Fuzzy classification-based shale oil yield main control factor optimization method and system

Abstract

The invention discloses a shale oil yield main control factor optimization method and system based on fuzzy classification, and the method comprises the steps: carrying out the collection and data cleaning of a plurality of basic sample data, and building a sample set through the cleaned sample data; wherein the basic sample data comprises characteristic parameters influencing the shale oil yield and target parameters corresponding to the characteristic parameters; performing category classification on each piece of sample data in the sample set by adopting a fuzzy classification method, and respectively drawing a mean value change trend chart of each characteristic parameter in each category of sample data under the condition of different classification numbers so as to analyze the correlation between each characteristic parameter and the category under the condition of different classification numbers; and drawing a relation curve between each characteristic parameter in each type of sample data and the corresponding target parameter, determining the correlation between each characteristic parameter and the corresponding target parameter, carrying out sorting, and selecting the characteristic parameter with high correlation as a main control factor influencing the shale oil yield.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas production, and in particular to a method and system for optimizing main controlling factors of shale oil production based on fuzzy classification. Background Art

[0002] Shale oil is a very important unconventional oil and gas resource. China's shale oil resources are very rich, ranking among the top in the world, and have very broad development prospects. However, the pore types and complex structures of shale oil reservoirs are diverse, and the occurrence states and flow mechanisms of shale oil are diverse, resulting in low shale oil recovery rates. There are many factors that affect shale oil production, including geological factors, rock mechanics and geostress factors, and engineering factors.

[0003] For data with simple influencing factors, strong correlation, and explicit correlation, the existing technology usually directly analyzes the sample point data to obtain the correlation between the feature parameters and the target parameters, and then sorts the feature parameters according to the size of the correlation, and selects the feature parameters with strong correlation as the main control parameters.

[0004] However, when the geological conditions are very complex and engineering factors have a lot of influence, the existing technology is often difficult to find subtle correlations based on sample point analysis, and the correlations are hidden in a large amount of data. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for optimizing the main controlling factors of shale oil production based on fuzzy classification. The present invention classifies sample data and takes one type of sample data as a sample point. By analyzing these new sample points, the hidden correlation in the data can be discovered.

[0006] To achieve the above object, the present invention provides a method for optimizing the main controlling factors of shale oil production based on fuzzy classification, comprising:

[0007] Collect and clean up a plurality of basic sample data, and use the cleaned sample data to establish a sample set; wherein the basic sample data includes: characteristic parameters that affect shale oil production and target parameters corresponding to the characteristic parameters;

[0008] A fuzzy classification method is used to classify each sample data in the sample set, and a mean change trend diagram of each characteristic parameter in each type of sample data is drawn under different classification numbers to analyze the correlation between each characteristic parameter and the category under different classification numbers;

[0009] A relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data is drawn, the correlation between each characteristic parameter and the corresponding target parameter is determined and sorted, and characteristic parameters with high correlation are selected as the main controlling factors affecting shale oil production.

[0010] Furthermore, multiple basic sample data are collected and cleaned, and a sample set is established using the cleaned sample data, including:

[0011] Collecting multiple groups of characteristic parameters and target data corresponding to each group of characteristic parameters;

[0012] Cleaning and eliminating basic sample data in which the characteristic parameter or the target parameter is zero and basic sample data in which the characteristic parameter or the target parameter is abnormal, to obtain cleaned sample data;

[0013] Use the cleaned sample data to create a sample set;

[0014] Wherein, each basic sample data includes: a set of the characteristic parameters and their corresponding target data;

[0015] A set of said characteristic parameters includes: net thickness, porosity, permeability, oil saturation, Poisson's ratio, cohesion, compressive strength; sand addition strength, main fracture half-length, number of clusters, fracturing fluid volume, fracturing section length, number of fracturing sections and horizontal section length;

[0016] The target parameter is the cumulative output within a predetermined number of days.

[0017] Furthermore, a fuzzy classification method is used to classify each sample data in the sample set, including:

[0018] Based on the fuzzy classification method, each sample data in the sample set is classified into different categories by establishing the membership function of each category;

[0019] Take the target parameter as the independent variable x and select the maximum value x of the target parameter in the sample set. max , minimum value x min As the maximum and minimum values ​​of the horizontal axis; and the membership function value of each category is used as the vertical axis y, the minimum value of the membership function is 0 and the maximum value is 1; the samples in the sample set are divided into n categories according to the requirements;

[0020] After dividing the samples in the sample set into n categories, the parabolic membership of each category corresponding to each sample data is calculated based on the membership function, and the category with the largest parabolic membership is selected as the classification result of the corresponding sample data.

[0021] Furthermore, the parabolic membership of each category corresponding to each sample data is calculated based on the membership function, including:

[0022] The parabola membership of the first category corresponding to each sample data is as follows:

[0023]

[0024] In the formula, y 1 and f 1 (x) represents the parabolic membership of the first type of sample data, d represents the average, Δd represents the deviation; x represents the independent variable, that is, the target parameter in the sample set; x min represents the maximum value of the target parameter in the sample set, x max Indicates the minimum value of the target parameter in the sample set;

[0025] The parabola membership of the i-th category corresponding to each sample data is as follows:

[0026]

[0027] In the formula, y i and f i (x) represents the parabolic membership of the i-th sample data, i represents the i-th category, 1<i<n, n represents the total number of categories;

[0028] The parabola membership of the nth class corresponding to each sample data is as follows:

[0029]

[0030] In the formula, y n and f n (x) represents the parabolic membership of the nth type of sample data;

[0031] The average amount d is calculated by the following formula:

[0032]

[0033] Furthermore, mean change trend diagrams of each characteristic parameter in each type of sample data are drawn under different classification numbers to analyze the correlation between each characteristic parameter and the category under different classification numbers, including:

[0034] Calculate the mean of each characteristic parameter in each type of sample data;

[0035] Draw the mean change trend graph of each characteristic parameter in each type of sample data under different classification numbers;

[0036] According to the mean change trend diagram of each characteristic parameter, the trend of each characteristic parameter changing with the number of categories is observed to analyze the correlation between each characteristic parameter and the category.

[0037] Furthermore, the mean value of each characteristic parameter is calculated by the following formula:

[0038]

[0039] In the formula, represents the mean value of the jth characteristic parameter in the i-th sample data, m i represents the total number of samples of the i-th category sample data, It represents the kth value of the jth feature parameter in the i-th category sample data, and k represents the sample number.

[0040] Furthermore, a relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data is drawn, the correlation between each characteristic parameter and the corresponding target parameter is determined and sorted, and characteristic parameters with high correlation are selected as the main controlling factors affecting shale oil production, including:

[0041] Calculate the mean of the target parameter in each type of sample data;

[0042] Normalizing the mean of each characteristic parameter and the corresponding mean of the target parameter respectively to obtain a normalized value of each characteristic parameter and a normalized value of the corresponding target parameter of the sample data of the corresponding category;

[0043] Draw the relationship curve between the normalized value of each feature parameter and the normalized value of the corresponding target parameter respectively;

[0044] According to the inflection point of the relationship curve corresponding to each characteristic parameter, a straight line segment of the relationship curve is determined, and the slope of the straight line segment corresponding to each characteristic parameter is calculated;

[0045] The absolute values ​​of the slopes of the straight line segments of each characteristic parameter obtained are sorted, and the characteristic parameters with large slopes are selected as the main controlling factors affecting shale oil production.

[0046] Furthermore, the mean of the target parameter in each type of sample data is calculated by the following formula:

[0047]

[0048] In the formula, represents the mean value of the target parameter in the i-th class sample data, is the kth target parameter of the i-th sample data, k represents the sample number; m i Represents the total number of samples of the i-th category sample data;

[0049] The mean of each characteristic parameter and the corresponding mean of the target parameter are normalized by the following formula:

[0050]

[0051] In the formula, represents the normalized value of the kth total parameter of the i-th category sample data, that is, the normalized value of the kth characteristic parameter of the i-th category sample data and the normalized value of the corresponding target parameter; represents the mean of the kth total parameter of the i-th type of sample data, represents the minimum mean of the kth total parameter, represents the maximum mean of the kth total parameter, and k represents the sample number.

[0052] Based on the same inventive concept, the present invention also provides a shale oil production main control factor optimization system based on fuzzy classification, comprising:

[0053] A cleaning unit, used to collect and clean multiple basic sample data, and use the cleaned sample data to establish a sample set;

[0054] An analysis unit, used to classify each sample data in the sample set by using a fuzzy classification method, and draw a mean change trend diagram of each characteristic parameter in each type of sample data under different classification numbers, so as to analyze the correlation between each characteristic parameter and the category under different classification numbers;

[0055] A selection unit is used to draw a relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data, determine the correlation between each characteristic parameter and the corresponding target parameter and sort them, and select characteristic parameters with high correlation as the main controlling factors affecting shale oil production;

[0056] Among them, the basic sample data includes: characteristic parameters that affect shale oil production and target parameters corresponding to the characteristic parameters.

[0057] Based on the same inventive concept, an embodiment of the present invention also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, it implements the aforementioned method for optimizing the main controlling factors of shale oil production based on fuzzy classification.

[0058] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are executed, the aforementioned method for optimizing the main controlling factors of shale oil production based on fuzzy classification is implemented.

[0059] Technical effects and advantages of the present invention: The present invention classifies sample data, takes one type of sample data as a sample point, and then analyzes these classified sample points, so as to extract clear change trends from seemingly chaotic data, thereby obtaining the correlation between the characteristic parameters and the target parameters after classification; that is, the present invention transforms the hidden correlation in the sample into an explicit correlation, which has extremely far-reaching significance for the subsequent shale oil production classification prediction research.

[0060] 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 pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0062] Figure 1 This is a flow chart of a method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to an embodiment of the present invention;

[0063] Figure 2 Schematic diagram of classification results of sample data when the sample set is divided into three categories in an embodiment of the present invention;

[0064] Figure 3 This is a schematic diagram of classification results of sample data when a sample set is divided into four categories in an embodiment of the present invention;

[0065] Figure 4 This is a schematic diagram of classification results of sample data when a sample set is divided into five categories in an embodiment of the present invention;

[0066] Figure 5 Schematic diagram of data distribution between horizontal segment length and 30-day cumulative output in an embodiment of the present invention;

[0067] Figure 6 This is a schematic diagram of data distribution between sand addition intensity and 30-day cumulative production in an embodiment of the present invention;

[0068] Figure 7 This is a schematic diagram of data distribution between Poisson's ratio and 30-day cumulative output in an embodiment of the present invention;

[0069] Figure 8It is a schematic diagram of the change trend of the mean value of the horizontal segment length of each category of sample data when the sample data in the sample set in an embodiment of the present invention is divided into three categories;

[0070] Fig. 9 It is a schematic diagram of the change trend of the mean value of the horizontal segment length of each category of sample data when the sample data in the sample set in an embodiment of the present invention is divided into 4 categories;

[0071] Fig.10 It is a schematic diagram of the change trend of the mean value of the horizontal segment length of each category of sample data when the sample data in the sample set in an embodiment of the present invention is divided into 5 categories;

[0072] Fig.11 It is a schematic diagram of the mean change trend of the sand adding intensity of each category of sample data when the sample data in the sample set in the embodiment of the present invention is divided into three categories;

[0073] Fig.12 It is a schematic diagram of the mean change trend of the sand adding intensity of each category of sample data when the sample data in the sample set in the embodiment of the present invention is divided into 4 categories;

[0074] Fig.13 It is a schematic diagram of the mean change trend of the sand adding intensity of each category of sample data when the sample data in the sample set in the embodiment of the present invention is divided into 5 categories;

[0075] Fig.14 It is a schematic diagram of the mean change trend of the Poisson's ratio of each category of sample data when the sample data in the sample set in an embodiment of the present invention is divided into three categories;

[0076] Fig.15 It is a schematic diagram of the mean change trend of the Poisson's ratio of each category of sample data when the sample data in the sample set in an embodiment of the present invention is divided into four categories;

[0077] Fig.16 It is a schematic diagram of the mean change trend of the Poisson's ratio of each category of sample data when the sample data in the sample set in an embodiment of the present invention is divided into 5 categories;

[0078] Fig.17 It is a schematic diagram of the relationship curve between the normalized value of the horizontal section length and the normalized value of the cumulative output in 30 days in an embodiment of the present invention;

[0079] Fig.18 It is a schematic diagram of the relationship curve between the normalized value of sand addition intensity and the normalized value of 30-day cumulative output in an embodiment of the present invention;

[0080] Fig.19 Schematic diagram of the relationship curve between the normalized value of Poisson's ratio and the normalized value of the cumulative output in 30 days in an embodiment of the present invention;

[0081] Fig. 20It is a schematic diagram of the ranking result of the absolute values ​​of the slopes of the straight line segments of all characteristic parameters in the embodiment of the present invention;

[0082] Fig.21 This is a structural schematic diagram of a system for optimizing the main control factors of shale oil production based on fuzzy classification according to an embodiment of the present invention;

[0083] Fig. 22 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0084] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0085] In order to solve the shortcomings of the prior art, the present invention discloses a method for optimizing the main controlling factors of shale oil production based on fuzzy classification, such as Figure 1 As shown, including:

[0086] Step S1: Collect and clean up a plurality of basic sample data, and use the cleaned sample data to establish a sample set; specifically including:

[0087] Based on geological research data and fracturing construction reports, multiple groups of characteristic parameters that affect shale oil production and target data corresponding to each group of characteristic parameters are collected and organized; among them, each basic sample data includes: a group of characteristic parameters that affect shale oil production and target parameters corresponding to this group of characteristic parameters.

[0088] Among them, the target parameter is the cumulative production within 30 days;

[0089] Each group of characteristic parameters mainly includes: geological parameters, rock mechanics and geostress parameters and engineering parameters; geological parameters include: net thickness (m), porosity (%), permeability (mD), oil saturation (%), etc.; rock mechanics and geostress parameters include: Poisson's ratio, cohesion (MPa), compressive strength (MPa), etc.; engineering parameters include: sand addition intensity (t / m), main fracture half length (m), cluster number, fracturing fluid volume (m 3 ), fracturing section length (m), number of fracturing sections, horizontal section length (m), etc.; therefore, each set of characteristic parameters includes 14 parameters in total.

[0090] The basic sample data with characteristic parameters or target parameters of zero and the basic sample data with abnormal characteristic parameters or target parameters are cleaned and eliminated to obtain cleaned sample data; and a sample set is established using the cleaned sample data.

[0091] Some of the sample data after cleaning are shown in Table 1:

[0092] Table 1

[0093]

[0094] .

[0095] Step 2: Use the fuzzy classification method to classify each sample data in the sample set, and draw the mean change trend diagram of each feature parameter in each type of sample data under different classification numbers to analyze the correlation between each feature parameter and the category under different classification numbers; specifically including:

[0096] Step 201: Classify each sample data in the sample set using a fuzzy classification method. The specific steps are as follows:

[0097] Based on the fuzzy classification method, each sample data in the sample set is classified into different categories by establishing the membership function of each category.

[0098] The target parameter (30-day cumulative output) is taken as the independent variable x, and the maximum value (6250t) and minimum value x of the target parameter in the sample set are selected. min (694t) is used as the maximum and minimum values ​​of the horizontal axis; and the membership function value of each category is used as the vertical axis y, the minimum value of the membership function is 0 and the maximum value is 1; the samples in the sample set are divided into n categories according to the needs.

[0099] After dividing the samples in the sample set into n categories, the parabolic membership of each category corresponding to each sample data is calculated based on the membership function, and the category with the largest parabolic membership is selected as the classification result of the corresponding sample data.

[0100] The formula for calculating the parabola membership of each category corresponding to each sample data includes:

[0101] The parabola membership of the first category corresponding to each sample data is as follows:

[0102]

[0103] In the formula, y 1 and f 1(x) represents the parabolic membership of the first type of sample data, d represents the average, Δd represents the deviation; x represents the independent variable, that is, the target parameter in the sample data; x min represents the maximum value of the target parameter in the sample set, x max Indicates the minimum value of the target parameter in the sample set.

[0104] The parabola membership of the i-th category corresponding to each sample data is as follows:

[0105]

[0106] In the formula, y i and f i (x) represents the parabolic membership of the i-th sample data, i represents the i-th category, 1<i<n, n represents the total number of categories; d represents the average, Δd represents the deviation; x represents the independent variable, that is, the target parameter in the sample set; x min represents the maximum value of the target parameter in the sample set, x max Indicates the minimum value of the target parameter in the sample set.

[0107] The parabolic membership of the nth class corresponding to each sample is given by the following formula:

[0108]

[0109] In the formula, y n and f n (x) represents the parabolic membership of the nth type of sample data, d represents the average, Δd represents the deviation; x represents the independent variable, that is, the target parameter in the sample set; x min represents the maximum value of the target parameter in the sample set, x max Indicates the minimum value of the target parameter in the sample set.

[0110] The average amount d is calculated by the following formula:

[0111]

[0112] In the formula, n represents the total number of categories, x min represents the maximum value of the target parameter in the sample set, x max Indicates the minimum value of the target parameter in the sample set.

[0113] Therefore, (1) in the embodiment, when the samples in the sample set are divided into three categories:

[0114] The parabola membership of each sample data corresponding to the first category is calculated by the following formula:

[0115] In the formula, y1 and f 1 (x) all represent the parabolic membership of the first type of sample data, and x represents the independent variable, that is, the target parameter in the sample data;

[0116] The parabola membership of each sample data corresponding to the second category is calculated by the following formula:

[0117] In the formula, y i and f i (x) represents the parabolic membership of the i-th sample data, i represents the i-th category, i=2, and x represents the independent variable, that is, the target parameter in the sample set;

[0118] The parabola membership of each sample data corresponding to the third category is calculated by the following formula:

[0119] In the formula, y n and f n (x) represents the parabolic membership of the nth category of sample data, n represents the total number of categories, and n=3 in this case; x represents the independent variable, that is, the target parameter in the sample set.

[0120] When the samples in the sample set are divided into three categories, the parabola membership of each sample data corresponding to each category is calculated according to the above membership calculation formula, and the category with the largest parabola membership is selected as the classification result of the sample data. The classification result is as follows: Figure 2 As shown: in the sample set, 51.8% of the sample data are classified as Class III wells, 37.2% of the sample data are classified as Class II wells, and 11% of the sample data are classified as Class I wells.

[0121] (2) In the embodiment, when the samples in the sample set are divided into four categories:

[0122] The parabola membership of each sample data corresponding to the first category is calculated by the following formula:

[0123] In the formula, y 1 and f 1 (x) represents the parabolic membership of the first type of sample data, x represents the independent variable, that is, the target parameter in the sample set;

[0124] The parabola membership of each sample data corresponding to the second category is calculated by the following formula:

[0125] In the formula, y i and f i(x) represents the parabola membership of the i-th sample data, i represents the i-th category, and i=2 in this case; x represents the independent variable, that is, the target parameter in the sample set;

[0126] The parabola membership of each sample data corresponding to the third category is calculated by the following formula:

[0127] Where y i and f i (x) represents the parabolic membership of the i-th category sample data, i represents the i-th category, and i=3 in this case; x represents the independent variable, that is, the target parameter in the sample set;

[0128] The parabola membership of each sample data corresponding to the fourth category is calculated by the following formula:

[0129] In the formula, y n and f n (x) represents the parabolic membership of the nth category of sample data, n represents the total number of categories, and n=4 in this case; x represents the independent variable, that is, the target parameter in the sample set.

[0130] When the samples in the sample set are divided into 4 categories, the classification results are as follows Figure 3 As shown: in the sample set, 36.4% of the sample data are classified as Class IV wells, 35.9% of the sample data are classified as Class III wells, 21.9% of the sample data are classified as Class II wells, and 5.8% of the sample data are classified as Class I wells.

[0131] (3) In the embodiment, when the samples in the sample set are divided into 5 categories:

[0132] The parabola membership of each sample data corresponding to the first category is calculated by the following formula:

[0133] In the formula, y 1 and f 1 (x) all represent the parabolic membership of the first type of sample data, and x represents the independent variable, that is, the target parameter in the sample data;

[0134] The parabola membership of each sample data corresponding to the second category is calculated by the following formula:

[0135] In the formula, y i and f i (x) represents the parabolic membership of the i-th sample data, i represents the i-th category, and i=2 in this case; x represents the independent variable, that is, the target parameter in the sample set;

[0136] The parabola membership of each sample data corresponding to the third category is calculated by the following formula:

[0137] Where y i and f i (x) represents the parabolic membership of the i-th category sample data, i represents the i-th category, and i=3 in this case; x represents the independent variable, that is, the target parameter in the sample set;

[0138] The parabola membership of each sample data corresponding to the fourth category is calculated by the following formula:

[0139] Where y i and f i (x) represents the parabola membership of the i-th category sample data, i represents the i-th category, and i=4 in this case; x represents the independent variable, that is, the target parameter in the sample set;

[0140] The parabola membership of each sample data corresponding to the fifth category is calculated by the following formula:

[0141] In the formula, y n and f n (x) represents the parabolic membership of the nth category of sample data, n represents the total number of categories, and n=5 in this case; x represents the independent variable, that is, the target parameter in the sample set.

[0142] When the samples in the sample set are divided into 5 categories, the classification results are as follows Figure 4 As shown: in the sample set, 25.8% of the sample data are classified as Class V wells, 31.6% of the sample data are classified as Class IV wells, 23.8% of the sample data are classified as Class III wells, 15.3% of the sample data are classified as Class II wells, and 3.5% of the sample data are classified as Class I wells.

[0143] Step 202: Draw the mean change trend diagram of each characteristic parameter in each type of sample data under different classification numbers to analyze the correlation between each characteristic parameter and the category under different classification numbers; the specific steps are as follows:

[0144] like Figure 5-7 As shown, it can be observed that no obvious correlation can be found in the data distribution between the horizontal section length, sand addition intensity, Poisson's ratio and the 30-day cumulative production; that is, no obvious correlation can be found through the data between the characteristic parameters and the target parameters (30-day cumulative production).

[0145] Therefore, the mean of each characteristic parameter in each type of sample data is calculated by the following formula:

[0146]

[0147] In the formula, represents the mean value of the jth characteristic parameter in the i-th sample data, m i represents the total number of samples of the i-th category sample data, represents the kth value of the jth feature parameter in the i-th category sample data (that is, the kth feature parameter value of the jth feature parameter in the i-th category sample data), and k represents the sample number.

[0148] Draw the mean change trend graph of each feature parameter in each category of sample data under different classification numbers. According to the mean change trend graph of each feature parameter, observe the trend of each feature parameter changing with the number of categories to analyze the correlation between each feature parameter and the category.

[0149] like Figure 8-16 As shown: Taking the horizontal section length, sand addition intensity and Poisson's ratio as examples, according to the mean change trend chart of the horizontal section length, sand addition intensity and Poisson's ratio, it can be found that no matter the samples are divided into 3 categories, 4 categories or 5 categories, the mean change trends of the horizontal section length, sand addition intensity and Poisson's ratio with the categories are the same, which means that there is a good correlation between the horizontal section length, sand addition intensity, Poisson's ratio and the categories.

[0150] Step 3: Draw a relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data, determine the correlation between each characteristic parameter and the corresponding target parameter and sort them, and select characteristic parameters with high correlation as the main controlling factors affecting shale oil production; including:

[0151] Set the number of classification categories to 50, and calculate the mean of the target parameter in each category of sample data as:

[0152]

[0153] In the formula, represents the mean value of the target parameter in the i-th class sample data, is the kth target parameter of the i-th sample data, k represents the sample number; m i Represents the total number of samples of the i-th category sample data.

[0154] Normalize the mean of each characteristic parameter and the corresponding mean of the target parameter respectively, and obtain the normalized value of each characteristic parameter of the corresponding category sample data and the corresponding normalized value of the target parameter as follows:

[0155]

[0156] In the formula, represents the normalized value of the kth total parameter of the i-th type of sample data, represents the mean of the kth total parameter of the i-th type of sample data, represents the minimum mean of the kth total parameter, represents the maximum mean of the kth total parameter, and k represents the sample number;

[0157] Since the normalization formulas of the characteristic parameters and the target parameters are the same, the characteristic parameters and the target parameters are combined in the formula, that is, the total parameter includes the characteristic parameters and the target parameters.

[0158] Draw the relationship curve between the normalized value of each feature parameter and the corresponding normalized value of the target parameter; (each point represents a category, the horizontal axis is the normalized value of the feature parameter of this category of sample data, and the vertical axis is the normalized value of the target parameter of this category of sample data) Figure 17-19 shown.

[0159] According to the inflection point of the relationship curve corresponding to each characteristic parameter, the straight line segment of the relationship curve is determined, and the slope of the straight line segment corresponding to each characteristic parameter is calculated; in the embodiment, the slopes of the straight line segments of the relationship curves of horizontal segment length, sand addition intensity, and Poisson's ratio are 5.6537, 3.4878, and -1.2458, respectively.

[0160] The slopes of the straight line segments of the relationship curves of all characteristic parameters are shown in Table 2:

[0161] Table 2

[0162] Characteristic parameters Slope of straight line segment Characteristic parameters Slope of straight line segment Net thickness 4.4552 Sand Adding Strength 3.4825 Main crack half length 4.0765 Horizontal segment length 5.6537 Permeability 3.4577 Fracturing stages 4.7244 Oil saturation 4.0421 Fracturing fluid volume 4.5346 Poisson's ratio -1.2458 Fracturing section length 3.2771 Cohesion -1.0724 Number of clusters 3.3571 Compressive strength -0.9042 Porosity 3.2691

[0163] The absolute values ​​of the slopes of the straight line segments of each characteristic parameter obtained are sorted, and the sorting result is as follows: Fig. 20 As shown in the figure, 11 parameters (characteristic parameters with large slopes) including horizontal section length, number of fracturing stages, fracturing fluid volume, net thickness, main fracture half-length, oil saturation, sand addition intensity, permeability, number of clusters, fracturing section length, and porosity are selected as the main controlling factors affecting shale oil production.

[0164] Based on the same inventive concept, the present invention also provides a shale oil production main control factor optimization system based on fuzzy classification, such as Fig.21 As shown, including:

[0165] A cleaning unit, used to collect and clean multiple basic sample data, and use the cleaned sample data to establish a sample set;

[0166] An analysis unit, used to classify each sample data in the sample set by using a fuzzy classification method, and draw a mean change trend diagram of each characteristic parameter in each type of sample data under different classification numbers, so as to analyze the correlation between each characteristic parameter and the category under different classification numbers;

[0167] A selection unit is used to draw a relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data, determine the correlation between each characteristic parameter and the corresponding target parameter and sort them, and select characteristic parameters with high correlation as the main controlling factors affecting shale oil production;

[0168] Among them, the basic sample data includes: characteristic parameters that affect shale oil production and target parameters corresponding to the characteristic parameters.

[0169] Regarding the system in the above embodiment, the specific manner in which each unit module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0170] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, whose structure is as follows: Fig. 22 As shown, it includes: a memory and a processor, wherein the processor is used to read and execute the computer program stored in the memory to implement the aforementioned method for optimizing the main controlling factors of shale oil production based on fuzzy classification.

[0171] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are executed, the aforementioned method for optimizing the main controlling factors of shale oil production based on fuzzy classification is implemented.

[0172] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for optimizing the main controlling factors of shale oil production based on fuzzy classification, characterized in that: include: Collect and clean up a plurality of basic sample data, and use the cleaned sample data to establish a sample set; wherein the basic sample data includes: characteristic parameters that affect shale oil production and target parameters corresponding to the characteristic parameters; A fuzzy classification method is used to classify each sample data in the sample set, and a mean change trend diagram of each characteristic parameter in each type of sample data is drawn under different classification numbers to analyze the correlation between each characteristic parameter and the category under different classification numbers; A relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data is drawn, the correlation between each characteristic parameter and the corresponding target parameter is determined and sorted, and characteristic parameters with high correlation are selected as the main controlling factors affecting shale oil production.

2. The method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to claim 1 is characterized in that: Collect and clean multiple basic sample data, and use the cleaned sample data to establish a sample set, including: Collecting multiple groups of characteristic parameters and target data corresponding to each group of characteristic parameters; Cleaning and eliminating basic sample data in which the characteristic parameter or the target parameter is zero and basic sample data in which the characteristic parameter or the target parameter is abnormal, to obtain cleaned sample data; Use the cleaned sample data to create a sample set; Wherein, each basic sample data includes: a set of the characteristic parameters and their corresponding target data; A set of said characteristic parameters includes: net thickness, porosity, permeability, oil saturation, Poisson's ratio, cohesion, compressive strength; sand addition strength, main fracture half-length, number of clusters, fracturing fluid volume, fracturing section length, number of fracturing sections and horizontal section length; The target parameter is the cumulative output within a predetermined number of days.

3. The method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to claim 1 is characterized in that: The fuzzy classification method is used to classify each sample data in the sample set, including: Based on the fuzzy classification method, each sample data in the sample set is classified into different categories by establishing the membership function of each category; Take the target parameter as the independent variable x and select the maximum value x of the target parameter in the sample set. max , minimum value x min As the maximum and minimum values ​​of the horizontal axis; and the membership function value of each category is used as the vertical axis y, the minimum value of the membership function is 0 and the maximum value is 1; the samples in the sample set are divided into n categories according to the requirements; After dividing the samples in the sample set into n categories, the parabolic membership of each category corresponding to each sample data is calculated based on the membership function, and the category with the largest parabolic membership is selected as the classification result of the corresponding sample data.

4. The method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to claim 1 is characterized in that: The parabolic membership of each category corresponding to each sample data is calculated based on the membership function, including: The parabola membership of the first category corresponding to each sample data is as follows: Where y1 and f1(x) both represent the parabolic membership of the first type of sample data, d represents the average, Δd represents the deviation; x represents the independent variable, that is, the target parameter in the sample set; x min represents the maximum value of the target parameter in the sample set, x max Indicates the minimum value of the target parameter in the sample set; The parabola membership of the i-th category corresponding to each sample data is as follows: In the formula, y i and f i (x) represents the parabolic membership of the i-th sample data, i represents the i-th category, 1<i<n, n represents the total number of categories; The parabola membership of the nth class corresponding to each sample data is as follows: In the formula, y n and f n (x) represents the parabolic membership of the nth type of sample data; The average amount d is calculated by the following formula:

5. The method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to claim 1 is characterized in that: And draw the mean change trend diagram of each characteristic parameter in each type of sample data under different classification numbers to analyze the correlation between each characteristic parameter and the category under different classification numbers, including: Calculate the mean of each characteristic parameter in each type of sample data; Draw the mean change trend graph of each characteristic parameter in each type of sample data under different classification numbers; According to the mean change trend diagram of each characteristic parameter, the trend of each characteristic parameter changing with the number of categories is observed to analyze the correlation between each characteristic parameter and the category.

6. The method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to claim 5 is characterized in that: The mean value of each characteristic parameter is calculated by the following formula: In the formula, represents the mean value of the jth characteristic parameter in the i-th sample data, m i represents the total number of samples of the i-th category sample data, It represents the kth value of the jth feature parameter in the i-th category sample data, and k represents the sample number.

7. The method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to claim 5 is characterized in that: Draw a relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data, determine the correlation between each characteristic parameter and the corresponding target parameter and sort them, and select characteristic parameters with high correlation as the main controlling factors affecting shale oil production, including: Calculate the mean of the target parameter in each type of sample data; Normalizing the mean of each characteristic parameter and the corresponding mean of the target parameter respectively to obtain a normalized value of each characteristic parameter and a normalized value of the corresponding target parameter of the sample data of the corresponding category; Draw the relationship curve between the normalized value of each feature parameter and the normalized value of the corresponding target parameter respectively; According to the inflection point of the relationship curve corresponding to each characteristic parameter, a straight line segment of the relationship curve is determined, and the slope of the straight line segment corresponding to each characteristic parameter is calculated; The absolute values ​​of the slopes of the straight line segments of each characteristic parameter obtained are sorted, and the characteristic parameters with large slopes are selected as the main controlling factors affecting shale oil production.

8. The method for optimizing the main controlling factors of shale oil production based on fuzzy classification according to claim 7 is characterized in that: The mean of the target parameter in each type of sample data is calculated by the following formula: In the formula, represents the mean value of the target parameter in the i-th class sample data, is the kth target parameter of the i-th sample data, k represents the sample number; m i Represents the total number of samples of the i-th category sample data; The mean of each characteristic parameter and the corresponding mean of the target parameter are normalized by the following formula: In the formula, represents the normalized value of the kth total parameter of the i-th category sample data, that is, the normalized value of the kth characteristic parameter of the i-th category sample data and the normalized value of the corresponding target parameter; represents the mean of the kth total parameter of the i-th type of sample data, represents the minimum mean of the kth total parameter, represents the maximum mean of the kth total parameter, and k represents the sample number.

9. A shale oil production main control factor optimization system based on fuzzy classification, characterized in that: include: A cleaning unit, used to collect and clean multiple basic sample data, and use the cleaned sample data to establish a sample set; An analysis unit, used to classify each sample data in the sample set by using a fuzzy classification method, and draw a mean change trend diagram of each characteristic parameter in each type of sample data under different classification numbers, so as to analyze the correlation between each characteristic parameter and the category under different classification numbers; A selection unit is used to draw a relationship curve between each characteristic parameter and the corresponding target parameter in each type of sample data, determine the correlation between each characteristic parameter and the corresponding target parameter and sort them, and select characteristic parameters with high correlation as the main controlling factors affecting shale oil production; Among them, the basic sample data includes: characteristic parameters that affect shale oil production and target parameters corresponding to the characteristic parameters.

10. An electronic device, characterized in that: include: Memory, processor; The processor is used to read and execute the computer program stored in the memory to implement the method for optimizing the main controlling factors of shale oil production based on fuzzy classification as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed, implement a method for optimizing main controlling factors of shale oil production based on fuzzy classification as described in any one of claims 1-8.

Images