CN118228080A - Reservoir classification method and device - Google Patents
Reservoir classification method and device Download PDFInfo
- Publication number
- CN118228080A CN118228080A CN202211632985.0A CN202211632985A CN118228080A CN 118228080 A CN118228080 A CN 118228080A CN 202211632985 A CN202211632985 A CN 202211632985A CN 118228080 A CN118228080 A CN 118228080A
- Authority
- CN
- China
- Prior art keywords
- logging
- parameters
- reservoir
- principal component
- characteristic parameter
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000007621 cluster analysis Methods 0.000 claims abstract description 13
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 57
- 238000005481 NMR spectroscopy Methods 0.000 claims description 15
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 claims description 15
- 229910052753 mercury Inorganic materials 0.000 claims description 15
- 230000035945 sensitivity Effects 0.000 claims description 13
- 230000035699 permeability Effects 0.000 claims description 11
- 238000003825 pressing Methods 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 239000011148 porous material Substances 0.000 claims description 8
- 239000002245 particle Substances 0.000 claims description 7
- 230000000704 physical effect Effects 0.000 claims description 7
- 239000004927 clay Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 239000011435 rock Substances 0.000 abstract description 20
- 238000011156 evaluation Methods 0.000 abstract description 4
- 238000011161 development Methods 0.000 abstract description 3
- 238000009472 formulation Methods 0.000 abstract description 3
- 239000000203 mixture Substances 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 239000007771 core particle Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 235000021185 dessert Nutrition 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 229910052734 helium Inorganic materials 0.000 description 1
- 239000001307 helium Substances 0.000 description 1
- SWQJXJOGLNCZEY-UHFFFAOYSA-N helium atom Chemical compound [He] SWQJXJOGLNCZEY-UHFFFAOYSA-N 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V11/00—Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Geophysics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a reservoir classification method and a device, wherein the reservoir classification method comprises the following steps: acquiring characteristic parameter sets of different depth points of a plurality of reservoir sections of a well section to be classified; the characteristic parameter set comprises a logging characteristic parameter set and a rock core characteristic parameter set; analyzing the characteristic parameter sets of the plurality of depth points by a principal component analysis method, thereby extracting at least one principal component parameter of each depth point; performing cluster analysis on principal component parameters of a plurality of depth points, and dividing the plurality of depth points into a plurality of types; and classifying the reservoir types of the well sections to be classified according to the logging parameters of various types. The method can realize the fine classification of the complex unconventional reservoir, provides references for comprehensive evaluation and exploration and development scheme formulation of the complex unconventional reservoir, and solves the technical problem that the conventional logging reservoir classification method based on core scale logging can not realize the fine classification of the complex reservoir only by means of simple cut-off or intersection of single parameters or double parameters.
Description
Technical Field
The invention relates to the technical field of petroleum exploration, in particular to a reservoir classification method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The fine classification of the reservoir has important significance in the aspects of reservoir classification evaluation, dessert optimization, productivity prediction and the like. According to the difference of input data types, the reservoir classification method mainly comprises a core reservoir classification method, a logging reservoir classification method and a geophysical prospecting reservoir classification method, wherein the logging reservoir classification method has the advantages of being rich in data sources, high in longitudinal resolution, capable of continuously processing well sections and the like, and is an important method for finely classifying reservoirs.
Currently, well logging reservoir classifications can be categorized into four general categories: (1) The semi-quantitative reservoir classification method based on the intersection plate is simple to operate, wide in application range and low in applicability; (2) The method is mainly based on core physical data, has definite geological significance, and depends on the core data; (3) The logging reservoir classification method based on the multivariate statistical method and the machine learning algorithm can effectively avoid the interference of human factors, is high in speed and various in method, but has an ambiguous meaning of classification results; (4) The reservoir classification method based on the new logging technology method carries a large amount of geological information, and can evaluate the reservoir more effectively and accurately, but the new logging technology method is more expensive and has limited application range. The logging reservoir classification method based on core scale logging effectively fuses core analysis test data and logging data, but the conventional logging reservoir classification method based on core scale logging only depends on simple cut-off or intersection of single parameters or double parameters, and is difficult to realize the requirement of fine classification of complex reservoirs, for example, a flow unit method only considers physical property data such as core porosity and permeability, and a pore structure method only considers core mercury-compaction data or core nuclear magnetic data.
The conventional logging reservoir classification method based on core scale logging can obtain a good application effect in conventional sandstone or carbonate reservoirs, but cannot obtain a good application effect in complex unconventional reservoirs such as tight sandstone, gritty, igneous rock and shale, because the complex unconventional reservoirs often have complex mineral components, clay content, particle size distribution and pore structures.
Disclosure of Invention
The invention aims to provide a reservoir classification method and a device, which are used for solving the technical problem that the prior reservoir classification method is difficult to obtain a better application effect in complex unconventional reservoirs such as tight sandstone, sand conglomerate, igneous rock and shale.
The above object of the present invention can be achieved by the following technical solutions:
The invention provides a reservoir classification method, which comprises the following steps: acquiring characteristic parameter sets of different depth points of a plurality of reservoir sections of a well section to be classified; the characteristic parameter set comprises a logging characteristic parameter set and a core characteristic parameter set, wherein the logging characteristic parameter set comprises lithology logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters, and the core characteristic parameter set comprises physical logging characteristic parameters, mercury pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters; analyzing the characteristic parameter sets of the depth points through a principal component analysis method, so as to extract at least one principal component parameter of each depth point; performing cluster analysis on the principal component parameters of the plurality of depth points, and classifying the plurality of depth points into a plurality of types; and classifying the reservoir types of the well sections to be classified according to the logging parameters of the types.
In an embodiment of the present invention, the lithologic logging characteristic parameters in the logging characteristic parameter set include a natural gamma logging value and a natural potential logging value.
In an embodiment of the present invention, the physical logging characteristic parameters in the logging characteristic parameter set include a density logging value, a compensated neutron logging value, and an acoustic time difference logging value.
In an embodiment of the present invention, the electrical logging characteristic parameters in the logging characteristic parameter set include a deep resistivity log, a medium resistivity log, a shallow resistivity log.
In an embodiment of the present invention, the physical property characteristic parameters in the core characteristic parameter set include core porosity and core permeability.
In an embodiment of the present invention, the mercury intrusion characteristic parameters in the core characteristic parameter set include a median pressure, a median radius, a displacement pressure, a maximum pore throat radius, mercury ejection efficiency, an average pore throat radius, and a maximum mercury intrusion saturation.
In an embodiment of the present invention, the nuclear magnetic resonance characteristic parameters in the core characteristic parameter set include magnetic porosity, geometric mean, arithmetic mean, argillaceous irreducible water saturation, capillary irreducible water saturation and movable water saturation.
In an embodiment of the present invention, the particle size characteristic parameters in the core characteristic parameter set include a argillaceous content, a C value, a median particle size, a peak value, a skewness, and a sorting coefficient.
In an embodiment of the present invention, the analyzing the feature parameter set of the plurality of depth points by a principal component analysis method, thereby extracting at least one principal component parameter of each depth point, includes the following steps: combining the feature parameter sets of a plurality of the depth points into a first matrix; the number of rows of the first matrix is equal to the number of data in each core characteristic parameter set, and the number of columns of the first matrix is equal to the number of depth points; subtracting the average value of the data of each row in the first matrix from the data of the row to obtain a second matrix; calculating a covariance matrix according to the second matrix; a singular value decomposition method is utilized to obtain a plurality of eigenvalues and corresponding eigenvectors of the covariance matrix, and the eigenvectors are sequenced from large to small according to the corresponding eigenvalues and respectively used as row vectors to form a third matrix from top to bottom; taking data of the previous rows in the third matrix to form a fourth matrix; the number of lines of the fourth matrix is equal to the number of principal component parameters required to be extracted for each depth point; and extracting the principal component parameters of each depth point according to the fourth matrix and the first matrix.
In an embodiment of the present invention, the performing cluster analysis on the principal component parameters of the plurality of depth points classifies the plurality of depth points into a plurality of types, includes: and classifying the principal component parameters of the depth points by adopting a K-means clustering method, and classifying the depth points into a plurality of types.
In an embodiment of the present invention, the number of principal component parameters of each depth point is two, and the principal component parameters are a first principal component parameter and a second principal component parameter respectively; the types are four.
In an embodiment of the present invention, the classifying the reservoir type of the well section to be classified according to a plurality of types includes the following steps: counting various logging parameters of the type by using a core calibration logging curve; establishing various discrimination models of the types based on Fisher discrimination analysis according to the logging parameters of the various types; and extracting a logging sensitivity curve of the well section to be classified, and substituting the sensitive logging curve value of the logging sensitivity curve into the discrimination models of various types, so as to realize continuous classification of the reservoir types of the well section to be classified.
In an embodiment of the invention, the logging parameters include one or more of porosity of the logging calculation, permeability of the logging calculation, natural gamma, natural potential, acoustic waves, density, compensated neutrons, and resistivity.
The invention also provides a reservoir classification device, comprising: the characteristic parameter set acquisition module is used for acquiring characteristic parameter sets of different depth points of a plurality of reservoir sections of the well section to be classified; the characteristic parameter set comprises a logging characteristic parameter set and a core characteristic parameter set, wherein the logging characteristic parameter set comprises lithology logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters, and the core characteristic parameter set comprises physical logging characteristic parameters, mercury pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters; the principal component analysis module is used for analyzing the characteristic parameter sets of the depth points through a principal component analysis method so as to extract at least one principal component parameter of each depth point; the depth point classification module is used for carrying out cluster analysis on the principal component parameters of a plurality of depth points and classifying the plurality of depth points into a plurality of types; and the reservoir type classification module is used for classifying the reservoir types of the well sections to be classified according to logging parameters of various types.
In an embodiment of the present invention, the reservoir type classification module includes: the logging parameter statistics unit is used for counting logging parameters of the reservoir section corresponding to various types by using a core calibration logging curve; the discrimination model building unit is used for building discrimination models of various types based on Fisher discrimination analysis according to the logging parameters; and the continuous classification unit is used for extracting the logging sensitivity curve of the well section to be classified, and substituting the sensitive logging curve value of the logging sensitivity curve into the corresponding discrimination model, so that the continuous classification of the reservoir type of the well section to be classified is realized.
The invention has the characteristics and advantages that:
According to the reservoir classification method and device, lithologic logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters of different depth points of a plurality of reservoir sections are fully excavated; and physical property characteristic parameters, mercury-pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters; and then, extracting at least one principal component parameter by adopting a principal component analysis method, and further, carrying out cluster analysis on the principal component parameters of each rock core, so that the rock cores of a plurality of reservoir sections are classified into a plurality of types, and further, the reservoir types of the well sections to be classified are classified according to the types of the plurality of rock cores, thereby realizing the fine classification of the complicated unconventional reservoir, providing references for the comprehensive evaluation and exploration development scheme formulation of the complicated unconventional reservoir, and solving the technical problem that the well logging reservoir classification method based on the rock core scale logging in the prior art can not realize the fine classification of the complicated reservoir only by means of simple cut-off or intersection of single parameters or double parameters.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a reservoir classification method of the present invention;
FIG. 2 is a graph showing the intersection of core porosity and permeability at multiple depth points according to the present embodiment;
FIG. 3 is a high pressure mercury original curve set for a plurality of reservoir segments in this embodiment;
FIG. 4 is a set of nuclear magnetic resonance T2 spectra of multiple reservoir segments according to the present embodiment;
FIG. 5 is a set of probability distribution curves of core particle sizes for a plurality of reservoir segments according to the present embodiment;
FIG. 6 is a cross-sectional view of a first principal component parameter and a second principal component parameter of a plurality of depth points according to the present embodiment;
FIG. 7 is a flow chart of the extraction of principal component parameters according to the present invention;
FIG. 8 is a flow chart of the continuous classification of reservoir types for a section to be tested according to the present invention;
FIG. 9 is a graph of the reservoir classification effect for a section of a typical well in this embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one
As shown in fig. 1, the present invention provides a reservoir classification method, comprising the steps of:
step 101, acquiring characteristic parameter sets of different depth points of a plurality of reservoir sections of a well section to be classified; the characteristic parameter set comprises a logging characteristic parameter set and a core characteristic parameter set, wherein the logging characteristic parameter set comprises lithology logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters, and the core characteristic parameter set comprises physical logging characteristic parameters, mercury pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters.
And acquiring logging characteristic parameter sets of different depth points by using logging curve statistics.
And counting lithologic logging characteristic parameters of each depth point by using a lithologic logging curve. Specifically, the lithology logging characteristic parameters comprise natural gamma logging values and natural potential logging values.
And counting physical logging characteristic parameters of each depth point by using the physical logging curve. Specifically, the physical logging characteristic parameters comprise a density logging value, a compensated neutron logging value and an acoustic time difference logging value.
And counting the electrical logging characteristic parameters of each depth point through the electrical logging curve. Specifically, the electrical logging characteristic parameters include a deep resistivity log, a medium resistivity log, and a shallow resistivity log.
The obtaining of the core characteristic parameter set comprises the following steps: by drilling rock samples at different depth locations of a plurality of reservoir intervals and pre-processing the rock samples into satisfactory cores, the pre-processing of the rock samples comprises: cutting and polishing a rock sample into a standard plunger-shaped rock core with the diameter of 2.5cm and the diameter of 3cm-4 cm; drying the rock core at the temperature of 90-110 ℃ for 12-24 hours to remove water in the rock core; and carrying out experiments on each rock core to obtain rock core characteristic parameter sets of different depth points. And obtaining physical property characteristic parameters of the rock core by carrying out physical property parameter experiments. In particular, the physical characteristic parameters include, but are not limited to, core porosity and core permeability. Helium is injected into the rock core by adopting the Boyle single-chamber method to measure the porosity of the rock core. And measuring the core permeability by adopting an air measurement method. In this embodiment, the intersection of core porosity and core permeability at each depth point is shown in fig. 2.
And acquiring the mercury-pressing characteristic parameters of the depth point by carrying out a rock core high-pressure mercury-pressing experiment. Specifically, mercury intrusion characteristic parameters include, but are not limited to, median pressure, median radius, displacement pressure, maximum pore throat radius, mercury ejection efficiency, average pore throat radius, and maximum mercury intrusion saturation. In this embodiment, the original curve of the core high-pressure mercury injection at each depth point is shown in fig. 3.
And acquiring nuclear magnetic resonance characteristic parameters of the depth points by carrying out a core nuclear magnetic resonance experiment. Specifically, the nuclear magnetic resonance characteristic parameters include, but are not limited to, magnetic porosity, geometric mean, arithmetic mean, argillaceous irreducible water saturation, capillary irreducible water saturation, and movable water saturation. In this embodiment, the core nuclear magnetic resonance T2 (transverse relaxation time) spectrum set of each depth point is shown in fig. 4.
And acquiring the granularity characteristic parameters of the core by carrying out a core granularity analysis experiment. Specifically, the particle size characteristic parameters include the clay content, the C value, the median particle size, the peak value, the skewness and the sorting coefficient. In this embodiment, the probability distribution of the core granularity of each depth point is shown in fig. 5.
And 102, analyzing the characteristic parameter sets of the plurality of depth points by a principal component analysis method, so as to extract at least one principal component parameter of each core.
The method comprises the steps of analyzing a characteristic parameter set of a plurality of depth points through a principal component analysis method to obtain a plurality of principal component parameters, and arranging the plurality of principal component parameters into a first principal component parameter, a second principal component parameter, … and an nth principal component parameter from large to small according to the contribution rate of each principal component parameter by calculating the contribution rate of each principal component parameter, wherein n is equal to the number of data in the characteristic parameter set. In this embodiment, the first two principal component parameters, i.e., the first principal component parameter and the second principal component parameter, are extracted for each depth point. Of course, only the first principal component parameter may be extracted, and a third principal component parameter or more may be extracted.
And 103, performing cluster analysis on principal component parameters of the plurality of depth points, and classifying the plurality of depth points into a plurality of types.
The principal component parameters of the plurality of depth points can be classified by adopting a K-means clustering method, and the plurality of depth points are classified into a plurality of types. Other cluster analysis known in the art may also be used for classification. As shown in fig. 6, in the present embodiment, a plurality of depth points are classified into four types by performing cluster analysis on the first principal component parameter and the second principal component parameter of each depth point. Of course, it is also possible to classify the depth points of multiple reservoir intervals acquired for different well intervals by the above steps into two, three, five, six, or even more.
Step 104, classifying the reservoir types of the well sections to be classified according to the multiple types.
According to the reservoir classification method, lithologic logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters of different depth points of a plurality of reservoir sections are fully excavated; and physical property characteristic parameters, mercury-pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters; and then, extracting at least one principal component parameter by adopting a principal component analysis method, and further, carrying out cluster analysis on the principal component parameters of each depth point, so as to divide the depth points of a plurality of reservoir sections into a plurality of types, and further, classifying the reservoir types of the well sections to be classified according to the types of the plurality of depth points, thereby realizing the fine classification of the complex unconventional reservoir, providing reference for the comprehensive evaluation and exploration development scheme formulation of the complex unconventional reservoir, and solving the technical problem that the well logging reservoir classification method based on core scale logging in the prior art can not realize the fine classification of the complex reservoir only by means of simple cut-off or intersection of single parameter or double parameter.
As shown in fig. 7, in an embodiment of the present invention, a feature parameter set of a plurality of depth points is analyzed by a principal component analysis method, so as to extract at least one principal component parameter of each depth point, including the following steps:
Step 201, combining the feature parameter sets of the plurality of depth points into a first matrix X 1. The number of rows n of the first matrix X 1 is equal to the number of data in the core feature parameter set, and the number of columns m of the first matrix is equal to the number of depth points.
Step 202, subtracting the average value of the data of each row in the first matrix X 1 from the data of the row to obtain a second matrix X 2;
Step 203, calculating a covariance matrix C according to the second matrix X 2. Specifically, the relationship between the covariance matrix C and the second matrix X 2 is:
204, solving a plurality of eigenvalues and corresponding eigenvectors of the covariance matrix C by using a singular value decomposition method, sequencing the eigenvectors from large to small according to the corresponding eigenvalues, and respectively forming a third matrix X 3 from top to bottom as row vectors;
Step 205, data of the previous rows in the third matrix X 3 are taken to form a fourth matrix X 4; the number of rows of the fourth matrix X 4 is equal to the number of principal component parameters to be extracted for each depth point. In this embodiment, the first principal component parameter and the second principal component parameter are selected, so that the first row data and the second row data in the third matrix X 3 are selected to form the fourth matrix X 4.
And 206, extracting principal component parameters of each depth point according to the fourth matrix X 4 and the first matrix X 1. Specifically, the relationship between the fourth matrix X 4 and the first matrix X 1 is: y=x 4X1, and Y is a matrix formed by principal component parameters extracted from each depth point.
The following describes the above steps by way of a simple example: assuming that the feature parameter sets for the depth points 5,5 are { -1-2 }, { -10 }, { 01 }, { 21 }, and { 01 }, respectively, the first matrix X 1 isSince the average value of each row is 0, the second matrix X 2 is the same as the first matrix X 1, and the covariance matrixFurther, the eigenvalue λ 1 =2,/>, of the covariance matrix C is calculatedCorresponding feature vector/>Then the third matrix X 3 is/>Assuming that only the first principal component parameters are extracted, the fourth matrix X 4 is/>Thus, the matrix of the first principal component parameters of the 5 cores is:
As shown in fig. 8, in an embodiment of the present invention, the method for classifying the reservoir types of the well section to be classified according to various logging parameters includes the following steps:
Step 301, counting various logging parameters by using a core calibration logging curve.
Wherein the logging parameters include one or more of logging calculated porosity, logging calculated permeability, natural gamma, natural potential, acoustic waves, density, compensated neutrons, and resistivity. In this embodiment, the logging parameters include six parameters, namely, porosity calculated by logging, permeability calculated by logging, density (DEN), acoustic wave (AC), compensated Neutron (CNL), natural gamma (Δgr), and natural potential (Δsp). The statistics of the four types of logging parameters are shown below:
step 302, establishing various types of discriminant models based on Fisher discriminant analysis according to various types of logging parameters.
Wherein, the discrimination model ：F＝A1*D1+A2*D2+A3*D3+A4*D4+A5,F is a discrimination standard of various types; wherein, A 1、A2、A3、A4、A5 is the undetermined coefficient, D 1、D2、D3、D4 is the logging parameter, and D 1、D2、D3、D4 is the logging sensitive parameter, namely the logging parameter with the most accurate distinguishing type, for improving the accuracy of the distinguishing model.
In this embodiment, the Density (DEN) is selected to be D 1, the sound wave (AC) is selected to be D 2, the natural gamma (Δgr) is selected to be D 3, and the natural potential (Δsp) is selected to be D 4, so as to obtain a specific discrimination model of each type:
the discriminating model of the type one is as follows:
F 1 =1282.83×den+21.23×ac-207.14 ×Δgr+66.75×Δsp-2292.35; substituting the logging parameter value corresponding to the type one in the statistical table into the discrimination model to obtain a discrimination standard F 1 of the type one. In this embodiment, 16 depth points are of type one, and the type of the 16 depth points is determined by using the determination model, so that the accuracy is 87.5%.
The discriminating model of the type II is as follows:
F 2 =1323.38×den+21.52×ac-212.04 ×Δgr+74.55 ×Δsp-2414.28; substituting the corresponding logging parameter value of the type two in the statistical table into the discrimination model to obtain a discrimination standard F 2 of the type two. In this embodiment, 38 depth points are of type two, and the accuracy is 89.4% when 38 depth points are determined by using the determination model.
The discriminating model of the type III is as follows:
F 3 =1300.87×den+20.97×ac-207.03 ×Δgr+69.81 ×Δsp-2315.76; substituting the corresponding logging parameter value of the type III in the statistical table into the discrimination model to obtain the discrimination standard F 3 of the type III. In this embodiment, 25 depth points are of type two, and 20 types of the depth points are discriminated by using the discrimination model, and the accuracy is 84.0%.
The discriminating model of the type four is as follows:
F 4 =1313.57×den+20.7×ac-198.78 ×Δgr+68.78 ×Δsp-2337.74; substituting the logging parameter value corresponding to the type four in the statistical table into the discrimination model to obtain the discrimination standard F 4 of the type four. In this embodiment, 10 depth points are of type four, and the accuracy is 80.0% by adopting the discrimination model and discriminating the types of 10 depth points.
Step 303, extracting a logging sensitivity curve of the well section to be classified, and substituting the sensitive logging curve value of the logging sensitivity curve into various types of discrimination models, so as to realize continuous classification of the reservoir type of the well section to be classified. The well sections to be classified are well sections with the clay content and the porosity calculated by logging reaching the effective reservoir standards, and the well sections with the clay content or the porosity calculated by logging not reaching the effective reservoir standards are not subjected to reservoir type discrimination and classification.
Specifically, when the value of the sensitive logging curve corresponding to a certain depth position in the logging sensitive curve, namely the value of each logging parameter corresponding to the discrimination model is substituted into the discrimination model, the obtained result accords with the discrimination standard corresponding to the discrimination model, and the reservoir type at the depth position is indicated to be the type corresponding to the discrimination model, so that the reservoir type at each depth position of the logging sensitive curve can be determined in this way, and the continuous classification of the reservoir type of the well section is realized. For example, values of Density (DEN), acoustic wave (AC), natural gamma (Δgr) and natural potential (Δsp) of a depth position of a logging sensitivity curve of a well section to be measured are substituted into the above four types of discrimination models respectively to obtain four results respectively, and only the result obtained by the contemporary type two discrimination model matches with the type two discrimination standard F 2, it is indicated that the reservoir at the depth position is classified as type two. In this embodiment, the well section to be classified is a well section with a typical depth of about 4090m to 4160 m. And using the four discrimination models and the sensitive log curves of the well sections to be classified, and continuously classifying the well sections, wherein an effect diagram is shown in fig. 9.
Second embodiment
The invention also provides a reservoir classification device, which can be implemented by referring to the reservoir classification method, and is not described herein.
The reservoir classification device of the present invention comprises: the characteristic parameter set acquisition module is used for acquiring characteristic parameter sets of different depth points of a plurality of reservoir sections of the well section to be classified; the characteristic parameters comprise a logging characteristic parameter set and a core characteristic parameter set, wherein the logging characteristic parameters comprise lithology logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters, and the core characteristic parameter set comprises physical characteristic parameters, mercury pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters. The principal component analysis module is used for analyzing the characteristic parameter sets of the plurality of depth points through a principal component analysis method so as to extract at least one principal component parameter of each depth point; the core classification module is used for carrying out cluster analysis on the principal component parameters of the plurality of depth points and classifying the plurality of depth points into a plurality of types; and the reservoir type classification module is used for classifying reservoir types of the well sections to be classified according to various logging curves.
In an embodiment of the present invention, a reservoir type classification module includes: the logging parameter statistics unit is used for counting various logging parameters by using the core calibration logging curve; the discrimination model building unit is used for building various discrimination models based on Fisher discrimination analysis according to various logging parameters; the continuous classification unit is used for extracting the logging sensitivity curve of the well section to be classified, and substituting the sensitive logging curve value of the logging sensitivity curve into various types of discrimination models, so that the continuous classification of the reservoir type of the well section to be classified is realized.
The foregoing is merely a few embodiments of the present invention and those skilled in the art may make various modifications or alterations to the embodiments of the present invention in light of the disclosure herein without departing from the spirit and scope of the invention.
Claims (15)
1. A method of reservoir classification, comprising the steps of:
Acquiring characteristic parameter sets of different depth points of a plurality of reservoir sections of a well section to be classified; the characteristic parameter set comprises a logging characteristic parameter set and a core characteristic parameter set, wherein the logging characteristic parameter set comprises lithology logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters, and the core characteristic parameter set comprises physical logging characteristic parameters, mercury pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters;
analyzing the characteristic parameter sets of the depth points through a principal component analysis method, so as to extract at least one principal component parameter of each depth point;
Performing cluster analysis on the principal component parameters of the plurality of depth points, and classifying the plurality of depth points into a plurality of types;
And classifying the reservoir types of the well sections to be classified according to the logging parameters of the types.
2. The reservoir classification method of claim 1, wherein,
The lithology logging characteristic parameters in the logging characteristic parameter set comprise natural gamma logging values and natural potential logging values.
3. The reservoir classification method of claim 1, wherein,
The physical logging characteristic parameters in the logging characteristic parameter set comprise a density logging value, a compensated neutron logging value and a sonic time difference logging value.
4. The reservoir classification method of claim 1, wherein,
The electrical logging characteristic parameters in the logging characteristic parameter set include a deep resistivity log, a medium resistivity log, and a shallow resistivity log.
5. The reservoir classification method of claim 1, wherein,
The physical property characteristic parameters in the core characteristic parameter set comprise core porosity and core permeability.
6. The reservoir classification method of claim 1, wherein,
The mercury-pressing characteristic parameters in the core characteristic parameter set comprise median pressure, median radius, displacement pressure, maximum pore throat radius, mercury ejection efficiency, average pore throat radius and maximum mercury-feeding saturation.
7. The reservoir classification method of claim 1, wherein,
The nuclear magnetic resonance characteristic parameters in the core characteristic parameter set include magnetic porosity, geometric mean, arithmetic mean, argillaceous irreducible water saturation, capillary irreducible water saturation, and movable water saturation.
8. The reservoir classification method of claim 1, wherein,
The particle size characteristic parameters in the core characteristic parameter set comprise clay content, C value, particle size median, peak value, skewness and sorting coefficient.
9. The reservoir classification method according to claim 1, wherein the analyzing the characteristic parameter sets of the plurality of depth points by principal component analysis to extract at least one principal component parameter of each of the depth points comprises the steps of:
Combining the feature parameter sets of a plurality of the depth points into a first matrix; the number of rows of the first matrix is equal to the number of data in each core characteristic parameter set, and the number of columns of the first matrix is equal to the number of depth points;
Subtracting the average value of the data of each row in the first matrix from the data of the row to obtain a second matrix;
calculating a covariance matrix according to the second matrix;
a singular value decomposition method is utilized to obtain a plurality of eigenvalues and corresponding eigenvectors of the covariance matrix, and the eigenvectors are sequenced from large to small according to the corresponding eigenvalues and respectively used as row vectors to form a third matrix from top to bottom;
taking data of the previous rows in the third matrix to form a fourth matrix; the number of lines of the fourth matrix is equal to the number of principal component parameters required to be extracted for each depth point;
and extracting the principal component parameters of each depth point according to the fourth matrix and the first matrix.
10. The reservoir classification method of claim 1, wherein the performing cluster analysis on the principal component parameters of the plurality of depth points classifies the plurality of depth points into a plurality of types, comprises:
And classifying the principal component parameters of the depth points by adopting a K-means clustering method, and classifying the depth points into a plurality of types.
11. The reservoir classification method of claim 1, wherein,
The number of the principal component parameters of each depth point is two, namely a first principal component parameter and a second principal component parameter; the types are four.
12. The reservoir classification method according to claim 1, wherein the classification of the reservoir type of the well section to be classified according to a plurality of the types comprises the steps of:
counting various logging parameters of the type by using a core calibration logging curve;
establishing various discrimination models of the types based on Fisher discrimination analysis according to the logging parameters of the various types;
and extracting a logging sensitivity curve of the well section to be classified, and substituting the sensitive logging curve value of the logging sensitivity curve into the discrimination models of various types, so as to realize continuous classification of the reservoir types of the well section to be classified.
13. The reservoir classification method as claimed in claim 12, wherein,
The logging parameters include one or more of porosity of the logging calculation, permeability of the logging calculation, natural gamma, natural potential, acoustic waves, density, compensated neutrons, and resistivity.
14. A reservoir classification device, comprising:
The characteristic parameter set acquisition module is used for acquiring characteristic parameter sets of different depth points of a plurality of reservoir sections of the well section to be classified; the characteristic parameter set comprises a logging characteristic parameter set and a core characteristic parameter set, wherein the logging characteristic parameter set comprises lithology logging characteristic parameters, physical logging characteristic parameters and electrical logging characteristic parameters, and the core characteristic parameter set comprises physical logging characteristic parameters, mercury pressing characteristic parameters, nuclear magnetic resonance characteristic parameters and granularity characteristic parameters;
The principal component analysis module is used for analyzing the characteristic parameter sets of the depth points through a principal component analysis method so as to extract at least one principal component parameter of each depth point;
The depth point classification module is used for carrying out cluster analysis on the principal component parameters of a plurality of depth points and classifying the plurality of depth points into a plurality of types;
and the reservoir type classification module is used for classifying the reservoir types of the well sections to be classified according to logging parameters of various types.
15. The reservoir classification device of claim 14, wherein the reservoir type classification module comprises:
The logging parameter statistics unit is used for counting various logging parameters of the type by using a core calibration logging curve;
The discrimination model building unit is used for building discrimination models of various types based on Fisher discrimination analysis according to the logging parameters of various types;
and the continuous classification unit is used for extracting the logging sensitivity curve of the well section to be classified, and substituting the sensitive logging curve value of the logging sensitivity curve into the discrimination models of various types, so that the continuous classification of the reservoir type of the well section to be classified is realized.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211632985.0A CN118228080A (en) | 2022-12-19 | 2022-12-19 | Reservoir classification method and device |
| PCT/CN2023/118717 WO2024131160A1 (en) | 2022-12-19 | 2023-09-14 | Reservoir classification method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211632985.0A CN118228080A (en) | 2022-12-19 | 2022-12-19 | Reservoir classification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118228080A true CN118228080A (en) | 2024-06-21 |
Family
ID=91499489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211632985.0A Pending CN118228080A (en) | 2022-12-19 | 2022-12-19 | Reservoir classification method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118228080A (en) |
| WO (1) | WO2024131160A1 (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8725477B2 (en) * | 2008-04-10 | 2014-05-13 | Schlumberger Technology Corporation | Method to generate numerical pseudocores using borehole images, digital rock samples, and multi-point statistics |
| CN102011583B (en) * | 2010-11-30 | 2013-05-22 | 中国石油天然气股份有限公司 | Method for identifying reservoir by combining electric imaging with reef geologic model |
| US10190999B2 (en) * | 2016-05-11 | 2019-01-29 | Saudi Arabian Oil Company | Nuclear magnetic resonance and saturation well logs for determining free water level and reservoir type |
| CN107315203A (en) * | 2017-08-04 | 2017-11-03 | 中国石油化工股份有限公司江汉油田分公司勘探开发研究院 | A kind of tight sandstone reservoir dessert identification and integrated evaluating method |
| CN113642772A (en) * | 2021-07-13 | 2021-11-12 | 重庆科技学院 | Logging reservoir identification and prediction method based on machine learning |
-
2022
- 2022-12-19 CN CN202211632985.0A patent/CN118228080A/en active Pending
-
2023
- 2023-09-14 WO PCT/CN2023/118717 patent/WO2024131160A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024131160A1 (en) | 2024-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110674841B (en) | Logging curve identification method based on clustering algorithm | |
| CN103670384B (en) | A kind of Reservoir Classification method and system | |
| CN112526107B (en) | Method for recognizing and quantitatively characterizing desserts in fractured compact sandstone reservoir | |
| CN110318745B (en) | Particle size lithology logging evaluation method under deposition microphase constraint | |
| CN104747185A (en) | Heterogeneous reservoir stratum synthetic classifying evaluation method | |
| CN109345007B (en) | Advantageous reservoir development area prediction method based on XGboost feature selection | |
| CN103336305B (en) | A kind of method dividing Sandstone Gas Reservoir high water cut based on gray theory | |
| WO2019232224A1 (en) | Systems and methods for special core analysis sample selection and assessment | |
| Zhu et al. | Rapid identification of high-quality marine shale gas reservoirs based on the oversampling method and random forest algorithm | |
| CN115659245A (en) | Sandstone-type uranium deposit rock stratum type identification method and device based on machine learning | |
| CN113419284B (en) | Method for identifying physical facies double desserts of well logging rock based on cluster analysis | |
| CN105064986A (en) | Method for building reservoir four-property relationship spectrum by using conventional well detection and logging information | |
| Zhang et al. | Evaluating the potential of carbonate sub-facies classification using NMR longitudinal over transverse relaxation time ratio | |
| CN115390155A (en) | Well logging interpretation method, device, electronic equipment and medium for heterogeneous reservoir | |
| Zhao et al. | Data-driven diagenetic facies classification and well-logging identification based on machine learning methods: a case study on Xujiahe tight sandstone in Sichuan Basin | |
| Yao-Jun et al. | Unsupervised seismic facies analysis using sparse representation spectral clustering | |
| CN114776304A (en) | Method, device, equipment and medium for identifying abnormal deep sea mineral areas | |
| CN110968840A (en) | Method for judging grade of tunnel surrounding rock based on magnetotelluric sounding resistivity | |
| CN112836393B (en) | Method for analyzing reservoir heterogeneity based on multi-scale entropy | |
| CN116540316B (en) | Geological Soil Layer Testing Method Based on SVM Classification Algorithm and Clustering Algorithm | |
| AU2017279838B1 (en) | Method for classifying deep rock geofacies based on data mining | |
| CN118228080A (en) | Reservoir classification method and device | |
| CN110847887A (en) | Method for identifying and evaluating cracks of fine-grain sedimentary continental facies shale | |
| CN110399649A (en) | A kind of metamorphic rock quantization recognition methods based on diagenesis indicator element | |
| US6272444B1 (en) | Method for characterizing the coherence of an environment characteristic measurements |
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 |