Shale reservoir fracturing influence factor analysis method and device, electronic equipment and medium

Abstract

The invention discloses a shale reservoir fracturing influence factor analysis method and device, electronic equipment and a medium. The method comprises the following steps: constructing a training data set through a plurality of influence factors and fracturing evaluation results thereof; according to the training data set, first dispersion of different influence factors is calculated for the same target, and second dispersion of the same influence factor under different targets is calculated; and according to the first dispersion and the second dispersion, calculating the sensitivity degree of the influence factor to the target. According to the method, shale gas reservoir compressibility sensitive parameter analysis and evaluation are carried out based on data-driven supervised learning.

Description

Technical Field

[0001] This invention relates to the field of oil and gas and coalbed methane exploration and development, and more specifically, to a method, apparatus, electronic equipment and medium for analyzing factors affecting the fracturability of shale reservoirs. Background Technology

[0002] Shale reservoir fracturing capability generally refers to the possibility of a shale reservoir being effectively fractured under hydraulic fracturing conditions. Fracturing capability is the most critical evaluation index in shale development. Shale gas fracturing capability can generally be divided into two categories based on data sources: numerical simulation and laboratory rock physics measurements. The former has the advantages of higher flexibility and lower cost, but numerical simulations are usually based on certain assumptions and simplifications, which can affect their accuracy and reliability. The latter's biggest advantage is its directness, speed, and efficiency, but the cost may be higher. Whether through numerical simulation or laboratory rock physics measurements, the ultimate goal is to obtain geological parameters of shale reservoirs, such as lithology, porosity, permeability, gas content, organic carbon content, elastic modulus, Poisson's ratio, and formation pressure (mostly from well logging and interpretation results, or from laboratory data); reservoir depth, reservoir thickness, elastic modulus, Poisson's ratio, formation pressure, and geostress (from seismic data); and engineering parameters such as horizontal section length, high-quality reservoir encounter rate, segmentation and clustering, and fracturing scale. These parameters are then used to determine and evaluate the compressibility of shale reservoirs. Due to the large number of parameters, identifying sensitive parameters or combinations of sensitive parameters is the most pressing task in evaluating the compressibility of shale gas field reservoirs.

[0003] Therefore, it is necessary to develop a method, device, electronic equipment, and medium for analyzing the influencing factors of shale reservoir fracturability.

[0004] The information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention and should not be construed as an admission or in any way implying that such information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] This invention proposes a method, apparatus, electronic equipment, and medium for analyzing factors affecting the fracturability of shale reservoirs. It is based on data-driven supervised learning to analyze and evaluate sensitive parameters of shale gas reservoir fracturability.

[0006] In a first aspect, embodiments of this disclosure provide a method for analyzing factors influencing the fracturability of shale reservoirs, including:

[0007] A training dataset was constructed using multiple influencing factors and their fracturing evaluation results.

[0008] Based on the training dataset, calculate the first dispersion of different influencing factors for the same target, and calculate the second dispersion of the same influencing factor for different targets;

[0009] Based on the first dispersion and the second dispersion, the sensitivity of the influencing factors to the target is calculated.

[0010] As a specific implementation of this disclosure, the influencing factors include the degree of development of natural cracks, the effectiveness of natural cracks, as well as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition, TOC content, gas content, and brittleness.

[0011] As a specific implementation of this disclosure, the first dispersion is:

[0012]

[0013] Among them, X ·c This represents the sample data for the c-th influencing factor; Y i and Y j Let N represent the target values ​​of the i-th and j-th classes, respectively. k This represents the number of samples when the target value is k. Represents the relationship with sample data X ·c The c-th influencing factor value from the most recent sample data.

[0014] As a specific implementation of this disclosure, the second dispersion is:

[0015]

[0016] in,

[0017] As one specific implementation of this disclosure, the sensitivity level is:

[0018]

[0019] Where F(c) represents the sensitivity.

[0020] As a specific implementation of this disclosure, it also includes:

[0021] For each objective, the sensitivity of each influencing factor is ranked by magnitude and displayed in the form of a histogram.

[0022] As a specific implementation of this disclosure, it also includes:

[0023] A sensitivity matrix between attributes and the target is established based on the influencing factors and the sensitivity of the target, and different colors are used to mark the values ​​of the sensitivity matrix.

[0024] Secondly, this disclosure also provides an apparatus for analyzing factors affecting the fracturability of shale reservoirs, comprising:

[0025] The module constructs a training dataset by using multiple influencing factors and their fracturing evaluation results;

[0026] The training module calculates the first dispersion of different influencing factors for the same target based on the training dataset, and calculates the second dispersion of the same influencing factor for different targets.

[0027] The calculation module calculates the sensitivity of the influencing factors to the target based on the first dispersion and the second dispersion.

[0028] As a specific implementation of this disclosure, the influencing factors include the degree of development of natural cracks, the effectiveness of natural cracks, as well as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition, TOC content, gas content, and brittleness.

[0029] As a specific implementation of this disclosure, the first dispersion is:

[0030]

[0031] Among them, X ·c This represents the sample data for the c-th influencing factor; Y i and Y j Let N represent the target values ​​of the i-th and j-th classes, respectively. k This represents the number of samples when the target value is k. Represents the relationship with sample data X ·c The c-th influencing factor value from the most recent sample data.

[0032] As a specific implementation of this disclosure, the second dispersion is:

[0033]

[0034] in,

[0035] As one specific implementation of this disclosure, the sensitivity level is:

[0036]

[0037] Where F(c) represents the sensitivity.

[0038] As a specific implementation of this disclosure, it also includes:

[0039] For each objective, the sensitivity of each influencing factor is ranked by magnitude and displayed in the form of a histogram.

[0040] As a specific implementation of this disclosure, it also includes:

[0041] A sensitivity matrix between attributes and the target is established based on the influencing factors and the sensitivity of the target, and different colors are used to mark the values ​​of the sensitivity matrix.

[0042] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0043] Memory, which stores executable instructions;

[0044] A processor that executes the executable instructions in the memory to implement the method for analyzing factors affecting the fracturability of shale reservoirs.

[0045] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for analyzing factors affecting the fracturability of shale reservoirs.

[0046] The methods and apparatus of the present invention have other features and advantages that will be apparent from or will be set forth in detail in the accompanying drawings and following detailed description, which together serve to explain the particular principles of the invention. Attached Figure Description

[0047] The above and other objects, features and advantages of the present invention will become more apparent from the more detailed description of exemplary embodiments of the invention in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same parts.

[0048] Figure 1 A flowchart illustrating the steps of a method for analyzing factors influencing the fracturability of shale reservoirs according to an embodiment of the present invention is shown.

[0049] Figure 2 A histogram of the dispersion of influencing factors according to an embodiment of the present invention is shown.

[0050] Figure 3 An influencing factor-target matrix diagram according to an embodiment of the present invention is shown.

[0051] Figure 4 A block diagram of an apparatus for analyzing factors affecting the fracturability of shale reservoirs according to an embodiment of the present invention is shown.

[0052] Explanation of reference numerals in the attached figures:

[0053] 201. Construction module; 202. Training module; 203. Calculation module. Detailed Implementation

[0054] Preferred embodiments of the invention will now be described in more detail. While preferred embodiments of the invention are described below, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0055] To facilitate understanding of the solutions and effects of the embodiments of the present invention, six specific application examples are given below. Those skilled in the art should understand that these examples are merely for the purpose of understanding the present invention, and any specific details therein are not intended to limit the present invention in any way.

[0056] Example 1

[0057] Figure 1 A flowchart illustrating the steps of a method for analyzing factors influencing the fracturability of shale reservoirs according to an embodiment of the present invention is shown.

[0058] like Figure 1 As shown, the analysis methods for factors affecting the fracturability of this shale reservoir include:

[0059] Step 101: Construct a training dataset using multiple influencing factors and their fracturing evaluation results;

[0060] Step 102: Based on the training dataset, calculate the first dispersion of different influencing factors for the same target, and calculate the second dispersion of the same influencing factor under different targets;

[0061] Step 103: Calculate the sensitivity of the influencing factors to the target based on the first dispersion and the second dispersion.

[0062] In one example, influencing factors include the degree of development of natural fractures, the effectiveness of natural fractures, as well as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition, TOC content, gas content, and brittleness.

[0063] In one example, the first degree of dispersion is:

[0064]

[0065] Among them, X ·c This represents the sample data for the c-th influencing factor; Y i and Yj Let N represent the target values ​​of the i-th and j-th classes, respectively. k This represents the number of samples when the target value is k. Represents the relationship with sample data X ·c The c-th influencing factor value from the most recent sample data.

[0066] In one example, the second dispersion is:

[0067]

[0068] in,

[0069] In one example, the sensitivity level is:

[0070]

[0071] Where F(c) represents the sensitivity.

[0072] In one example, it also includes:

[0073] For each objective, the sensitivity of each influencing factor is ranked by magnitude and displayed in the form of a histogram.

[0074] In one example, it also includes:

[0075] A sensitivity matrix between attributes and targets is established based on the sensitivity of influencing factors and targets, and different colors are used to mark the values ​​in the sensitivity matrix.

[0076] Specifically, based on laboratory measurements of rock cores to assess the development and effectiveness of natural fractures, as well as factors influencing fracturability such as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition (quartz and other mineral content), TOC content, gas content (or free gas content), and brittleness, the corresponding rock cores are then subjected to fracturing in the laboratory (simulating actual engineering fracturing). XDR is used to detect and determine the fracturing fracture height. The fracture complexity is characterized by the normalized average values ​​of fracture porosity and fracture dip angle dispersion, as well as fracture height and fracture opening. The core fracturability index is defined as the ratio of fracture complexity to strength. The fracturing effect is observed and evaluated in conjunction with post-fracturing pressure drop data. The above parameters and fracturing effect evaluation results are then used to construct training sample data.

[0077] The aforementioned laboratory core data and their fracturing evaluation results together constitute the training dataset D(X). ij ,Y i ), where X ijThis represents the data measured from each core sample, where i = 1, 2, ..., N represents the data point number, j = 1, 2, ..., P represents the variable number (data dimension) of the data at each data point, and Y... i Indicates the degree of fracturing (target effect).

[0078] First, for a specific target effect, calculate the first dispersion of each influencing factor in turn:

[0079]

[0080] For each type of target effect, these influencing factors are arranged in ascending order according to their degree of dispersion, and then displayed visually in the form of a histogram. This allows for a direct observation of which influencing factor is more stable for the same type of target effect. Finally, the degree of dispersion between each influencing factor and the target for all targets forms a correlation matrix between the influencing factors and the target. This correlation matrix is ​​represented and displayed using color, which is very useful for selecting a single attribute to represent the target object.

[0081] Furthermore, for different types of target effects, for the arranged influencing factors, a certain influencing factor is selected in turn, and the second dispersion of the influencing factor itself as a function of the target effect is calculated under different target effects:

[0082]

[0083] Then, these influencing factors are arranged in descending order of their dispersion and displayed visually in the form of a histogram. Finally, for all target effects, the dispersion of all influencing factors forms a dispersion matrix between influencing factors and targets. This dispersion is represented and displayed using color, making the correlation between influencing factors immediately clear.

[0084] The sensitivity of an influencing factor to a given target is calculated using the following formula: The attribute that simultaneously minimizes the dispersion of influencing factor data for the same type of target while maximizing the dispersion of influencing factor data for different types of targets is the sensitivity of that influencing factor to that target.

[0085]

[0086] Finally, for each type of target, the sensitivity of each influencing factor obtained in step three is arranged in order of magnitude and displayed visually in the form of a histogram. This makes the sensitivity of all attributes that meet the requirements clear at a glance. The sensitivity between all influencing factors and all targets finally forms an attribute-target sensitivity matrix. This sensitivity matrix is ​​represented and displayed with colors, which is helpful for selecting certain combinations of influencing factors to characterize the target object.

[0087] Example 2

[0088] The present invention also provides an analysis device for factors affecting the fracturability of shale reservoirs, comprising:

[0089] The module constructs a training dataset by using multiple influencing factors and their fracturing evaluation results;

[0090] The training module calculates the first dispersion of different influencing factors for the same objective based on the training dataset, and calculates the second dispersion of the same influencing factor for different objectives.

[0091] The calculation module calculates the sensitivity of influencing factors to the target based on the first and second dispersion.

[0092] In one example, influencing factors include the degree of development of natural fractures, the effectiveness of natural fractures, as well as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition, TOC content, gas content, and brittleness.

[0093] In one example, the first degree of dispersion is:

[0094]

[0095] Among them, X ·c This represents the sample data for the c-th influencing factor; Y i and Y j Let N represent the target values ​​of the i-th and j-th classes, respectively. k This represents the number of samples when the target value is k. Represents the relationship with sample data X ·c The c-th influencing factor value from the most recent sample data.

[0096] In one example, the second dispersion is:

[0097]

[0098] in,

[0099] In one example, the sensitivity level is:

[0100]

[0101] Where F(c) represents the sensitivity.

[0102] In one example, it also includes:

[0103] For each objective, the sensitivity of each influencing factor is ranked by magnitude and displayed in the form of a histogram.

[0104] In one example, it also includes:

[0105] A sensitivity matrix between attributes and targets is established based on the sensitivity of influencing factors and targets, and different colors are used to mark the values ​​in the sensitivity matrix.

[0106] Specifically, based on laboratory measurements of rock cores to assess the development and effectiveness of natural fractures, as well as factors influencing fracturability such as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition (quartz and other mineral content), TOC content, gas content (or free gas content), and brittleness, the corresponding rock cores are then subjected to fracturing in the laboratory (simulating actual engineering fracturing). XDR is used to detect and determine the fracturing fracture height. The fracture complexity is characterized by the normalized average values ​​of fracture porosity and fracture dip angle dispersion, as well as fracture height and fracture opening. The core fracturability index is defined as the ratio of fracture complexity to strength. The fracturing effect is observed and evaluated in conjunction with post-fracturing pressure drop data. The above parameters and fracturing effect evaluation results are then used to construct training sample data.

[0107] The aforementioned laboratory core data and their fracturing evaluation results together constitute the training dataset D(X). ij ,Y i ), where X ij This represents the data measured from each core sample, where i = 1, 2, ..., N represents the data point number, j = 1, 2, ..., P represents the variable number (data dimension) of the data at each data point, and Y... i Indicates the degree of fracturing (target effect).

[0108] First, for a specific target effect, calculate the first dispersion of each influencing factor in turn:

[0109]

[0110] For each type of target effect, these influencing factors are arranged in ascending order according to their degree of dispersion, and then displayed visually in the form of a histogram. This allows for a direct observation of which influencing factor is more stable for the same type of target effect. Finally, the degree of dispersion between each influencing factor and the target for all targets forms a correlation matrix between the influencing factors and the target. This correlation matrix is ​​represented and displayed using color, which is very useful for selecting a single attribute to represent the target object.

[0111] Furthermore, for different types of target effects, for the arranged influencing factors, a certain influencing factor is selected in turn, and the second dispersion of the influencing factor itself as a function of the target effect is calculated under different target effects:

[0112]

[0113] Then, these influencing factors are arranged in descending order of their dispersion and displayed visually in the form of a histogram. Finally, for all target effects, the dispersion of all influencing factors forms a dispersion matrix between influencing factors and targets. This dispersion is represented and displayed using color, making the correlation between influencing factors immediately clear.

[0114] The sensitivity of an influencing factor to a given target is calculated using the following formula: The attribute that simultaneously minimizes the dispersion of influencing factor data for the same type of target while maximizing the dispersion of influencing factor data for different types of targets is the sensitivity of that influencing factor to that target.

[0115]

[0116] Finally, for each type of target, the sensitivity of each influencing factor obtained in step three is arranged in order of magnitude and displayed visually in the form of a histogram. This makes the sensitivity of all attributes that meet the requirements clear at a glance. The sensitivity between all influencing factors and all targets finally forms an attribute-target sensitivity matrix. This sensitivity matrix is ​​represented and displayed with colors, which is helpful for selecting certain combinations of influencing factors to characterize the target object.

[0117] Example 3

[0118] Based on laboratory measurements of rock cores to determine the degree of natural fracture development, effectiveness of natural fractures, and factors influencing fracturability such as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition (quartz and other mineral content), TOC content, gas content (or free gas content), and brittleness, the corresponding rock cores were then subjected to fracturing in the laboratory (simulating actual engineering fracturing). XDR was used to detect and determine the fracturing fracture height. The fracture complexity was characterized by the normalized average values ​​of fracture porosity and fracture dip angle dispersion, as well as fracture height and fracture opening. The core fracturability index was defined as the ratio of fracture complexity to strength. The fracturing effect was observed and evaluated using post-fracturing pressure drop data. The above parameters and fracturing effect evaluation results were then used to construct training sample data.

[0119] The aforementioned laboratory core data and their fracturing evaluation results together constitute the training dataset D(X). ij ,Y i ), where X ij This represents the data measured from each core sample, where i = 1, 2, ..., N represents the data point number, j = 1, 2, ..., P represents the variable number (data dimension) of the data at each data point, and Y... i Indicates the degree of fracturing (target effect).

[0120] First, for a specific target effect, calculate the first dispersion of each influencing factor in turn:

[0121]

[0122] For each type of target effect, these influencing factors are arranged in ascending order according to their degree of dispersion, and then displayed visually in the form of a histogram. This allows for a direct observation of which influencing factor is more stable for the same type of target effect. Finally, the degree of dispersion between each influencing factor and the target for all targets forms a correlation matrix between the influencing factors and the target. This correlation matrix is ​​represented and displayed using color, which is very useful for selecting a single attribute to represent the target object.

[0123] Furthermore, for different types of target effects, for the arranged influencing factors, a certain influencing factor is selected in turn, and the second dispersion of the influencing factor itself as a function of the target effect is calculated under different target effects:

[0124]

[0125] Then, these influencing factors are arranged in descending order of their dispersion and displayed visually in the form of a histogram. Finally, for all target effects, the dispersion of all influencing factors forms a dispersion matrix between influencing factors and targets. This dispersion is represented and displayed using color, making the correlation between influencing factors immediately clear.

[0126] The sensitivity of an influencing factor to a given target is calculated using the following formula: The attribute that simultaneously minimizes the dispersion of influencing factor data for the same type of target while maximizing the dispersion of influencing factor data for different types of targets is the sensitivity of that influencing factor to that target.

[0127]

[0128] Figure 2 A histogram of the dispersion of influencing factors according to an embodiment of the present invention is shown.

[0129] Figure 3 An influencing factor-target matrix diagram according to an embodiment of the present invention is shown.

[0130] Finally, for each type of objective, the sensitivity of each influencing factor obtained in step three is ranked by magnitude and visually displayed in the form of a histogram, such as... Figure 2 As shown, this makes the sensitivity of all attributes that meet the requirements immediately apparent. The sensitivity between all influencing factors and all targets ultimately forms an attribute-target sensitivity matrix. This sensitivity matrix is ​​represented and displayed using colors, as shown below. Figure 3As shown, this makes it easier to select a combination of certain influencing factors to characterize the target object.

[0131] Example 4

[0132] Figure 4 A block diagram of an apparatus for analyzing factors affecting the fracturability of shale reservoirs according to an embodiment of the present invention is shown.

[0133] like Figure 4 As shown, the device for analyzing factors affecting the fracturability of this shale reservoir includes:

[0134] Module 201 is used to construct a training dataset based on multiple influencing factors and their fracturing evaluation results.

[0135] Training module 202 calculates the first dispersion of different influencing factors for the same target based on the training dataset, and calculates the second dispersion of the same influencing factor under different targets;

[0136] The calculation module 203 calculates the sensitivity of the influencing factors to the target based on the first dispersion and the second dispersion.

[0137] In one example, influencing factors include the degree of development of natural fractures, the effectiveness of natural fractures, as well as porosity, permeability, elastic modulus, Poisson's ratio, mineral composition, TOC content, gas content, and brittleness.

[0138] In one example, the first degree of dispersion is:

[0139]

[0140] Among them, X ·c This represents the sample data for the c-th influencing factor; Y i and Y j Let N represent the target values ​​of the i-th and j-th classes, respectively. k This represents the number of samples when the target value is k. Represents the relationship with sample data X ·c The c-th influencing factor value from the most recent sample data.

[0141] In one example, the second dispersion is:

[0142]

[0143] in,

[0144] In one example, the sensitivity level is:

[0145]

[0146] Where F(c) represents the sensitivity.

[0147] In one example, it also includes:

[0148] For each objective, the sensitivity of each influencing factor is ranked by magnitude and displayed in the form of a histogram.

[0149] In one example, it also includes:

[0150] A sensitivity matrix between attributes and targets is established based on the sensitivity of influencing factors and targets, and different colors are used to mark the values ​​in the sensitivity matrix.

[0151] Example 5

[0152] This disclosure provides an electronic device, comprising: a memory storing executable instructions; and a processor executing the executable instructions in the memory to implement the above-described method for analyzing factors affecting the fracturability of shale reservoirs.

[0153] An electronic device according to an embodiment of the present disclosure includes a memory and a processor.

[0154] This memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0155] The processor may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of this disclosure, the processor is used to execute computer-readable instructions stored in the memory.

[0156] Those skilled in the art will understand that, in order to solve the technical problem of how to achieve a good user experience, this embodiment may also include well-known structures such as communication buses and interfaces, and these well-known structures should also be included within the protection scope of this disclosure.

[0157] For a detailed description of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0158] Example 6

[0159] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for analyzing factors affecting the fracturability of shale reservoirs.

[0160] A computer-readable storage medium according to embodiments of the present disclosure stores non-transitory computer-readable instructions. When these non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the methods described in the foregoing embodiments of the present disclosure are performed.

[0161] The aforementioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or portable hard drive), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).

[0162] Those skilled in the art should understand that the above description of the embodiments of the present invention is only intended to illustrate the beneficial effects of the embodiments of the present invention, and is not intended to limit the embodiments of the present invention to any of the examples given.

[0163] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method for analyzing factors affecting the fracturability of shale reservoirs, characterized in that, The method comprises the following steps: a training data set is constructed by a plurality of influence factors and their fracture evaluation results; first dispersions of different influence factors for the same target are calculated according to the training data set, and second dispersions of the same influence factor for different targets are calculated; sensitivity of the influence factors to the targets is calculated according to the first dispersions and the second dispersions.

2. The method of shale reservoir fracability impact factor analysis of claim 1, wherein, The influence factors include natural fracture development degree, natural fracture effectiveness, and porosity, permeability, elastic modulus, Poisson's ratio, mineral composition, TOC content, gas content, and brittleness.

3. The method of shale reservoir fracability impact factor analysis of claim 1, wherein, The first dispersion is: wherein X ·c represents the sample data of the cth influencing factor; Y i and Y j represent the i th and j th target values, respectively, N k represents the number of samples when the target value is k; represents the cth influencing factor value of the most recent sample data X ·c of the cth influencing factor.

4. The method of shale reservoir fracability impact factor analysis of claim 1, wherein, The second dispersion is: wherein 5. The method of shale reservoir fracability impact factor analysis of claim 1, wherein, The sensitivity is: wherein F(c) is the sensitivity.

6. The method of shale reservoir fracability impact factor analysis of claim 1, wherein, The method further comprises the following steps: For each target, the sensitivities of the influence factors are arranged in size and displayed in the form of a histogram.

7. The method of shale reservoir fracability impact factor analysis of claim 1, wherein, The method further comprises the following steps: A sensitivity matrix of the attributes and the targets is established according to the sensitivities of the influence factors and the targets, and the sensitivity matrix is marked by different colors according to the numerical size.

8. A shale reservoir fracturability influencing factor analysis device characterized by, The method comprises the following steps: a training data set is constructed by a plurality of influence factors and their fracture evaluation results; a training module calculates first dispersions of different influence factors for the same target according to the training data set, and calculates second dispersions of the same influence factor for different targets; a calculation module calculates sensitivity of the influence factors to the targets according to the first dispersions and the second dispersions.

9. An electronic device, comprising: The electronic device comprises: a memory storing executable instructions; a processor running the executable instructions in the memory to implement the shale reservoir fracturing property influence factor analysis method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program which, when executed by a processor, implements the shale reservoir fracturing property influence factor analysis method in any one of claims 1-7.

Images