CN111797575B - Deep shale fracturing process parameter optimization method - Google Patents

Deep shale fracturing process parameter optimization method Download PDF

Info

Publication number
CN111797575B
CN111797575B CN202010716805.1A CN202010716805A CN111797575B CN 111797575 B CN111797575 B CN 111797575B CN 202010716805 A CN202010716805 A CN 202010716805A CN 111797575 B CN111797575 B CN 111797575B
Authority
CN
China
Prior art keywords
clustering
process parameter
deep shale
parameter optimization
distance
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010716805.1A
Other languages
Chinese (zh)
Other versions
CN111797575A (en
Inventor
刘彧轩
蒲麒兵
郭建春
路千里
陈天翔
何杰
谢宗财
王世彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest Petroleum University
Original Assignee
Southwest Petroleum University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southwest Petroleum University filed Critical Southwest Petroleum University
Priority to CN202010716805.1A priority Critical patent/CN111797575B/en
Publication of CN111797575A publication Critical patent/CN111797575A/en
Application granted granted Critical
Publication of CN111797575B publication Critical patent/CN111797575B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
    • E21B43/25—Methods for stimulating production
    • E21B43/26—Methods for stimulating production by forming crevices or fractures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Optimization (AREA)
  • Mining & Mineral Resources (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geology (AREA)
  • Computational Mathematics (AREA)
  • Software Systems (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Environmental & Geological Engineering (AREA)
  • Fluid Mechanics (AREA)
  • Algebra (AREA)
  • Evolutionary Biology (AREA)
  • Medical Informatics (AREA)
  • Geochemistry & Mineralogy (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a deep shale fracturing process parameter optimization method, which comprises the following steps: collecting basic parameters of deep shale of a plurality of different blocks; carrying out reservoir division on the deep shale by adopting a fuzzy clustering method; simulating the hydraulic fracture form by using software, and determining the hydraulic fracture target of each divided reservoir stratum according to the simulation result; and simulating the hydraulic fracturing results of different construction parameters by adopting a numerical simulation method according to the hydraulic fracturing target, and optimizing the construction parameters according to the hydraulic fracturing results. According to the invention, the clustering reservoir partitions of deep shale in different blocks can be carried out, and then fracturing process parameter optimization is carried out on each type of reservoir, so that the workload of fracturing process parameter optimization is greatly reduced, and the cost is saved.

Description

Deep shale fracturing process parameter optimization method
Technical Field
The invention relates to the technical field of fracturing reformation, in particular to a deep shale fracturing process parameter optimization method.
Background
Shale gas resources in China are quite rich, and according to latest research results of oil and gas centers of the China soil resource department in 2012, the amount of shale gas resources in China is 25 trillion square, only shale gas resources of a Gangwu tumidinodactyla Temminck group and a Xilinglinglingju group in Sichuan province can be compared favorably with the total amount of conventional natural gas resources in Sichuan basin, and the development and utilization potential is huge. In order to reduce the external dependence of natural gas resources in China, change the energy consumption structure mainly based on coal in China at present, develop green and environment-friendly shale gas resources, and have important strategic significance on the long-term rapid development of national economy and national energy safety.
The reservoir forming mechanism and the occurrence mechanism of the shale gas are essentially different from those of the conventional oil gas. The shale is not only a hydrocarbon-producing parent rock but also a reservoir bed due to the self compactness, and is saturated in situ and early-formed. The shale reservoir matrix has extremely low permeability, and particularly the shale gas reservoir is of a Nadarcy grade. In order to realize the economic development of the shale gas, large-scale hydraulic fracturing is needed, a reservoir stratum is crushed to the greatest extent to form a complex fracture network, so that the seepage area of the shale gas is effectively increased, and the seepage resistance is reduced.
Due to the heterogeneity of stratum rocks on the plane and in the longitudinal direction, the differences of the mineral components, the mechanical properties, the natural fractures and the ground stress states of the reservoir rock of each block are large, so that the capability of the shale reservoir of each block for forming a complex fracture network in the hydraulic fracturing process also has certain differences.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a deep shale fracturing process parameter optimization method, which adopts a clustering method to divide reservoirs according to the characteristics of shale reservoirs in different blocks, and adopts a numerical simulation method to realize the aims and ideas of maximizing effective modification volume and maximizing the complexity of fractures in the modification volume so as to finely design construction parameters, thereby forming a set of fracturing parameter optimization methods aiming at different shale reservoir characteristics.
The technical scheme of the invention is as follows:
a deep shale fracturing process parameter optimization method comprises the following steps: collecting basic parameters of deep shale of a plurality of different blocks; carrying out reservoir division on the deep shale by adopting a fuzzy clustering method; simulating the hydraulic fracture form by using software, and determining the hydraulic fracture target of each divided reservoir according to the simulation result; and simulating the hydraulic fracturing results of different construction parameters by adopting a numerical simulation method according to the hydraulic fracturing target, and optimizing the construction parameters according to the hydraulic fracturing results.
Preferably, the basic parameters include brittle minerals, poisson's ratio, elastic modulus, tensile strength, shear strength, fracture toughness, natural fracture, mechanical brittleness index, maximum horizontal principal stress, minimum horizontal principal stress, horizontal ground stress difference, vertical ground stress difference.
Preferably, the fuzzy clustering method adopts a systematic clustering method, and specifically comprises the following steps:
setting a data matrix of the basic parameters, carrying out data standardization on data in the matrix, and compressing the data to a [0,1] interval;
establishing a fuzzy similar matrix, and calculating the similarity degree of each block;
and clustering each block according to the calculation result of the similarity.
Preferably, the data matrix establishing method is as follows: assuming that the domain U is { x ═ x1,x2,……,xnIs classified object, each object has m indexes to represent its property, i.e.
xi＝{xi1,xi2,…,xim}(i＝1,2,…,n) (1)
Then, the data matrix is obtained as:
Figure BDA0002598495350000021
wherein xnmRaw data representing the mth index of the nth class object.
Preferably, the data normalization is implemented by using a translation and range transformation method, which specifically comprises the following steps:
Figure BDA0002598495350000022
Figure BDA0002598495350000023
Figure BDA0002598495350000024
Figure BDA0002598495350000025
in the formula: x is more than or equal to 0 ≦ x ″)ikLess than or equal to 1, and eliminates the influence of dimension.
Preferably, the similarity degree is calculated by a similarity coefficient method or a distance method, the similarity coefficient method includes an angle cosine method, a maximum and minimum method, a calculated number average minimum method, a geometric average minimum method, a number product method, a correlation coefficient method, and an exponential similarity coefficient method, and the distance method includes a direct distance method, a hamming distance method, a euclidean distance method, a chebyshev distance method, a reciprocal distance method, and an exponential distance method.
Preferably, a fuzzy equivalent matrix-based clustering method or a direct clustering method is adopted for clustering, a threshold value is determined during clustering, and the threshold value is determined through an F statistic.
Preferably, the construction parameters include the number of clusters, the displacement and the strength of the fluid.
Compared with the prior art, the invention has the following advantages:
according to the invention, firstly, a fuzzy clustering method is adopted to perform clustering reservoir division on deep shale in a plurality of different blocks, and then a numerical simulation method is adopted to perform fracturing process parameter optimization on each type of reservoir, so that the workload of fracturing process parameter optimization is greatly reduced, and the cost is saved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of a reservoir cluster partitioning result according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating the result of the variation of the numerical simulation slit width with the number of clusters according to the embodiment of the present invention;
FIG. 3 is a diagram illustrating the result of the variation of the cluster number with the length of the simulated half-seam according to the embodiment of the present invention;
FIG. 4 is a diagram illustrating the variation of the cluster number with the volume of cluster number in the embodiment of the present invention;
FIG. 5 is a diagram illustrating the result of the numerical displacement simulation of the slot width varying with the displacement according to the embodiment of the present invention;
FIG. 6 is a diagram illustrating the displacement variation with the displacement of the displacement numerical simulation half-slit length according to the embodiment of the present invention;
FIG. 7 is a diagram illustrating the result of the numerical displacement simulation of the modified volume varying with the displacement according to the embodiment of the present invention;
FIG. 8 is a graph showing the results of numerical simulation of the seam width with the strength of the applied liquid according to the embodiment of the present invention;
FIG. 9 is a diagram illustrating the results of numerical simulation of half-seam length with liquid strength according to the embodiment of the present invention;
FIG. 10 is a diagram showing the results of numerical simulation of the modification volume with the strength of the applied liquid according to the embodiment of the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples. It should be noted that, in the present application, the embodiments and the technical features of the embodiments may be combined with each other without conflict. Unless defined otherwise, technical or scientific terms used in the present disclosure should have the ordinary meaning as understood by those of ordinary skill in the art to which the present disclosure belongs. The use of the terms "comprising" or "including" and the like in the present disclosure is intended to mean that the elements or items listed before the term cover the elements or items listed after the term and their equivalents, but not to exclude other elements or items.
A deep shale fracturing process parameter optimization method comprises the following steps:
s1: collecting basic parameters of deep shale of a plurality of different blocks, wherein the basic parameters comprise brittle minerals, Poisson's ratio, elastic modulus, tensile strength, shear strength, fracture toughness, natural fracture, mechanical brittleness index, maximum horizontal main stress, minimum horizontal main stress, horizontal earth stress difference and vertical earth stress difference.
S2: carrying out reservoir division on the deep shale by adopting a fuzzy clustering method, wherein the fuzzy clustering method adopts a systematic clustering method, and specifically comprises the following steps:
s21: setting a data matrix of the basic parameters, performing data standardization on data in the matrix, and compressing the data to a [0,1] interval, specifically:
assuming that the domain U is { x ═ x1,x2,……,xnIs classified object, each object has m indexes to represent its property, i.e.
xi＝{xi1,xi2,…,xim}(i＝1,2,…,n) (1)
Then, the data matrix is obtained as:
Figure BDA0002598495350000041
wherein xnmRaw data representing the mth index of the nth class object.
And (3) carrying out data standardization by adopting any one of the following methods:
1) translation and range conversion
Figure BDA0002598495350000042
Figure BDA0002598495350000043
Figure BDA0002598495350000044
Figure BDA0002598495350000045
In the formula: x is more than or equal to 0 ≦ x ″)ikLess than or equal to 1, and eliminates the influence of dimension.
2) Translation, standard deviation transformation
Data were normalized directly by equations (4) - (6), and after transformation, the mean value of each variable was 0, the standard deviation was 1, and the dimensional influence was eliminated, but x 'obtained was reused'ikNot necessarily in the interval [0,1]]The above.
3) Logarithmic transformation
x′″ik＝lg xik (7)
Taking the logarithm can reduce the order of magnitude between the variables.
S22: establishing a fuzzy similarity matrix, and calculating the similarity degree of each block, specifically: x is the number ofiAnd xjDegree of similarity r ofij＝R(xi,xj) The value is calculated by the following method:
(1) method of similarity coefficient
1) Cosine method of included angle
Figure BDA0002598495350000051
2) Maximum and minimum method
Figure BDA0002598495350000052
3) Method of arithmetic mean minimization
Figure BDA0002598495350000053
4) Geometric mean minimization method
Figure BDA0002598495350000054
5) Quantitative product method
Figure BDA0002598495350000055
Figure BDA0002598495350000056
6) Method of correlation coefficient
Figure BDA0002598495350000057
Figure BDA0002598495350000058
7) Exponential similarity coefficient method
Figure BDA0002598495350000061
(2) Distance method
1) Direct distance method
rij＝1-cd(xi,xj) (17)
Wherein c is a parameter selected such that 0 ≦ rij≤1，d(xi,xj) Representing the distance between them, which can be calculated by:
distance from Haiming
Figure BDA0002598495350000062
Euclidean distance
Figure BDA0002598495350000063
Chebyshev distance
Figure BDA0002598495350000064
2) Reciprocal distance method
Figure BDA0002598495350000065
Wherein M is a parameter selected such that 0 ≦ rij≤1。
3) Exponential distance method
rij＝exp[-d(xi,xj)] (22)
S23: and according to the calculation result of the similarity degree, clustering each block by adopting a fuzzy equivalent matrix-based clustering method or a direct clustering method, wherein a threshold value is determined during clustering, and the threshold value is determined through an F statistic.
(1) Clustering method based on fuzzy equivalent matrix
1) Method of transmitting closed package
According to the fuzzy matrix R obtained by calibration, it must be reformed into the fuzzy equivalent matrix R*. Using a quadratic method to obtain a transitive closure of R, i.e. t (R) ═ R*. Then let λ change from large to small, so as to form dynamic clustering graph.
2) Boolean matrix method
The theoretical basis of the boolean matrix method is the following theorem: assuming that R is a subset of U and is a similar Boolean matrix on R, then R has transitivity (when it is an equivalent Boolean matrix)
Figure BDA0002598495350000071
Matrix R2＝R*R≤R。
The specific steps of the boolean matrix method are as follows:
solving a lambda-cut matrix R of a fuzzy similarity matrixλIf R isλJudged to be equivalent according to theorem, then the formula is shown by RλThe classification of U on the λ level can be obtained; if R isλIf determined to be not equivalent, RλIn a certain arrangement, there are special sub-matrixes of the above form, and in this case, it is only necessary to change 0 of the special sub-matrix to 1 uniformly until the sub-matrix of the above form is not generated any more. Thus obtained
Figure BDA0002598495350000072
Is an equivalent matrix. Thus, is composed of
Figure BDA0002598495350000073
A classification at the lambda level can be obtained.
(2) Direct clustering method
The direct clustering method is to directly obtain a clustering graph from a fuzzy similarity matrix without obtaining a transfer closure t (R) and using a Boolean matrix method after establishing the fuzzy similarity matrix. The method comprises the following steps:
1) take lambda11 (max), for each xiMaking similar classes [ x ]i]RAnd is made of
[xi]R＝{xj|rij＝1} (23)
Will satisfy rijX being 1iAnd xjPut in one category and form a similar category. Similarity classes differ from equivalence classes in that different similarity classes may have common elements, i.e., may occur
Figure BDA0002598495350000074
At the moment, only similar classes with common elements are combined to obtain the lambda11 on a horizontal equivalent scale.
2) Take lambda2Is a second largest value, and the similarity is lambda directly found from R2Element pair (x) of (c)i,xj) (i.e. r)ij＝λ2) Will correspond to λ1Equivalence class of 1iClass and xjThe classes are combined, and all the conditions are combined to obtain the corresponding lambda2The equivalence class of (1).
3) Take lambda3Is the third largest value, and the similarity is directly found from R3Element pair (x) ofi,xj) (i.e. r)ij＝λ3) Will correspond to λ2In an equivalence classification of xiClass and xjAll classes are mergedThese conditions are combined to obtain the corresponding lambda3The equivalence class of (1).
4) And so on until merging to U as one class.
(3) Determination of threshold values
Different classifications can be obtained for different lambda epsilon [0,1] in fuzzy clustering analysis, and many practical problems need to select a certain threshold lambda and determine a specific classification of a sample, so that the problem of how to determine the threshold is provided. There are generally two methods:
1) in the dynamic cluster map, the value of λ is adjusted to obtain proper classification as needed, without accurately estimating in advance that the sample should be classified into several classes. Of course, the threshold λ may also be determined by an expert with great experience in combination with expert knowledge, resulting in an equivalent classification at the λ level.
2) Determine the best value with the F statistic: assuming that the domain U is { x ═ x1,x2,……,xnIs the sample space (total number of samples n), and each sample xiThere are m features, equation (1), and thus the raw data matrix is obtained, as shown in the following table:
TABLE 1 index relationship Table
Figure BDA0002598495350000081
Wherein,
Figure BDA0002598495350000082
Figure BDA0002598495350000083
referred to as the center vector of the population of samples.
Let the classification number corresponding to the lambda value be r and the sample number of the j-th class be njAnd the j-th sample is recorded as:
Figure BDA00025984953500000813
class j cluster centers are vectors
Figure BDA0002598495350000084
Wherein
Figure BDA0002598495350000085
Is the average of the kth feature, i.e.
Figure BDA0002598495350000086
Making F statistics
Figure BDA0002598495350000087
Figure BDA0002598495350000088
Is composed of
Figure BDA0002598495350000089
And
Figure BDA00025984953500000810
the distance between the two parts of the main body,
Figure BDA00025984953500000811
for the ith sample x in the jth class(j)And the center thereof
Figure BDA00025984953500000812
The distance between them. Referred to as the F statistic, which is a distribution that follows a degree of freedom r-1, n-r. Its numerator characterizes the distance between classes, and its denominator characterizes the distance between samples in a class. Therefore, the larger the value of F, the larger the class-to-class distance; the greater the class-to-class difference, the better the classification.
S3: and simulating the hydraulic fracture form by using software, and determining the hydraulic fracture target of each divided reservoir according to the simulation result.
S4: and simulating the hydraulic fracturing results of different construction parameters by adopting a numerical simulation method according to the hydraulic fracturing target, and optimizing the construction parameters according to the hydraulic fracturing results, wherein the construction parameters comprise cluster number, discharge capacity and liquid consumption strength.
Example 1
S1: the basic parameters of deep shale of a plurality of different blocks are collected, as shown in table 2:
TABLE 2 reservoir base parameters
Figure BDA0002598495350000091
S2: and (5) carrying out reservoir division on the blocks 1 to 5 by adopting a fuzzy clustering method. The blocks 1 to 5 are classified objects, and each object is determined by 11 factor indexes, so that the original data matrix can be obtained. Of the 11 factor indices, different data have different dimensions, and in order to enable comparison of data having different dimensions, the data are also projected onto the interval (0, 1). Calculating the similarity between 11 parameters of different blocks, regarding the factor parameter of each block as a point in the space, and using a certain measure, such as Euclidean distance, to measure the distance between the point and the point, wherein the points with closer distance are classified into one class, and the points with farther distance are classified into the same class.
The clustering result is shown in FIG. 1, and it can be seen from FIG. 1 that the similarity degree between segments is expressed by relative distance (0 ~ 25) in the clustering connection dendrogram. The smaller the distance, the higher the similarity degree between the segment and the segment; the larger the distance, the larger the difference. The relative distance between the fracturing geological parameters of the block 1 and the block 2 is 0-1, the two blocks are close to each other, and the two blocks are classified as a first type; the relative distance between the fracturing geological parameters of the block 3 and the block 5 is 15-20, the two blocks are close to each other and are classified as a second type; the relative distance of the fracturing geological parameters of the block 4 is 20-25, the difference with other 4 blocks is large, and the three blocks are classified as a third type.
S3: and simulating the hydraulic fracture morphology by using software according to the geological characteristics of each block, and determining the hydraulic fracture target of each divided reservoir according to the simulation result. The block 1 and the block 2 use a complex fracture network as a hydraulic fracturing target, the block 3 and the block 5 use a main fracture and a branch fracture as the hydraulic fracturing target, and the block 4 uses a main fracture as the hydraulic fracturing target.
S4: and simulating the hydraulic fracturing results of different construction parameters by adopting a numerical simulation method according to the hydraulic fracturing target, and optimizing the construction parameters according to the hydraulic fracturing results.
The numerical simulation results of the cluster numbers of the block 1 and the block 2 are shown in fig. 2-4, and as can be seen from fig. 2-4, the total reconstruction volume of the hydraulic fracture shows an increasing trend along with the increase of the cluster number, but the width and the length of the fracture are both reduced; when the cluster number is larger than 4 clusters, the reconstruction volume is in a decreasing trend, and the recommended cluster number is 3-4 clusters. And obtaining the recommended cluster number of the block 3 and the block 5 as 4-6 clusters by adopting the same method, and obtaining the recommended cluster number of the block 4 as 6-8 clusters.
Wherein, on the basis that the number of clusters of the block 1 and the block 2 is 4, the numerical simulation result of the displacement is shown in fig. 5-7, the prevention of the deformation and the pursuit of the reconstruction volume are comprehensively considered, and the recommended displacement is 12-14m under 4 clusters3And/min. The recommended displacement of the block 3 and the block 5 is 14-16m obtained by the same method3Min, recommended displacement of block 4 is 16m3More than min.
Wherein, the block 1 and the block 2 have a cluster number of 4 and a displacement of 14m3On the basis of/min, the results of numerical simulation of the liquid strength are shown in FIGS. 8 to 10, and it can be seen from FIGS. 8 to 10 that the number of clusters is 4 and the discharge amount is 14m3In the case of/m, the recommended strength of the liquid is 24-26m3And/m. The recommended liquid strength of the blocks 3 and 5 is 24-28m obtained by the same method3Per m, recommended liquid strength of block 4 is 30m3More than m.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (5)

1. A deep shale fracturing process parameter optimization method is characterized by comprising the following steps:
collecting basic parameters of deep shale of a plurality of different blocks, wherein the basic parameters comprise brittle minerals, Poisson's ratio, elastic modulus, tensile strength, shear strength, fracture toughness, natural fracture, mechanical brittleness index, maximum horizontal main stress, minimum horizontal main stress, horizontal earth stress difference and vertical earth stress difference;
carrying out reservoir division on the deep shale by adopting a fuzzy clustering method; the fuzzy clustering method adopts a system clustering method, and specifically comprises the following steps:
setting a data matrix of the basic parameters, carrying out data standardization on data in the matrix, and compressing the data to [0,1]]On the interval; the data matrix establishing method comprises the following steps: assuming that the domain U is { x ═ x1,x2,……,xnThe classified objects are provided with m indexes to represent the characters of the objects, namely:
xi＝{xi1,xi2,…,ximand i ═ 1,2, …, n (1)
Then, the data matrix is obtained as:
Figure FDA0003535260480000011
wherein xnmRaw data representing an mth index of an nth classification object;
establishing a fuzzy similar matrix, and calculating the similarity degree of each block;
clustering each block according to the calculation result of the similarity;
simulating the hydraulic fracture form by using software, and determining the hydraulic fracture target of each divided reservoir stratum according to the simulation result;
and simulating the hydraulic fracturing results of different construction parameters by adopting a numerical simulation method according to the hydraulic fracturing target, and optimizing the construction parameters according to the hydraulic fracturing results.
2. The deep shale fracturing process parameter optimization method according to claim 1, wherein the data standardization is realized by a translation and range transformation method, and the method specifically comprises the following steps:
Figure FDA0003535260480000012
Figure FDA0003535260480000013
Figure FDA0003535260480000014
Figure FDA0003535260480000021
in the formula: x is more than or equal to 0 ≦ x ″)ikLess than or equal to 1, and eliminates the influence of dimension.
3. The deep shale fracturing process parameter optimization method of claim 1, wherein the similarity degree is calculated by a similarity coefficient method or a distance method, the similarity coefficient method comprises an included angle cosine method, a maximum and minimum method, a calculated number average minimum method, a geometric average minimum method, a number product method, a correlation coefficient method and an index similarity coefficient method, and the distance method comprises a direct distance method, a hamming distance method, an euclidean distance method, a chebyshev distance method, a reciprocal distance method and an index distance method.
4. The deep shale fracturing process parameter optimization method of claim 1, wherein clustering is performed by a fuzzy equivalent matrix-based clustering method or a direct clustering method, a threshold value is determined during clustering, and the threshold value is determined by an F statistic.
5. The deep shale fracturing process parameter optimization method of claim 1, wherein the construction parameters comprise cluster number, displacement and fluid intensity.
CN202010716805.1A 2020-07-23 2020-07-23 Deep shale fracturing process parameter optimization method Active CN111797575B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010716805.1A CN111797575B (en) 2020-07-23 2020-07-23 Deep shale fracturing process parameter optimization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010716805.1A CN111797575B (en) 2020-07-23 2020-07-23 Deep shale fracturing process parameter optimization method

Publications (2)

Publication Number Publication Date
CN111797575A CN111797575A (en) 2020-10-20
CN111797575B true CN111797575B (en) 2022-05-20

Family

ID=72828318

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010716805.1A Active CN111797575B (en) 2020-07-23 2020-07-23 Deep shale fracturing process parameter optimization method

Country Status (1)

Country Link
CN (1) CN111797575B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115099164B (en) * 2022-08-26 2022-12-30 中国科学技术大学 Machine learning-based tin-based perovskite thin film transistor optimization method and device

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9201164B2 (en) * 2011-11-15 2015-12-01 Chevron U.S.A. Inc. System and method of using spatially independent subsets of data to calculate property distribution uncertainty of spatially correlated reservoir data
CN105156103B (en) * 2015-09-29 2018-06-05 西南石油大学 A kind of multiple dimensioned shale reservoir three-dimensional compressibility evaluation method of landwaste-rock core-wellbore-reservoir
CN105201479B (en) * 2015-10-09 2017-10-24 西南石油大学 A kind of horizontal well on shale reservoir stratum staged fracturing perforation cluster method for optimally designing parameters
CN107387051B (en) * 2017-09-05 2020-03-27 西南石油大学 Repeated fracturing well selection method for multi-stage fractured horizontal well with low-permeability heterogeneous oil reservoir

Also Published As

Publication number Publication date
CN111797575A (en) 2020-10-20

Similar Documents

Publication Publication Date Title
CN108009716A (en) A kind of horizontal well volume fracturing influential effect factor mutiple-stage model method
Liu et al. Microseismicity-based method for the dynamic estimation of the potential rockburst scale during tunnel excavation
Sun et al. Based on multi-algorithm hybrid method to predict the slope safety factor--stacking ensemble learning with bayesian optimization
CN103995947A (en) Improved coal seam floor water inrush vulnerability evaluation method
CN105005712B (en) Limestone aquifer watery evaluation methodology
CN103617147A (en) Method for identifying mine water-inrush source
CN113486570A (en) Method for predicting tunnel seismic vulnerability based on random IDA and machine learning
Dongqi et al. Fine classification of ultra-low permeability reservoirs around the Placanticline of Daqing oilfield (PR of China)
CN110717301A (en) Flow unit information classification and identification method based on support vector machine algorithm
CN115358285B (en) Method, device and equipment for selecting key geological parameters of block to be surveyed
CN104850867A (en) Object identification method based on intuitive fuzzy c-means clustering
CN111797575B (en) Deep shale fracturing process parameter optimization method
CN113283180A (en) K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application
CN109118004B (en) Prediction method for suitable area for engineering construction site selection
CN105046080A (en) Rock mass quality evaluation method
CN112365054A (en) Comprehensive grading prediction method for deep well roadway surrounding rock
CN102704924B (en) Method and device for determining effective dry layer
Cheng et al. Improved combination weighted prediction model of aquifer water abundance based on a cloud model
CN114460639B (en) Shale oil reservoir permeability prediction method and device
CN118013344A (en) Tunneling parameter classification optimization method and system based on tunneling performance surrounding rock classification
CN116562428A (en) Fracturing construction parameter optimization method based on machine learning
CN110956388A (en) Method for generating yield increasing scheme of offshore oil and gas reservoir
CN112065370B (en) Method and device for evaluating oil-gas-containing property of broken block trap
CN114298246A (en) Tunnel underground water discharge amount determination method based on fuzzy clustering analysis analogy
CN108510211A (en) A kind of organic matter abundance in hydrocarbon source rock evaluation method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant