CN116607931A - Method, device and medium for calculating permeability of tight reservoir based on big data analysis - Google Patents
Method, device and medium for calculating permeability of tight reservoir based on big data analysis Download PDFInfo
- Publication number
- CN116607931A CN116607931A CN202310388903.0A CN202310388903A CN116607931A CN 116607931 A CN116607931 A CN 116607931A CN 202310388903 A CN202310388903 A CN 202310388903A CN 116607931 A CN116607931 A CN 116607931A
- Authority
- CN
- China
- Prior art keywords
- permeability
- data
- sample
- calculating
- big data
- 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.)
- Pending
Links
- 230000035699 permeability Effects 0.000 title claims abstract description 144
- 238000007405 data analysis Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000010606 normalization Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 5
- 238000005553 drilling Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 239000004575 stone Substances 0.000 description 3
- 239000004927 clay Substances 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 239000009798 Shen-Fu Substances 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- E21B47/00—Survey of boreholes or wells
- E21B47/08—Measuring diameters or related dimensions at the borehole
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Geochemistry & Mineralogy (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Fluid Mechanics (AREA)
- Environmental & Geological Engineering (AREA)
- Geophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Investigation Of Foundation Soil And Reinforcement Of Foundation Soil By Compacting Or Drainage (AREA)
Abstract
The invention relates to a method, a device and a medium for calculating permeability of a tight reservoir based on big data analysis, which comprises the following steps: establishing a regional permeability big data analysis data set; selecting sample data according to the blocks and the layers of the calculation wells to form a modeling data subset; selecting a logging parameter feature space in a modeling data subset; the Euclidean distance between a predicted point at a certain depth and all sample points in the data subset is calculated in the feature space and is sequenced; selecting K permeability sample points closest to the sample points, and carrying out weighted average according to the reciprocal of the distance to predict the normalized permeability value of the point at a certain depth; repeatedly obtaining different depth points to obtain a depth continuous normalized permeability value; and reducing the continuous normalized permeability value inlet wire to obtain the permeability value with continuous depth. The method can continuously improve the calculation accuracy of the permeability of the tight sandstone reservoir, and meets the requirement of tight sandstone gas productivity evaluation.
Description
Technical Field
The invention belongs to the field of petroleum exploitation, and particularly relates to a method, a device and a medium for calculating permeability of a tight reservoir based on big data analysis.
Background
In the exploration and development of tight sandstone natural gas, accurate estimation of reservoir permeability plays an important role in productivity evaluation.
The method for acquiring the permeability of the reservoir mainly comprises a core analysis method and a logging calculation method, wherein the core analysis permeability is the most accurate, but the drilling and coring cost is high, and the acquired permeability of the reservoir is not comprehensive and discontinuous; estimating permeability using log data is an economical and feasible method. Therefore, research is of great importance in estimating permeability using well logging data. The pore structure of the tight sandstone reservoir is abnormal and complicated, so that the accurate calculation of the permeability is particularly difficult, the error of calculating the permeability by simply utilizing a logging information fitting mode is large, and the calculation accuracy requirement cannot be met. The big data analysis method can quickly search similar sample points in the logging parameter feature space of the sample data set, establish a hidden relation between the predicted value and the feature parameter, and be used for estimating the permeability of the predicted point, so as to solve the problem that simple fitting cannot be solved.
Disclosure of Invention
Aiming at the problems in the background art, the invention aims to provide a method for acquiring the permeability of compact sandstone continuously changing along with depth by a big data analysis method based on logging data, which can accurately predict the permeability of the compact sandstone.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, the present invention provides a method for calculating permeability of a tight reservoir based on big data analysis, comprising the steps of:
(1) Establishing a regional permeability big data analysis data set;
(2) Selecting sample data according to the blocks and the layers of the calculation wells to form a modeling data subset;
(3) Selecting a logging parameter feature space in a modeling data subset;
(4) The Euclidean distance between a predicted point at a certain depth and all sample points in the data subset is calculated in the feature space and is sequenced;
(5) Selecting K permeability sample points with the nearest Euclidean distance, and carrying out weighted average according to the inverse of the Euclidean distance to obtain a normalized permeability value of a predicted point at a certain depth;
(6) Repeating the step (5) to obtain continuous normalized permeability values of different depth points;
(7) And reducing the continuous normalized permeability value inlet wire to obtain the permeability value with continuous depth.
Further, forming the modeling data subset according to the block of the computation well and the horizon selection sample data is specifically: the same area, the same layer permeability and logging data as the tight reservoir to be interpreted are selected in the big data analysis dataset as the modeling data subset.
Further, the logging parameter feature space selected in the modeling data subset is specifically: and selecting a logging curve with the highest permeability correlation of the same block and the same horizon as a characteristic parameter to form a big data analysis characteristic space.
Further, the establishing of the regional permeability big data analysis data set specifically includes: and performing overburden correction on the core analysis permeability data of each block to obtain permeability data under stratum conditions, performing environmental correction and standardization processing on the well logging data, aligning the core analysis permeability with the depth of the well logging data, and normalizing the core analysis permeability with the well logging curve data to ensure that the normalized sample data range is between [0,1] to form a large data analysis sample data set.
Further, the collected core analysis permeability and log data are normalized by standard deviation, so that the process of normalizing the sample data range between [0,1] is as follows:
x ij is x ij， Is a normalized result of (2);is the mean value of characteristic logging parameters; s is S j Standard deviation of characteristic logging parameters; n is assuming n permeability sample points and m is that each sample has m logs as characteristic logging parameters.
Standard deviation normalization of core analysis permeability sample data according to formulas (4), (5) and (6)
In the formula (4), K i Analyzing the permeability for the ith depth point core; k_normal i For K i Normalization results; in the formulas (5) and (6),is the mean value of characteristic logging parameters; s is the standard deviation of the characteristic logging parameters.
Further, the process of calculating the euclidean distance between a predicted point at a certain depth and all sample points in the feature space is as follows:
d i the Euclidean distance between the predicted point in the selected characteristic parameter space and the ith sample point in the modeling data subset is determined; x is X j The j characteristic parameters after normalization of the predicted points are obtained; x is x ij The j characteristic parameters of the i sample points after normalization in the modeling sample subset are provided; n is the number of sample points in the modeling data subset; m is the number of feature parameters in the feature space, and the number of parameters in the feature space determined by this example is 9.
Further, the calculating the permeability by using the data of the k sample points closest to the predicted point is specifically:
selecting permeability values of k nearest sample points, carrying out weighted average according to the reciprocal of the distance, and calculating to obtain permeability values of predicted points, wherein the process is as follows:
in the formula (8), Y is the predicted point permeability value to be calculated; y is i Normalizing the permeability value of the ith sample closest to the predicted point; d, d i The Euclidean distance of the ith sample closest to the predicted point; k is the number of sample points nearest to the predicted point, and the determination of k generally requires selecting different values from low to high in the modeling data subset, and comparing the calculation result of each sample point in the modeling data subset with the measured permeability data, so that the value with the minimum average relative error is taken as the final k value.
In a second aspect, the present invention also provides an apparatus for calculating permeability of a tight reservoir based on big data analysis, comprising:
the first processing unit is used for establishing a regional permeability big data analysis data set;
the second processing unit is used for forming a modeling data subset according to the block of the computing well and the horizon selection sample data;
a third processing unit for selecting a logging parameter feature space in the modeling data subset;
a fourth processing unit, configured to calculate euclidean distances between a predicted point of a certain depth and all sample points in the data subset in the feature space, and sort the euclidean distances;
a fifth processing unit for selecting a k value that minimizes a calculated permeability average relative error using the subset of modeling data;
a sixth processing unit for calculating the permeability using the k sample point data nearest to the predicted point;
and a seventh processing unit for repeating different depth points to obtain the permeability value with continuous depth.
In a third aspect, the invention also provides a computer readable storage medium storing a computer program for implementing the method of calculating tight reservoir permeability based on big data analysis when executed by a processor.
In a fourth aspect, the present invention also provides a computer device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for calculating permeability of a tight reservoir based on big data analysis when executing the computer program.
Due to the adoption of the technical scheme, the invention has the following advantages:
according to the method for calculating the permeability of the tight sandstone by using the logging data, disclosed by the invention, the sample points most similar to the logging characteristic parameters of the predicted points are searched in the data set based on the big data analysis technology, the permeability of the predicted points is estimated by using the measured permeability data of the sample points, the calculation accuracy of the permeability of the tight sandstone reservoir can be continuously improved along with the sample data in the data set, and the requirement of the tight sandstone gas productivity evaluation is met.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Like parts are designated with like reference numerals throughout the drawings.
In the drawings:
FIG. 1 illustrates a flow chart of a method for calculating tight reservoir permeability based on big data analysis provided by an embodiment of the present invention;
FIG. 2 illustrates a sample dataset data storage format based on a geographic information system provided by an embodiment of the present invention;
FIG. 3 illustrates a modeling data subset permeability versus log correlation histogram provided by an embodiment of the present invention;
FIG. 4 shows the results of A3 well Dan Qianfeng group continuous depth tight sandstone permeability calculation provided by an embodiment of the present invention;
FIG. 5 shows a histogram of calculated average relative errors of permeability for different k values in a subset of modeled data provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The embodiment of the invention provides a method for calculating permeability of a tight reservoir based on big data analysis, which comprises the following steps:
1) Establishing a regional permeability big data analysis data set;
2) Selecting sample data according to the blocks and the layers of the calculation wells to form a modeling data subset;
3) Selecting a logging parameter feature space in a modeling data subset;
4) The Euclidean distance between a predicted point of a certain depth and all sample points is calculated in a feature space and is sequenced;
5) Selecting a k value that minimizes the calculated permeability average relative error using the subset of modeling data;
6) Calculating permeability by using data of k sample points nearest to the predicted point;
7) Repeating the different depth points results in a depth continuous permeability value.
According to the method for calculating the permeability of the tight sandstone by using the logging data, disclosed by the invention, the sample points most similar to the logging characteristic parameters of the predicted points are searched in the data set based on the big data analysis technology, the permeability of the predicted points is estimated by using the measured permeability data of the sample points, the calculation accuracy of the permeability of the tight sandstone reservoir can be continuously improved along with the sample data in the data set, and the requirement of the tight sandstone gas productivity evaluation is met.
As shown in fig. 1, embodiment 1 of the present invention provides a method for calculating permeability of a tight reservoir based on big data analysis, comprising the steps of:
1) Establishing big data analysis database
Collecting 6 blocks of 52 drilling coring well core analysis permeability and natural gamma, natural potential, well diameter, deep resistivity, shallow resistivity, flushing zone resistivity, lithology density, neutron porosity, longitudinal wave time difference, density-neutron porosity difference, clay content, effective porosity, water saturation and 13 groups of logging data comprising Dan Qianfeng groups, upper stone box group, lower stone box group, shanxi group, taiyuan group and Benxi group; and (3) performing overpressure correction on the core analysis permeability data of each block to obtain permeability data under stratum conditions, performing environmental correction and standardization treatment on the logging data, aligning the core analysis permeability with the logging data depth, normalizing the core analysis permeability with the logging curve data so that the sample data range is between [0,1] to form a large data analysis sample data set in the Linxing and Shenfu areas, wherein the data storage form of the sample data set based on a geographic information system is shown in FIG. 2.
2) Selecting modeling data and feature parameters
Taking the calculation of the permeability of the A3 well Dan Qianfeng group tight sandstone as an example, firstly selecting all drilling coring well stone thousand peak group sample data of an A block in a sample data set as a modeling data subset, and if the block drilling coring well corresponding horizon sample data is absent, searching the nearest block drilling coring well corresponding horizon sample data according to the well spacing as the modeling data subset; in the construction data subset, adopting a gray correlation method, a Pearson index method and other numerical analysis methods, selecting 9 groups of logging data of natural gamma, deep resistivity, shallow resistivity, lithology density, neutron porosity, longitudinal wave time difference, density-neutron porosity difference, porosity and clay content with high correlation of the logging data as characteristic parameters to form a big data analysis characteristic parameter space, wherein the permeability and logging data correlation histogram is shown in fig. 3.
3) Calculating the Euclidean distance between the predicted point and the sample point: in the selected feature parameter space with dimension 9, euclidean distances between a depth prediction point of the A3 well Dan Qianfeng group and all sample points in the modeling data subset are calculated.
4) And 3) sorting the sample points according to the calculation result of the step 3), wherein the smaller the Euclidean distance between the predicted point and the sample point is, the more similar or similar the predicted point is to the logging characteristic parameter of the sample point, so that K permeability sample points closest to the predicted point are selected, weighted average is carried out according to the reciprocal of the distance, and the normalized permeability value of the predicted point of a certain depth of the A3 well is obtained.
5) Repeating the step 4) to obtain a normalized permeability value with continuous A3 well depth, and reducing the normalized permeability value to obtain a permeability value with continuous A3 well depth, wherein FIG. 4 shows the permeability data of the group of the continuous A3 wells Dan Qianfeng of dense sandstones.
In the step 1), the collected core analysis permeability and logging curve data are normalized by standard deviation, so that the sample data range between [0,1] is as follows:
x ij is x ij， Is a normalized result of (2);is the mean value of characteristic logging parameters; s is S j Standard deviation of characteristic logging parameters; n is assuming n permeability sample points and m is that each sample has m logs as characteristic logging parameters.
Standard deviation normalization of core analysis permeability sample data according to formulas (4), (5) and (6)
Wherein K is i Analyzing the permeability for the ith depth point core; k_normal i For K i Normalization results;is the mean value of characteristic logging parameters; s is the standard deviation of the characteristic logging parameters.
In the step 3), the procedure of calculating the Euclidean distance between the predicted point and the sample point of the modeling subset is as follows:
in the formula (7), d i The Euclidean distance between the predicted point in the selected characteristic parameter space and the ith sample point in the modeling data subset is determined; x is X j The j characteristic parameters after normalization of the predicted points are obtained; x is x ij The j characteristic parameters of the i sample points after normalization in the modeling sample subset are provided; n is the number of sample points in the modeling data subset; m is the number of feature parameters in the feature space, and the number of parameters in the feature space determined by this example is 9.
In the step 4), the permeability values of K sample points closest to the sample points are selected, weighted average is carried out according to the reciprocal of the distance, and the permeability value process of the predicted point is calculated as follows:
in the formula (8), Y is the predicted point permeability value to be calculated; y is i Normalizing the permeability value of the ith sample closest to the predicted point; d, d i The Euclidean distance of the ith sample closest to the predicted point; k is the number of nearest sample points to the predicted point, different k=2, 3,4, …,12, 15,18 and 20 values are respectively selected from low to high by using sample point data in the modeling data subset, and the calculated result and the measured permeability data of each sample point in the modeling data subset are compared, so that the value with the minimum average relative error is taken as the final k=10 value, and fig. 5 shows the average relative error of the permeability of the sample points in the modeling data subset with different k values.
According to the method for calculating the permeability of the tight sandstone by using the logging data, disclosed by the invention, the sample points most similar to the logging characteristic parameters of the predicted points are searched in the data set based on the big data analysis technology, the permeability of the predicted points is estimated by using the measured permeability data of the sample points, the calculation accuracy of the permeability of the tight sandstone reservoir can be continuously improved along with the sample data in the data set, and the requirement of the tight sandstone gas productivity evaluation is met.
The embodiment of the invention also provides a device for calculating the permeability of the tight reservoir based on big data analysis, which comprises the following components:
the first processing unit is used for establishing a regional permeability big data analysis data set;
the second processing unit is used for forming a modeling data subset according to the block of the computing well and the horizon selection sample data;
a third processing unit for selecting a logging parameter feature space in the modeling data subset;
a fourth processing unit, configured to calculate euclidean distances between a predicted point of a certain depth and all sample points in the data subset in the feature space, and sort the euclidean distances;
a fifth processing unit, configured to select K permeability sample points with the nearest euclidean distance, and perform weighted average according to the reciprocal of the euclidean distance to obtain a normalized permeability value of a predicted point at a certain depth; repeating the steps to obtain continuous normalized permeability values of different depth points;
and the sixth processing unit is used for reducing the continuous normalized permeability value inlet wire to obtain the permeability value with continuous depth.
Embodiments of the present invention also provide a computer readable storage medium storing a computer program for implementing the method of calculating tight reservoir permeability based on big data analysis when executed by a processor.
The embodiment of the invention also provides computer equipment, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program is executed by the processor to realize the method for calculating the permeability of the tight reservoir based on big data analysis.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for calculating permeability of a tight reservoir based on big data analysis, comprising the steps of:
(1) Establishing a regional permeability big data analysis data set;
(2) Selecting sample data according to the blocks and the layers of the calculation wells to form a modeling data subset;
(3) Selecting a logging parameter feature space in a modeling data subset;
(4) The Euclidean distance between a predicted point at a certain depth and all sample points in the data subset is calculated in the feature space and is sequenced;
(5) Selecting K permeability sample points with the nearest Euclidean distance, and carrying out weighted average according to the inverse of the Euclidean distance to obtain a normalized permeability value of a predicted point at a certain depth;
(6) Repeating the step (5) to obtain continuous normalized permeability values of different depth points;
(7) And reducing the continuous normalized permeability value inlet wire to obtain the permeability value with continuous depth.
2. The method of calculating tight reservoir permeability based on big data analysis of claim 1, wherein forming the modeled data subset from the block of calculation wells and the horizon selection sample data is: the same area, the same layer permeability and logging data as the tight reservoir to be interpreted are selected in the big data analysis dataset as the modeling data subset.
3. The method for calculating tight reservoir permeability based on big data analysis according to claim 2, wherein the selected logging parameter feature space in the modeling data subset is specifically: and selecting a logging curve with the highest permeability correlation of the same block and the same horizon as a characteristic parameter to form a big data analysis characteristic space.
4. The method of calculating tight reservoir permeability based on big data analysis of claim 1, wherein creating a regional permeability big data analysis dataset is specifically: and performing overburden correction on the core analysis permeability data of each block to obtain permeability data under stratum conditions, performing environmental correction and standardization processing on the well logging data, aligning the core analysis permeability with the depth of the well logging data, and normalizing the core analysis permeability with the well logging curve data to ensure that the normalized sample data range is between [0,1] to form a large data analysis sample data set.
5. The method for calculating tight reservoir permeability based on big data analysis of claim 4, wherein the collected core analysis permeability is normalized with standard deviation from log data such that the normalized sample data range between [0,1] is as follows:
x ij is x ij′ Is a normalized result of (2);is the mean value of characteristic logging parameters; s is S j Standard deviation of characteristic logging parameters; n is assumed to have n permeabilitiesSample points, m is that each sample has m log curves as characteristic logging parameters;
standard deviation normalization of core analysis permeability sample data according to formulas (4), (5) and (6)
In the formula (4), K i Analyzing the permeability for the ith depth point core; k_normal i For K i ' normalization result; in the formulas (5) and (6),is the mean value of characteristic logging parameters; s is the standard deviation of the characteristic logging parameters.
6. The method for calculating permeability of a tight reservoir based on big data analysis according to claim 5, wherein the process of calculating euclidean distance of a depth prediction point from all sample points in a feature space is as follows:
d i the Euclidean distance between the predicted point in the selected characteristic parameter space and the ith sample point in the modeling data subset is determined; x is X j The j characteristic parameters after normalization of the predicted points are obtained; x is x ij The j characteristic parameters of the i sample points after normalization in the modeling sample subset are provided; n is a modeling data subsetThe number of sample points; m is the number of feature parameters in the feature space.
7. The method for calculating permeability of a tight reservoir based on big data analysis according to claim 1, wherein the permeability values of k nearest sample points are selected, weighted average is performed according to the reciprocal of the distance, and the process of calculating the permeability values of the predicted points is as follows:
in the formula (8), Y is the predicted point permeability value to be calculated; y is i Normalizing the permeability value of the ith sample closest to the predicted point; d, d i The Euclidean distance of the ith sample closest to the predicted point; k is the number of sample points nearest to the predicted point, and the determination of k generally requires selecting different values from low to high in the modeling data subset, and comparing the calculation result of each sample point in the modeling data subset with the measured permeability data, so that the value with the minimum average relative error is taken as the final k value.
8. An apparatus for calculating permeability of a tight reservoir based on big data analysis, comprising:
the first processing unit is used for establishing a regional permeability big data analysis data set;
the second processing unit is used for forming a modeling data subset according to the block of the computing well and the horizon selection sample data;
a third processing unit for selecting a logging parameter feature space in the modeling data subset;
a fourth processing unit, configured to calculate euclidean distances between a predicted point of a certain depth and all sample points in the data subset in the feature space, and sort the euclidean distances;
a fifth processing unit, configured to select K permeability sample points with the nearest euclidean distance, and perform weighted average according to the reciprocal of the euclidean distance to obtain a normalized permeability value of a predicted point at a certain depth; repeating the steps to obtain continuous normalized permeability values of different depth points;
and the sixth processing unit is used for reducing the continuous normalized permeability value inlet wire to obtain the permeability value with continuous depth.
9. A computer readable storage medium, characterized in that a computer program is stored for implementing the method of calculating tight reservoir permeability based on big data analysis according to any of claims 1-7 when executed by a processor.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of calculating tight reservoir permeability based on big data analysis of any of claims 1 to 7 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310388903.0A CN116607931A (en) | 2023-04-12 | 2023-04-12 | Method, device and medium for calculating permeability of tight reservoir based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310388903.0A CN116607931A (en) | 2023-04-12 | 2023-04-12 | Method, device and medium for calculating permeability of tight reservoir based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116607931A true CN116607931A (en) | 2023-08-18 |
Family
ID=87680764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310388903.0A Pending CN116607931A (en) | 2023-04-12 | 2023-04-12 | Method, device and medium for calculating permeability of tight reservoir based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116607931A (en) |
-
2023
- 2023-04-12 CN CN202310388903.0A patent/CN116607931A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110284873B (en) | Method and device for detecting oil well reservoir properties | |
| CN111472765A (en) | Stratigraphic division method and device for target well | |
| WO2024012222A1 (en) | Method and apparatus for selecting key geological parameter of block to be surveyed, and device | |
| CN113033648A (en) | Method for realizing logging interpretation by using machine learning algorithm | |
| CN112578441A (en) | Reservoir thickness prediction analysis method, computer equipment and storage medium | |
| CN104965237A (en) | Method of quantitatively and optimally selecting unconventional oil-gas favorable area | |
| CN112282742B (en) | Prediction method for shale oil high-quality reservoir | |
| CN111626377B (en) | Lithology recognition method, device, equipment and storage medium | |
| CN116821786A (en) | Hypotonic reservoir classification method, device and medium | |
| CN116607931A (en) | Method, device and medium for calculating permeability of tight reservoir based on big data analysis | |
| CN116335648A (en) | Method for quantitatively evaluating dessert quality of conglomerate horizontal well based on logging while drilling data | |
| CN113530533B (en) | Dessert region prediction method and system based on three quality parameters | |
| CN113378999B (en) | Compact sandstone reservoir classification grading method based on cloud model | |
| CN113945992B (en) | Mudstone and oil shale identification method and device, electronic equipment and medium | |
| CN117633658B (en) | Rock reservoir lithology identification method and system | |
| CN113807359B (en) | Intelligent identification method for inter-well communication path and electronic equipment | |
| CN112906242B (en) | Geophysical modeling method based on combination of naive Bayes method and proximity classification method | |
| CN113361111B (en) | Partitioning method of low-permeability reservoir characteristic model | |
| Wu et al. | Real‐Time Intelligent Recognition Method for Horizontal Well Marker Bed | |
| CN116662569B (en) | Knowledge-graph-based oil-gas geological evaluation method | |
| CN117386312B (en) | Drilling fluid filling device and control method thereof | |
| CN113553546B (en) | Method, system and computer readable storage medium for extracting rock continuous cementation index from electric imaging data | |
| CN115481571A (en) | Coal bed gas content qualitative evaluation method based on grey correlation and K neighbor | |
| CN112302638B (en) | Streamline field characterization method and device for oil reservoir | |
| Wu et al. | Research Article Real-Time Intelligent Recognition Method for Horizontal Well Marker Bed |
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 |