Intelligent comprehensive fracturing sweet spot identification method while drilling

Abstract

The application discloses an intelligent comprehensive fracturing sweet spot identification method while drilling, which comprises the following steps: corresponding the logging data of different small layers in the target block reservoir to the sweet spot comprehensive evaluation coefficient and the production well gas production data, and establishing an intelligent sweet spot identification model training database. A neural network model is established, part of the data in the intelligent fracturing sweet spot identification model training database is taken as a training set to input the neural network model for training, the establishment of a deep learning model is completed, and the intelligent fracturing sweet spot identification model is formed. In the drilling construction process, the logging-while-drilling data is fed back in real time, the logging-while-drilling data is taken as input parameters and uploaded to the intelligent fracturing sweet spot identification model, the corresponding sweet spot comprehensive evaluation coefficient and the production well gas production data are output in real time, and the intelligent comprehensive fracturing sweet spot identification while drilling is realized according to the output sweet spot comprehensive evaluation coefficient and the production well gas production data. The application comprehensively realizes the real-time identification of the sweet spot during the drilling process.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of fracturing sweet spot identification, and particularly relates to an intelligent comprehensive fracturing sweet spot identification method while drilling. BACKGROUND

[0002] In recent years, with the gradual deepening of oil and gas reservoir exploration and development, unconventional oil and gas reservoirs represented by shale and tight sandstone oil and gas have become an important replacement block for increasing reserves and production and tapping potential and stable production. Such reservoirs can only be effectively released by fracturing. In addition, the development of onshore conventional oil and gas reservoirs and shallow sea oil and gas reservoirs has gradually entered the marginal area, and the reservoir quality has deteriorated, and also needs to be transformed by fracturing to achieve stable production. Therefore, the continuous progress of fracturing technology is the key to promoting the deep development of oil and gas resources.

[0003] The purpose of fracturing is that the oil and gas reservoirs are strongly heterogeneous, and the reservoir properties and geomechanical properties of long horizontal sections drilled are greatly changed. In order to achieve precise and low-cost fracturing and achieve the effect of increasing production and stable production, it is necessary to efficiently, quickly and accurately identify the "sweet spot" area before fracturing to improve the pertinence and effectiveness of the transformation. The conventional "sweet spot" identification usually needs to determine various parameters such as physical properties through indoor nuclear magnetic resonance, scanning electron microscope and other experiments, and to qualitatively distinguish in combination with seismic, logging, lithology analysis and the like, which is very dependent on human experience, has insufficient reliability, takes a long time, and the identification is more of a geological "sweet spot". But good geological sweet spot is not necessarily good engineering sweet spot. When identifying engineering sweet spot, a large amount of basic data such as reservoir properties, logging, rock mechanics need to be collected, analyzed, calculated and interpreted, which takes a long time and is complicated and time-consuming. The pertinence of the model used in the calculation to the fractured block is not strong, and it cannot provide a quick and accurate sweet spot marker for the next step of fracturing. Therefore, this technology still has deficiencies in the integrated identification of geological "sweet spot" and engineering "sweet spot" using the idea of geological engineering integration, and cannot well unify the reservoir gas enrichment area and the area favorable to fracturing, affecting the overall production increase effect.

[0004] In addition, fracturing of unconventional oil and gas blocks has been widely used, and the logging data, fracturing operation data and other data of each block are large in amount and various in type, but the application of these data is mainly limited to single well logging interpretation, post-fracturing analysis and the like, and the data potential and comprehensive utilization are far from enough. SUMMARY

[0005] The present application provides an intelligent comprehensive fracturing sweet spot identification method while drilling, which can realize real-time identification of "sweet spot" during drilling.

[0006] The embodiment of the present application provides an intelligent comprehensive fracturing sweet spot identification method while drilling, which comprises the following steps:

[0007] Collecting reservoir characteristic data and production well gas production data of a target block reservoir.

[0008] According to the reservoir characteristic data, characteristic parameters for evaluating reservoir physical property quality and characteristic parameters for evaluating well completion quality are screened to form sweet spot evaluation characteristic parameters, and a corresponding relationship is established with the corresponding production well gas production data to form a basic database.

[0009] The grey correlation degree of the sweet spot evaluation characteristic parameters and the production well gas production data in the basic database is calculated, and the sweet spot identification master control factors are determined according to the size of the grey correlation degree.

[0010] The sweet spot identification master control factors are analyzed to determine the weight of the sweet spot identification master control factors.

[0011] The sweet spot evaluation comprehensive coefficient is calculated according to the sweet spot identification master control factors and the corresponding weight.

[0012] The logging data of different small layers in the target block reservoir are corresponded to the sweet spot comprehensive evaluation coefficient and the production well gas production data to establish an intelligent sweet spot identification model training database.

[0013] The neural network model is established, part of the data in the intelligent sweet spot identification model training database is input into the neural network model as a training set for training to complete the establishment of the deep learning model, the remaining part of the data in the intelligent sweet spot identification model training database is input into the deep learning model as a test set for testing, the accuracy of the sweet spot comprehensive evaluation coefficient and the production well gas production data is verified to reach the preset effect, and the intelligent sweet spot identification model is formed.

[0014] During the drilling operation process, the logging while drilling data is fed back in real time, the logging while drilling data is uploaded to the intelligent sweet spot identification model as an input parameter, the corresponding sweet spot comprehensive evaluation coefficient and production well gas production data are output in real time, and the intelligent drilling comprehensive sweet spot identification is realized according to the output sweet spot comprehensive evaluation coefficient and production well gas production data.

[0015] In some embodiments, during the drilling operation process, the reservoir physical property characteristic parameters and the geomechanical parameters output by the intelligent sweet spot identification model are transmitted into the target block wellbore geological model in real time to update the target block wellbore geological model.

[0016] In some embodiments, after the drilling operation is completed, the geomechanical parameter profile along the wellbore trajectory and the integrated sweet spot profile of geology and engineering are output by the intelligent sweet spot identification model to guide the next step of fracturing layer selection.

[0017] In some embodiments, the grey correlation degree of the sweet spot evaluation characteristic parameters and the production well gas production data in the basic database is calculated, including:

[0018] ①Establishing evaluation matrix X iX0, respectively, correspond to the dessert evaluation characteristic parameters and the production well gas production rate;

[0019]

[0020] X0= [X0(1), X2(2)…, X m (n)]

[0021] In the formula: m - the number of dessert evaluation characteristic parameters, pieces;

[0022] n - the number of data contained in each dessert evaluation characteristic parameter, pieces;

[0023] X i - the value of the dessert identification characteristic parameter, pieces;

[0024] X0 - the production well gas production rate, m3 / d.

[0025] ②Adopting mean standardization to make the matrix [X0, X1, X2…, X n ] T dimensionless.

[0026] ③Calculating the correlation coefficient ξ i ;

[0027]

[0028] In the formula: ξ i - correlation coefficient, dimensionless;

[0029] P - resolution coefficient, P = 0.5;

[0030] k - the number of rows of the evaluation matrix, rows;

[0031] i - the number of columns of the evaluation matrix, columns.

[0032] ④Calculating the grey correlation degree;

[0033]

[0034] In the formula: R i - grey correlation degree.

[0035] In some embodiments, the dessert identification master control factor is analyzed, and the weight of the dessert identification master control factor is determined, including:

[0036] ①Through the range method, the dessert identification master control factor X ij as an evaluation index is standardized;

[0037] When X ij is a positive index:

[0038]

[0039] When X ij is a negative index:

[0040]

[0041] In the formula, X ij is the value of the jth evaluation index in the ith group of dessert evaluation characteristic parameters; Y ij is the standardized evaluation index value; max(X ij ) and min(X ij ) represent the maximum and minimum values of X ij , respectively.

[0042] 2. Calculate the proportion of the evaluation index;

[0043] i = 1, 2, ···, n; j = 1, 2, ···, m

[0044] In the formula, P ij is the proportion of the jth evaluation index in the ith group of dessert evaluation characteristic parameters; Y ij is the standardized evaluation index value.

[0045] 3. Calculate the information entropy of the evaluation index;

[0046]

[0047] In the formula, E j is the information entropy; n is the number of data included in each dessert evaluation characteristic parameter; P ij is the proportion of the jth evaluation index in the ith group of dessert evaluation characteristic parameters; if P ij is 0, then define

[0048]

[0049] 4. Calculate the weight of the evaluation index based on the information entropy;

[0050]

[0051] In the formula, W j is the weight of the jth evaluation index; E j is the information entropy; and m is the number of dessert evaluation characteristic parameters.

[0052] In some embodiments, the master factor and the corresponding weight are determined according to the dessert, and a comprehensive coefficient of the dessert evaluation is calculated, including:

[0053]

[0054] In the formula: δ—dessert evaluation comprehensive coefficient;

[0055] G i —dessert identification master factor normalization, dimensionless;

[0056] W i —dessert identification master factor weight.

[0057] In some embodiments, the well logging data is normalized before establishing the neural network model.

[0058] In some embodiments, the well logging data includes: natural gamma, resistivity, acoustic time difference, shale content, density, porosity, hole diameter.

[0059] In some embodiments, the characteristic parameters for evaluating reservoir physical property quality include permeability, porosity, and saturation.

[0060] In some embodiments, the characteristic parameters for evaluating well completion quality include Young's modulus, Poisson's ratio, horizontal principal stress, brittleness index, and horizontal stress difference coefficient.

[0061] The intelligent drilling comprehensive fracturing sweet spot identification method according to the embodiment of the present application comprises the following steps: collecting reservoir characteristic data and production well gas production data of a target block reservoir. According to the reservoir characteristic data, characteristic parameters for evaluating reservoir physical property quality and characteristic parameters for evaluating well completion quality are screened to form sweet spot evaluation characteristic parameters, and a corresponding relationship is established with the corresponding production well gas production data to form a basic database. The grey correlation degree of the sweet spot evaluation characteristic parameters and the production well gas production data in the basic database is calculated, and the sweet spot identification master control factor is determined according to the grey correlation degree. The sweet spot identification master control factor is analyzed to determine the weight of the sweet spot identification master control factor. The sweet spot evaluation comprehensive coefficient is calculated according to the sweet spot identification master control factor and the corresponding weight. The logging data of different layers in the target block reservoir is corresponded to the sweet spot comprehensive evaluation coefficient and the production well gas production data to establish an intelligent sweet spot identification model training database. A neural network model is established, part of the data in the intelligent fracturing sweet spot identification model training basic database is input into the neural network model as a training set for training, the establishment of the deep learning model is completed, the remaining part of the data in the intelligent fracturing sweet spot identification model training basic database is used as a test set to test the deep learning model, the accuracy of the sweet spot comprehensive evaluation coefficient and the production well gas production data is verified to reach the preset effect, and the intelligent fracturing sweet spot identification model is formed. In the drilling construction process, the logging while drilling data is fed back in real time, the logging while drilling data is uploaded to the intelligent fracturing sweet spot identification model as an input parameter, and the corresponding sweet spot comprehensive evaluation coefficient and production well gas production data are output in real time. The intelligent drilling comprehensive fracturing sweet spot identification is realized according to the output sweet spot comprehensive evaluation coefficient and production well gas production data. The intelligent drilling comprehensive fracturing sweet spot identification method of the present application can deeply mine multi-dimensional data such as logging, reservoir physical property characteristics, geomechanics and post-fracturing production, organically combine engineering sweet spots and geological sweet spots, use machine learning means, take the expert analysis result as a reference, and comprehensively realize real-time identification of the sweet spot in the drilling process. The problems of too large human factor and experiential influence and insufficient reliability in the fracturing section and layer selection process are solved. The decision result difference caused by the human factor is reduced to affect the final fracturing effect. The fracturing design and construction efficiency is improved. The cost is reduced. The yield increase purpose is more targetedly achieved. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application. Those skilled in the art can also obtain other drawings according to these drawings without creating any inventive labor.

[0063] Figure 1 The flowchart of the intelligent drilling comprehensive fracturing sweet spot identification method in the embodiment of the present application is shown. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] See Figure 1 The embodiments of this application provide an intelligent method for identifying sweet spots in integrated fracturing while drilling, comprising the following steps:

[0066] Step 1: Collect reservoir characteristic data and gas production data of production wells in the target block.

[0067] In the steps described above, current logging-while-drilling (LWD) can basically cover most of the logging information obtained from traditional wireline logging, including: natural gamma ray, resistivity, sonic transit time, clay content, density, porosity, well diameter, and even imaging logging data. We select a certain amount of LWD data and conventional logging data from different layers in the target block, combined with the gas production of the corresponding layers, as the data foundation for subsequent data processing and analysis. Therefore, reservoir characteristic data can include reservoir logging data and reservoir physical property experimental analysis data. Logging data can include: natural gamma ray, resistivity, sonic transit time, clay content, density, porosity, well diameter, etc.

[0068] Step 2: Based on reservoir characteristic data, select characteristic parameters for evaluating reservoir physical properties and well completion quality, form sweet spot evaluation characteristic parameters, and establish a correspondence with the gas production data of production wells in the corresponding target layer to form a basic database.

[0069] In the above steps, the evaluation of reservoir sweet spots should follow the integrated geological and engineering concept, comprehensively considering both geological and engineering sweet spots. This includes two main aspects: reservoir physical quality (RQ) and completion quality (CQ). Reservoir physical quality characteristic parameters mainly include porosity, permeability (k), and saturation (Sg or So), which can be directly obtained through well logging interpretation. Completion quality characteristic parameters mainly include Young's modulus, Poisson's ratio, horizontal principal stress, brittleness, and horizontal stress difference coefficient, which need to be calculated using well logging data. Therefore, permeability, porosity, and saturation can be selected as characteristic parameters for evaluating reservoir physical quality by combining well logging data and reservoir physical property experimental analysis data. Young's modulus, Poisson's ratio, horizontal principal stress, brittleness index, and horizontal stress difference coefficient can be calculated from well logging data as characteristic parameters for evaluating completion quality.

[0070] in,

[0071] (1) Young's modulus: The higher the Young's modulus, the better the well completion quality of the reservoir generally represents. The calculation method is as follows:

[0072]

[0073] Wherein, E is Young's modulus, GPa; is the formation shear wave interval transit time, μs / m; is the formation compressional wave interval transit time, μs / m; p b is the rock bulk density, g / cm 3 ; β is the conversion coefficient.

[0074] (2) Poisson's ratio: The lower the Poisson's ratio, the better the well completion quality of the reservoir generally represents. The calculation method is as follows:

[0075]

[0076] Wherein, Δt s is the shear wave interval transit time, μs / m; Δt c is the compressional wave interval transit time, μs / m; v is Poisson's ratio, dimensionless.

[0077] (3) Horizontal principal stress: The lower the horizontal principal stress, the better the well completion quality of the reservoir generally represents. The calculation method is as follows:

[0078]

[0079]

[0080] Wherein, σ H is the horizontal maximum principal stress, MPa; σ h is the horizontal minimum principal stress, MPa; σ v is the overburden pressure, MPa; α is the Biot coefficient, dimensionless; is the maximum and minimum hole diameter, cm; D g is the rock density, g / cm 3 .

[0081] (4) Brittleness index: Brittleness index is an important index to judge the compressibility of the reservoir. The larger the brittleness index, the better the well completion quality. The calculation method is as follows:

[0082] BRIT = (YM_BRIT + PR_BRIT) / 2

[0083] YM_BRIT = (E - E min ) / (E max - E min ) x 100%

[0084] PR_BRIT = (v - υ min) / (v max -v min )×100%

[0085] Wherein, BRIT is the rock brittleness index; YM_BRIT is the normalized Young's modulus; PR_BRIT is the normalized Poisson's ratio; Emax is the maximum Young's modulus; Emin is the minimum Young's modulus; υ max υmin is the maximum Poisson's ratio; E is Young's modulus; υ is Poisson's ratio.

[0086] (5) Horizontal stress difference coefficient: The horizontal stress difference coefficient is an important indicator for judging the formation of complex fractures. The larger the coefficient, the better the well completion quality. The calculation method is as follows:

[0087]

[0088] Wherein, ψ is the horizontal stress difference coefficient, which is dimensionless.

[0089] Steps one and two above establish a database of block physical properties and well completion quality.

[0090] Step 3: Use grey relational analysis to obtain the grey relational degree between the sweet spot evaluation feature parameters and the gas production data of production wells in the basic database, and determine the main control factors for sweet spot identification according to the size of the grey relational degree.

[0091] The above steps, including obtaining the grey relational degree between the sweet spot evaluation feature parameters and the gas production data of production wells in the basic database, may include:

[0092] ①Establish the evaluation matrix X i The reference matrix X0 corresponds to the sweet spot evaluation characteristic parameters and the gas production of the production well, respectively;

[0093]

[0094] X0 = [X0(1), X2(2), ..., X m (n)]

[0095] In the formula: m — the number of dessert evaluation feature parameters;

[0096] n — the number of data points contained in each dessert evaluation feature parameter;

[0097] X i —The numerical values ​​of the dessert recognition feature parameters, in units;

[0098] X0 — Gas production from production wells, cubic meters per day.

[0099] ② Apply mean standardization to the matrix [X0, X1, X2, ..., X... n ] TNon-dimensionalization is performed.

[0100] ③ Calculate the correlation coefficient ξ i ;

[0101]

[0102] In the formula: ξ i Correlation coefficient, dimensionless;

[0103] P - resolution coefficient, P = 0.5;

[0104] k - the number of rows of the evaluation matrix, row;

[0105] i - the number of columns of the evaluation matrix, column.

[0106] ④ Calculate the grey correlation degree;

[0107]

[0108] In the formula: R i Grey correlation degree.

[0109] According to the size of the grey correlation degree, the main control factors of the dessert identification can include: selecting the dessert evaluation characteristic parameters with a correlation coefficient greater than 0.8 as the main control factors of the dessert evaluation.

[0110] The above steps study each characteristic parameter through the grey correlation degree analysis method, and the greater the correlation degree, the greater the influence on the dessert evaluation.

[0111] Step four, through the entropy weight method, the main control factors of the dessert identification are analyzed to determine the weight of each main control factor of the dessert identification.

[0112] In the above steps, the main control factors of the dessert identification are analyzed to determine the weight of the main control factors of the dessert identification, which can include:

[0113] ① Through the range method, the main control factors of the dessert identification X ij are standardized as evaluation indexes;

[0114] When X ij is a positive index:

[0115]

[0116] When X ij is a negative index:

[0117]

[0118] In the formula, X ij is the value of the jth evaluation index in the ith group of dessert evaluation characteristic parameters; Y ijmax(X ij ) and min(X ij ) represent the maximum and minimum values of X ij , respectively.

[0119] ②Calculate the proportion of evaluation indicators;

[0120] i = 1, 2, ···, n; j = 1, 2, ···, m

[0121] In the formula, P ij is the proportion of the jth evaluation indicator in the ith group of dessert evaluation characteristic parameters; Y ij is the standardized evaluation indicator value.

[0122] ③Calculate the information entropy of the evaluation indicators;

[0123]

[0124] In the formula, E j is the information entropy; n is the number of data included in each dessert evaluation characteristic parameter; P ij is the proportion of the jth evaluation indicator in the ith group of dessert evaluation characteristic parameters; if P ij is 0, then define

[0125] ④Calculate the weight of the evaluation indicators based on the information entropy;

[0126]

[0127] In the formula, W j is the weight of the jth evaluation indicator; E j is the information entropy; m is the number of dessert evaluation characteristic parameters, such as the number of reservoir physical parameters such as porosity, permeability k, saturation Sg or So, and the number of geomechanical parameters such as Young's modulus, Poisson's ratio, horizontal principal stress, brittleness, and horizontal stress difference coefficient.

[0128] According to the main control factors and corresponding weights of the dessert, the comprehensive coefficient of the dessert evaluation is calculated, including:

[0129]

[0130] In the formula: δ——dessert evaluation comprehensive coefficient;

[0131] G i ——dessert identification main control factor normalization, dimensionless;

[0132] W i ——dessert identification main control factor weight.

[0133] The above steps obtain the weight coefficients by establishing a dependent variable (gas production) and a plurality of independent variables (sweet spot evaluation master control factors) entropy weight method model.

[0134] Step five, according to the sweet spot identification master control factors selected above and the corresponding weight calculated, the sweet spot evaluation comprehensive coefficient is calculated.

[0135] The above steps three to five consider that there is a certain correlation between the characteristic parameters of the sweet spot evaluation and the gas production, and different parameters have different influences on the post-frac production. Therefore, combined with the post-frac production data, the grey correlation analysis method is used to select the high correlation degree as the evaluation master control factor, the entropy weight method is used to determine the evaluation weight, and the sweet spot evaluation standard is comprehensively determined to realize the establishment of the block fracturing sweet spot comprehensive evaluation standard.

[0136] Step six, through the above calculation, the well logging data of different small layers in the target block reservoir is directly corresponded to the sweet spot comprehensive evaluation coefficient and the production well gas production data, and then the intelligent sweet spot identification model training database is established.

[0137] In the above steps, the well logging data can include: natural gamma, resistivity, acoustic time difference, shale content, density, porosity, caliper, etc.

[0138] Step seven, a neural network model is established, part of the data (80% of the data) in the intelligent fracturing sweet spot identification model training database is input into the neural network model as training set data for training, and the key parameters such as activation function and neuron number in the neural network model are continuously optimized and adjusted until the loss function reaches the minimum, the optimization of the neural network model is completed, that is, the establishment of the deep learning model, the remaining part of the data (remaining 20% of the data) in the intelligent fracturing sweet spot identification model training database is used as test set data to test the deep learning model, the accuracy of the sweet spot comprehensive evaluation coefficient and the production well gas production data is verified to reach the preset effect (more than 85%), the prediction result of the optimized neural network model is realized, that is, the prediction result of the deep learning model, the intelligent fracturing sweet spot identification model is formed, or the intelligent fracturing comprehensive sweet spot model.

[0139] In the above steps, before establishing the neural network model, the standard deviation method can be used to normalize the well logging data, so as to eliminate the influence of different dimensions on data analysis, make the data comparable, and complete the normalization of well logging data, and then establish the neural network model.

[0140] The normalization processing method is as follows:

[0141]

[0142] In the formula, x max , x minThe maximum and minimum values in the sequence, respectively.

[0143] On this basis, considering that more logging curve categories and a large amount of data can improve the accuracy of the identification model, but there is also a certain degree of correlation between part of the logging curve categories, which causes data redundancy, reduces the model running speed and data processing efficiency, and needs to be analyzed for correlation and principal component dimension reduction, and the main categories with poor correlation are selected as the feature parameters for model training in the later stage.

[0144] Generally, the correlation coefficient method or regression analysis method can be used, as follows:

[0145]

[0146]

[0147] In the formula, r xy is the sample correlation coefficient, s xy is the sample covariance, s x is the sample standard deviation of x, and s y is the sample standard deviation of y.

[0148] Step eight, in the drilling construction process, real-time feedback while-drilling logging data, upload the while-drilling logging data as input parameters to the intelligent fracturing sweet spot identification model, through the calculation and analysis of the model, real-time output the corresponding sweet spot comprehensive evaluation coefficient and production well gas production data, according to the output sweet spot comprehensive evaluation coefficient and production well gas production data, judge the production layer sweet spot area of the current drilled horizon, guide the well trajectory adjustment, accurately hit the target area, ensure the reservoir drilling rate, and realize the intelligent while-drilling comprehensive fracturing sweet spot identification.

[0149] In the above steps, when the corresponding sweet spot comprehensive evaluation coefficient and production well gas production data are output in real time, the oil and water layer discrimination of the drilled horizon can also be output in real time, so as to realize the purpose layer discrimination and adjustment in the drilling process.

[0150] The above steps one to eight realize the determination of the comprehensive sweet spot of fracturing.

[0151] During the drilling construction process, the reservoir physical property characteristic parameters and geomechanics parameters output by the intelligent fracturing sweet spot identification model can be transmitted into the target block well surrounding geological model in real time, the input of the basic parameters for the construction of the fracturing model is realized, the target block well surrounding geological model is constantly updated, which is beneficial to update the reservoir understanding, guide the subsequent well drilling and fracturing scheme design, and improve the block production analysis and prediction accuracy.

[0152] After the drilling operation is completed, the intelligent fracturing sweet spot identification model can directly output the geomechanics parameter profile (including Young's modulus, Poisson's ratio, brittleness index, horizontal principal stress, etc.) along the wellbore trajectory and the geology-engineering integrated comprehensive sweet spot profile, to efficiently and quickly and intuitively guide the next step of fracturing layer selection.

[0153] In summary, the intelligent drilling comprehensive fracturing sweet spot identification method of the present application can deeply mine multi-dimensional data such as logging, reservoir physical properties, geomechanics, and post-fracturing production, organically combine engineering sweet spots and geological sweet spots, use machine learning methods, use expert analysis results as a reference, and comprehensively realize real-time identification of'sweet spots' during drilling, solve the problem of excessive influence of human factors and experience and insufficient reliability during fracturing section and layer selection, reduce the differences in decision results caused by human factors and affect the final fracturing effect, improve the fracturing design and construction efficiency, reduce the cost, and more targetedly achieve the purpose of increasing production.

[0154] The same or similar reference numerals in the drawings of the embodiments correspond to the same or similar components; in the description of the present application, it should be understood that if the orientations or positional relationships indicated by the terms "upper", "lower", "left", "right" and the like are based on the orientations or positional relationships shown in the drawings, they are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, therefore the terms describing the positional relationship in the drawings are only used for exemplary illustration, and cannot be understood as a limitation of the present patent, for those skilled in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0155] The above only describes the preferred embodiments of the present application and does not limit the present application, any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent comprehensive fracturing sweet spot identification while drilling method, characterized in that, The method comprises the following steps: collecting reservoir characteristic data and production well gas production data of a target block reservoir; screening characteristic parameters for evaluating reservoir physical property quality and characteristic parameters for evaluating well completion quality according to the reservoir characteristic data, to form a sweet spot evaluation characteristic parameter, and establishing a corresponding relationship with the corresponding production well gas production data to form a basic database; calculating a grey correlation degree of the sweet spot evaluation characteristic parameter and the production well gas production data in the basic database, and determining a sweet spot identification master control factor according to the grey correlation degree; analyzing the sweet spot identification master control factor to determine a weight of the sweet spot identification master control factor; calculating a sweet spot evaluation comprehensive coefficient according to the sweet spot identification master control factor and the corresponding weight; corresponding the logging data of different layers in the target block reservoir to the sweet spot comprehensive evaluation coefficient and the production well gas production data to establish an intelligent sweet spot identification model training database; establishing a neural network model, inputting part of data in the intelligent sweet spot identification model training database into the neural network model for training as a training set to complete establishment of a deep learning model, and inputting the remaining data in the intelligent sweet spot identification model training database into the deep learning model for testing as a test set to verify that the accuracy of the sweet spot comprehensive evaluation coefficient and the production well gas production data reaches a preset effect, thereby forming an intelligent sweet spot identification model; in a drilling operation process, real-time feedback logging while drilling data, uploading the logging while drilling data as input parameters to the intelligent sweet spot identification model, and real-time output of the corresponding sweet spot comprehensive evaluation coefficient and the production well gas production data to realize intelligent comprehensive sweet spot identification while drilling and fracturing.

2. The intelligent comprehensive sweet spot identification method while drilling and fracturing according to claim 1, wherein in the drilling operation process, the reservoir physical property characteristic parameters and the geomechanical parameters output by the intelligent sweet spot identification model are transmitted into a target block wellbore geological model in real time to update the target block wellbore geological model.

3. The intelligent comprehensive sweet spot identification method while drilling and fracturing according to claim 1, wherein after the drilling operation is completed, the intelligent sweet spot identification model outputs a geomechanical parameter profile along a wellbore trajectory and a geology-engineering integrated comprehensive sweet spot profile to guide the next fracturing layer selection.

4. The intelligent comprehensive sweet spot identification method while drilling and fracturing according to claim 1, wherein the calculation of the grey correlation degree of the sweet spot evaluation characteristic parameter and the production well gas production data in the basic database comprises: ① Establish evaluation matrix X i The reference matrix X0, respectively, corresponding to the characteristics of the dessert evaluation parameters and production well gas production; X0= [X0(1), X2(2),..., X m (n)] wherein m is the number of the sweet spot evaluation characteristic parameters, n is the number of data contained in each sweet spot evaluation characteristic parameter, X0 is the production well gas production, p is a resolution coefficient, p = 0.5, k is the number of rows of the evaluation matrix, and i is the number of columns of the evaluation matrix. ④ calculating the grey correlation degree X i - the number of values of the dessert recognition feature parameters; 5. The intelligent comprehensive sweet spot identification method while drilling and fracturing according to claim 1, wherein ② The matrix [X0, X1, X2…, Xn] is normalized by mean value standardization. n ] T and dimensionless. ③Calculate the correlation coefficient ξ i ; where: ξ i — correlation coefficient, dimensionless the analysis of the sweet spot identification master control factor to determine the weight of the sweet spot identification master control factor comprises: ② calculating the proportion of the evaluation index ③ calculating the information entropy of the evaluation index ​ In the formula, R i Grey correlation degree. ​ ​ ① The main control factor X of the dessert recognition as the evaluation index is determined by the range method ij Standardization is performed When X ij is a positive indicator: When X ij is a negative indicator: In the formula, X ij is the value of the jth evaluation index in the ith group of dessert evaluation characteristic parameters; Y ij is the normalized evaluation index value; max(X ij ) and min(X ij ) represent the maximum value and the minimum value of X ij , respectively. ​ In the formula, P ij is the proportion of the jth evaluation index in the ith group of dessert evaluation characteristic parameters; Y ij is the standardized evaluation index value; ​ In the formula, E j is information entropy; n is the number of data contained in each dessert evaluation characteristic parameter; P ij is the proportion of the jth evaluation index in the ith group of dessert evaluation characteristic parameters; if P ij is 0, then define ④The weight of the evaluation index is calculated based on information entropy In the formula, W j is the weight of the evaluation index j; E j is the information entropy; and m is the number of the sweet dessert evaluation characteristic parameters. 6.The intelligent comprehensive fracturing sweet spot identification method while drilling according to claim 1, characterized in that, According to the sweet spot identification master factor and the corresponding weight, the sweet spot evaluation comprehensive coefficient is calculated, including: In the formula: δ——sweet spot evaluation comprehensive coefficient; G i - Dessert recognition master factor normalization, dimensionless; W i - the weight of the main control factors for the dessert recognition. 7.The intelligent comprehensive fracturing sweet spot identification method while drilling according to claim 1, characterized in that, Before establishing the neural network model, the logging data is normalized. 8.The intelligent comprehensive fracturing sweet spot identification method while drilling according to claim 1, characterized in that, The logging data includes: natural gamma, resistivity, acoustic time difference, shale content, density, porosity, hole diameter. 9.The intelligent comprehensive fracturing sweet spot identification method while drilling according to claim 1, characterized in that, The characteristic parameters for evaluating the reservoir physical property quality include permeability, porosity, and saturation. 10.The intelligent comprehensive fracturing sweet spot identification method while drilling according to claim 1, characterized in that, The characteristic parameters for evaluating the well completion quality include Young's modulus, Poisson's ratio, horizontal principal stress, brittleness index, and horizontal stress difference coefficient.

Images