Quantitative prediction method and device for shale brittleness index, electronic equipment and medium
By utilizing the relationship between the brittleness index and sensitive elastic parameters in the shale reservoir, combined with mutual information and sparse Bayesian learning, high-precision prediction of the shale brittleness index is achieved, solving the problem of inaccurate prediction of brittleness index in the existing technology, and providing effective guidance for fracturing operations.
Patent Information
- Application Number
- CN202311582744.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-24
- Publication Date
- 2025-05-27
AI Technical Summary
The prior art is difficult to accurately predict the shale brittleness index, which affects the fracturing effect of shale reservoirs.
By using the relationship between the brittleness index and the sensitive elastic parameters obtained on the well, combining mutual information and petrophysical analysis, elastic parameters that are sensitive to the brittleness index are screened out, and the nonlinear mapping relationship between the brittleness index and the sensitive elastic parameters are obtained based on sparse Bayesian learning to achieve quantitative prediction of the brittleness index.
It realizes high-precision prediction of the shale brittleness index, avoids the problem of seismic mineral component prediction, provides an assessment of the uncertainty of the prediction results of the brittleness index, and guides the fracturing operation of the shale reservoir.
Smart Images
Figure CN120044631A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of oil and gas geophysical exploration, and more particularly, to a method, device, electronic device and medium for quantitatively predicting shale brittleness index. Background Art
[0002] Shale oil and gas reservoirs are rich in resources. However, due to the influence of low porosity and low permeability, it is necessary to optimize the pore and permeability structure through hydraulic fracturing to reduce the mining difficulty. The brittleness index is an important parameter reflecting the fracturing quality of shale reservoirs, and its accurate prediction can guide the fracturing of shale reservoirs. The conventional methods for predicting brittleness index mainly include the following: (1) Using elastic parameters (Young's modulus and Poisson's ratio) to characterize brittleness. This method does not consider the influence of anisotropy on brittleness, while shale has strong anisotropy, and a single elastic parameter or its combination is difficult to accurately describe shale brittleness; (2) Describing brittleness based on mineral composition. This method characterizes brittleness according to the percentage of brittle mineral components. However, due to the complex mineral composition of shale, it is difficult to accurately obtain the mineral composition curve by conventional seismic methods.
[0003] Therefore, it is necessary to develop a method, device, electronic device and medium for quantitatively predicting shale brittleness index.
[0004] The information disclosed in the background art part of the present invention is only intended to deepen the understanding of the general background art of the present invention, and should not be regarded as an admission or any form of suggestion that this information constitutes the prior art known to those skilled in the art. Summary of the Invention
[0005] The present invention provides a method, device, electronic device and medium for quantitatively predicting shale brittleness index, which realizes the quantitative prediction of brittleness index by using the relationship between the brittleness index obtained in the well and the sensitive elastic parameters.
[0006] In a first aspect, an embodiment of the present disclosure provides a method for quantitatively predicting shale brittleness index, including:
[0007] Calibrating and processing the logging data for consistency to obtain optimized logging data;
[0008] According to the optimized logging data, obtain the brittleness index curve in the well;
[0009] Determine the elastic parameters sensitive to the brittleness index as sensitive elastic parameters, and obtain the sensitive elastic parameter curve;
[0010] According to the brittleness index curve and the sensitive elastic parameter curve, obtain the brittleness index prediction model;
[0011] Invert the sensitive elastic parameters to obtain the inversion result of the sensitive elastic parameters;
[0012] Based on the brittle index prediction model and the inversion result of the sensitive elastic parameters, obtain the seismic prediction result of the brittle index.
[0013] As a specific implementation manner of the embodiments of the present disclosure, the calibration and consistency processing includes well logging data environmental calibration, wild value removal, and inter-well consistency processing.
[0014] As a specific implementation manner of the embodiments of the present disclosure, obtaining the in-well brittle index curve based on the optimized well logging data includes:
[0015] Based on the optimized well logging data, and based on well logging interpretation theory, starting from the well logging curves, combined with logging and core data, obtain the interpretation result of the in-well mineral component curve, and further obtain the in-well brittle index curve.
[0016] As a specific implementation manner of the embodiments of the present disclosure, determining the elastic parameters sensitive to the brittle index as the sensitive elastic parameters includes:
[0017] Taking the in-well P-wave and S-wave velocities and density elastic parameters as the data basis, and adopting a method combining mutual information and rock physics analysis, determine the elastic parameters sensitive to the brittle index as the sensitive elastic parameters.
[0018] As a specific implementation manner of the embodiments of the present disclosure, the mutual information is:
[0019]
[0020] where p(x,y) is the joint probability distribution function of variables X and Y, and p(x) and p(y) are the probability distribution functions of X and Y respectively.
[0021] As a specific implementation manner of the embodiments of the present disclosure, obtaining the brittle index prediction model based on the brittle index curve and the sensitive elastic parameter curve includes:
[0022] According to the brittle index curve and the sensitive elastic parameter curve, make a sample set, and divide the training set and the test set according to a ratio of 7:3;
[0023] Based on sparse Bayesian learning, obtain the non-linear mapping relationship between the brittle index and the sensitive elastic parameters, which is the brittle index prediction model, and use the test set to evaluate the brittle index prediction model.
[0024] As a specific implementation manner of the embodiments of the present disclosure, the mathematical expression of sparse Bayesian learning is:
[0025]
[0026] where t i is the objective function, ω nis the linear fitting weight coefficient, K i is the kernel function, ε i ∈N(0, σ 2 ) is the random noise.
[0027] In a second aspect, the embodiments of the present disclosure also provide a device for quantitatively predicting the shale brittleness index, including:
[0028] A processing module that corrects and performs consistency processing on well logging data to obtain optimized well logging data;
[0029] An on-well brittleness index curve acquisition module that obtains an on-well brittleness index curve according to the optimized well logging data;
[0030] A sensitive elastic parameter curve acquisition module that determines the elastic parameters sensitive to the brittleness index as sensitive elastic parameters and obtains a sensitive elastic parameter curve;
[0031] A prediction model acquisition module that obtains a brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curve;
[0032] An inversion module that performs inversion on the sensitive elastic parameters to obtain an inversion result of the sensitive elastic parameters;
[0033] A prediction module that obtains a seismic prediction result of the brittleness index according to the brittleness index prediction model and the inversion result of the sensitive elastic parameters.
[0034] As a specific implementation manner of the embodiments of the present disclosure, the correction and consistency processing include well logging data environment correction, wild value removal, and inter-well consistency processing.
[0035] As a specific implementation manner of the embodiments of the present disclosure, obtaining the on-well brittleness index curve according to the optimized well logging data includes:
[0036] According to the optimized well logging data, based on well logging interpretation theory, starting from the well logging curve, combining logging and core data, obtaining the interpretation result of the on-well mineral component curve, and further obtaining the on-well brittleness index curve.
[0037] As a specific implementation manner of the embodiments of the present disclosure, determining the elastic parameters sensitive to the brittleness index as sensitive elastic parameters includes:
[0038] Taking the on-well P-wave and S-wave velocities and density elastic parameters as the data basis, using a method combining mutual information and rock physics analysis to determine the elastic parameters sensitive to the brittleness index as sensitive elastic parameters.
[0039] As a specific implementation manner of the embodiments of the present disclosure, the mutual information is:
[0040]
[0041] Among them, p(x, y) is the joint probability distribution function of variables X and Y, and p(x) and p(y) are the probability distribution functions of X and Y respectively.
[0042] As a specific implementation manner of the embodiment of the present disclosure, obtaining a brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curve includes:
[0043] Making a sample set according to the brittleness index curve and the sensitive elastic parameter curve, and dividing the training set and the test set according to a ratio of 7:3;
[0044] Based on sparse Bayesian learning, obtaining the non-linear mapping relationship between the brittleness index and the sensitive elastic parameter, which is the brittleness index prediction model, and evaluating the brittleness index prediction model using the test set.
[0045] As a specific implementation manner of the embodiment of the present disclosure, the mathematical expression of sparse Bayesian learning is:
[0046]
[0047] Among them, t i is the objective function, ω n is the linear fitting weight coefficient, K i is the kernel function, ε i ∈N(0, σ 2 ) is the random noise.
[0048] In a third aspect, the embodiment of the present disclosure further provides an electronic device, which includes:
[0049] A memory storing executable instructions;
[0050] A processor, and the processor runs the executable instructions in the memory to implement the shale brittleness index quantitative prediction method described above.
[0051] In a fourth aspect, the embodiment of the present disclosure further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the shale brittleness index quantitative prediction method described above is implemented.
[0052] Its beneficial effects are as follows:
[0053] (1) The present invention uses a method combining mutual information and rock physics analysis to optimize the elastic parameter curve sensitive to the brittleness index. Starting from both qualitative and quantitative perspectives, the elastic parameters sensitive to the brittleness index can be screened out effectively.
[0054] (2) Based on the sparse Bayesian learning method, the present invention can effectively obtain the non-linear mapping relationship between sensitive elastic parameters and brittleness index. At the same time, the sparse Bayesian learning method can give the posterior distribution of the prediction result, which is convenient for interpreters to evaluate the uncertainty of the brittleness index prediction result.
[0055] (3) By integrating seismic, logging and other data and based on the process described in the invention, the present invention avoids the difficult problem of seismic mineral component prediction and realizes high-precision prediction of brittleness index.
[0056] The method and device of the present invention have other characteristics and advantages, which will be obvious from the accompanying drawings incorporated herein and the subsequent specific embodiments, or will be described in detail in the accompanying drawings incorporated herein and the subsequent specific embodiments. These accompanying drawings and specific embodiments are jointly used to explain the specific principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] By describing the exemplary embodiments of the present invention in more detail with reference to the accompanying drawings, the above and other objects, features and advantages of the present invention will become more obvious. Among them, in the exemplary embodiments of the present invention, the same reference numerals generally represent the same components.
[0058] Figure 1 A flowchart showing the steps of a method for quantitatively predicting shale brittleness index.
[0059] Figure 2 A flowchart showing the steps of a method for quantitatively predicting shale brittleness index according to an embodiment of the present invention.
[0060] Figure 3 A schematic diagram showing the logging interpretation results of a typical well according to an embodiment of the present invention.
[0061] Figure 4 A schematic diagram showing the intersection of brittleness index and Young's modulus according to an embodiment of the present invention.
[0062] Figure 5 A schematic diagram showing the intersection of brittleness index and Poisson's ratio according to an embodiment of the present invention.
[0063] Figure 6 A schematic diagram showing the brittleness index prediction profile across Well A1 according to an embodiment of the present invention.
[0064] Figure 7 A block diagram showing a device for quantitatively predicting shale brittleness index according to an embodiment of the present invention.
[0065] Description of the reference numerals:
[0066] 201. Processing module; 202. In-well brittleness index curve acquisition module; 203. Sensitive elastic parameter curve acquisition module; 204. Prediction model acquisition module; 205. Inversion module; 206. Prediction module. Detailed implementation manners
[0067] The preferred implementation manners of the present invention will be described in more detail below. Although the preferred implementation manners of the present invention are described below, it should be understood that the present invention can be implemented in various forms and should not be limited by the implementation manners set forth herein.
[0068] To facilitate understanding of the solutions and effects of the embodiments of the present invention, six specific application examples are given below. Those skilled in the art should understand that this example is only for facilitating the understanding of the present invention, and any specific details are not intended to limit the present invention in any way.
[0069] Example 1
[0070] Figure 1 A flowchart showing the steps of the quantitative prediction method for shale brittleness index is shown.
[0071] As Figure 1 shown, the quantitative prediction method for shale brittleness index includes: Step 101, performing correction and consistency processing on well logging data to obtain optimized well logging data; Step 102, obtaining an in-well brittleness index curve according to the optimized well logging data; Step 103, determining elastic parameters sensitive to the brittleness index as sensitive elastic parameters, and obtaining sensitive elastic parameter curves; Step 104, obtaining a brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curves; Step 105, performing inversion on the sensitive elastic parameters to obtain the inversion result of the sensitive elastic parameters; Step 106, obtaining the seismic prediction result of the brittleness index according to the brittleness index prediction model and the inversion result of the sensitive elastic parameters.
[0072] In one example, the correction and consistency processing includes well logging data environmental correction, wild value removal, and inter-well consistency processing.
[0073] In one example, obtaining an in-well brittleness index curve according to the optimized well logging data includes:
[0074] According to the optimized well logging data, based on well logging interpretation theory, starting from well logging curves, combined with logging and core data, obtaining the interpretation result of the in-well mineral component curve, and further obtaining the in-well brittleness index curve.
[0075] In one example, determining elastic parameters sensitive to the brittleness index as sensitive elastic parameters includes:
[0076] Based on the in - well P - wave and S - wave velocities and density elastic parameters as data, a method combining mutual information and rock physics analysis is used to determine the elastic parameters sensitive to the brittleness index as the sensitive elastic parameters.
[0077] In one example, the mutual information is:
[0078]
[0079] where \(p(x,y)\) is the joint probability distribution function of variables \(X\) and \(Y\), and \(p(x)\) and \(p(y)\) are the probability distribution functions of \(X\) and \(Y\) respectively.
[0080] In one example, according to the brittleness index curve and the sensitive elastic parameter curve, obtaining the brittleness index prediction model includes:
[0081] According to the brittleness index curve and the sensitive elastic parameter curve, make a sample set and divide the training set and the test set according to the ratio of 7:3;
[0082] Based on sparse Bayesian learning, obtain the non - linear mapping relationship between the brittleness index and the sensitive elastic parameters, which is the brittleness index prediction model, and use the test set to evaluate the brittleness index prediction model.
[0083] In one example, the mathematical expression of sparse Bayesian learning is:
[0084]
[0085] where \(t\) i is the objective function, \(\omega\) n is the linear fitting weight coefficient, \(K\) i is the kernel function, \(\epsilon\) i \(\in N(0,\sigma\) 2 ) is the random noise.
[0086] Specifically, well - logging data correction and consistency processing. It mainly includes operations such as well - logging data environmental correction, wild - value removal, and inter - well consistency processing to obtain optimized well - logging data.
[0087] Obtaining the in - well brittleness index. Based on well - logging interpretation theory, starting from conventional well - logging curves and combining logging and core data, obtain the interpretation results of the in - well mineral composition curves, and further obtain the in - well brittleness index curve.
[0088] Optimizing sensitive parameters. Based on elastic parameters such as in - well P - wave and S - wave velocities and density as data, use a method combining mutual information and rock physics analysis to optimize the elastic parameter curves sensitive to the brittleness index.
[0089] Mutual information is an index that can describe the mutual dependence of two random variables, and its definition is as follows:
[0090]
[0091] Among them, p(x, y) is the joint probability distribution function of variables X and Y, and p(x) and p(y) are the probability distribution functions of X and Y respectively.
[0092] Obtain a brittle index prediction model. Using the logging brittle index curve and the sensitive elastic parameter curve, a sample set is made, and the training set and the test set are divided according to a ratio of 7:3. Based on sparse Bayesian learning, the non-linear mapping relationship between the brittle index and the sensitive elastic parameters is obtained, and the brittle index prediction model is evaluated using the test set.
[0093] Sparse Bayesian learning is a mathematical model under the Bayesian framework, and its mathematical expression is as follows:
[0094]
[0095] Among them: t i is the objective function, ω n is the linear fitting weight coefficient, K i is the kernel function, ε i ∈N(0, σ 2 ) is the random noise.
[0096] According to Bayesian theory, the posterior distribution of ω satisfies a Gaussian distribution with variance ∑ and expectation μ:
[0097] ∑ = (σ -2 φ T φ + A) -1
[0098] μ = σ -2 ∑φ T t
[0099] Among them, A = diag(α 1 , α 1 , …, α N ).
[0100] For the prediction of new data, the posterior distribution is:
[0101] p(t x |t) ~ N(μ T φ(x), σ x 2 )
[0102] Among them: t x = μ T φ(x),
[0103] Inversion of sensitive elastic parameters. Based on the prestack synchronous inversion method, the inversion results of P-wave and S-wave velocities and density are obtained, and further transformed to obtain the inversion results of sensitive elastic parameters.
[0104] Obtain the brittleness index. Based on the inverted sensitive elastic parameters as the data basis, use the brittleness index prediction model to obtain the seismic prediction results of the brittleness index.
[0105] Aiming at the problem of brittleness index prediction, this invention comprehensively uses seismic, logging, geological and other data. First, perform logging data correction and consistency processing, and use the optimized logging data to obtain the brittleness index prediction results on the well; then, through the method combining mutual information and rock physics analysis, screen the elastic parameters sensitive to the brittleness index; finally, based on sparse Bayesian learning, obtain the non-linear mapping relationship between the sensitive elastic parameters and the brittleness index, and based on the prestack inversion results, further transform to obtain the elastic parameters sensitive to the brittleness index, and use the relationship between the brittleness index obtained on the well and the sensitive elastic parameters to realize the quantitative seismic prediction of the brittleness index. This method can effectively predict the brittleness index, and is simple to apply, with strong popularization and application prospects.
[0106] Example 2
[0107] This invention also provides a device for quantitative prediction of shale brittleness index, including:
[0108] A processing module that corrects and performs consistency processing on logging data to obtain optimized logging data;
[0109] A module for obtaining the brittleness index curve on the well, which obtains the brittleness index curve on the well according to the optimized logging data;
[0110] A module for obtaining the sensitive elastic parameter curve, which determines the elastic parameters sensitive to the brittleness index as the sensitive elastic parameters and obtains the sensitive elastic parameter curve;
[0111] A module for obtaining the prediction model, which obtains the brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curve;
[0112] An inversion module that performs inversion on the sensitive elastic parameters to obtain the inversion results of the sensitive elastic parameters;
[0113] A prediction module that obtains the seismic prediction results of the brittleness index according to the brittleness index prediction model and the inversion results of the sensitive elastic parameters.
[0114] In one example, the correction and consistency processing include logging data environmental correction, outlier removal and inter-well consistency processing.
[0115] In one example, obtaining the brittleness index curve on the well according to the optimized logging data includes:
[0116] Based on the optimized logging data, starting from the logging curves and combining with mud logging and core data according to the logging interpretation theory, the interpretation results of the mineral component curves in the well are obtained, and further the brittleness index curve in the well is obtained.
[0117] In one example, determining the elastic parameters sensitive to the brittleness index as sensitive elastic parameters includes:
[0118] Based on the in-well P-wave and S-wave velocities and density elastic parameters as data, a method combining mutual information and rock physics analysis is adopted to determine the elastic parameters sensitive to the brittleness index as sensitive elastic parameters.
[0119] In one example, the mutual information is:
[0120]
[0121] where p(x,y) is the joint probability distribution function of variables X and Y, and p(x) and p(y) are the probability distribution functions of X and Y respectively.
[0122] In one example, obtaining the brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curve includes:
[0123] According to the brittleness index curve and the sensitive elastic parameter curve, a sample set is made and divided into a training set and a test set according to a ratio of 7:3;
[0124] Based on sparse Bayesian learning, the non-linear mapping relationship between the brittleness index and the sensitive elastic parameters is obtained, which is the brittleness index prediction model, and the test set is used to evaluate the brittleness index prediction model.
[0125] In one example, the mathematical expression of sparse Bayesian learning is:
[0126]
[0127] where t i is the objective function, ω n is the linear fitting weight coefficient, K i is the kernel function, ε i ∈N(0,σ 2 ) is the random noise.
[0128] Specifically, logging data correction and consistency processing. It mainly includes operations such as logging data environmental correction, wild value removal, and inter-well consistency processing to obtain optimized logging data.
[0129] Obtaining the brittleness index in the well. Based on the logging interpretation theory, starting from the conventional logging curves and combining with mud logging and core data, the interpretation results of the mineral component curves in the well are obtained, and further the brittleness index curve in the well is obtained.
[0130] Optimization of sensitive parameters. Based on elastic parameters such as in-well P-wave and S-wave velocities and density, the elastic parameter curves sensitive to the brittleness index are optimized by combining mutual information and petrophysical analysis.
[0131] Mutual information is an index that can describe the mutual dependence of two random variables, and its definition is as follows:
[0132]
[0133] where p(x,y) is the joint probability distribution function of variables X and Y, and p(x) and p(y) are the probability distribution functions of X and Y respectively
[0134] Obtain the brittleness index prediction model. Using the well logging brittleness index curve and the sensitive elastic parameter curve, a sample set is made, and the training set and the test set are divided according to the ratio of 7:3. Based on sparse Bayesian learning, the non-linear mapping relationship between the brittleness index and the sensitive elastic parameters is obtained, and the brittleness index prediction model is evaluated using the test set.
[0135] Sparse Bayesian learning is a mathematical model under the Bayesian framework, and its mathematical expression is as follows:
[0136]
[0137] where: t i is the objective function, ω n is the linear fitting weight coefficient, K i is the kernel function, ε i ∈N(0,σ 2 ) is the random noise.
[0138] According to Bayesian theory, the posterior distribution of ω satisfies a Gaussian distribution with variance ∑ and mean μ:
[0139] ∑=(σ -2 φ T φ+A) -1
[0140] μ=σ -2 ∑φ T t
[0141] where, A = diag(α 1 ,α 1 ,…,α N ).
[0142] For the prediction of new data, the posterior distribution is:
[0143] p(t x |t)~N(μ Tφ(x), σ x 2 )
[0144] where: t x = μ T φ(x),
[0145] Inversion of sensitive elastic parameters. Based on the prestack synchronous inversion method, the inversion results of P-wave and S-wave velocities and density are obtained, and further transformed to obtain the inversion results of sensitive elastic parameters.
[0146] Obtaining the brittleness index. Based on the inverted sensitive elastic parameters as the data basis, using the brittleness index prediction model, the seismic prediction results of the brittleness index are obtained.
[0147] Example 3
[0148] Figure 2 The flowchart showing the steps of the shale brittleness index quantitative prediction method according to an embodiment of the present invention is shown.
[0149] As Figure 2 shown, taking the data of a certain shale actual work area as an example, the quantitative prediction research of the brittleness index is carried out based on the method mentioned in the present invention.
[0150] Step 1: Log data correction and consistency processing. There are 5 wells in the study area. For the well data in the study area, operations such as logging data environment correction, wild value removal, and inter-well consistency processing are carried out to obtain the optimized logging data.
[0151] Figure 3 The schematic diagram showing the logging interpretation results of a typical well according to an embodiment of the present invention is shown.
[0152] Step 2: Obtaining the brittleness index on the well. Based on the logging interpretation theory, starting from the conventional logging curves, combined with mud logging and core data, the interpretation results of the mineral component curves on the well are obtained, and further the brittleness index curve on the well is obtained. Figure 3 The logging interpretation results diagram of typical wells in the work area is shown.
[0153] Figure 4 The schematic diagram showing the intersection of the brittleness index and Young's modulus according to an embodiment of the present invention is shown.
[0154] Figure 5 The schematic diagram showing the intersection of the brittleness index and Poisson's ratio according to an embodiment of the present invention is shown.
[0155] Step 3: Optimization of sensitive parameters. Based on the elastic parameters such as P-wave and S-wave velocities and density on the well as the data basis, the elastic parameter curves sensitive to the brittleness index are optimized by using the method combining mutual information and rock physics analysis. Figure 4 andFigure 5 They are cross plots of brittleness index vs. Young's modulus and Poisson's ratio respectively. Based on the above method, the elastic parameters sensitive to the brittleness index in the study area are selected as Young's modulus, Poisson's ratio, and the ratio of Young's modulus to Poisson's ratio.
[0156] Step 4: Obtain the brittleness index prediction model. Using the logging brittleness index curve and the sensitive elastic parameter curves, a sample set is made. Four wells are selected as training wells, and the remaining one well is used as a verification well. Based on sparse Bayesian learning, the non-linear mapping relationship between the brittleness index and the sensitive elastic parameters is obtained, and the brittleness index prediction model is evaluated using the test set.
[0157] Step 5: Inversion of sensitive elastic parameters. Based on the prestack simultaneous inversion method, the inversion results of P-wave and S-wave velocities and density are obtained, and further transformed to obtain the inversion results of sensitive elastic parameters (Young's modulus, Poisson's ratio, and the ratio of Young's modulus to Poisson's ratio).
[0158] Figure 6 The schematic diagram of the brittleness index prediction profile passing through Well A1 according to an embodiment of the present invention is shown.
[0159] Step 6: Obtain the brittleness index. Taking the sensitive elastic parameters obtained in Step 5 as the data basis, and using the brittleness index prediction model obtained in Step 4, the seismic prediction result of the brittleness index is obtained, as Figure 6 shown. It can be seen from the figure that the brittleness index prediction result has a high consistency with that of the well, proving that the method can effectively achieve the quantitative prediction of the brittleness index.
[0160] Example 4
[0161] Figure 7 The block diagram of a device for quantitatively predicting the shale brittleness index according to an embodiment of the present invention is shown.
[0162] As Figure 7 shown, the device for quantitatively predicting the shale brittleness index includes:
[0163] A processing module 201, which corrects and performs consistency processing on logging data to obtain optimized logging data;
[0164] An on-well brittleness index curve acquisition module 202, which obtains the on-well brittleness index curve according to the optimized logging data;
[0165] A sensitive elastic parameter curve acquisition module 203, which determines the elastic parameters sensitive to the brittleness index as sensitive elastic parameters and obtains the sensitive elastic parameter curves;
[0166] A prediction model acquisition module 204, which obtains the brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curves;
[0167] The inversion module 205 performs inversion on sensitive elastic parameters to obtain the inversion results of sensitive elastic parameters;
[0168] The prediction module 206 obtains the seismic prediction results of the brittleness index according to the brittleness index prediction model and the inversion results of sensitive elastic parameters.
[0169] As an optional solution, the correction and consistency processing include logging data environmental correction, outlier removal, and inter-well consistency processing.
[0170] As an optional solution, obtaining the brittleness index curve on the well based on the optimized logging data includes:
[0171] Based on the optimized logging data, starting from the logging curves, combining with mud logging and core data according to logging interpretation theory, the interpretation results of the mineral component curves on the well are obtained, and further the brittleness index curve on the well is obtained.
[0172] As an optional solution, determining the elastic parameters sensitive to the brittleness index as sensitive elastic parameters includes:
[0173] Taking the in-well P-wave and S-wave velocities and density elastic parameters as the data basis, a method combining mutual information and rock physics analysis is used to determine the elastic parameters sensitive to the brittleness index as sensitive elastic parameters.
[0174] As an optional solution, the mutual information is:
[0175]
[0176] where p(x,y) is the joint probability distribution function of variables X and Y, and p(x) and p(y) are the probability distribution functions of X and Y respectively.
[0177] As an optional solution, obtaining the brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curve includes:
[0178] According to the brittleness index curve and the sensitive elastic parameter curve, a sample set is made and divided into a training set and a test set according to a ratio of 7:3;
[0179] Based on sparse Bayesian learning, the non-linear mapping relationship between the brittleness index and the sensitive elastic parameters is obtained, which is the brittleness index prediction model, and the test set is used to evaluate the brittleness index prediction model.
[0180] As an optional solution, the mathematical expression of sparse Bayesian learning is:
[0181]
[0182] where t i is the objective function, ω nis the linear fitting weight coefficient, K i is the kernel function, ε i ∈N(0, σ 2 ) is the random noise.
[0183] Example 5
[0184] The present disclosure provides an electronic device, which includes: a memory storing executable instructions; and a processor that runs the executable instructions in the memory to implement the above-mentioned shale brittleness index quantitative prediction method.
[0185] The electronic device according to an embodiment of the present disclosure includes a memory and a processor.
[0186] The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.
[0187] The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In an embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory.
[0188] Those skilled in the art should understand that, in order to solve the technical problem of how to obtain good user experience effects, this embodiment may also include well-known structures such as communication buses, interfaces, etc., and these well-known structures should also be included in the protection scope of the present disclosure.
[0189] For the detailed description of this embodiment, reference may be made to the corresponding descriptions in the foregoing embodiments, and details will not be repeated here.
[0190] Example 6
[0191] The embodiment of the present disclosure provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the shale brittleness index quantitative prediction method is implemented.
[0192] The computer-readable storage medium according to an embodiment of the present disclosure stores non-temporary computer-readable instructions. When the non-temporary computer-readable instructions are run by a processor, all or part of the steps of the methods in the foregoing embodiments of the present disclosure are executed.
[0193] The above computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROMs and DVDs), magneto-optical storage media (e.g., MOs), magnetic storage media (e.g., magnetic tapes or removable hard disks), media with built-in rewritable non-volatile memories (e.g., memory cards), and media with built-in ROMs (e.g., ROM cartridges).
[0194] Those skilled in the art should understand that the purpose of the above description of the embodiments of the present invention is only to exemplarily illustrate the beneficial effects of the embodiments of the present invention, and is not intended to limit the embodiments of the present invention to any of the examples given.
[0195] The embodiments of the present invention have been described above. The above description is exemplary and not exhaustive, and is also not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
Claims
1. A quantitative prediction method for shale brittleness index, characterized in that, it includes: Carry out calibration and consistency processing on logging data to obtain optimized logging data; According to the optimized logging data, obtain the in-well brittleness index curve; Determine the elastic parameters sensitive to the brittleness index as sensitive elastic parameters, and obtain the sensitive elastic parameter curve; According to the brittleness index curve and the sensitive elastic parameter curve, obtain the brittleness index prediction model; Invert the sensitive elastic parameters to obtain the inversion result of the sensitive elastic parameters; According to the brittleness index prediction model and the inversion result of the sensitive elastic parameters, obtain the seismic prediction result of the brittleness index.
2. The quantitative prediction method for shale brittleness index according to claim 1, wherein, The calibration and consistency processing includes logging data environmental calibration, wild value removal and inter-well consistency processing.
3. The quantitative prediction method for shale brittleness index according to claim 1, wherein, Obtaining the in-well brittleness index curve according to the optimized logging data includes: According to the optimized logging data, based on logging interpretation theory, starting from the logging curve, combining logging and core data, obtain the interpretation result of the in-well mineral component curve, and further obtain the in-well brittleness index curve.
4. The quantitative prediction method for shale brittleness index according to claim 1, wherein, Determining the elastic parameters sensitive to the brittleness index as sensitive elastic parameters includes: Taking the in-well P-wave and S-wave velocities and density elastic parameters as the data basis, and using the method combining mutual information and rock physics analysis to determine the elastic parameters sensitive to the brittleness index as sensitive elastic parameters.
5. The quantitative prediction method for shale brittleness index according to claim 4, wherein, The mutual information is: where p(x,y) is the joint probability distribution function of variables X and Y, and p(x) and p(y) are the probability distribution functions of X and Y respectively.
6. The quantitative prediction method for shale brittleness index according to claim 1, wherein, Obtaining the brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curve includes: According to the brittleness index curve and the sensitive elastic parameter curve, make a sample set, and divide the training set and the test set according to the ratio of 7:3; Based on sparse Bayesian learning, obtain the non-linear mapping relationship between the brittleness index and the sensitive elastic parameters, which is the brittleness index prediction model, and use the test set to evaluate the brittleness index prediction model.
7. The quantitative prediction method for shale brittleness index according to claim 6, wherein, The mathematical expression of sparse Bayesian learning is: where t i is the objective function, ω n is the linear fitting weight coefficient, K i is the kernel function, ε i ∈N(0,σ 2 ) is the random noise.
8. A quantitative prediction device for shale brittleness index, characterized in that, it includes: A processing module that performs calibration and consistency processing on logging data to obtain optimized logging data; An in-well brittleness index curve acquisition module that obtains the in-well brittleness index curve according to the optimized logging data; A sensitive elastic parameter curve acquisition module that determines the elastic parameters sensitive to the brittleness index as sensitive elastic parameters and obtains the sensitive elastic parameter curve; A prediction model acquisition module that obtains the brittleness index prediction model according to the brittleness index curve and the sensitive elastic parameter curve; An inversion module that performs inversion on the sensitive elastic parameters to obtain the inversion result of the sensitive elastic parameters; A prediction module that obtains the seismic prediction result of the brittleness index according to the brittleness index prediction model and the inversion result of the sensitive elastic parameters.
9. An electronic device, characterized in that, the electronic device includes: a memory storing executable instructions; a processor that runs the executable instructions in the memory to implement the shale brittleness index quantitative prediction method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the shale brittleness index quantitative prediction method according to any one of claims 1-7.