shown in table 2. Wherein the granularity of the shallow sea mud is the finest, and the content of the fine-powder sand-clay grade is between 72.7 percent and 84.5 percent; shoreface the sand dam has a relatively coarse particle size and a fine-silt-clay grade content of between 24.5% and 52.1%; while the sand is interposed between the two.
TABLE 2 particle size characterization of different deposition microphases
Classical well logging interpretation theory generally roughly uses fragments with particle size smaller than 0.01mm as a clay classification standard, and unified particle size standard is generally adopted on well loggingValue) or uniform particle size. However, the clastic rock of different deposit microphase types has different granularity, so that the analysis data of granularity can be used for fine determination of the clay content according to the deposit microphase types. Shallow sea Mat Sand in research area/>6 As a muddy standard, shoreface sand dams/>7 As a muddy standard, shallow sea mud/>And 8, combining the calibrated data to obtain core argillaceous content label data.
Step five: extracting characteristic parameters representing the content of the muddy matter
The sediment of fine particles has high mud content, has complex relation with a single logging curve and has nonlinear mapping relation. In order to obtain the clay content finely, characteristic parameter extraction is required to be carried out on logging data to obtain better training data, and the performance and the accuracy of a machine learning model are improved. And extracting logging characteristic parameters representing the shale content of the rock core by using a main component analysis method and other dimension reduction methods, wherein characteristic parameter curves representing the shale content of an analysis research area comprise natural Gamma (GR), natural potential (SP), compensation Neutron (CNL), compensation sound wave (AC) and deep induction resistivity (Rt).
Step six: creating training data sets and test data sets
And (3) combining the label data of the shale content of the core obtained in the step (IV) and the characteristic parameter data obtained in the step (V) into a label database, wherein 80% of the label data are used as a model training data set, and the rest 20% of the label data are used as model test data.
Step seven: building a muddy content calculation model based on LSTM neural network algorithm aiming at training data set
Considering the time sequence of stratum deposit sequence, the clay content and the depth sequence relation of logging curve, the invention uses LSTM neural network algorithm with long-term memory function to build clay content fine model. Firstly, standardized processing is carried out on training data, then the data is input into a designed long-short-term memory network (LSTM) algorithm to train a network model, the fitting capacity of the network model to the training data is measured by using a loss function, model parameters (namely weight values of the network) are adjusted through multiple training iterations, and finally whether the algorithm has obtained an ideal deep neural network model or not is judged through the descending trend of the loss function, so that a muddy content prediction model based on the LSTM neural network algorithm is established.
Step eight: the LSTM neural network model is examined using the test dataset.
And D, using the LSTM neural network model trained in the step seven for testing the data set to calculate the clay content, and using the label (clay content calibrated by the core) in the test data set to perform effect test on the calculation result. Through correlation coefficient and root mean square error analysis, if the effect is good, the model can be considered to be popularized and applied.
Step nine: calculating the clay content
And step eight, the LSTM neural network model established through inspection is popularized and applied to calculation of the clay content of each single well in the zone, clay content parameters are obtained, and a foundation is laid for calculation of reservoir parameters such as porosity, oil saturation and the like.
The successful application of the method in calculation of the mud content of the mud sandstone stratum deposited by one section of fine particles in the Zhujiang group of Wenchang oil fields proves that the method can effectively solve the problem of accurate evaluation of the mud content of the mud sandstone stratum deposited by the fine particles, and can be widely popularized and applied to stratum evaluation similar to the mud sediment of Wenchang oil fields.
Claims (1)
1. A method for fine determination of the clay content of a fine-grained deposit, comprising the steps of:
Step one: dividing the deposition microphase types; under the large background of regional deposition, dividing a deposition microphase type according to the combined characteristics of a logging curve by taking a deposition phase as a basis and combining core analysis and logging data;
step two: carrying out a granularity experiment; carrying out a granularity experiment on the rock core of the research area, wherein the obtained granularity experiment analysis data are used for calibrating the parameters of the clay content;
step three: homing the core depth for the granularity analysis experiment to the logging depth;
Step four: making core argillaceous content label data; classifying and finely calibrating the shale content according to the sediment microphase type by using the rock core granularity experimental analysis data after the homing in the step three, and particularly calibrating the shale content by adopting a uniform granularity standard phi value on well logging; classifying and finely calibrating the shale content according to the sediment microphase types by adopting the particle size analysis experimental data, wherein phi is 6 for shallow sea basket sand as a shale standard, phi is 7 for a shoreface sand dam as a shale standard, phi is 8 for shallow sea mud as a shale standard, and combining the calibrated data to obtain core shale content label data;
Step five: extracting logging characteristic parameters representing the clay content; specifically, a main component analysis method is adopted to extract logging characteristic parameters representing the clay content; the logging characteristic parameter curves for representing the clay content comprise natural gamma GR, natural potential SP, compensation neutron CNL, compensation sound wave AC and deep induction resistivity Rt;
Step six: establishing a training data set and a test data set; combining the label data of the shale content of the core obtained in the step four and the logging characteristic parameters obtained in the step five into a label database, taking 80% of the label data as model training data and the remaining 20% of the label data as model test data;
Step seven: establishing a muddy content calculation model by using an LSTM neural network algorithm;
Step eight: checking the LSTM neural network model by using the test data set; the muddy content model in the seventh step is used for testing a data set to calculate the muddy content, then the muddy content of the core of the data set is used for carrying out effect test on the calculation result, and if the effect is good, the model can be considered to be applied;
step nine: calculating the clay content; and step eight, the LSTM neural network model established through inspection is popularized and applied to calculation of the clay content of each single well in the area, and clay content parameters are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210233604.5A CN114482995B (en) | 2022-03-10 | 2022-03-10 | Fine determination method for clay content of fine sediment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210233604.5A CN114482995B (en) | 2022-03-10 | 2022-03-10 | Fine determination method for clay content of fine sediment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114482995A CN114482995A (en) | 2022-05-13 |
| CN114482995B true CN114482995B (en) | 2024-06-18 |
Family
ID=81486811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210233604.5A Active CN114482995B (en) | 2022-03-10 | 2022-03-10 | Fine determination method for clay content of fine sediment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114482995B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116087042B (en) * | 2023-02-16 | 2023-09-08 | 中国矿业大学 | Real-time monitoring system and method for dust deposition volume spatial distribution |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9117169B2 (en) * | 2012-05-24 | 2015-08-25 | Halliburton Energy Services, Inc. | Methods and apparatuses for modeling shale characteristics in wellbore servicing fluids using an artificial neural network |
| CN106223942A (en) * | 2016-08-26 | 2016-12-14 | 中国石油新疆油田分公司勘探开发研究院 | A kind of Conglomerate Reservoir shale content computational methods based on Well logging curve reconstruction |
| CN108227036A (en) * | 2018-01-22 | 2018-06-29 | 中国石油大港油田勘探开发研究院 | A kind of method of pulveryte core Location |
| CN109653725B (en) * | 2018-09-13 | 2022-03-15 | 山东鼎维石油科技有限公司 | Mixed reservoir flooding degree logging interpretation method based on sedimentary microfacies and rock facies |
| CN110954942A (en) * | 2018-09-26 | 2020-04-03 | 中国石油化工股份有限公司 | Method and system for making chart with clay content identification function |
| CN110489769B (en) * | 2019-01-30 | 2023-03-10 | 中国海洋石油集团有限公司 | Oil reservoir shale content calculation method and electronic equipment |
| CN110318745B (en) * | 2019-06-10 | 2022-09-23 | 中国石油大学(华东) | Particle size lithology logging evaluation method under deposition microphase constraint |
| US11892581B2 (en) * | 2019-10-25 | 2024-02-06 | Schlumberger Technology Corporation | Methods and systems for characterizing clay content of a geological formation |
| CN112987122A (en) * | 2019-12-13 | 2021-06-18 | 北京国双科技有限公司 | Method and device for calculating mud content, electronic equipment and storage medium |
| CN111255435B (en) * | 2020-01-17 | 2021-09-07 | 西安石油大学 | Method for calculating shale content of complex reservoir |
| CN112541523B (en) * | 2020-11-17 | 2023-02-28 | 中海油田服务股份有限公司 | Method and device for calculating mud content |
-
2022
- 2022-03-10 CN CN202210233604.5A patent/CN114482995B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 浅析用测井资料识别地层岩性;宁创;张丽伟;高候林;赵华胜;;广东化工;20120525(第05期);全文 * |
| 砂岩储层胶结指数m的一种标定方法;赵培华，谭廷栋;测井技术;19941222(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114482995A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107703560B (en) | shale lithofacies fine identification method based on triple information | |
| CA2579138C (en) | Geologic models of subsurface sedimentary volumes | |
| CN109061765B (en) | Trap evaluation method for heterogeneous thin sandstone interbed reservoir | |
| CN109613612A (en) | A kind of carbonate rock particle beach meticulous depiction and prediction technique | |
| Yasin et al. | Estimation of petrophysical parameters from seismic inversion by combining particle swarm optimization and multilayer linear calculator | |
| CN105467464B (en) | The effective connected component of Analyze of Nearshore Subaqueous Fans glutenite is divided and control methods | |
| Chehrazi et al. | Pore-facies as a tool for incorporation of small-scale dynamic information in integrated reservoir studies | |
| CN107133670A (en) | A kind of Complex lithologic identification method and system based on decision tree data mining algorithm | |
| Kadkhodaie-Ilkhchi et al. | Seismic inversion and attributes analysis for porosity evaluation of the tight gas sandstones of the Whicher Range field in the Perth Basin, Western Australia | |
| CN112698399A (en) | Gravel well seismic-logging linkage constraint efficient reservoir quantitative prediction method and system | |
| CN114482995B (en) | Fine determination method for clay content of fine sediment | |
| Obafemi et al. | Characterization of deep water turbidite channels and submarine fan lobes using artificial intelligence; Case study of Frem field deep offshore Niger Delta | |
| Iltaf et al. | Facies and petrophysical modeling of Triassic Chang 6 tight sandstone reservoir, Heshui oil field, Ordos basin, China | |
| CN115857047B (en) | Comprehensive prediction method for earthquake reservoir | |
| Tavoosi Iraj et al. | Integrated petrophysical and heterogeneity assessment of the Karstified Fahliyan formation in the Abadan Plain, Iran | |
| Rotimi et al. | Reservoir characterization and modeling of lateral heterogeneity using multivariate analysis | |
| CN112379435A (en) | Phase-controlled karst type seam hole aggregate carving method and device | |
| Moraes et al. | Using outcrop analogs to improve 3D heterogeneity modeling of Brazilian sand-rich turbidite reservoirs | |
| Li et al. | Predicting the thermal maturity of source rock from well logs and seismic data in basins with low-degree exploration | |
| Lozano et al. | Integrated Geocellular Static Model for Geomechanical and Dynamic Simulations in the Vaca Muerta Formation | |
| Kondratyev et al. | Submarine fan reservoir architecture and heterogeneity influence on hard-to-recover reserves. Achimov Fm | |
| Correia | Integration of reservoir characterization with history matching guided by pilot wells: Application to the Norne Field | |
| Lv et al. | Geological Modeling of Semideep Reservoir Based on Seismic Frequency Division Processing and Sedimentary Numerical Simulation | |
| Xu et al. | A multiple-point stochastic-based turbidite lobe architecture geomodeling: A case study from L Oilfield, Lower Congo Basin, West Africa | |
| Puttiwongrak et al. | Compaction Model for Shale in Differences of Geological Ages Using A 3D Empirical Relationship in Northeastern Thailand |
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 |