Method, device, storage medium and equipment for predicting diagenesis of continental shale

Abstract

The present application relates to a kind of prediction method, device, storage medium and equipment of terrestrial mud shale diagenesis, method includes: 1) extraction terrestrial mud shale reservoir characteristics, obtain the Archie parameter in terrestrial mud shale, determine the cementation coefficient m of terrestrial mud shale by three-dimensional regression, and calculate diagenetic coefficient MD;2) determine the most sensitive parameter data to diagenesis, and the most sensitive parameter data is divided into training set, verification set and test set;3) according to the artificial neural network model of Archie parameter and cementation coefficient is established, and the training set is used to train artificial neural network model;4) the error of model is constantly tested in the training process of artificial neural network model using verification set and test set;5) the performance of artificial neural network model after training is evaluated, if performance acceptance is good, step 6) is carried out, otherwise step 3) is returned;6) the diagenesis of terrestrial mud shale is predicted using the artificial neural network model with good performance acceptance.

Description

Technical Field

[0001] This invention relates to the field of geophysical technology, specifically to a method, apparatus, storage medium, and device for predicting diagenesis of terrestrial mudstone and shale. Background Technology

[0002] Compared to sandstone and carbonate rocks, shale and mudstone have smaller grain sizes, making them more difficult to observe. Furthermore, limitations in microscopic experimental conditions have made their diagenesis a weak area of ​​research in sedimentology and even geology. The diagenesis of shale and mudstone is constrained by the evolution of physical, chemical, and biological factors, and the driving mechanisms are complex and variable due to the superposition of actual geological conditions and complex factors. Moreover, microorganisms participate in almost all diagenetic processes, making diagenesis a typical biogeochemical process. Characteristics inherited from early diagenesis can influence the progress of intermediate and late-stage diagenesis, thus affecting the physical and mechanical properties of shale and mudstone strata. Controlled by complex actual geological conditions, especially the limitations in research on the material transport processes and mechanisms during intermediate and late-stage diagenesis, research on the driving mechanisms and evolutionary paths of diagenesis is relatively weak, and the control mechanisms of diagenesis are exceptionally complex. In addition, during diagenesis, deformation and fracture morphology are usually related to stress distribution and geometry.

[0003] Diagenesis refers to the effects of physical, chemical, and / or biological processes on the structure and mineral composition of rocks during sedimentation and diagenesis. Diagenesis continues as long as sediments are in contact with sufficient amounts of chemically active fluids, whether atmospheric or marine (brackish, normal, or hypersaline). Diagenesis is typically confined to low-temperature and low-pressure conditions, explicitly excluding processes and products associated with metamorphism. Diagenetic processes are usually associated with the diagenetic environment, which provides the overall framework for interpreting the geometry of cementation and porous units. Several factors influence diagenesis, including key chemical conditions (redox conditions, pH, and CO2), diffusion and ion exchange rates, the ratio of low-Mg calcite to aragonite, erosion rates, pre-diagenetic sediments, grain size, organic matter utilization, the rate and composition of interstitial hydrocarbon fluids, bacterial abundance, clay percentage, and physical conditions. Diagenesis typically reduces total porosity through various forms of cementation and mineral growth, and may also increase porosity by leaching the matrix of particles (dissolution) to form secondary pore spaces or by creating / redistributing pores through dolomitization.

[0004] However, current technology makes it difficult to accurately predict the diagenesis of terrestrial mudstones and shale. Summary of the Invention

[0005] To address the aforementioned problems, the purpose of this invention is to provide a method, apparatus, storage medium, and device for predicting diagenesis of terrestrial mudstone and shale, which can accurately predict diagenesis of terrestrial mudstone and shale.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] The method for predicting diagenesis of terrestrial mudstones and shale as described in this invention includes the following steps:

[0008] 1) Extract the reservoir characteristics of continental mudstone and shale, obtain the Archie parameters in continental mudstone and shale, determine the cementation coefficient m of continental mudstone and shale through three-dimensional regression, and calculate the diagenetic coefficient MD;

[0009] 2) Based on the diagenetic coefficient, determine the most sensitive parameter data for diagenesis, and divide the most sensitive parameter data into training set, validation set and test set;

[0010] 3) Establish an artificial neural network model based on Archie parameters and cementation coefficients, and train the artificial neural network model using the training set;

[0011] 4) Continuously test the model's error during the training process of the artificial neural network model using validation and test sets;

[0012] 5) Evaluate the performance of the trained artificial neural network model. If the performance is acceptable, proceed to step 6); otherwise, return to step 3.

[0013] 6) Predict the diagenesis of terrestrial mudstones and shale using artificial neural network models with good performance acceptance.

[0014] Preferably, in step 1) above, the method involves using Resform software to extract the characteristics of continental mudstone and shale reservoirs and using Pickett Plot technology to obtain Archie parameters in continental mudstone and shale.

[0015] Preferably, in step 2) above, the method uses the relative importance algorithm of Microsoft Excel to determine the most sensitive parameter data for diagenesis.

[0016] The method described herein, preferably, involves determining the cementation coefficient m of terrestrial mudstone and shale through three-dimensional regression in step 1) as follows:

[0017] In rock physics, the formation coefficient F and effective porosity Representing the fundamental parameters controlling electrical properties, these are physically measured using resistivity and porosity logging or conventional core analysis. Mathematically, the formation coefficient is related to resistivity as follows:

[0018]

[0019] In the formula, F is the formation coefficient; R o R represents the true resistivity of the water-saturated formation. w The resistivity of formation water; is the effective porosity; a is the rock-related proportionality coefficient, ranging from 0.6 to 1.55; m is the cementation coefficient of terrestrial mudstone and shale;

[0020] The formation water saturation S is quantitatively calculated using the formation coefficient F in formula (1). w :

[0021]

[0022] In the formula, S w R represents formation water saturation; n represents the saturation index; R t This represents the true resistivity of the geological formation rocks;

[0023] Substituting formula (1) into formula (2) yields the saturation S of the rock texture characteristics. wa and saturation S regarding pore structure characteristics wr :

[0024]

[0025] Picket Plot technology can be mathematically represented by the well logging measurement value S using formula (5). w R w / R t and porosity The function is as follows:

[0026]

[0027] Furthermore, equation (5) can be decomposed into three new equations, which can serve as plane equations in three-dimensional space with x, y, and z coordinates:

[0028] Therefore, formula (5) can be rewritten as the formula for each physical measurement point i:

[0029] Z i =-A+mX i +nY i (6)

[0030] Among them, parameters X, Y, and Z are related to the logging curve, A = loga, and a, m, and n are obtained by constructing three different equations through drilling records at different physical measurement points i. Formula (7) is obtained by summing formula (6) over N measurement points. Formulas (8) and (9) are obtained by multiplying formula (7) by ∑X. i and ∑Y i The three equations are as follows:

[0031] ∑Z i =-N*A+m*∑X i +n*∑Y i (7)

[0032]

[0033] ∑Y i Z i =-N*A*∑Y i +m*∑X i Y i +n*∑Y i 2 (9)

[0034] By using MATLAB to simultaneously solve the system of equations consisting of formulas (7)-(9), the values ​​of A, m, and n are obtained. The results are then compared with those obtained by the Picket Plot technique to obtain a reasonable cementation coefficient m for terrestrial mudstone and shale.

[0035] The method described herein, preferably, uses a diagenetic coefficient MD that can be expressed by formula (10):

[0036] MD=m 2 +m*(S wr -S wa (10)

[0037] Substituting formulas (3) and (4) into formula (10), we get:

[0038]

[0039] In the formula, R lls Shallow resistivity; R lld For deep resistivity; R mf The resistivity of the mud filtrate.

[0040] The apparatus for predicting diagenesis of terrestrial mudstones and shale as described in this invention comprises:

[0041] The first processing unit is used to extract the characteristics of continental mudstone and shale reservoirs, obtain the Archie parameters in continental mudstone and shale, determine the cementation coefficient m of continental mudstone and shale through three-dimensional regression, and calculate the diagenetic coefficient MD.

[0042] The second processing unit is used to determine the most sensitive parameter data to diagenesis based on the diagenetic coefficient, and to divide the most sensitive parameter data into training set, validation set and test set;

[0043] The third processing unit is used to establish an artificial neural network model based on Archie parameters and cementation coefficients, and to train the artificial neural network model using a training set.

[0044] The fourth processing unit is used to continuously test the model's error during the training process of the artificial neural network model using the validation set and the test set;

[0045] The fifth processing unit is used to evaluate the performance of the trained artificial neural network model;

[0046] The sixth processing unit is used to predict the diagenesis of terrestrial mudstones and shale using an artificial neural network model with good performance acceptance.

[0047] The computer storage medium of the present invention stores a computer program thereon, which, when executed by a processor, implements the method steps for predicting the diagenesis of terrestrial mudstone and shale.

[0048] The computer device of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method steps for predicting the diagenesis of terrestrial mudstone and shale.

[0049] The present invention has the following advantages due to the adoption of the above technical solutions:

[0050] The method for predicting diagenesis of terrestrial mudstone and shale described in this invention can accurately predict diagenesis of terrestrial mudstone and shale, and the artificial neural network is highly efficient in quantifying diagenesis using well logging data, thereby better characterizing complex mudstone and shale systems. Attached Figure Description

[0051] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. In the drawings:

[0052] Figure 1 This is a flowchart of a method for predicting diagenesis of terrestrial mudstones and shale, provided in an embodiment of the present invention. Detailed Implementation

[0053] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.

[0054] This invention provides a method for predicting diagenesis of continental mudstone and shale. It utilizes an artificial neural network with feedforward-backpropagation to directly predict diagenesis from well logs of different reservoirs with varying characteristics. The method analyzes well logs and core data to quantify diagenesis (calculating diagenesis coefficients or MD coefficients) and correlates these diagenesis values ​​with known diagenesis types and pore types. The final artificial neural network output model develops a numerical scale between 0 and 10 for diagenesis and compares it with the main diagenetic processes in the corresponding core samples to determine the relationship between the numerical scale and diagenesis.

[0055] The method for predicting diagenesis of terrestrial mudstones and shale provided by this invention includes the following steps:

[0056] 1) Extract the reservoir characteristics of continental mudstone and shale using Resform software; obtain Archie parameters in continental mudstone and shale using Pickett Plot technology; determine the cementation coefficient m of continental mudstone and shale through three-dimensional regression; and calculate the diagenetic coefficient MD.

[0057] 2) Based on the diagenetic coefficient MD, the most sensitive parameter data for diagenesis is determined using the relative importance algorithm of Microsoft Excel, and the most sensitive parameter data is divided into training set, validation set and test set;

[0058] 3) Establish an artificial neural network model based on Archie parameters and cementation coefficients, and train the artificial neural network model using the training set;

[0059] 4) Continuously test the model's error during the training process of the artificial neural network model using validation and test sets;

[0060] 5) Evaluate the performance of the trained artificial neural network model. If the performance is acceptable, proceed to step 6); otherwise, return to step 3.

[0061] 6) Predict the diagenesis of terrestrial mudstones and shale using artificial neural network models with good performance acceptance.

[0062] In the above embodiments, preferably, the cementation coefficient m of the terrestrial mudstone and shale determined by three-dimensional regression in step 1) is as follows:

[0063] In rock physics, the formation coefficient F and effective porosity Representing the fundamental parameters controlling electrical properties, these are physically measured using resistivity and porosity logging or conventional core analysis. Mathematically, the formation coefficient is related to resistivity as follows:

[0064]

[0065] In the formula, F is the formation coefficient; R o R represents the true resistivity of the water-saturated formation. w The resistivity of formation water; 1 represents the effective porosity; a is the rock-related proportionality coefficient, generally 0.6 to 1.55; m is the cementation coefficient of terrestrial mudstone and shale.

[0066] The formation water saturation S is quantitatively calculated using the formation coefficient F in formula (1). w :

[0067]

[0068] In the formula, S w R represents formation water saturation; n represents the saturation index; R t This represents the true resistivity of the geological formation rocks;

[0069] Substituting formula (1) into formula (2) yields the saturation S of the rock texture characteristics. wa and saturation S regarding pore structure characteristics wr :

[0070]

[0071] Picket Plot technology can be mathematically represented by the well logging measurement value S using formula (5). w R w / R t and porosity The function is as follows:

[0072]

[0073] Furthermore, equation (5) can be decomposed into three new equations, which can serve as plane equations in three-dimensional space with x, y, and z coordinates:

[0074] Therefore, formula (5) can be rewritten as the formula for each physical measurement point i:

[0075] Z i =-A+mX i +nY i (6)

[0076] Among them, parameters X, Y, and Z are related to the logging curve, A = loga, and a, m, and n are obtained by constructing three different equations through drilling records at different physical measurement points i. Formula (7) is obtained by summing formula (6) over N measurement points. Formulas (8) and (9) are obtained by multiplying formula (7) by ∑X. i and ∑Y i The three equations are as follows:

[0077] ∑Z i =-N*A+m*∑X i +n*∑Y i (7)

[0078]

[0079] ∑Y i Z i =-N*A*∑Y i +m*∑X i Y i +n*∑Y i 2 (9)

[0080] The values ​​of A, m, and n were obtained by simultaneously solving the system of equations consisting of formulas (7)-(9) using MATLAB. The results were then compared with those obtained by the Picket Plot technique to obtain the cementation coefficient m of the reasonable terrestrial mudstone and shale.

[0081] In the above embodiments, preferably, the diagenetic coefficient MD can be expressed by formula (10):

[0082] MD=m 2 +m*(S wr -S wa (10) Substituting formulas (3) and (4) into formula (10) yields:

[0083]

[0084] In the formula, R lls Shallow resistivity; R lld For deep resistivity; R mf The resistivity of the mud filtrate.

[0085] The present invention also provides an apparatus for predicting the diagenesis of terrestrial mudstone and shale, comprising:

[0086] The first processing unit is used to extract the characteristics of continental mudstone and shale reservoirs, obtain Archie parameters in continental mudstone and shale, determine the cementation coefficient m in continental mudstone and shale through three-dimensional regression, and calculate the diagenetic coefficient MD.

[0087] The second processing unit is used to determine the most sensitive parameter data to diagenesis based on the diagenetic coefficient; and to divide the most sensitive parameter data into training set, validation set and test set.

[0088] The third processing unit is used to establish an artificial neural network model based on Archie parameters and cementation coefficients, and to train the artificial neural network model using a training set.

[0089] The fourth processing unit is used to continuously test the model's error during the training process of the artificial neural network model using the validation set and the test set;

[0090] The fifth processing unit is used to evaluate the performance of the trained artificial neural network model;

[0091] The sixth processing unit is used to predict the diagenesis of terrestrial mudstones and shale using an artificial neural network model with good performance acceptance.

[0092] The present invention also provides a computer storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method steps for predicting the diagenesis of terrestrial mudstone and shale.

[0093] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method steps for predicting the diagenesis of terrestrial mudstone and shale.

[0094] Additionally, it should be noted that, to facilitate the calculation of the diagenetic coefficient (MD), a feedforward backpropagation artificial neural network technique was developed to link the diagenetic coefficient MD with direct logging measurements. To achieve this, formula (6) uses Microsoft Excel's relative importance algorithm to determine the most sensitive parameter, thereby deriving the MD coefficient and subsequently the correlation between the MD coefficient and the logging measurement value. Among various logging parameters (S... wr -S wa In ), NPHI, PHIE, S w Gamma rays and calculated MD coefficients show a high correlation. LLS and LLD logging are highly correlated due to (S wr -S waThe data were well-represented but overlooked. A total of 3077 measurements were used to construct the artificial neural network, of which 70% (2156) were randomly selected for training and validation, and the remaining 30% (921) were used for testing. The training of the artificial neural network involved testing various hidden layer configurations, different numbers of neutrons per layer, and various types of activation functions. In addition, several learning techniques that modified the weights and biases of individual input variables were tested to help establish a stable computational system. The optimal artificial neural network structure was determined based on the best correlation between the artificial neural network prediction coefficients and the diagenetic coefficients “MD” calculated according to formula (11). Finally, the developed neural network structure was tested with the remaining 30% of the total data, and the performance of the neural network prediction was guaranteed by comparing the output of the artificial neural network with the actual target “MD” coefficients. The performance and development of the artificial neural network were evaluated using the techniques described by Abdulaziz et al. All logging calculations and interpretations were performed using Resform software, and the construction and prediction management of the artificial neural network and three-dimensional regression were performed using MATLAB 2016b.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the diagenesis of terrestrial mudstones and shale, characterized in that, Includes the following steps: 1) Extract reservoir characteristics of continental mudstone and shale, obtain Archie parameters in continental mudstone and shale, and determine the cementation coefficient of continental mudstone and shale through three-dimensional regression. And calculate the diagenetic coefficient. ; 2) Based on the diagenetic coefficient, determine the most sensitive parameter data for diagenesis, and divide the most sensitive parameter data into training set, validation set and test set; 3) Establish an artificial neural network model based on Archie parameters and cementation coefficients, and train the artificial neural network model using the training set; 4) Continuously test the model's error during the training process of the artificial neural network model using validation and test sets; 5) Evaluate the performance of the trained artificial neural network model. If the performance is acceptable, proceed to step 6; otherwise, return to step 3. 6) Predict the diagenesis of terrestrial mudstones and shale using artificial neural network models with good performance acceptance; The method for determining the cementation coefficient m of terrestrial mudstone and shale through three-dimensional regression in step 1) is as follows: In rock physics, the stratigraphic coefficient and effective porosity Representing the fundamental parameters controlling electrical properties, physical measurements are performed using resistivity and porosity logging or conventional core analysis. Mathematically, the formation coefficient is related to resistivity as follows: In the formula, This refers to the stratigraphic coefficient; This represents the true resistivity of the water-saturated strata. The resistivity of formation water; Effective porosity; The proportionality coefficient related to the rock ranges from 0.6 to 1.55; The cementation coefficient of terrestrial mudstone and shale; Using the formation coefficient in formula (1) Quantitative calculation of formation water saturation : In the formula, Formation water saturation; It is the saturation index; This represents the true resistivity of the geological formation rocks; Substituting formula (1) into formula (2) yields the saturation of rock texture characteristics. and saturation regarding pore structure characteristics : Picket Plot technology can be mathematically represented by well logging measurements using formula (5). , / and porosity The function is as follows: Furthermore, formula (5) can be decomposed into three new equations, which can be used as plane equations in three-dimensional space with x, y, and z coordinates: Therefore, formula (5) can be rewritten for each physical measurement point. The formula: Among them, parameters , , Related to well logging curves, a、 and Drilling data at different physical measurement points To obtain formula (7), we construct three different equations, and formula (7) is derived from formula (6). The summation of the measurements at each measurement point is used to obtain formulas (8) and (9), which are obtained by multiplying formula (7) by the given values. and The three equations are as follows: By using MATLAB to simultaneously solve the system of equations consisting of formulas (7)-(9), A can be obtained. and The values ​​are then compared with those obtained using the Picket Plot technique to determine a reasonable cementation coefficient for terrestrial mudstone and shale. ; The diagenetic coefficient MD can be expressed by formula (10): Substituting formulas (3) and (4) into formula (10), we get: In the formula, Shallow resistivity; For deep resistivity; The resistivity of the mud filtrate.

2. The method according to claim 1, characterized in that, In step 1) above, the characteristics of continental mudstone and shale reservoirs are extracted using Resform software, and the Archie parameters in continental mudstone and shale are obtained using Pickett Plot technology.

3. The method according to claim 1, characterized in that, In step 2) above, the most sensitive parameter data for diagenesis are determined using the relative importance algorithm of Microsoft Excel.

4. A device for predicting the diagenesis of terrestrial mudstone and shale, characterized in that, include: The first processing unit is used to extract the reservoir characteristics of continental mudstone and shale, obtain the Archie parameters in continental mudstone and shale, and determine the cementation coefficient of continental mudstone and shale through three-dimensional regression. And calculate the diagenetic coefficient. ; The second processing unit is used to determine the most sensitive parameter data to diagenesis based on the diagenetic coefficient, and to divide the most sensitive parameter data into training set, validation set and test set; The third processing unit is used to establish an artificial neural network model based on Archie parameters and cementation coefficients, and to train the artificial neural network model using a training set. The fourth processing unit is used to continuously test the model's error during the training process of the artificial neural network model using the validation set and the test set; The fifth processing unit is used to evaluate the performance of the trained artificial neural network model; The sixth processing unit is used to predict the diagenesis of terrestrial mudstones and shale using an artificial neural network model with good performance acceptance. The method for determining the cementation coefficient m of terrestrial mudstone and shale through three-dimensional regression is as follows: In rock physics, the stratigraphic coefficient and effective porosity Representing the fundamental parameters controlling electrical properties, physical measurements are performed using resistivity and porosity logging or conventional core analysis. Mathematically, the formation coefficient is related to resistivity as follows: In the formula, This refers to the stratigraphic coefficient; This represents the true resistivity of the water-saturated strata. The resistivity of formation water; Effective porosity; The proportionality coefficient related to the rock ranges from 0.6 to 1.55; The cementation coefficient of terrestrial mudstone and shale; Using the formation coefficient in formula (1) Quantitative calculation of formation water saturation : In the formula, Formation water saturation; It is the saturation index; This represents the true resistivity of the geological formation rocks; Substituting formula (1) into formula (2) yields the saturation of rock texture characteristics. and saturation regarding pore structure characteristics : Picket Plot technology can be mathematically represented by well logging measurements using formula (5). , / and porosity The function is as follows: Furthermore, formula (5) can be decomposed into three new equations, which can be used as plane equations in three-dimensional space with x, y, and z coordinates: Therefore, formula (5) can be rewritten for each physical measurement point. The formula: Among them, parameters , , Related to well logging curves, a、 and Drilling data at different physical measurement points To obtain formula (7), we construct three different equations, and formula (7) is derived from formula (6). The summation of the measurements at each measurement point is used to obtain formulas (8) and (9), which are obtained by multiplying formula (7) by the given values. and The three equations are as follows: By using MATLAB to simultaneously solve the system of equations consisting of formulas (7)-(9), A can be obtained. and The values ​​are then compared with those obtained using the Picket Plot technique to determine a reasonable cementation coefficient for terrestrial mudstone and shale. The diagenetic coefficient MD can be expressed by formula (10): Substituting formulas (3) and (4) into formula (10), we get: In the formula, Shallow resistivity; For deep resistivity; The resistivity of the mud filtrate.

5. A computer storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method steps for predicting the diagenesis of terrestrial mudstone and shale as described in any one of claims 1-3.

6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for predicting diagenesis of terrestrial mudstone and shale as described in any one of claims 1-3.

Images