A shale reservoir fracture identification method, device, equipment and storage medium

Abstract

The present invention discloses a shale reservoir fracture identification method, device, equipment and storage medium, including: obtaining a detection image of a shale layer segment through imaging logging, preprocessing the detection image to obtain a preprocessed image; identifying fracture features of the preprocessed image to obtain and mark the fracture features in the preprocessed image; obtaining the sonic curve of the shale reservoir through sonic logging, and obtaining the resistivity curve of the shale reservoir through resistivity logging; identifying and integrating the marked fracture features according to the sonic curve and the resistivity curve to form an initial fracture image; collecting the current stress data of the shale reservoir, determining the geological movement resultant force vector of the shale reservoir according to the stress data; and correcting the initial fracture image according to the geological movement resultant force vector to obtain a final fracture image. The present invention solves the technical problem of insufficient accuracy in shale reservoir fracture identification in the existing fracture identification technology, and effectively reduces the multi-solution of fracture interpretation.

Description

Technical Field

[0001] The present invention relates to the technical field of geological data processing, and in particular to a shale reservoir fracture identification method, device, equipment and storage medium. Background Art

[0002] With the gradual depletion of conventional oil and gas resources and the continuous increase in energy demand for economic development, the importance of unconventional oil and gas resources has become increasingly prominent. Shale oil and gas has been a hot exploration field in recent years, and its development and utilization value is of great significance to alleviating my country's energy pressure and ensuring my country's energy security. Shale oil and gas are oil and gas resources enriched in mud shale formations, including oil and gas in mud shale pores and fractures, as well as oil and gas in dense carbonate or clastic interlayers in mud shale formations. The porosity and permeability of shale are generally low, and it is difficult to achieve the natural production capacity of shale oil and gas. Horizontal well fracture transformation is usually used to obtain production capacity. The presence of microfractures can greatly improve the porosity and permeability conditions of shale, and it is easy to be transformed to form a complex fracture network. Therefore, shale layers with developed fractures are sweet spots for shale oil and gas, and are also the key target layers for fracture transformation. Finding sweet spots with developed fractures is one of the key factors for achieving high production of shale oil and gas.

[0003] Existing fracture identification technology is mainly based on microresistivity imaging logging, but the measurement effect is poor when the borehole is irregular, the accuracy is not high, and the image interpretation is multi-solution, which is greatly affected by subjective experience. The drilling trajectory of shale oil and gas horizontal wells often travels hundreds or thousands of meters in thick shale. Shale is very easy to fall off, resulting in irregular boreholes, which affects the accuracy of imaging logging and increases the multi-solution of image interpretation.

[0004] Therefore, there is an urgent need for an accurate identification strategy for shale reservoir fracture images to solve the technical problem of low accuracy in shale reservoir fracture image identification in the existing technology, improve the reliability of image interpretation, and provide accurate data support for fracturing layer selection. Summary of the invention

[0005] The present invention provides a shale reservoir fracture identification method, device, equipment and storage medium to solve the technical problem of low recognition rate of shale reservoir fracture images in the prior art.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a shale reservoir fracture identification method, comprising:

[0007] Obtaining a detection image of the shale reservoir by imaging logging, and preprocessing the detection image to obtain a preprocessed image;

[0008] Performing feature recognition on the preprocessed image to obtain crack features in the preprocessed image and mark them;

[0009] Obtaining an acoustic wave curve of the shale reservoir by acoustic wave logging, and obtaining a resistivity curve of the shale reservoir by resistivity logging;

[0010] According to the acoustic wave curve and the resistivity curve, the marked crack features are identified and integrated to form an initial crack image;

[0011] Collecting current stress data of the shale reservoir, and determining a geological movement resultant force vector in the shale reservoir according to the stress data;

[0012] The initial fracture image is corrected according to the resultant force vector of the geological movement to obtain a final fracture image.

[0013] As a preferred solution, the step of preprocessing the detection image to obtain a preprocessed image is specifically as follows:

[0014] Performing grayscale processing on the detection image to obtain a grayscale image;

[0015] Normalizing the grayscale image to obtain a normalized image;

[0016] The normalized image is binarized to obtain a preprocessed image.

[0017] As a preferred solution, the step of performing feature recognition on the preprocessed image, obtaining crack features in the preprocessed image and marking the crack features is specifically as follows:

[0018] Inputting the preprocessed image into a crack recognition model to identify crack features; wherein the crack recognition model is used to identify and output crack features in the input image;

[0019] The crack features are marked.

[0020] As a preferred solution, the process of establishing the crack identification model is specifically as follows:

[0021] Acquire an image sample set containing crack features, and divide the image sample set into a training sample set and a test sample set;

[0022] Establishing an initial recognition model, inputting the training sample set into the initial recognition model for training, and obtaining a training recognition model when the number of training times reaches a training threshold or the training accuracy reaches a first accuracy value;

[0023] The test sample set is input into the training recognition model for testing, and when the test accuracy reaches a second accuracy value, a crack recognition model is obtained.

[0024] As a preferred solution, the step of identifying and integrating the marked crack features according to the acoustic wave curve and the resistivity curve to form an initial crack image is specifically as follows:

[0025] Establishing a spatial rectangular coordinate system, and determining a coordinate coefficient of each crack feature according to the position of each crack feature in the detection image;

[0026] According to the acoustic wave curve, each crack feature in the spatial rectangular coordinate system is matched, the crack features that do not have an acoustic wave curve are deleted, and the length value of the crack features that have an acoustic wave curve is corrected;

[0027] According to the resistivity curve, each crack feature after length correction is matched, the crack features without resistivity curve are deleted, and the crack features with resistivity curve are corrected in depth value;

[0028] The crack features with corrected length and depth values ​​are integrated to form an initial crack image.

[0029] As a preferred solution, the step of integrating the crack features whose length values ​​and depth values ​​have been corrected to form an initial crack image is specifically as follows:

[0030] According to the corrected length value and depth value, the coordinate coefficient of the corrected crack feature is determined;

[0031] According to the coordinate coefficient of each crack feature, the corrected crack features are connected to generate multiple crack curves;

[0032] It is determined whether the crack curve overlaps with the deleted crack feature. If overlap occurs, the overlapping crack feature is connected with the crack curve closest to it to form an initial crack image.

[0033] As a preferred solution, the calculation formula for the resultant force of geological movement is:

[0034] X a =y1×…×y i ;

[0035] Among them, X0 is the resultant force vector of geological movement, y i is the vector of each stress data.

[0036] As a preferred solution, the step of correcting the initial fracture image according to the resultant force vector of the geological movement to obtain the final fracture image is specifically as follows:

[0037] Determining the crack development direction in the initial crack image according to the direction of the geological movement resultant force vector;

[0038] According to the magnitude of the resultant force vector of the geological movement, the fracture features in the initial fracture image are controlled to expand outwardly in the fracture development direction by a preset proportion to obtain a final fracture image.

[0039] Accordingly, an embodiment of the present invention further provides a shale reservoir fracture identification device including: a preprocessing module, an identification module, a data acquisition module, an integration module, a resultant force vector module and a correction module;

[0040] The preprocessing module is used to obtain a detection image of the shale reservoir through imaging logging, and preprocess the detection image to obtain a preprocessed image;

[0041] As a preferred solution, the step of preprocessing the detection image to obtain a preprocessed image is specifically as follows:

[0042] Performing grayscale processing on the detection image to obtain a grayscale image;

[0043] Normalizing the grayscale image to obtain a normalized image;

[0044] The normalized image is binarized to obtain a preprocessed image.

[0045] The recognition module is used to perform feature recognition on the preprocessed image, obtain crack features in the preprocessed image and mark them;

[0046] As a preferred solution, the step of performing feature recognition on the preprocessed image, obtaining crack features in the preprocessed image and marking the crack features is specifically as follows:

[0047] Inputting the preprocessed image into a crack recognition model to identify crack features; wherein the crack recognition model is used to identify and output crack features in the input image;

[0048] The crack features are marked.

[0049] As a preferred solution, the process of establishing the crack identification model is specifically as follows:

[0050] Acquire an image sample set containing crack features, and divide the image sample set into a training sample set and a test sample set;

[0051] Establishing an initial recognition model, inputting the training sample set into the initial recognition model for training, and obtaining a training recognition model when the number of training times reaches a training threshold or the training accuracy reaches a first accuracy value;

[0052] The test sample set is input into the training recognition model for testing, and when the test accuracy reaches a second accuracy value, a crack recognition model is obtained.

[0053] The data acquisition module is used to obtain the sonic curve of the shale reservoir through sonic logging, and to obtain the resistivity curve of the shale reservoir through resistivity logging;

[0054] The integration module is used to identify and integrate the marked crack features according to the acoustic wave curve and the resistivity curve to form an initial crack image;

[0055] As a preferred solution, the step of identifying and integrating the marked crack features according to the acoustic wave curve and the resistivity curve to form an initial crack image is specifically as follows:

[0056] Establishing a spatial rectangular coordinate system, and determining a coordinate coefficient of each crack feature according to the position of each crack feature in the detection image;

[0057] According to the acoustic wave curve, each crack feature in the spatial rectangular coordinate system is matched, the crack features that do not have an acoustic wave curve are deleted, and the length value of the crack features that have an acoustic wave curve is corrected;

[0058] According to the resistivity curve, each crack feature after length correction is matched, the crack features without resistivity curve are deleted, and the crack features with resistivity curve are corrected in depth value;

[0059] The crack features with corrected length and depth values ​​are integrated to form an initial crack image.

[0060] As a preferred solution, the step of integrating the crack features whose length values ​​and depth values ​​have been corrected to form an initial crack image is specifically as follows:

[0061] According to the corrected length value and depth value, the coordinate coefficient of the corrected crack feature is determined;

[0062] According to the coordinate coefficient of each crack feature, the corrected crack features are connected to generate multiple crack curves;

[0063] It is determined whether the crack curve overlaps with the deleted crack feature. If overlap occurs, the overlapping crack feature is connected with the crack curve closest to it to form an initial crack image.

[0064] The resultant force vector module is used to collect current stress data of the shale reservoir and determine the resultant force vector of geological movement in the shale reservoir according to the stress data;

[0065] As a preferred solution, the calculation formula for the resultant force of geological movement is:

[0066] X0=y1×…×y i ;

[0067] Among them, X0 is the resultant force vector of geological movement, y i is the vector of each stress data.

[0068] The correction module is used to correct the initial fracture image according to the geological movement resultant force vector to obtain a final fracture image.

[0069] As a preferred solution, the step of correcting the initial fracture image according to the resultant force vector of the geological movement to obtain the final fracture image is specifically as follows:

[0070] Determining the crack development direction in the initial crack image according to the direction of the geological movement resultant force vector;

[0071] According to the magnitude of the resultant force vector of the geological movement, the fracture features in the initial fracture image are controlled to expand outwardly in the fracture development direction by a preset proportion to obtain a final fracture image.

[0072] Correspondingly, the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the shale reservoir fracture identification method as described in any one of the above items is implemented.

[0073] Accordingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the shale reservoir fracture identification method as described in any one of the above.

[0074] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0075] The present invention pre-processes the detection image of the shale reservoir in the target area, and performs feature recognition on the pre-processed image to obtain and mark the crack features in the pre-processed image. At the same time, the crack features are recognized by the obtained acoustic wave curve and resistivity curve to form an initial crack image, thereby improving the accuracy and clarity of the initial crack image. Moreover, the geological movement resultant force vector is determined by the current stress data of the shale reservoir, and the initial crack image obtained is corrected by the geological movement resultant force vector, thereby finally obtaining a clearer and more accurate crack image. Moreover, the crack development direction in the initial crack image can be predicted according to the direction of the geological movement resultant force vector, and a fracturing process plan, such as a slit angle, a hydraulic fracture direction, etc., can be formulated according to the predicted crack development direction during fracturing. Compared with the prior art, this method ensures the high recognition of the crack image through multi-faceted considerations and corrections, improves the accuracy of the crack image, and can provide accurate data support for fracturing layer selection and fracturing construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 : A flowchart of the steps of a shale reservoir fracture identification method provided by an embodiment of the present invention;

[0077] Figure 2 : A flowchart of the steps of establishing a fracture identification model in a shale reservoir fracture identification method provided by an embodiment of the present invention;

[0078] Figure 3 : A schematic structural diagram of a shale reservoir fracture identification device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0079] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0080] Embodiment 1

[0081] Please refer to Figure 1 , a shale reservoir fracture identification method provided by an embodiment of the present invention includes the following steps S101-S106:

[0082] S101: obtaining a detection image of a shale reservoir through imaging logging, and preprocessing the detection image to obtain a preprocessed image.

[0083] Specifically, grayscale processing is performed on the detection image to obtain a grayscale image; normalization processing is performed on the grayscale image to obtain a normalized image; and binarization processing is performed on the normalized image to obtain a preprocessed image.

[0084] It should be noted that the preprocessing of the image can eliminate irrelevant information in the image, restore useful information, enhance the detectability of relevant information and simplify the data to the maximum extent, thereby improving the accuracy of the detection image processing of shale reservoirs in the target area, including but not limited to grayscale processing, normalization processing, binarization processing and thinning processing. Grayscale processing means that the three color variables R, B, and G of each pixel in the color image satisfy: R=B=G, that is, the value of the red variable, the value of the green variable and the value of the blue variable are all equal. At this time, this value of the pixel is the grayscale value, and the range of the grayscale value is [0,255]. Normalization processing is to perform a series of transformations on the image, use the invariant moment of the image to find a set of parameters that can eliminate the influence of other transformation functions on the image transformation, and convert the original image to be processed into a corresponding unique standard form. The standard form image has invariant characteristics to affine transformations such as translation, rotation, and scaling. Binarization processing is to make the grayscale value of each pixel in the pixel matrix of the image 0 (black) or 255 (white), that is, to make the entire image appear to be only black and white. After binarization, the grayscale value of the pixel in the image is 0 or 255.

[0085] S102: Perform feature recognition on the preprocessed image to obtain crack features in the preprocessed image and mark them.

[0086] Specifically, the preprocessed image is input into a crack recognition model to identify crack features; wherein the crack recognition model is used to identify and output crack features in the input image; and the crack features are marked.

[0087] As a preferred solution of this embodiment, please refer to Figure 2 The process of establishing the crack identification model specifically includes the following steps S201-S203:

[0088] S201: Acquire an image sample set containing crack features, and divide the image sample set into a training sample set and a test sample set.

[0089] S202: Establishing an initial recognition model, inputting the training sample set into the initial recognition model for training, and obtaining a training recognition model when the number of training times reaches a training threshold or the training accuracy reaches a first accuracy value.

[0090] S203: Inputting the test sample set into the training recognition model for testing, and when the test accuracy reaches a second accuracy value, obtaining a crack recognition model.

[0091] It should be noted that after obtaining the image sample set containing crack features, the established recognition model is trained, and after the number of training times reaches the training threshold or the accuracy of the model output reaches the first accuracy, the training recognition model is obtained. At the same time, the training recognition model is tested, and when the test accuracy reaches the second accuracy value, the crack recognition model is obtained; the setting of the second accuracy value can further test the training recognition model obtained after training, and can further improve the accuracy of the model output result, ensuring the recognition effect of small cracks. Preferably, the training threshold, the first accuracy value and the second accuracy value are determined according to the actual training situation and needs. In another preferred embodiment, if the test accuracy does not reach the second accuracy value, the number of training times is increased or the first accuracy value is increased, so as to improve the accuracy of the training recognition model, so that a crack recognition model with high accuracy and meeting actual needs can be obtained. After obtaining the crack recognition model, the preprocessed image is input into the crack recognition model, the crack features are obtained and marked, so that the marked crack features can be intuitively identified later.

[0092] S103: Obtaining an acoustic wave curve of the shale reservoir by acoustic wave logging, and obtaining a resistivity curve of the shale reservoir by resistivity logging.

[0093] It should be noted that both the acoustic wave curve and the resistivity curve are obtained by conventional logging methods. Acoustic logging is obtained by measuring the acoustic characteristics such as the change in velocity, amplitude and frequency of the acoustic wave when it propagates in the shale reservoir. In the prior art, acoustic logging is a measurement method for judging the quality of cementing. Resistivity logging is a method of measuring the resistivity of rock by using power supply electrodes and measuring points at different positions in the borehole. Through acoustic logging and resistivity logging, the acoustic wave curve and resistivity curve of the shale reservoir can be obtained respectively.

[0094] S104: According to the acoustic wave curve and the resistivity curve, the marked crack features are identified and integrated to form an initial crack image.

[0095] Specifically, a spatial rectangular coordinate system is established, and the coordinate coefficient of each crack feature is determined according to the position of each crack feature in the detection image; each crack feature in the spatial rectangular coordinate system is matched according to the acoustic wave curve, the crack features that do not have the acoustic wave curve are deleted, and the length values ​​of the crack features that have the acoustic wave curve are corrected; each crack feature after the length correction is matched according to the resistivity curve, the crack features that do not have the resistivity curve are deleted, and the depth values ​​of the crack features that have the resistivity curve are corrected; the crack features whose length values ​​and depth values ​​have been corrected are integrated to form an initial crack image.

[0096] It should be noted that a spatial rectangular coordinate system is first established, and the coordinate coefficients of each fracture feature are determined in the detection image, so that the marked fracture features are identified and integrated according to the acoustic wave curve and the resistivity curve, and the length value of the fracture features with the acoustic wave curve is corrected, and the depth value of the fracture features with the resistivity curve is corrected, so that the fracture features with both the length value and the depth value corrected are integrated, and finally the initial fracture image is obtained. In this embodiment, the initial fracture image obtained does not have fracture features that are unrelated to the acoustic wave curve or the resistivity curve, so the accuracy of the initial fracture image can be improved, and the accuracy of the shale reservoir fracture image recognition can be further improved.

[0097] As a preferred solution of this embodiment, in the step of integrating the crack features whose length values ​​and depth values ​​have been corrected to form an initial crack image, specifically:

[0098] The coordinate coefficients of the corrected crack features are determined according to the corrected length and depth values; the corrected crack features are connected according to the coordinate coefficients of each crack feature to generate multiple crack curves; it is determined whether the crack curve overlaps with the deleted crack features, and if so, the overlapping crack features are connected with the crack curve closest to them to form an initial crack image.

[0099] It should be noted that in the step of integrating the fracture features after the length value and the depth value are corrected, the coordinate coefficients of the corrected fracture features are determined, and according to the coordinate coefficients of each fracture feature, the fracture features that are connected and overlapped are connected with the fracture curves that are closest to them to form an initial fracture image. The integrated initial fracture image has the fracture curves that have been deleted, corrected in length and depth values, and overlapped, and can directly observe and obtain the measured shale reservoir detection image features, which can further ensure the detection accuracy.

[0100] S105: Collect current stress data of the shale reservoir, and determine the resultant force vector of geological movement in the shale reservoir according to the stress data.

[0101] As a preferred solution of this embodiment, the calculation formula of the geological movement resultant force value is:

[0102] X0=y1×…×y i ; Among them, X0 is the resultant force vector of geological movement, y i is the vector of each stress data.

[0103] It should be noted that the geological movement resultant force vector X0 is the product of the vectors of each stress data. The stress data is collected by drilling at key locations and implanting stress collectors downhole to ensure that the geological movement resultant force vector in the shale reservoir can be accurately obtained and determined.

[0104] S106: Correcting the initial fracture image according to the geological movement resultant force vector to obtain a final fracture image.

[0105] Specifically, according to the direction of the resultant force vector of the geological movement, the crack development direction in the initial crack image is determined; according to the size of the resultant force vector of the geological movement, the crack features in the initial crack image are controlled to expand outwardly in the crack development direction by a preset proportion to obtain the final crack image.

[0106] It should be noted that the initial fracture image is corrected by the direction of the resultant force vector of geological movement to determine the fracture development direction in the initial fracture image, and the fracture features in the initial fracture image are controlled to expand outward by a preset proportion in the fracture development direction by the magnitude of the resultant force vector of geological movement, thereby obtaining the final fracture image. Preferably, the preset proportion is determined according to the actual image requirements. Further correction of the fracture image can take into account the influence of the resultant force vector of geological movement on the recognition of the fracture image, that is, the current stress data of the shale reservoir, so that the final fracture image obtained after correction has high accuracy and high definition, so that the recognition of the shale reservoir fracture image is high.

[0107] Compared with the prior art, the implementation of the embodiments of the present invention has the following effects:

[0108] The embodiment of the present invention pre-processes the detection image of the shale reservoir obtained by imaging logging, and performs feature recognition on the pre-processed image, thereby identifying the crack characteristics through the obtained acoustic wave curve and resistivity curve, forming an initial crack image, improving the accuracy and clarity of the initial crack image, and at the same time collecting the current stress data of the shale reservoir to determine the resultant force vector of geological movement, thereby correcting the initial crack image to obtain the final crack image. Compared with the prior art, the accuracy of the corrected crack image is further improved, and the high recognition of the crack image is ensured through multi-faceted considerations and corrections. Moreover, the crack development direction in the initial crack image can be predicted according to the direction of the resultant force vector of geological movement. When making cracks, a fracturing process plan can be formulated according to the predicted crack development direction, such as the cutting angle, hydraulic fracturing direction, etc., thereby providing accurate data support for fracturing layer selection and fracturing construction.

[0109] Embodiment 2

[0110] Accordingly, see Figure 3 , an embodiment of the present invention further provides a shale reservoir fracture identification device including: a preprocessing module 301, an identification module 302, a data acquisition module 303, an integration module 304, a resultant force vector module 305 and a correction module 306.

[0111] The preprocessing module 301 is used to obtain a detection image of a shale reservoir through imaging logging, and preprocess the detection image to obtain a preprocessed image.

[0112] As a preferred solution of this embodiment, the preprocessing module 301 is specifically used for:

[0113] The detection image is subjected to grayscale processing to obtain a grayscale image; the grayscale image is subjected to normalization processing to obtain a normalized image; the normalized image is subjected to binarization processing to obtain a preprocessed image.

[0114] The recognition module 302 is used to perform feature recognition on the pre-processed image, obtain crack features in the pre-processed image and mark them.

[0115] As a preferred solution of this embodiment, the identification module 302 is specifically used for:

[0116] The preprocessed image is input into a crack recognition model to identify crack features; wherein the crack recognition model is used to identify and output crack features in the input image; and the crack features are marked.

[0117] As a preferred solution of this embodiment, the process of establishing the crack identification model is specifically as follows:

[0118] An image sample set containing crack features is obtained, and the image sample set is divided into a training sample set and a test sample set; an initial recognition model is established, and the training sample set is input into the initial recognition model for training, and when the number of training times reaches a training threshold or the training accuracy reaches a first accuracy value, a training recognition model is obtained; the test sample set is input into the training recognition model for testing, and when the test accuracy reaches a second accuracy value, a crack recognition model is obtained.

[0119] The data acquisition module 303 is used to obtain the sonic curve of the shale reservoir through sonic logging, and to obtain the resistivity curve of the shale reservoir through resistivity logging.

[0120] The integration module 304 is used to identify and integrate the marked crack features according to the acoustic wave curve and the resistivity curve to form an initial crack image.

[0121] As a preferred solution of this embodiment, the integration module 304 is specifically used for:

[0122] A spatial rectangular coordinate system is established, and the coordinate coefficient of each crack feature is determined according to the position of each crack feature in the detection image; each crack feature in the spatial rectangular coordinate system is matched according to the acoustic wave curve, the crack features that do not have an acoustic wave curve are deleted, and the length value of the crack features that exist in the acoustic wave curve is corrected; each crack feature after length correction is matched according to the resistivity curve, the crack features that do not have a resistivity curve are deleted, and the depth value of the crack features that exist in the resistivity curve is corrected; the crack features whose length values ​​and depth values ​​have been corrected are integrated to form an initial crack image.

[0123] As a preferred solution of this embodiment, the step of integrating the crack features whose length values ​​and depth values ​​have been corrected to form an initial crack image is specifically as follows:

[0124] The coordinate coefficients of the corrected crack features are determined according to the corrected length and depth values; the corrected crack features are connected according to the coordinate coefficients of each crack feature to generate multiple crack curves; it is determined whether the crack curve overlaps with the deleted crack features, and if so, the overlapping crack features are connected with the crack curve closest to them to form an initial crack image.

[0125] The resultant force vector module 305 is used to collect the current stress data of the shale reservoir and determine the resultant force vector of the geological movement in the shale reservoir according to the stress data.

[0126] As a preferred solution of this embodiment, the calculation formula of the geological movement resultant force value is:

[0127] X0=y1×…×y i ; Among them, X0 is the resultant force vector of geological movement, y i is the vector of each stress data.

[0128] The correction module 306 is used to correct the initial fracture image according to the geological motion resultant force vector to obtain a final fracture image.

[0129] As a preferred solution of this embodiment, the correction module 306 is specifically used for:

[0130] According to the direction of the resultant force vector of the geological movement, the crack development direction in the initial crack image is determined; according to the size of the resultant force vector of the geological movement, the crack features in the initial crack image are controlled to expand outwardly in the crack development direction by a preset proportion to obtain a final crack image.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0132] In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative work.

[0133] Implementing the embodiments of the present invention has the following effects:

[0134] The embodiment of the present invention pre-processes the detection image of the shale reservoir obtained by imaging logging, and performs feature recognition on the pre-processed image to obtain and mark the fracture features in the pre-processed image; the marked fracture features are recognized by obtaining the acoustic wave curve and the resistivity curve to form an initial fracture image, thereby improving the accuracy and clarity of the initial fracture image; at the same time, the current stress data of the shale reservoir is collected to determine the resultant force vector of the geological movement, thereby correcting the initial fracture image, further improving the accuracy of the corrected fracture image; and through various considerations and corrections, the high recognition of the final fracture image is ensured, thereby avoiding the inability to provide accurate data support for fracturing layer selection in the prior art.

[0135] Embodiment 3

[0136] Correspondingly, the present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the shale reservoir fracture identification method as described in any one of the above embodiments is implemented.

[0137] The terminal device of this embodiment includes: a processor, a memory, and a computer program and a computer instruction stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above-mentioned embodiment 1 is implemented, for example: Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment are realized, such as the prediction module 301, the identification module 302, the data acquisition module 303, the integration module 304, the resultant force vector module 305 and the correction module 306.

[0138] Exemplarily, the computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the computer program may be divided into an image set generation module, and the specific functions of the module are as follows: used to obtain a surface remote sensing image set of the target area within the preset time period, and divide the surface remote sensing image set into a first remote sensing image set and a second remote sensing image set according to the geographical scope of the shale reservoir in the target area.

[0139] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0140] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0141] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile terminal (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0142] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0143] Embodiment 4

[0144] Accordingly, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the shale reservoir fracture identification method described in any one of the above embodiments.

[0145] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying shale reservoir fractures, characterized in that: include: Obtaining a detection image of the shale reservoir by imaging logging, and preprocessing the detection image to obtain a preprocessed image; Performing feature recognition on the preprocessed image to obtain crack features in the preprocessed image and mark them; Obtaining an acoustic wave curve of the shale reservoir by acoustic wave logging, and obtaining a resistivity curve of the shale reservoir by resistivity logging; According to the acoustic wave curve and the resistivity curve, the marked crack features are identified and integrated to form an initial crack image; Collecting current stress data of the shale reservoir, and determining a geological movement resultant force vector in the shale reservoir according to the stress data; Correcting the initial fracture image according to the resultant force vector of the geological movement to obtain a final fracture image; The step of identifying and integrating the marked crack features according to the acoustic wave curve and the resistivity curve to form an initial crack image specifically includes: Establishing a spatial rectangular coordinate system, and determining a coordinate coefficient of each crack feature according to the position of each crack feature in the detection image; According to the acoustic wave curve, each crack feature in the spatial rectangular coordinate system is matched, the crack features that do not have an acoustic wave curve are deleted, and the length value of the crack features that have an acoustic wave curve is corrected; According to the resistivity curve, each crack feature after length correction is matched, the crack features without resistivity curve are deleted, and the crack features with resistivity curve are corrected in depth value; Integrate the crack features whose length and depth values ​​have been corrected to form an initial crack image; The step of integrating the crack features whose length values ​​and depth values ​​have been corrected to form an initial crack image specifically includes: According to the corrected length value and depth value, the coordinate coefficient of the corrected crack feature is determined; According to the coordinate coefficient of each crack feature, the corrected crack features are connected to generate multiple crack curves; It is determined whether the crack curve overlaps with the deleted crack feature. If overlap occurs, the overlapping crack feature is connected with the crack curve closest to it to form an initial crack image.

2. The shale reservoir fracture identification method according to claim 1, characterized in that: The step of preprocessing the detection image to obtain a preprocessed image specifically comprises: Performing grayscale processing on the detection image to obtain a grayscale image; Normalizing the grayscale image to obtain a normalized image; The normalized image is binarized to obtain a preprocessed image.

3. The shale reservoir fracture identification method according to claim 1, characterized in that: The step of performing feature recognition on the preprocessed image to obtain crack features in the preprocessed image and marking the crack features is specifically as follows: Inputting the preprocessed image into a crack recognition model to identify crack features; wherein the crack recognition model is used to identify and output crack features in the input image; The crack features are marked.

4. The shale reservoir fracture identification method according to claim 3, characterized in that: The process of establishing the crack identification model is specifically as follows: Acquire an image sample set containing crack features, and divide the image sample set into a training sample set and a test sample set; Establishing an initial recognition model, inputting the training sample set into the initial recognition model for training, and obtaining a training recognition model when the number of training times reaches a training threshold or the training accuracy reaches a first accuracy value; The test sample set is input into the training recognition model for testing, and when the test accuracy reaches a second accuracy value, a crack recognition model is obtained.

5. The shale reservoir fracture identification method according to claim 1, characterized in that: The step of correcting the initial fracture image according to the resultant force vector of the geological movement to obtain the final fracture image specifically comprises: Determining the crack development direction in the initial crack image according to the direction of the geological movement resultant force vector; According to the magnitude of the resultant force vector of the geological movement, the crack features in the initial crack image are controlled to expand outwardly in the crack development direction by a preset proportion to obtain a final corrected crack image.

6. A shale reservoir fracture identification device, characterized in that: include: Preprocessing module, identification module, data acquisition module, integration module, resultant force vector module and correction module; The preprocessing module is used to obtain a detection image of the shale reservoir through imaging logging, and preprocess the detection image to obtain a preprocessed image; The recognition module is used to perform feature recognition on the preprocessed image, obtain crack features in the preprocessed image and mark them; The data acquisition module is used to obtain the sonic curve of the shale reservoir through sonic logging, and to obtain the resistivity curve of the shale reservoir through resistivity logging; The integration module is used to identify and integrate the marked crack features according to the acoustic wave curve and the resistivity curve to form an initial crack image; The resultant force vector module is used to collect current stress data of the shale reservoir and determine the resultant force vector of geological movement in the shale reservoir according to the stress data; The correction module is used to correct the initial fracture image according to the geological movement resultant force vector to obtain a final fracture image; The marked crack features are identified and integrated according to the acoustic wave curve and the resistivity curve to form an initial crack image, specifically: Establishing a spatial rectangular coordinate system, and determining a coordinate coefficient of each crack feature according to the position of each crack feature in the detection image; According to the acoustic wave curve, each crack feature in the spatial rectangular coordinate system is matched, the crack features that do not have an acoustic wave curve are deleted, and the length value of the crack features that have an acoustic wave curve is corrected; According to the resistivity curve, each crack feature after length correction is matched, the crack features without resistivity curve are deleted, and the crack features with resistivity curve are corrected in depth value; Integrate the crack features whose length and depth values ​​have been corrected to form an initial crack image; The crack features whose length and depth values ​​have been corrected are integrated to form an initial crack image, specifically: According to the corrected length value and depth value, the coordinate coefficient of the corrected crack feature is determined; According to the coordinate coefficient of each crack feature, the corrected crack features are connected to generate multiple crack curves; It is determined whether the crack curve overlaps with the deleted crack feature. If overlap occurs, the overlapping crack feature is connected with the crack curve closest to it to form an initial crack image.

7. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the shale reservoir fracture identification method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the shale reservoir fracture identification method according to any one of claims 1 to 5.

Images