Horizontal well fracturing main control factor analysis method and system for eliminating influence of construction parameters

Abstract

The invention provides a horizontal well fracturing main control factor analysis method and system capable of eliminating construction parameter influences, and the method comprises the steps: comprehensively collecting geological and construction factors of the productivity of a fractured horizontal well, analyzing the preliminary influence weight of each factor on the productivity of the fractured horizontal well through a combined machine learning algorithm, and determining a preliminary influence factor; performing dual normalization processing on the productivity of different wells based on the preliminary influence construction factors and the influence weights, eliminating the influence of inconsistency of construction parameters, and determining the secondary influence weight of each preliminary influence geological factor on the processed productivity by applying an analysis algorithm; and establishing an analytic hierarchy process judgment matrix in combination with the preliminary comprehensive influence weight, calculating the final influence weight of each factor on the processed capacity, and determining a target main control factor. According to the scheme, the defects that in the prior art, construction parameter interference cannot be avoided, and the accuracy is insufficient can be overcome, the fracturing main control factors of the demand block are accurately selected, and powerful support is provided for building a productivity correlation model and a fracturing comprehensive dessert calculation model.

Description

Technical Field

[0001] The present invention relates to the technical field of on-site fracturing optimization in oil and gas fields, and in particular to a method and system for analyzing main control factors of horizontal well fracturing that eliminates the influence of construction parameters. Background Art

[0002] The post-fracture production capacity of horizontal wells is affected by a variety of geological factors and construction factors, and there are complex correlations between the factors; therefore, when analyzing the impact of geological factors on the production capacity of fractured wells based on the data of already fractured wells, the differences in the construction parameters of already fractured wells will interfere with the analysis and calculation results. Before implementing fracturing construction, the original geological potential of the block and the drilled horizontal wells is usually the main consideration for fracturing well selection and section selection. Formulating a fracturing construction plan based on the geological high potential section can effectively improve the fracturing transformation effect. Therefore, when analyzing the impact of the main geological control factors on the fracturing effect of horizontal wells based on the data of already fractured wells, and establishing a geological sweet spot evaluation model, the influence of construction parameters on the evaluation model should be eliminated.

[0003] At present, there are mainly two methods in the field that use the data of well-pressed wells to analyze the influence of the main controlling geological factors of horizontal wells on the production capacity of fracturing wells. One is to evaluate all geological factors and construction factors together, and uniformly rank them to determine the main controlling factors. For example, the patent document CN202011392976.X provides a tight oil and gas horizontal well production detection method with three-dimensional coupling of geology and engineering, establishes a tight oil and gas geology-engineering coupling data set along the horizontal well trajectory space, extracts and classifies the output characteristic data of tight oil and gas horizontal wells, and screens the main controlling factors of geology-engineering coupling and detects the control effect characteristics of tight oil and gas horizontal well production effects; the document "Main Controlling Factors and Development Countermeasures Optimization of Shale Oil Horizontal Well Production Capacity in Qingcheng Oilfield, Ordos Basin" takes more than 180 horizontal wells in Qingcheng Oilfield as samples, and uses the grey correlation method and random forest algorithm to systematically analyze the influence of geology, fracturing construction and other parameters on production capacity, and clarify the main controlling factors of single well production capacity. Such schemes do not consider the impact of mutual interference between geological factors and construction factors on the evaluation results, and cannot establish an accurate correlation model between the main controlling geological factors and production capacity, nor a reliable fracturing sweet spot calculation model based on the main controlling geological factors;

[0004] The other type is to consider the influence of geological factors and construction factors on the fracturing effect respectively, and construct an evaluation model. For example, patent document CN202011466585.8 provides a comprehensive geological-engineering classification evaluation method for low permeability reservoirs. The grey correlation method is used to obtain the main controlling factors of reservoir geology that affect the fracturing effect of low permeability reservoirs, and the principal component analysis method is used to construct a low permeability reservoir geological classification evaluation index. Based on the main controlling factors of geomechanics, the hierarchical analysis method is used to construct a low permeability reservoir engineering classification evaluation index. When establishing geological parameter evaluation indicators, this type of method cannot eliminate the influence of construction parameters on production. Different construction parameters of wells have interfered with the evaluation results, and it is impossible to establish an accurate geological sweet spot calculation model.

[0005] It can be seen that the current research on the main influencing factors of horizontal well fracturing effect and clarifying the influence of the main controlling geological factors on the production capacity of fracturing wells are the key to improving the fracturing effect. However, when using the data of wells that have been fracturing to carry out analysis and research, it is often interfered by inconsistent construction parameters. Therefore, it is necessary to screen the main controlling geological factors that affect the production capacity of fracturing wells on the basis of eliminating the influence of construction parameters on the fracturing effect of horizontal wells.

[0006] The information disclosed in the background technology section of the present invention is only intended to deepen the understanding of the general background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0007] In order to solve the above problems, the present invention provides a method for analyzing the main controlling factors of horizontal well fracturing by eliminating the influence of construction parameters. On the basis of analyzing the weights of the influence of geological and construction factors on the production capacity, the production capacity is normalized based on the construction data, the influence of the construction parameters on the post-fracturing production capacity is eliminated, and the main controlling geological factors affecting the production capacity are obtained; preferably, in one embodiment, the method includes:

[0008] Parameter collection step: select a target block according to the analysis requirements, and comprehensively collect all sample factors related to production capacity based on the set scale of fractured horizontal wells in the target block, wherein the sample factors include geological factors and construction factors;

[0009] Preliminary analysis steps: Obtain the production capacity data of each fractured horizontal well, use the combined machine learning algorithm to analyze the influence weight of each factor on the production capacity of the fractured horizontal well, and preliminarily determine the preliminary influencing factors with analysis value;

[0010] The step of eliminating the influence of construction parameters: performing double normalization processing on the production capacity of wells with different fracturing levels based on the preliminary influencing construction factors in the preliminary influencing factors combined with the corresponding influence weights, so as to eliminate the influence of the inconsistency of the construction parameters of each well on the production capacity;

[0011] Steps for determining the final weights of factors: Apply the analytical algorithm to determine the secondary impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters, determine the scale parameters based on the preliminary comprehensive impact weight data, and then establish a hierarchical analysis judgment matrix and calculate and obtain the final impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters;

[0012] Steps for determining the main controlling factors: Analyze the final influence weights of each preliminary influencing geological factor, determine the target main controlling factor based on the set selection principles, and establish a correlation model between the main controlling factors and production capacity that eliminates the influence of construction parameters, so as to achieve accurate comprehensive sweet spot evaluation.

[0013] Preferably, in one embodiment, in the parameter collection step, the geological factors include but are not limited to formation porosity, permeability, water saturation, oil saturation, reservoir thickness, shale content, horizontal principal stress difference, brittleness index, Young's modulus and Poisson's ratio;

[0014] The construction factors include but are not limited to the length of the horizontal well fracturing section, the amount of fracturing fluid, the amount of sand added, the number of fracturing stages, the construction displacement, the pre-fluid ratio and the sand ratio.

[0015] Furthermore, in one embodiment, the preliminary analysis step includes the following operations:

[0016] Based on various factors, the hierarchical analysis method is used to establish a hierarchical analysis framework of factors affecting production capacity;

[0017] The grey correlation method is used to preliminarily calculate the preliminary comprehensive impact weights of various geological and construction factors on the productivity of fracturing wells;

[0018] Preliminary influencing factors are selected according to the comprehensive weight value.

[0019] Optionally, in one embodiment, in the preliminary analysis step, the process of using the grey correlation method to preliminarily calculate the preliminary comprehensive influence weights of factors on the productivity of the fracturing well includes:

[0020] The calculation results of the initial weights of the grey relational analysis were used as quantitative scaling parameters to establish a pairwise comparison matrix.

[0021] The eigenvectors of each factor corresponding to the maximum eigenroot of the pairwise comparison judgment matrix are solved, and the preliminary comprehensive impact weights of each factor relative to the production capacity are obtained through normalization.

[0022] In a preferred embodiment, the step of eliminating the influence of construction parameters includes the following operations:

[0023] A1. Establishing a corresponding set of construction influencing factors based on the preliminary influencing factors;

[0024] A2. Normalize each element of the construction influencing factors;

[0025] A3. Perform primary normalization on the production capacity of wells with different fracturing levels;

[0026] A4. Establish a construction factor impact weight set corresponding to the construction factor based on the preliminary comprehensive impact weight data calculated in the preliminary analysis step;

[0027] A5. Further secondary normalization is performed on the production capacity processed in step A3 based on the weight data of construction factors.

[0028] Furthermore, in one embodiment, the production capacity processed in step A3 is further subjected to secondary normalization processing based on the construction factor impact weight data according to the following formula:

[0029]

[0030] in,

[0031]

[0032] In the formula, is the normalized value of the jth factor of the ith sample, min(t 1j ,t 2j …t nj ) is the minimum value of the jth factor in all n samples, max(t 1j ,t 2j …t nj ) is the maximum value of the jth factor in all n samples, is the primary normalized yield value of the ith sample, Q i represents the post-fracture production of the i-th sample, min(Q1,Q2...Q n ) is the minimum output value among n samples, max(Q1,Q2...Q n ) is the maximum yield among n samples, The secondary normalized yield value of the i-th sample that eliminates the influence of construction parameters.

[0033] Preferably, in one embodiment, the step of determining the final weight of the factors includes:

[0034] B1. Establish a set of preliminary geological factors, and use grey correlation analysis and entropy method to calculate the secondary impact weights of each preliminary geological factor on production capacity after eliminating the impact of construction parameters;

[0035] B2. Calculate the average value of the secondary impact weight and the corresponding weight in the preliminary comprehensive impact weight as the scaling parameter of the geological factor;

[0036] B3. Establishing a hierarchical analysis judgment matrix based on the geological factor scaling parameters, performing pairwise comparisons on the extreme values ​​of various geological factors, and establishing a corresponding judgment matrix;

[0037] B4. Solve the maximum characteristic root of the judgment matrix and normalize the calculation results to obtain the final influence weight of each preliminary geological factor on the production capacity after double normalization.

[0038] In an optional embodiment, in the main control factor determination step, the main control construction factors that are analyzed to ultimately affect the weight determination include: reservoir thickness, permeability, porosity, horizontal principal stress difference, oil saturation and brittleness index.

[0039] Based on other aspects of the method described in any one or more of the above embodiments, the present invention further provides a storage medium storing program codes that can implement the method described in any one or more of the above embodiments.

[0040] Based on the application aspects of the method described in any one or more of the above embodiments, the present invention also provides a horizontal well fracturing main control factor analysis system that eliminates the influence of construction parameters, and the system executes the method described in any one or more of the above embodiments.

[0041] Compared with the closest prior art, the present invention also has the following beneficial effects:

[0042] The present invention provides a method and system for analyzing the main control factors of horizontal well fracturing for eliminating the influence of construction parameters. The method comprehensively collects the geological and construction factors of the production capacity of the fracturing horizontal well, uses a combined machine learning algorithm to analyze the initial influence weights of various factors on the production capacity of the fracturing horizontal well and determines the initial influence factors; performs double normalization processing on the production capacity of different wells based on the initial influencing construction factors and the influence weights; performs normalization processing on the production capacity based on the data of the initial influencing construction factors of each sample well, and eliminates the influence of the inconsistency of the construction parameters of each well on the production capacity; ensures the scientific correlation between the main control factors and the production capacity, avoids the interference of the inconsistency of the construction parameters on the production capacity calculation in the engineering application, and saves the resource consumption of the subsequent production capacity correlation calculation based on complicated factors;

[0043] The analytical algorithm is applied to determine the secondary influence weights of each preliminary geological factor on the post-processing production capacity. The hierarchical analysis judgment matrix is ​​established in combination with the preliminary comprehensive influence weights, and the final influence weights of each factor on the post-processing production capacity are calculated to determine the target main controlling factors. This scheme can provide support for the subsequent construction of a more realistic main controlling factor and production capacity correlation model, thereby achieving accurate inversion of geological sweet spots, guiding the selection of new well fracturing sections and optimal design, and facilitating the fracturing analysis and transformation optimization of oil and gas wells.

[0044] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0046] Figure 1 It is a flow chart of a method for analyzing main control factors of horizontal well fracturing to eliminate the influence of construction parameters provided by an embodiment of the present invention;

[0047] Figure 2 It is a schematic diagram of a hierarchical structure model of acquisition factors of a fracturing well in an implementation case of a method for analyzing main control factors of horizontal well fracturing to eliminate the influence of construction parameters provided in an embodiment of the present invention;

[0048] Figure 3 It is a schematic diagram of the initial influence weight results of various factors in a fracturing well of an implementation case in the horizontal well fracturing main control factor analysis method for eliminating the influence of construction parameters provided by an embodiment of the present invention;

[0049] Figure 4 It is a schematic diagram of the preliminary comprehensive influence weight results of various factors of a fracturing well in an implementation case of the method for analyzing the main control factors of horizontal well fracturing to eliminate the influence of construction parameters provided by an embodiment of the present invention;

[0050] Figure 5 It is a schematic diagram of the final influence weights of various geological factors in a fracturing well in an implementation case of the horizontal well fracturing main control factor analysis method for eliminating the influence of construction parameters provided in an embodiment of the present invention;

[0051] Figure 6 It is a schematic diagram of a neural network computing model for productivity correlation in a method for analyzing main control factors of horizontal well fracturing to eliminate the influence of construction parameters provided by an embodiment of the present invention;

[0052] Figure 7 It is a schematic diagram of the sweetness value distribution along the horizontal well section of a fracturing well in an implementation case of the horizontal well fracturing main control factor analysis method for eliminating the influence of construction parameters provided in an embodiment of the present invention;

[0053] Figure 8 It is a schematic diagram of the overall sweetness value distribution of a block in an implementation case of the method for analyzing the main control factors of horizontal well fracturing to eliminate the influence of construction parameters provided in an embodiment of the present invention;

[0054] Fig. 9It is a structural schematic diagram of a horizontal well fracturing main control factor analysis system for eliminating the influence of construction parameters provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will describe the implementation methods of the present invention in detail in conjunction with the accompanying drawings and embodiments, so that the implementers of the present invention can fully understand how the present invention applies technical means to solve technical problems and achieve the implementation process of technical effects and implement the present invention specifically according to the above implementation process. It should be noted that as long as there is no conflict, the various embodiments and various features of the embodiments in the present invention can be combined with each other, and the technical solutions formed are all within the protection scope of the present invention.

[0056] Although the flowcharts describe the operations as sequential processes, many of the operations may be performed in parallel, concurrently, or simultaneously. The order of the operations may be rearranged. A process may be terminated when its operations are completed, but may also have additional steps not included in the accompanying drawings. A process may correspond to a method, function, procedure, subroutine, subprogram, etc.

[0057] Computer devices include user devices and network devices. Among them, user devices or clients include but are not limited to computers, smart phones, PDAs (Personal Digital Assistants), etc.; network devices include but are not limited to a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Computer devices can be run alone to implement the present invention, or they can be connected to the network and implement the present invention through interactive operations with other computer devices in the network. The network where the computer device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, VPN network, etc.

[0058] The terms "first", "second", etc. may be used herein to describe various units, but these units should not be limited by these terms, and these terms are used only to distinguish one unit from another unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items. When a unit is referred to as being "connected" or "coupled" to another unit, it can be directly connected or coupled to the other unit, or there can be intermediate units.

[0059] The terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms "one", "one" and "item" used herein are also intended to include plural numbers. It should also be understood that the terms "include" and / or "comprise" used herein specify the existence of stated features, integers, steps, operations, units and / or components, without excluding the existence or addition of one or more other features, integers, steps, operations, units, components and / or combinations thereof.

[0060] The post-fracture production capacity of horizontal wells is affected by a variety of geological factors and construction factors, and there are complex correlations between the factors; therefore, when analyzing the impact of geological factors on the production capacity of fractured wells based on the data of already fractured wells, the differences in the construction parameters of already fractured wells will interfere with the analysis and calculation results. Before implementing fracturing construction, the original geological potential of the block and the drilled horizontal wells is usually the main consideration for fracturing well selection and section selection. Formulating a fracturing construction plan based on the geological high potential section can effectively improve the fracturing transformation effect. Therefore, when analyzing the impact of the main geological control factors on the fracturing effect of horizontal wells based on the data of already fractured wells, and establishing a geological sweet spot evaluation model, the influence of construction parameters on the evaluation model should be eliminated.

[0061] At present, the method of using killed well data to analyze the influence of the main geological factors of horizontal wells on the productivity of fractured wells has obvious limitations in practical application, mainly manifested in:

[0062] (1) Some technologies evaluate all geological factors and construction factors together, and uniformly rank them to determine the main controlling factors. For example, patent document CN202011392976.X provides a geological-engineering three-dimensional coupled tight oil and gas horizontal well production detection method, which establishes a tight oil and gas geological-engineering coupled data set along the horizontal well trajectory space, extracts and classifies the tight oil and gas horizontal well production characteristic data, and screens the geological-engineering coupled main controlling factors of the tight oil and gas horizontal well production effect and detects the control effect characteristics; patent document CN2016108294 57.2 provides a method for analyzing the weight of the main controlling factors of oilfield production. According to the daily production data of production wells in the actual blocks of the oilfield and the factors affecting production, a database is established, a comparison matrix of the factors affecting production is constructed, the weight of the factors affecting production is calculated, and a consistency test is passed; the document "Main controlling factors of production capacity of shale oil horizontal wells in Qingcheng Oilfield, Ordos Basin and optimization of development countermeasures" uses more than 180 horizontal wells in Qingcheng Oilfield as samples, and uses the grey correlation method and random forest algorithm to systematically analyze the influence of geological and fracturing construction parameters on production capacity, and clarify the main controlling factors of single well production capacity. None of these schemes consider the influence of mutual interference between geological factors and construction factors on the evaluation results, and it is impossible to establish an accurate correlation model between the main controlling geological factors and production capacity and a reliable fracturing sweet spot calculation model based on the main controlling geological factors.

[0063] (2) Some technologies consider the influence of geological factors and construction factors on the fracturing effect and construct an evaluation model. For example, patent document CN202011466585.8 provides a comprehensive geological-engineering classification evaluation method for low permeability reservoirs. The grey correlation method is used to obtain the main controlling factors of reservoir geology that affect the fracturing effect of low permeability reservoirs, and the principal component analysis method is used to construct the geological classification evaluation index of low permeability reservoirs. Based on the main controlling factors of geomechanics, the analytic hierarchy process is used to construct the engineering classification evaluation index of low permeability reservoirs. The document "Study on the Main Controlling Factors of Volume Fracturing Capacity of Horizontal Wells in the Ma X Block" first applies statistical methods to conduct a qualitative analysis of the influence of each factor on the production, and then uses the grey correlation method and random forest method to obtain the main controlling geological factors and main controlling engineering factors that affect the production capacity of fracturing wells. At present, the method of classifying and analyzing the influence of geological factors and construction factors on the production capacity of fracturing wells cannot eliminate the influence of construction parameters on production when establishing geological parameter evaluation indicators. Different construction parameters of wells that have been fracturing will interfere with the evaluation results, and it is impossible to establish an accurate geological sweet spot calculation model.

[0064] In summary, the current research on the main influencing factors of horizontal well fracturing effect and clarifying the influence of the main controlling geological factors on the production capacity of fracturing wells are the key to improving the fracturing effect. However, the application of well data for analysis and research is often interfered by inconsistent construction parameters. Therefore, it is necessary to screen the main controlling geological factors that affect the production capacity of fracturing wells on the basis of eliminating the influence of construction parameters on the fracturing effect of horizontal wells, establish a geological sweet spot evaluation calculation model, provide guidance for the fracturing section selection and optimization design of new wells, and maximize the fracturing transformation effect.

[0065] In order to solve the above problems and improve the fracturing transformation effect, the present invention provides a method and system for analyzing the main controlling factors of horizontal well fracturing that eliminates the influence of construction parameters, including weight analysis of production capacity influencing factors based on a combined machine learning algorithm, production capacity normalization processing that eliminates the influence of construction parameters, weight analysis of the influence of geological factors on normalized production capacity, establishment of a model associating the main controlling geological factors with production capacity, establishment of a comprehensive sweet spot calculation model, and sweet spot evaluation.

[0066] This method analyzes the weights of the impact of geological and construction factors on production capacity, normalizes the production capacity based on construction data, eliminates the impact of construction parameters on post-fracturing production capacity, obtains the main controlling geological factors affecting production capacity, establishes a correlation model between the main controlling geological factors and normalized production capacity, realizes the accurate calculation of sweet spots along horizontal well sections, evaluates the regional sweet spot distribution, and provides guidance for repeated fracturing of old wells and fracturing section selection of new wells.

[0067] Next, the detailed process of the method of the embodiment of the present invention is described in detail based on the accompanying drawings. The steps shown in the flowchart of the accompanying drawings can be executed in a computer system including a set of computer executable instructions. Although the logical order of each step is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0068] Embodiment 1:

[0069] Figure 1 FIG. 1 is a flow chart showing a method for analyzing main control factors of horizontal well fracturing to eliminate the influence of construction parameters provided in the first embodiment of the present invention, referring to FIG. Figure 1 It can be seen that the method includes the following steps.

[0070] Parameter collection step: selecting a target block based on analysis requirements, and comprehensively collecting all sample factors that may be associated with production capacity based on a set scale of fractured horizontal wells in the target block, the sample factors including geological factors and construction factors;

[0071] Preliminary analysis steps: Obtain the production capacity data of each fractured horizontal well, use the combined machine learning algorithm to analyze the influence weight of each factor on the production capacity of the fractured horizontal well, and preliminarily determine the preliminary influencing factors with analysis value;

[0072] The step of eliminating the influence of construction parameters: performing double normalization processing on the production capacity of wells with different fracturing levels based on the preliminary influencing construction factors in the preliminary influencing factors combined with the corresponding influence weights, so as to eliminate the influence of the inconsistency of the construction parameters of each well on the production capacity;

[0073] Steps for determining the final weights of factors: Apply the analytical algorithm to determine the secondary impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters, determine the scale parameters based on the preliminary comprehensive impact weight data, and then establish a hierarchical analysis judgment matrix and calculate and obtain the final impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters;

[0074] Steps for determining the main controlling factors: Analyze the final influence weights of each preliminary influencing geological factor, determine the target main controlling factor based on the set selection principles, and establish a correlation model between the main controlling factors and production capacity that eliminates the influence of construction parameters, so as to achieve accurate comprehensive sweet spot evaluation.

[0075] The horizontal well fracturing main controlling factor analysis method of the embodiment of the present invention adopts a specific logic to normalize the production capacity based on the construction data, effectively eliminates the influence of the construction parameters on the post-fracturing production capacity, obtains the main controlling geological factors affecting the production capacity, and then based on the geological main controlling factors, applies the BP artificial neural network method to establish a sweet spot prediction model, so as to realize the intelligent and high-precision prediction and display of the overall fracturing geological sweet spots along the well and the block of the horizontal well; it can realize the accurate calculation of the sweet spots along the horizontal well section, obtain the real and reliable regional sweet spot distribution evaluation results, and provide better guidance for repeated fracturing of old wells and the selection of fracturing sections for new wells.

[0076] The embodiment of the present invention first analyzes the preliminary influence weights of various geological and construction factors on the production capacity of fracturing wells based on the hierarchical analysis method, grey correlation analysis and machine learning algorithm, and preliminarily selects the primary controlling geological and construction factors.

[0077] Preferably, in one embodiment, in the parameter collection step, the geological factors include but are not limited to formation porosity, permeability, water saturation, oil saturation, reservoir thickness, mud content, horizontal principal stress difference, brittleness index, Young's modulus and Poisson's ratio; the construction factors include but are not limited to horizontal well fracturing section length, fracturing fluid volume, sand addition volume, number of fracturing stages, construction displacement, pre-fluid ratio and sand ratio.

[0078] Next, the production capacity data of each fractured horizontal well is obtained through preliminary analysis steps, and the combined machine learning algorithm is used to analyze the influence weight of each factor on the production capacity of fractured horizontal wells, and the preliminary influencing factors with analysis value are preliminarily determined.

[0079] Furthermore, in an optional embodiment, the preliminary analysis step includes the following operations:

[0080] Based on various factors, the hierarchical analysis method is used to establish a hierarchical analysis framework of factors affecting production capacity;

[0081] The grey correlation method is used to preliminarily calculate the preliminary comprehensive impact weights of various geological and construction factors on the productivity of fracturing wells;

[0082] Preliminary influencing factors are selected according to the comprehensive weight value.

[0083] In practical application, the geological and construction factors of the horizontal wells in the block are first collected comprehensively. For example, 30 fracturing wells in the S block of the northwest tight oil reservoir are used as samples, and 17 geological and construction parameters are extracted. The corresponding multi-factor hierarchical structure model is as follows: Figure 2 shown.

[0084] Specifically, in one embodiment, in the preliminary analysis step, the process of using the grey correlation method to preliminarily calculate the preliminary comprehensive influence weights of factors on the productivity of the fracturing well includes:

[0085] The calculation results of the initial weights of the grey relational analysis were used as quantitative scaling parameters to establish a pairwise comparison matrix.

[0086] The eigenvectors of each factor corresponding to the maximum eigenroot of the pairwise comparison judgment matrix are solved, and the preliminary comprehensive impact weights of each factor relative to the production capacity are obtained through normalization.

[0087] In actual application, the hierarchical analysis method is used to establish a hierarchical analysis framework of factors affecting production capacity. The initial weight calculation results of grey correlation analysis are used as quantitative scaling parameters to establish a pairwise comparison matrix. The eigenvectors of each factor corresponding to the maximum eigenroot of the pairwise comparison judgment matrix are solved, and the comprehensive preliminary weight values ​​of each factor are obtained after normalization processing. The calculation results can also be verified by the consistency test method.

[0088] Taking 30 fracturing wells in Block S of the Northwest tight oil reservoir as an example, the grey correlation method is used to preliminarily calculate the initial influence weights of the geological and construction factors of 30 fracturing wells in Block S of the Northwest tight oil reservoir on the production capacity of the fracturing wells. The calculation results are shown in Figure 3 .

[0089] Then, the initial weight calculation result of grey relational analysis is used as the quantitative scale parameter to establish a pairwise comparison matrix, solve the eigenvector of each factor corresponding to the maximum eigenvalue of the pairwise comparison judgment matrix, and obtain the comprehensive weight value of each factor after normalization. Figure 4 and passed the consistency test.

[0090] Furthermore, it is necessary to normalize the production capacity according to the preliminary influencing construction factor data of each sample well to eliminate the impact of the inconsistency of the construction parameters of each well on the production capacity. Therefore, the construction parameter impact elimination step is performed: based on the preliminary influencing construction factors in the preliminary influencing factors combined with the corresponding impact weights, the production capacity of wells with different fracturing levels is double normalized to eliminate the impact of the inconsistency of the construction parameters of each well on the production capacity.

[0091] Preferably, in one embodiment, the step of eliminating the influence of construction parameters includes the following operations:

[0092] A1. Establishing a corresponding set of construction influencing factors based on the preliminary influencing factors;

[0093] A2. Normalize each element of the construction influencing factors;

[0094] A3. Perform primary normalization on the production capacity of wells with different fracturing levels;

[0095] A4. Establish a construction factor impact weight set corresponding to the construction factor based on the preliminary comprehensive impact weight data calculated in the preliminary analysis step;

[0096] A5. Further secondary normalization is performed on the production capacity processed in step A3 based on the weight data of construction factors.

[0097] Among them, in step A1, according to the preliminary comprehensive influence weight calculation result in the preliminary analysis step, the preliminary influencing construction factors affecting the production capacity of the fracturing sample well are determined, and the corresponding construction influencing factor set is established:

[0098]

[0099] Among them, t nm It represents the mth preliminary influencing construction factor of the nth sample well, where n is the number of samples and m is the number of preliminary influencing construction factors.

[0100] In actual application, according to the calculation results of the preliminary comprehensive weight values, the main control construction factors affecting the production capacity of the fracturing well are determined to include the amount of fracturing fluid, the length of the horizontal well fracturing section, the number of fracturing sections, and the amount of sand added.

[0101] Then the main control construction factors and production capacity are normalized:

[0102]

[0103] In the formula, is the normalized value of the jth factor of the ith sample, min(t 1j ,t 2j …t nj ) is the minimum value of the jth factor in all samples, max(t 1j ,t 2j ...t nj ) is the maximum value of the jth factor in all samples.

[0104] The production capacity of wells with different fracturing levels is further normalized:

[0105]

[0106] In the formula, is the primary normalized yield value of the ith sample, Q i represents the post-fracture production of the i-th sample, min(Q1,Q2...Q n ) is the minimum output value among n samples, max(Q1,Q2...Q n ) is the maximum yield among n samples.

[0107] According to the preliminary comprehensive impact weight calculation results in the preliminary analysis step, the construction factor impact weight set ω is established:

[0108] ω=[ω1 ω2 … ω j ] (3)

[0109] Among them, ω j It represents the weight value of the jth initial construction factor affecting the original production capacity.

[0110] In order to eliminate the influence of construction parameters, the capacity is further normalized according to the following formula:

[0111]

[0112] In the formula, The secondary normalized yield value of the i-th sample that eliminates the influence of construction parameters.

[0113] In actual application, since there are multiple sample wells, in order to effectively save calculation time, a mathematical model can be established to achieve the steps of eliminating the influence of construction parameters. Then, the production of 30 fracturing sample wells is normalized using the mathematical model established specifically, eliminating the influence of construction parameters on the production capacity of fracturing wells.

[0114] Furthermore, the final weight determination step of the execution factors is carried out, and the analysis algorithm is applied to determine the secondary impact weights of each preliminary geological factor on the production capacity after eliminating the influence of construction parameters. The scale parameters are determined in combination with the preliminary comprehensive impact weight data, and then a hierarchical analysis judgment matrix is ​​established and the final impact weights of each preliminary geological factor on the production capacity after eliminating the influence of construction parameters are calculated.

[0115] In a preferred embodiment, the step of determining the final weight of the factors includes:

[0116] B1. Establish a set of preliminary geological factors, and use grey correlation analysis and entropy method to calculate the secondary impact weights of each preliminary geological factor on production capacity after eliminating the impact of construction parameters;

[0117] B2. Calculate the average value of the secondary impact weight and the corresponding weight in the preliminary comprehensive impact weight as the scaling parameter of the geological factor;

[0118] B3. Establishing a hierarchical analysis judgment matrix based on the geological factor scaling parameters, performing pairwise comparisons on the extreme values ​​of various geological factors, and establishing a corresponding judgment matrix;

[0119] B4. Solve the maximum characteristic root of the judgment matrix and normalize the calculation results to obtain the final influence weight of each preliminary geological factor on the production capacity after double normalization.

[0120] This embodiment calculates the influence weight of each geological factor on the normalized production capacity by comprehensively applying the analytic hierarchy process, grey correlation analysis and entropy method to determine the main controlling geological factors.

[0121] Specifically, in an optional embodiment, a geological factor set G is established:

[0122]

[0123] Among them, g nm It represents the mth preliminary geological factor affecting the nth sample well, where n is the number of samples and m is the number of preliminary factors affecting construction.

[0124] Normalize the geological factors:

[0125]

[0126] Based on this, the normalized geological factor set is characterized as follows:

[0127]

[0128] Establish a preliminary set of influence weights for geological factors:

[0129]

[0130] Among them, ω m It represents the weight value of the impact of the mth preliminary geological factor on the original production capacity.

[0131] Then, the grey correlation analysis and entropy method were used to calculate the normalized capacity of each initial geological factor after eliminating the influence of construction parameters. The weight of influence;

[0132] Specifically, in this embodiment, the average value of the weight values ​​calculated by the two methods is taken as the scaling parameter, a hierarchical analysis judgment matrix is ​​established, the extreme values ​​of each factor are compared pairwise, a judgment matrix is ​​established, the maximum characteristic root is solved, and the calculation results are normalized to obtain the influence weight of each preliminary geological factor on the production capacity after eliminating the construction factor, and the main controlling geological factor is determined according to the weight value sorting; the final influence weight set of each preliminary geological factor on the production capacity after eliminating the construction factor is as follows:

[0133]

[0134] in, It represents the final impact weight of the mth initial geological factor on the production capacity after eliminating the construction factor.

[0135] In practical application, taking 30 fracturing wells in Block S of the tight oil reservoir in Northwest China as an example, the grey correlation analysis method and entropy value method are used to calculate the influence weights of each preliminary geological factor on the normalized production capacity after eliminating the influence of construction parameters, and then the average value of the weight values ​​calculated by the two methods is taken as the scaling parameter to establish a hierarchical analysis judgment matrix, compare the extreme values ​​of each factor pairwise, establish a judgment matrix, solve the maximum characteristic root, and normalize the calculation results to obtain the final influence weights of each preliminary geological factor on the production capacity after eliminating the construction factors, such as Figure 5 shown.

[0136] Furthermore, the main controlling factor determination step is executed to analyze the final influence weights of each preliminary influencing geological factor, and the target main controlling factor is determined in combination with the set selection principle, so as to establish a correlation model between the main controlling factors and production capacity that eliminates the influence of construction parameters, and realize accurate comprehensive sweet spot evaluation.

[0137] In an optional embodiment, in the main control factor determination step, the main control construction factors that are analyzed to ultimately affect the weight determination include: reservoir thickness, permeability, porosity, horizontal principal stress difference, oil saturation and brittleness index.

[0138] In actual application, the main control factor analysis method of horizontal well fracturing effect based on the embodiment of the present invention can accurately invert the geological sweet spot on the basis of eliminating the interference of construction factors, and guide the new well fracturing section selection and optimization design.

[0139] Specifically, in an optional embodiment, a correlation model between the main control factors and the production capacity is established to eliminate the influence of the construction parameters, and a process of achieving accurate comprehensive sweet spot evaluation includes:

[0140] The BP artificial neural network method is used to establish the correlation model between the selected main control factors and the production capacity after eliminating the influence of construction parameters;

[0141] Based on the association model, a comprehensive fracturing sweetness calculation model for each fracturing section of the horizontal well is established to evaluate the distribution of sweet spots along the horizontal well section, and then interpolate to determine the overall sweet spot distribution of the block.

[0142] Specifically, when the BP neural network system is used to establish a normalized production correlation model that eliminates the influence of the main geological factors and construction parameters, the established BP neural network system structure is as follows: Figure 6 As shown in the figure, the input layer is the main controlling geological factors, the hidden layer is the intermediate calculation unit, and the output layer is the calculated normalized yield. Through the cyclic forward propagation calculation and the reverse propagation calculation, the calculated normalized yield gradually approaches the real normalized yield value. The calculation is stopped when the error value is <ε, and ε can be 0.001-0.05. At this time, the correlation model between each geological factor and yield can be obtained, as follows:

[0143]

[0144] In the formula, It represents the weight value of the jth influencing factor after being processed by the BP artificial neural network. Through the forward and backward propagation of the BP artificial neural network, the calculated normalized output is effectively approached to the real normalized output value. The calculation is stopped when the error value is less than ε. i It represents the correction constant of the i-th sample after the BP artificial neural network stops calculating. Among them, l is a naming symbol, which is used to distinguish the weight calculation results of each factor before and the weight value after the forward propagation and reverse propagation of the BP artificial neural network, so that the calculated normalized output gradually approaches the true normalized output value, and the error value <ε stops calculating.

[0145] Furthermore, the establishment of a comprehensive sweetness calculation model and the evaluation of sweet spots can be realized. A comprehensive fracturing sweetness calculation model can be established based on the production capacity correlation model to evaluate the fracturing sweet spots along the horizontal well section and the overall sweet spot distribution of the block.

[0146] Preferably, in one embodiment, a comprehensive sweetness value calculation model can be established based on the established correlation model between various geological factors and yield.

[0147] In practical application, assuming that a horizontal well is divided into r fracturing stages, the comprehensive sweetness value S of the kth fracturing stage is k It can be characterized as follows:

[0148]

[0149] In the formula, j represents the jth main controlling influencing factor, and m represents the number of main controlling influencing factors; Represents the normalized value of the jth main controlling factor of the kth fracturing stage.

[0150] In actual application, the sweetness value along the horizontal well section can be calculated based on the established sweet spot evaluation model; the sweetness values ​​of all fracturing wells in the block can be further calculated, and the sweetness value distribution of the entire block can be obtained by interpolation.

[0151] Taking 30 fractured wells in Block S of the tight oil reservoir in Northwest China as an example, the BP neural network system was used to establish a normalized production correlation model that eliminated the influence of the main geological factors and construction parameters. Based on the production capacity correlation model, a comprehensive sweetness value calculation model was established. The sweetness value of the HW1 horizontal well along the horizontal well section is shown in Figure 2. Figure 7 ; Calculate the sweetness value of the fracturing well in block S, and interpolate to obtain the sweetness value distribution of the entire block, such as Figure 8 shown.

[0152] The present invention aims at the problem of interference of construction factors in the process of analyzing the influence of geological factors on the production capacity of fracturing wells based on the data of wells that have been pressed, and provides a method for analyzing the main control factors of horizontal well fracturing effect to eliminate the influence of construction parameters. The weights of the influence of various geological and construction factors on the production capacity of fracturing wells are analyzed based on the hierarchical analysis method, grey correlation analysis and machine learning algorithm; the production capacity is normalized according to the main control construction factor data of each sample well to eliminate the influence of the inconsistency of the construction parameters of each well on the production capacity; the BP artificial neural network method is used to establish the correlation model between the main control geological factors and the production capacity and the comprehensive sweetness calculation model of fracturing. The horizontal well fracturing effect evaluation method designed by the present invention can accurately invert the geological sweet spot on the basis of eliminating the interference of construction factors, and guide the selection and optimization design of new well fracturing.

[0153] For the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0154] It should be pointed out that in other embodiments of the present invention, the method can also obtain a new method for analyzing the main controlling factors of horizontal well fracturing effects by combining one or several of the above embodiments, so as to achieve accurate analysis of the factors affecting horizontal well fracturing and optimization of fracturing effect transformation.

[0155] It should be noted that, based on the method in any one or more of the above embodiments of the present invention, the present invention also provides a storage medium, which stores program codes that can implement the method as described in any one or more of the above embodiments, and when the code is executed by the operating system, it can implement the above-mentioned method for analyzing the main controlling factors of horizontal well fracturing that eliminates the influence of construction parameters.

[0156] Embodiment 2:

[0157] The method is described in detail in the embodiments disclosed in the present invention. The method of the present invention can be implemented by various forms of devices or systems. Therefore, based on other aspects of the method described in any one or more embodiments, the present invention also provides a horizontal well fracturing main control factor analysis system for eliminating the influence of construction parameters. The system is used to execute the horizontal well fracturing main control factor analysis method for eliminating the influence of construction parameters described in any one or more embodiments. Specific embodiments are given below for detailed description.

[0158] Specifically, Fig. 9FIG. 4 is a schematic diagram showing a structure of a main control factor analysis system for horizontal well fracturing to eliminate the influence of construction parameters provided in an embodiment of the present invention. Fig. 9 As shown, the system includes the following structure.

[0159] A parameter collection module is configured to select a target block according to analysis requirements, and comprehensively collect all sample factors associated with production capacity based on a set scale of fractured horizontal wells in the target block, wherein the sample factors include geological factors and construction factors;

[0160] A preliminary analysis module, which is configured to obtain the production capacity data of each fractured horizontal well, analyze the influence weight of each factor on the production capacity of the fractured horizontal well by using a combined machine learning algorithm, and preliminarily determine the preliminary influencing factors with analysis value;

[0161] A construction parameter influence elimination module, which is configured to perform double normalization processing on the production capacity of wells with different fracturing levels based on the preliminary construction influence factors in the preliminary influence factors combined with the corresponding influence weights, so as to eliminate the influence of the inconsistency of the construction parameters of each well on the production capacity;

[0162] The module for determining the final weight of factors is configured to apply an analytical algorithm to determine the secondary impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters, determine the scale parameters in combination with the preliminary comprehensive impact weight data, and then establish a hierarchical analysis judgment matrix and calculate and obtain the final impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters;

[0163] The main controlling factor determination module is configured to analyze the final influence weights of each preliminary influencing geological factor, determine the target main controlling factor in combination with the set selection principle, so as to establish a correlation model between the main controlling factor and the production capacity that eliminates the influence of the construction parameters, and realize accurate comprehensive sweet spot evaluation.

[0164] Preferably, the horizontal well fracturing main control factor analysis system for eliminating the influence of construction parameters provided by the embodiment of the present invention implements the steps or operations of the method described in the embodiment of the present invention based on a computer system. In one embodiment, the geological factors comprehensively collected by the parameter collection module include but are not limited to formation porosity, permeability, water saturation, oil saturation, reservoir thickness, mud content, horizontal principal stress difference, brittleness index, Young's modulus and Poisson's ratio; the collected construction factors include but are not limited to horizontal well fracturing section length, fracturing fluid volume, sand addition volume, number of fracturing stages, construction displacement, pre-fluid ratio and sand ratio.

[0165] Furthermore, in one embodiment, the preliminary analysis module is configured to perform the following operations:

[0166] Based on various factors, the hierarchical analysis method is used to establish a hierarchical analysis framework of factors affecting production capacity;

[0167] The grey correlation method is used to preliminarily calculate the preliminary comprehensive impact weights of various geological and construction factors on the productivity of fracturing wells;

[0168] Preliminary influencing factors are selected according to the comprehensive weight value.

[0169] Optionally, in one embodiment, the preliminary analysis module uses the grey correlation method to preliminarily calculate the preliminary comprehensive impact weights of factors on the productivity of the fracturing well according to the following operations:

[0170] The calculation results of the initial weights of the grey relational analysis were used as quantitative scaling parameters to establish a pairwise comparison matrix.

[0171] The eigenvectors of each factor corresponding to the maximum eigenroot of the pairwise comparison judgment matrix are solved, and the preliminary comprehensive impact weights of each factor relative to the production capacity are obtained through normalization.

[0172] Furthermore, in a preferred embodiment, the construction parameter influence elimination module is configured to perform the following operations:

[0173] A1. Establishing a corresponding set of construction influencing factors based on the preliminary influencing factors;

[0174] A2. Normalize each element of the construction influencing factors;

[0175] A3. Perform primary normalization on the production capacity of wells with different fracturing levels;

[0176] A4. Establish a construction factor impact weight set corresponding to the construction factor based on the preliminary comprehensive impact weight data calculated in the preliminary analysis step;

[0177] A5. Further secondary normalization is performed on the production capacity processed in step A3 based on the weight data of construction factors.

[0178] Specifically, in an optional embodiment, the construction parameter influence elimination module further performs secondary normalization processing on the production capacity processed in step A3 based on the construction factor influence weight data according to the following formula:

[0179]

[0180] in,

[0181]

[0182] In the formula, is the normalized value of the jth factor of the ith sample, min(t 1j ,t 2j …t nj) is the minimum value of the jth factor in all n samples, max(t 1j ,t 2j …t nj ) is the maximum value of the jth factor in all n samples; is the primary normalized yield value of the ith sample, Q i represents the post-fracture production of the i-th sample, min(Q1,Q2...Q n ) is the minimum output value among n samples, max(Q1,Q2...Q n ) is the maximum yield among n samples; The secondary normalized yield value of the i-th sample that eliminates the influence of construction parameters.

[0183] Furthermore, in an optional embodiment, the factor final weight determination module is configured to perform the following operations:

[0184] B1. Establish a set of preliminary geological factors, and use grey correlation analysis and entropy method to calculate the secondary impact weights of each preliminary geological factor on production capacity after eliminating the impact of construction parameters;

[0185] B2. Calculate the average value of the secondary impact weight and the corresponding weight in the preliminary comprehensive impact weight as the scaling parameter of the geological factor;

[0186] B3. Establishing a hierarchical analysis judgment matrix based on the geological factor scaling parameters, performing pairwise comparisons on the extreme values ​​of various geological factors, and establishing a corresponding judgment matrix;

[0187] B4. Solve the maximum characteristic root of the judgment matrix and normalize the calculation results to obtain the final influence weight of each preliminary geological factor on the production capacity after double normalization.

[0188] Based on the above embodiment, preferably, the main control factors determining module analyzes the main control construction factors that ultimately affect the weight determination, including: reservoir thickness, permeability, porosity, horizontal principal stress difference, oil saturation and brittleness index.

[0189] In the horizontal well fracturing main control factor analysis system for eliminating the influence of construction parameters provided by the embodiment of the present invention, each module or unit structure can operate independently or in combination according to actual parameter processing requirements or calculation analysis requirements to achieve corresponding technical effects.

[0190] It should be understood that the embodiments disclosed in the present invention are not limited to the specific structures, processing steps or materials disclosed herein, but should be extended to equivalent substitutions of these features understood by ordinary technicians in the relevant field. It should also be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not meant to be limiting.

[0191] The "one embodiment" mentioned in the specification means that a particular feature, structure or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention. Therefore, the phrase "one embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0192] Although the embodiments disclosed in the present invention are as above, the above contents are only embodiments adopted for facilitating the understanding of the present invention and are not intended to limit the present invention. Any technician in the technical field to which the present invention belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present invention, but the patent protection scope of the present invention shall still be subject to the scope defined in the attached claims.

Claims

1. A method for analyzing main control factors of horizontal well fracturing to eliminate the influence of construction parameters, characterized in that: The method comprises: Parameter collection step: select a target block according to the analysis requirements, and comprehensively collect all sample factors related to production capacity based on the set scale of fractured horizontal wells in the target block, wherein the sample factors include geological factors and construction factors; Preliminary analysis steps: Obtain the production capacity data of each fractured horizontal well, use the combined machine learning algorithm to analyze the influence weight of each factor on the production capacity of the fractured horizontal well, and preliminarily determine the preliminary influencing factors with analysis value; The step of eliminating the influence of construction parameters: performing double normalization processing on the production capacity of wells with different fracturing levels based on the preliminary influencing construction factors in the preliminary influencing factors combined with the corresponding influence weights, so as to eliminate the influence of the inconsistency of the construction parameters of each well on the production capacity; Steps for determining the final weights of factors: Apply the analytical algorithm to determine the secondary impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters, determine the scale parameters based on the preliminary comprehensive impact weight data, and then establish a hierarchical analysis judgment matrix and calculate and obtain the final impact weights of each preliminary geological factor on the production capacity after eliminating the impact of construction parameters; Steps for determining the main controlling factors: Analyze the final influence weights of each preliminary influencing geological factor, determine the target main controlling factor based on the set selection principles, and establish a correlation model between the main controlling factors and production capacity that eliminates the influence of construction parameters, so as to achieve accurate comprehensive sweet spot evaluation.

2. The method according to claim 1, characterized in that In the parameter collection step, the geological factors include but are not limited to formation porosity, permeability, water saturation, oil saturation, reservoir thickness, shale content, horizontal principal stress difference, brittleness index, Young's modulus and Poisson's ratio; The construction factors include but are not limited to the length of the horizontal well fracturing section, the amount of fracturing fluid, the amount of sand added, the number of fracturing stages, the construction displacement, the pre-fluid ratio and the sand ratio.

3. The method according to claim 1, characterized in that The initial analysis step includes the following operations: Based on various factors, the hierarchical analysis method is used to establish a hierarchical analysis framework of factors affecting production capacity; The grey correlation method is used to preliminarily calculate the preliminary comprehensive impact weights of various geological and construction factors on the productivity of fracturing wells; Preliminary influencing factors are selected according to the comprehensive weight value.

4. The method according to claim 3, characterized in that In the preliminary analysis step, the process of using the grey correlation method to preliminarily calculate the preliminary comprehensive impact weights of factors on the productivity of fracturing wells includes: The calculation results of the initial weights of the grey relational analysis were used as quantitative scaling parameters to establish a pairwise comparison matrix. The eigenvectors of each factor corresponding to the maximum eigenroot of the pairwise comparison judgment matrix are solved, and the preliminary comprehensive impact weights of each factor relative to the production capacity are obtained through normalization.

5. The method according to claim 1, characterized in that The construction parameter influence elimination step includes the following operations: A1. Establishing a corresponding set of construction influencing factors based on the preliminary influencing factors; A2. Normalize each element of the construction influencing factors; A3. Perform primary normalization on the production capacity of wells with different fracturing levels; A4. Establish a construction factor impact weight set corresponding to the construction factor based on the preliminary comprehensive impact weight data calculated in the preliminary analysis step; A5. Further secondary normalization is performed on the production capacity processed in step A3 based on the weight data of construction factors.

6. The method according to claim 5, characterized in that The capacity processed in step A3 is further normalized in the second level based on the construction factor impact weight data according to the following formula: in, In the formula, is the normalized value of the jth factor of the ith sample, min(t 1j ,t 2j …t nj ) is the minimum value of the jth factor in all n samples, max(t 1j ,t 2j …t nj ) is the maximum value of the jth factor in all n samples, is the primary normalized yield value of the ith sample, Q i represents the post-fracture production of the i-th sample, min(Q1,Q2...Q n ) is the minimum output value among n samples, max(Q1,Q2...Q n ) is the maximum yield among n samples, The secondary normalized yield value of the i-th sample that eliminates the influence of construction parameters.

7. The method according to claim 1, characterized in that The final weight determination step of the factors includes: B1. Establish a set of preliminary geological factors, and use grey correlation analysis and entropy method to calculate the secondary impact weights of each preliminary geological factor on production capacity after eliminating the impact of construction parameters; B2. Calculate the average value of the secondary impact weight and the corresponding weight in the preliminary comprehensive impact weight as the scaling parameter of the geological factor; B3. Establishing a hierarchical analysis judgment matrix based on the geological factor scaling parameters, performing pairwise comparisons on the extreme values ​​of various geological factors, and establishing a corresponding judgment matrix; B4. Solve the maximum characteristic root of the judgment matrix and normalize the calculation results to obtain the final influence weight of each preliminary geological factor on the production capacity after double normalization.

8. The method according to claim 1, characterized in that In the main control factor determination step, the main control construction factors that ultimately affect the weight determination are analyzed, including: reservoir thickness, permeability, porosity, horizontal principal stress difference, oil saturation and brittleness index.

9. A storage medium, characterized in that: The storage medium stores program codes that can implement the method as claimed in any one of claims 1 to 8.

10. A horizontal well fracturing main control factor analysis system for eliminating the influence of construction parameters, characterized in that: The system executes the method according to any one of claims 1 to 8.

Images