Shale gas reservoir fracture identification and evaluation method and device

Abstract

The invention discloses a shale gas reservoir crack identification and evaluation method and device, and the method comprises the steps: collecting a rock sample surface image in advance, and carrying out the training of the rock sample surface image to obtain a crack identification model; obtaining a shale gas reservoir image to be identified; identifying the shale gas reservoir image by using the crack identification model to obtain effective crack information of the shale gas reservoir; and evaluating the shale gas reservoir according to the effective crack information of the shale gas reservoir. By means of the scheme, the near-wellbore shale gas reservoir fracture development section and the development degree of the near-wellbore shale gas reservoir fracture development section can be rapidly recognized, and a theoretical basis is provided for reservoir interpretation and evaluation and auxiliary fracturing construction.

Description

Technical Field

[0001] The present invention relates to the technical field of geological exploration of shale gas reservoirs, and particularly relates to a method and device for identifying and evaluating fractures in shale gas reservoirs. Background Art

[0002] In the exploration stage of shale gas, the prediction of reservoir fractures mainly relies on post-stack seismic fracture prediction technology. This technology can accurately identify faults and large and medium-sized fractures according to the spatial variation law of seismic attributes, and can effectively reflect the underground fault and fracture development areas. However, due to the limitations of seismic technology, both the resolution and the resolution accuracy are relatively low, and it is difficult to detect small faults and fractures in shale, especially micro-fractures. The fracture prediction only stays at the meter or decimeter level. At present, after the completion of vertical shale gas wells, imaging logging is used to obtain the fracture development of the reservoir around the wellbore. However, the vast majority of shale gas wells adopt the horizontal well drilling construction method, and imaging logging has high risks and cannot be applied in horizontal wells, so the fracture information of the horizontal section of the wellbore cannot be obtained, which has become a difficult problem in the evaluation of shale gas reservoirs.

[0003] It is very necessary to identify the micro-fractures in shale reservoirs, especially the identification of micro-fractures (micro-nano level), because the existence of natural fractures is of great significance to the shale gas production. For example, before hydraulic fracturing, it is necessary to systematically characterize and evaluate the development characteristics of all natural fractures in the formation, which is of great significance for the reasonable optimization of hydraulic fracturing construction.

[0004] In summary, how to identify the fracture development zone of the horizontal wellbore and distinguish fractures with different origins in order to better realize the fracture evaluation of shale gas reservoirs has become an urgent problem to be solved in shale gas exploration and development. Summary of the Invention

[0005] The present invention provides a method and device for identifying and evaluating fractures in shale gas reservoirs, which can quickly identify the fracture development section and its development degree of the shale gas reservoir near the wellbore, and provide a theoretical basis for reservoir interpretation and evaluation and auxiliary fracturing construction.

[0006] To this end, the present invention provides the following technical solutions:

[0007] A method for identifying and evaluating fractures in a shale gas reservoir, the method comprising:

[0008] Pre-collect the surface image of a rock sample, and train a fracture recognition model by using the surface image of the rock sample;

[0009] Obtain the image of the shale gas reservoir to be identified;

[0010] Use the fracture identification model to identify the shale gas reservoir image, and obtain the effective fracture information of the shale gas reservoir;

[0011] Evaluate the shale gas reservoir according to the effective fracture information of the shale gas reservoir.

[0012] Optionally, the acquisition of the surface image of the rock sample includes:

[0013] Collect a rock sample;

[0014] Preprocess the rock sample to obtain a polished sample surface;

[0015] Perform an electron beam line-by-line scan on the selected area of the polished sample surface to obtain the surface image of the rock sample.

[0016] Optionally, the preprocessing of the rock sample to obtain a polished sample surface includes:

[0017] Cut in a direction perpendicular to the bedding plane of the shale sample;

[0018] Embed the cut sample in resin;

[0019] Polish and carbon coat the cut surface after embedding to generate a polished sample surface.

[0020] Optionally, the surface image of the rock sample is a two-dimensional BSE image.

[0021] Optionally, the training of the fracture identification model using the surface image of the rock sample includes:

[0022] Determine the effective fractures and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample;

[0023] Determine the category of the effective fractures according to the characteristic parameters of the effective fractures;

[0024] Establish a training data set according to the characteristic parameters and categories of the effective fractures corresponding to the surface image of the rock sample;

[0025] Train a fracture identification model using the training data set.

[0026] Optionally, the determination of the effective fractures and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample includes:

[0027] Extract a set of candidate pores and fractures from the background of the surface image of the rock sample according to the set pore and fracture gray-scale thresholds;

[0028] Determine the effective fractures in the candidate pore and fracture set according to the set fracture basic parameters, and obtain the effective fractures and their characteristic parameters of the rock sample.

[0029] Optionally, the categories of the fractures include any one or more of the following: dry fractures, mechanical fractures, and microfractures.

[0030] Optionally, the effective fracture information includes: effective fracture characteristics and their quantity per unit area;

[0031] The evaluation of the shale gas reservoir according to the effective fracture information of the shale gas reservoir includes:

[0032] Determine the fracture quantity and effective fracture density of the shale gas reservoir according to the effective fracture information of the shale gas reservoir;

[0033] Calculate the fracture index of the shale gas reservoir according to the effective fracture quantity, effective fracture length, and effective fracture density of the shale gas reservoir;

[0034] Determine the development degree of the fractures in the shale gas reservoir according to the fracture index of the shale gas reservoir.

[0035] A device for identifying and evaluating fractures in a shale gas reservoir, the device includes:

[0036] A model construction module, the model construction module includes a data acquisition module and a training module; the data acquisition module is used to pre-collect the surface image of the rock sample; the training module is used to train a fracture recognition model by using the surface image of the rock sample;

[0037] An image acquisition module, used to acquire the shale gas reservoir image to be identified;

[0038] An identification module, used to identify the shale gas reservoir image by using the fracture recognition model to obtain the effective fracture information of the shale gas reservoir;

[0039] An evaluation module, used to evaluate the shale gas reservoir according to the effective fracture information of the shale gas reservoir.

[0040] Optionally, the data acquisition module includes:

[0041] A sample collection unit, used to collect rock samples;

[0042] A preprocessing unit, used to preprocess the rock sample to obtain a polished sample surface;

[0043] A scanning unit, used to perform electron beam line-by-line scanning on a selected area of the polished sample surface to obtain the surface image of the rock sample.

[0044] Optionally, the training module includes:

[0045] A crack determination unit, configured to determine cracks and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample;

[0046] A crack category determination unit, configured to determine the category of the crack according to the characteristic parameters of the crack;

[0047] A training set establishment unit, configured to establish a training data set according to the characteristic parameters and categories of each crack corresponding to the surface image of the rock sample;

[0048] A training unit, configured to train a crack recognition model by using the training data set.

[0049] Optionally, the effective crack information includes: effective crack characteristics and their quantity per unit area;

[0050] The evaluation module includes:

[0051] A statistics unit, configured to determine the crack quantity and effective crack density of the shale gas reservoir according to the effective crack information of the shale gas reservoir;

[0052] A calculation unit, configured to calculate a crack index of the shale gas reservoir according to the effective crack quantity, effective crack length, and effective crack density of the shale gas reservoir;

[0053] An evaluation unit, configured to determine the development degree of the cracks in the shale gas reservoir according to the crack index of the shale gas reservoir.

[0054] The method and device for identifying and evaluating cracks in a shale gas reservoir provided by the present invention perform backscattering imaging on cores and cuttings through a rock and mineral scanning technology, extract characteristic parameters of cracks on a BSE (backscattered electron) image, define different types of cracks, realize crack type classification, and obtain a crack recognition model through training, so as to quickly identify the fracture development section and its development degree of the shale gas reservoir near the wellbore, providing a theoretical basis for reservoir interpretation and evaluation and assisting hydraulic fracturing construction. Description of the Drawings

[0055] Figure 1 is a flowchart for constructing a crack recognition model in an embodiment of the present invention;

[0056] Figure 2 is a grayscale calibration curve graph of a rock sample of Well A in an example of the method of the present invention;

[0057] Figure 3 is a flowchart of a method for identifying and evaluating cracks in a shale gas reservoir provided by the present invention;

[0058] Figure 4It is a diagram showing the fracture distribution and reservoir classification of the horizontal section reservoir in Well A in the method example of the present invention;

[0059] Figure 5 It is an attribute slice diagram of the ant body at the bottom boundary of the Wufeng Formation passing through Well A;

[0060] Figure 6 It is a schematic structural diagram of a shale gas reservoir fracture identification and evaluation device provided by the present invention;

[0061] Figure 7 It is a schematic structural diagram of a data acquisition module in an embodiment of the present invention;

[0062] Figure 8 It is a schematic structural diagram of a training module in an embodiment of the present invention. Detailed implementation manners

[0063] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the accompanying drawings required for use in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other accompanying drawings based on these drawings without creative efforts.

[0064] The present invention will be described in detail below in conjunction with the accompanying drawings and specific implementation manners. The implementation manners cannot be elaborated one by one here, but the implementation manners of the present invention are not limited to the following implementation manners.

[0065] Aiming at the problem that there are high risks in imaging logging in the prior art and it is impossible to obtain fracture information of the horizontal section wellbore, the present invention provides a shale gas reservoir fracture identification and evaluation method and device, which pre-collects the surface images of rock samples, trains a fracture identification model using the surface images of the rock samples, uses the model to identify the effective fracture information of the shale gas reservoir, and realizes the evaluation of the shale gas reservoir according to the effective fracture information of the shale gas reservoir.

[0066] The construction process of the fracture identification model in the embodiments of the present invention will be described in detail below.

[0067] As Figure 1 shown, it is a construction flow chart of the fracture identification model in the embodiments of the present invention, including the following steps:

[0068] Step 101, collect the surface images of rock samples.

[0069] Specifically, collect rock samples; preprocess the rock samples to obtain a sample polished surface; perform an electron beam line-by-line scan on the selected area of the sample polished surface to obtain the surface images of the rock samples.

[0070] Among them, the pretreatment of the rock sample mainly includes:

[0071] Cutting in a direction perpendicular to the bedding plane of the shale sample;

[0072] Embedding the cut sample with resin (the cuttings sample is directly embedded after sieving);

[0073] Polishing and carbon plating the cut surface after embedding to meet the requirements of backscattered electron observation of the scanning electron microscope.

[0074] Through the above treatment, a polished surface of the sample can be generated.

[0075] In addition, it should be noted that the sample needs to be calibrated for gray scale before image acquisition.

[0076] The gray scale standard sample can be one of two substances, resin or quartz. After calibrating the gray scale peak positions of quartz and resin under the electron microscope, the selected area of the polished surface of the sample is scanned row by row with an electron beam to obtain a two-dimensional BSE image of the surface of the rock sample, and this image is stored by a computer.

[0077] BSE (backscattered electron) is a high-energy electron generated by the elastic or inelastic scattering of the incident electron beam with the atomic nucleus. Using the BSE image can distinguish different component regions, provide imaging of the sample component composition information. In addition, the BSE image can also provide information about the crystal phase, morphology, etc. of the sample.

[0078] Step 102, determine the effective fractures and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample.

[0079] Specifically, the pore and fracture gray scale thresholds can be set according to the image gray scale of the same batch of samples, and pores and fractures are extracted from the image background to obtain a pore set {pore} and a fracture set {fracture}. That is, candidate pores and fracture sets are extracted from the background of the surface image of the rock sample according to the set pore and fracture gray scale thresholds.

[0080] Then, according to the set basic fracture parameters, the fractures in the candidate pore and fracture sets are determined to obtain the fractures and their characteristic parameters of the rock sample.

[0081] The basic fracture parameters may include three parameters: fracture length (fl), fracture width (fw), and fracture length-width ratio (fl / fw). These three basic parameters are used to distinguish pores and fractures, and the fractures are peeled off and extracted to obtain effective fractures. The pore-fracture discrimination function F is as follows:

[0082]

[0083] In the formula, fl represents the fracture length, that is, the fracture length per unit area;

[0084] fw represents the fracture aperture, that is, the fracture width, which is also the distance between the fracture walls;

[0085] fl / fw is the aspect ratio of the fracture, that is, the ratio of the major axis length to the minor axis length of the fracture;

[0086] a, b, c, and d are constants related to pores and fractures.

[0087] If the value of the pore-fracture discrimination function F conforms to the fracture function, it is determined that the pore accommodation space is a fracture; otherwise, it is determined that the pore accommodation space is a pore.

[0088] Through the above pore-fracture discrimination function F, all fractures in the pore set {pore} and the fracture set {fracture} can be determined, and the characteristic parameters of each fracture, that is, the length and width of the fracture, can be obtained.

[0089] Step 103: Determine the category of the effective fracture according to the characteristic parameters of the effective fracture.

[0090] In the embodiment of the present invention, fractures can be classified according to fracture parameter differences to determine effective fractures. For example, the following three types of fractures can be defined according to the fracture occurrence, that is, the fracture length, width, and filling degree:

[0091] ① Dry fracture

[0092] Definition: Caused by the dehydration of clay minerals during the long-term weathering, drying, or vacuum pumping of core and cuttings samples.

[0093] Occurrence: The fracture length fl≥a1μm, very straight, the fracture aperture fw≤b1μm, without filling.

[0094] ② Mechanical fracture

[0095] Definition: Generated due to the mechanical rock-breaking force generated by the drill bit, and the rock itself disintegrates, mostly seen at the edge of cuttings.

[0096] Occurrence: The fracture length fl≥a2μm, relatively straight, the fracture aperture fw≥b2μm, and the inside of the fracture is often invaded by barite.

[0097] ③ Microfracture

[0098] Definition: Formed during the diagenesis of sediments or generated by the release of natural stress.

[0099] Occurrence: The fracture length fl≤a3μm, multiple groups of fractures are distributed in a network, and the fracture aperture fw<b3μm.

[0100] a1 to a3 and b1 to b3 are defined as different crack discrimination constants, which can be determined according to the actual measured statistical values.

[0101] Among them, mechanical cracks and micro-cracks are reflections of the mechanical properties of underground rocks and have certain guiding significance for hydraulic fracturing. Therefore, mechanical cracks and micro-cracks can be defined as effective cracks, that is:

[0102]

[0103] Among them, n is the number of mechanical cracks and m is the number of micro-cracks.

[0104] Step 104: Establish a training data set according to the characteristic parameters and categories of each effective crack corresponding to the surface image of the rock sample.

[0105] Among them, each surface image of the rock sample, the effective crack corresponding to the image, the characteristic parameters and categories of the effective crack form a training sample.

[0106] Step 105: Train a crack recognition model using the training data set.

[0107] Use the training data set for modeling and machine learning to obtain a crack recognition model.

[0108] The crack recognition model can be derived from the hierarchical structure model of classical machine learning, and its training process includes: data input → artificial design → machine learning → data output.

[0109] The data input is to obtain high-resolution SEM (scanning electron microscope) images using a scanning electron microscope and input them into the computer. The computer measures the crack length and aperture through an image analysis and processing algorithm. An artificial design is used to establish a crack objective function, and different types of cracks are distinguished based on the crack size and its characteristics, and effective cracks are defined on this basis, that is, a training data set is established. After completing the above data input, machine learning begins, and the objective function is optimized during the process of training with a large amount of data. Finally, different types of cracks and related information are batch-extracted. Finally, the effective crack information of the shale gas reservoir is output, and the effective crack information includes the characteristics of the effective cracks and their quantity per unit area. The characteristics of the effective cracks can include, for example, but are not limited to: effective crack length L, effective crack density D, crack index RFI, etc. The crack index RFI is an index representing the crack density of the reservoir and indicates the crack sensitivity of the reservoir.

[0110] The following further details the process of establishing a crack recognition model in the embodiments of the present invention with specific examples.

[0111] Well A is a well in the self-operated block of Changcheng Weiyuan in the Sichuan Basin, and the target layer belongs to the shale gas reservoir.

[0112] For Well A, the process of establishing a fracture identification model is as follows:

[0113] (1) Obtain the fracture observation surface

[0114] The fracture observation surface is obtained by resin embedding, polishing, and carbon plating of a batch of cores (or cuttings), and it can be specifically carried out in accordance with relevant standards.

[0115] (2) BSE image acquisition

[0116] First, it is necessary to calibrate the image acquisition grayscale using a standard sample, such as Figure 2 the grayscale calibration curve shown.

[0117] Figure 2 It reflects the grayscale concept of substances, and each substance has a fixed numerical range of grayscale under the electron microscope. The abscissa is the grayscale value, the ordinate is the pixel value, the left peak is the grayscale peak of the resin, and the right peak is the grayscale peak of the mineral quartz. By adjusting the brightness and contrast of the electron microscope, the peak positions of the two can be fixed to achieve the grayscale calibration of the sample to be measured.

[0118] Set the scanning area and scanning path of the sample, set the image resolution to 1024x768, set the energy spectrum analysis step size to 64μm, set the number of scanned frame images to 64, perform electron beam scanning line by line, obtain 64 two-dimensional BSE images of the rock sample surface, and perform mosaic processing on the 64 frame pictures by computer and store the BSE image.

[0119] (3) Pore and fracture extraction

[0120] According to the image grayscale of the same batch of samples, set the pore and fracture grayscale thresholds, set the pore and fracture grayscale threshold in the BSE image obtained this time to 73, and obtain that the total porosity and fracture porosity of the first shale sample A1 is 9.1%.

[0121] (4) Pore and fracture discrimination

[0122] Use the fracture discrimination function F to distinguish pores and fractures and obtain the number of fractures in the sample. The specific calculation process is as follows:

[0123] Set Then there is

[0124] Through computer calculation, the number of fractures in the shale sample A1 is obtained as 138 fractures / cm 2 .

[0125] (5) Calculate the effective number of fractures through fracture classification

[0126] According to the fracture classification scheme, the fractures in the shale sample A1 include: 8 dry fractures / cm2 , 42 mechanical seams per cm 2 , 88 microcracks per cm 2 .

[0127] The number of effective cracks in sample A1 = 88 + 42 = 130 cracks per cm 2 .

[0128] In the manner of steps (3) to (5) above, the effective crack information of all shale samples in this batch is obtained.

[0129] (6) Crack machine learning

[0130] Based on the effective crack information of all the above shale samples, a training data set is established. Using this training data set, a crack recognition model is trained.

[0131] Based on the crack recognition model pre-trained above, the effective cracks in the reservoir can be quickly and accurately identified, and then the shale gas reservoir can be evaluated according to the effective cracks in the reservoir.

[0132] As Figure 3 shown, it is a flowchart of a method for crack recognition and evaluation of a shale gas reservoir provided by the present invention, including the following steps:

[0133] Step 301, pre-collect the surface image of the rock sample, and use the surface image of the rock sample to train a crack recognition model.

[0134] The process of establishing the crack recognition model can refer to the description in the foregoing Figure 1 illustrated embodiment and will not be elaborated herein.

[0135] Step 302, obtain the shale gas reservoir image to be recognized.

[0136] Specifically, rock samples of the shale gas reservoir can be collected. The collection of rock samples can select multiple location areas, and one or more rock samples can be collected in each location area. The specific quantity can be determined according to needs, and the embodiments of the present invention do not make limitations thereto.

[0137] For each rock sample, it can be processed according to the pretreatment method in step 101 above Figure 1 , and then the selected area of the polished surface of the sample is scanned row by row with an electron beam to obtain a two-dimensional BSE image of the rock sample surface.

[0138] Step 303, use the crack recognition model to recognize the shale gas reservoir image to obtain the effective crack information of the shale gas reservoir.

[0139] Specifically, the two-dimensional BSE images of each rock sample are input into the fracture recognition model, and the effective fracture information corresponding to the rock sample is obtained according to the output of the fracture recognition model.

[0140] The effective fracture information may include, but is not limited to: effective fractures and their quantity per unit area.

[0141] Step 304, evaluate the shale gas reservoir according to the effective fracture information of the shale gas reservoir.

[0142] First, determine the fracture quantity and effective fracture density of the shale gas reservoir according to the effective fracture information of the shale gas reservoir. It should be noted that the effective fracture density can also be directly output by the fracture recognition model.

[0143] Then, calculate the fracture index RFI of the shale gas reservoir according to the effective fracture quantity C, effective fracture length L, and effective fracture density D of the shale gas reservoir.

[0144] In a non-limiting embodiment, the fracture index RFI of the shale gas reservoir can be obtained by weighted calculation of the above parameters, that is:

[0145]

[0146] Where "*" represents the multiplication operation. W 1 、W 2 、W 3 Are the corresponding weight coefficients.

[0147] Finally, determine the development degree of the fractures in the shale gas reservoir according to the fracture index of the shale gas reservoir. For example:

[0148] If the fracture index RFI of the shale gas reservoir ≥ x%, it is determined that the fractures in the shale gas reservoir are well developed and belong to the G reservoir;

[0149] If x% > RFI ≥ y%, it is determined that the fractures in the shale gas reservoir are moderately developed and belong to the M reservoir;

[0150] If RFI < y%, it is determined that the fractures in the shale gas reservoir are poorly developed and belong to the P reservoir.

[0151] Where x and y are the reservoir fracture evaluation threshold values, which can be set according to application needs, and are not limited in the embodiments of the present invention.

[0152] Where the G reservoir is the first letter G of Good, representing a type of reservoir as a high-quality reservoir; the M reservoir is the first letter M of Medium, representing the second type of reservoir, which is a good reservoir; the P reservoir is the first letter P of Poor, representing the third type of reservoir, that is, a poor reservoir.

[0153] It can be seen that by using the solution of the present invention, the rapid identification and evaluation of the fracture development section of the shale gas reservoir can be accurately and efficiently carried out.

[0154] For example, using the method of the present invention to identify fractures in Well A above, calculating the fracture index RFI of the shale gas reservoir according to the obtained effective fracture data, evaluating the fracture properties of the reservoir in the horizontal section, and obtaining the effective fracture number and reservoir classification statistical table 1 of the entire horizontal section of Well A and Figure 4 the fracture distribution and reservoir classification map of the reservoir in the horizontal section of Well A shown.

[0155] Table 1

[0156]

[0157]

[0158]

[0159] Based on the analysis and statistics, 10 fracture development sections are selected for the horizontal section of Well A, and compared with Figure 5 the attribute slice of the ant body at the bottom boundary of the Wufeng Formation of the well in the shown seismic data. There are responses at 3448 - 3772m and 4650 - 4738m in the ant body passing through Well A, and most of the ant bodies show good agreement with the natural fracture development sections interpreted by this method.

[0160] In addition, the statistical table of the fracture development section of the reservoir in the horizontal section of Well A and the ant body response is shown in Table 2.

[0161] Table 2

[0162] Serial number Stratigraphic horizon Well section (m) Thickness (m) Interpretation conclusion Remarks 1 Wufeng Formation 3600～3687 87 Fracture-developed section Ant body 2 <![CDATA[Long Yi 1 1 > 3858～3890 32 Fracture-developed section High quartz section 3 <![CDATA[Long Yi 1 1 > 3944～4050 106 Fracture-developed section High quartz section 4 <![CDATA[Long Yi 1 1 > 4088～4204 116 Fracture-developed section High quartz section 5 <![CDATA[Long Yi 1 1 > 4532～4570 38 Fracture-developed section Near the ant body 6 <![CDATA[Wufeng Formation - Long 1 1 1 > 4650～4736 86 Fracture-developed section Ant body 7 <![CDATA[Long Yi 1 1 > 4794～4888 94 Fracture-developed section High quartz section 8 <![CDATA[Long Yi 1 1 > 4908～4944 36 Fracture-developed section Ant body 9 <![CDATA[Wufeng Formation - Longyi 1 1 > 5146～5238 92 Fracture-developed section High quartz section 10 Wufeng Formation 5276～5294 18 Fracture-developed section Ant body

[0163] As can be seen from Table 2, in addition to the well sections corresponding to the seismic ant body slices, the method of the solution of the present invention also interprets 5 fracture development zones caused by high quartz, which cannot be found by the seismic ant body slices, improving the identification rate of the fracture development zones in the wellbore and providing data support for the optimization of the fracturing design.

[0164] Correspondingly, the present invention also provides a shale gas reservoir fracture identification and evaluation device, as Figure 6 shown, which is a schematic structural diagram of the device.

[0165] The shale gas reservoir fracture identification and evaluation device 600 provided in this embodiment includes the following modules:

[0166] Model construction module 601, where the model construction module includes a data acquisition module 611 and a training module 612; the image acquisition module 611 is used to pre-acquire the surface image of the rock sample; the training module 612 is used to train a fracture recognition model 60 using the surface image of the rock sample;

[0167] Image acquisition module 602, used to acquire the shale gas reservoir image to be recognized;

[0168] Recognition module 603, used to recognize the shale gas reservoir image using the fracture recognition model 60 to obtain the effective fracture information of the shale gas reservoir;

[0169] Evaluation module 604, used to evaluate the shale gas reservoir according to the effective fracture information of the shale gas reservoir.

[0170] As Figure 7 shown, it is a schematic structural diagram of the data acquisition module in an embodiment of the present invention.

[0171] The data acquisition module 611 includes the following units:

[0172] Sample acquisition unit 6111, used to acquire rock samples;

[0173] Pretreatment unit 6112, used to pretreat the rock sample to obtain a polished sample surface;

[0174] Scanning unit 6113, used to perform an electron beam line-by-line scan on a selected area of the polished sample surface to obtain the surface image of the rock sample.

[0175] As Figure 8 shown, it is a schematic structural diagram of the training module in an embodiment of the present invention.

[0176] The training module 612 includes the following units:

[0177] Fracture determination unit 6121, used to determine the fractures and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample;

[0178] Fracture category determination unit 6122, used to determine the category of the fracture according to the characteristic parameters of the fracture;

[0179] Training set establishment unit 6123, used to establish a training data set according to the characteristic parameters and categories of each fracture corresponding to the surface image of the rock sample;

[0180] Training unit 6124, used to train a fracture recognition model using the training data set.

[0181] In an embodiment of the present invention, the effective fracture information may include, but is not limited to, effective fractures and their quantity per unit area. Correspondingly, a non-limiting structure of the evaluation module may include the following units:

[0182] A statistical unit for determining the fracture quantity and effective fracture density of the shale gas reservoir according to the effective fracture information of the shale gas reservoir;

[0183] A calculation unit for calculating the fracture index of the shale gas reservoir according to the effective fracture quantity, effective fracture length, and effective fracture density of the shale gas reservoir;

[0184] An evaluation unit for determining the development degree of the fractures in the shale gas reservoir according to the fracture index of the shale gas reservoir.

[0185] For example, the development degree standard of the fractures in the shale gas reservoir corresponding to different fracture index ranges can be preset in advance, and the development degree of the fractures in the shale gas reservoir can be determined according to this standard and the calculated fracture index of the shale gas reservoir.

[0186] For the specific implementation manners of the above modules and units, reference may be made to the corresponding descriptions in the method embodiments of the present invention above, which will not be elaborated herein.

[0187] The device for identifying and evaluating fractures in a shale gas reservoir provided by the present invention performs backscattering imaging on cores and cuttings through rock mineral scanning technology, extracts the characteristic parameters of fractures on the BSE map, defines different types of fractures, realizes fracture type classification, and obtains a fracture identification model through training, so as to quickly identify the fracture development sections and their development degrees in the near-wellbore shale gas reservoir, providing a theoretical basis for reservoir interpretation and evaluation and assisting hydraulic fracturing construction.

[0188] The method and device for identifying and evaluating fractures in a shale gas reservoir provided by the present invention have the following advantages:

[0189] (1) The solution of the present invention uses drilling cuttings and cores to identify and characterize fractures, and uses the shale gas fracture index RFI to judge the microfracture development in the near-wellbore reservoir. The operation is convenient and simple, solving the problems of low seismic prediction accuracy and high risk of imaging logging, reducing the construction cost, accelerating the well construction period, and promoting the early production of gas wells.

[0190] (2) The solution of the present invention realizes the extraction of pores and fractures from backscattering images through gray scale calibration, and establishes a set of methods for fracture discrimination, classification and rapid evaluation of shale gas reservoirs, providing technical support for further shale gas exploration and development.

[0191] (3) The fracture-developed intervals identified by the solution of the present invention are all in good agreement with the seismic prediction ant bodies. By comparing and verifying with the seismic ant bodies, the fracture-developed sections and their development degrees of the shale gas reservoirs near the wellbore can be quickly identified, providing a theoretical basis for reservoir interpretation and evaluation and assisting fracturing construction.

[0192] (4) The solution of the present invention has broad application prospects. The fracture identification, characterization and evaluation methods can be well applied to shale and tight sandstone reservoirs to achieve method replication.

[0193] It should be noted that the terms "including" and "having" and any variations thereof in the description and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0194] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Moreover, the system embodiments described above are only illustrative. The modules and units described as separate components may or may not be physically separated, that is, they may be located on one network unit or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0195] The above has introduced the embodiments of the present invention in detail. The specific implementation manners are used to elaborate the present invention herein. The description of the above embodiments is only used to help understand the method and system of the present invention. They are only a 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 a person of ordinary skill in the art without creative work shall fall within the protection scope of the present invention. The content of this specification should not be construed as a limitation to the present invention. Therefore, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying and evaluating fractures in a shale gas reservoir, characterized in that, the method includes: Pre-collecting the surface image of a rock sample, and training a fracture identification model using the surface image of the rock sample; Obtaining the shale gas reservoir image to be identified; Using the fracture identification model to identify the shale gas reservoir image to obtain the effective fracture information of the shale gas reservoir; Evaluating the shale gas reservoir according to the effective fracture information of the shale gas reservoir.

2. The method for identifying and evaluating fractures in a shale gas reservoir according to claim 1, characterized in that, the collecting of the surface image of the rock sample includes: Collecting a rock sample; Preprocessing the rock sample to obtain a polished sample surface; Performing an electron beam line-by-line scan on a selected area of the polished sample surface to obtain the surface image of the rock sample.

3. The method for identifying and evaluating fractures in a shale gas reservoir according to claim 2, characterized in that, the preprocessing of the rock sample to obtain a polished sample surface includes: Cutting in a direction perpendicular to the bedding plane of the shale sample; Embedding the cut sample in resin; Polishing and carbon plating the cut surface after embedding to generate a polished sample surface.

4. The method for identifying and evaluating fractures in a shale gas reservoir according to claim 2, characterized in that, the surface image of the rock sample is a two-dimensional BSE image.

5. The method for identifying and evaluating fractures in a shale gas reservoir according to claim 1, characterized in that, the training of the fracture identification model using the surface image of the rock sample includes: Determining the effective fractures and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample; Determining the category of the effective fractures according to the characteristic parameters of the effective fractures; Establishing a training data set according to the characteristic parameters and categories of the effective fractures corresponding to the surface image of the rock sample; Training a fracture identification model using the training data set.

6. The method for identifying and evaluating fractures in a shale gas reservoir according to claim 5, characterized in that, the determining of the effective fractures and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample includes: Extracting a candidate pore and fracture set from the background of the surface image of the rock sample according to the set pore and fracture gray-scale thresholds; Determining the effective fractures in the candidate pore and fracture set according to the set basic fracture parameters to obtain the effective fractures and their characteristic parameters of the rock sample.

7. The method for identifying and evaluating fractures in a shale gas reservoir according to claim 5, characterized in that, the categories of the fractures include any one or more of the following: dry fractures, mechanical fractures, micro-fractures.

8. The method for identifying and evaluating fractures in a shale gas reservoir according to any one of claims 1 to 7, characterized in that, the effective fracture information includes: effective fracture characteristics and their quantity per unit area; the evaluating of the shale gas reservoir according to the effective fracture information of the shale gas reservoir includes: Determining the fracture quantity and effective fracture density of the shale gas reservoir according to the effective fracture information of the shale gas reservoir. Calculate the fracture index of the shale gas reservoir according to the number of effective fractures, the length of effective fractures, and the effective fracture density of the shale gas reservoir; Determine the development degree of the fractures in the shale gas reservoir according to the fracture index of the shale gas reservoir.

9. A device for fracture identification and evaluation of a shale gas reservoir, characterized in that the device includes: a model construction module, which includes a data acquisition module and a training module; the data acquisition module is used to pre-acquire the surface image of a rock sample; the training module is used to train a fracture identification model by using the surface image of the rock sample; an image acquisition module, which is used to acquire the image of the shale gas reservoir to be identified; an identification module, which is used to identify the image of the shale gas reservoir by using the fracture identification model to obtain the effective fracture information of the shale gas reservoir; an evaluation module, which is used to evaluate the shale gas reservoir according to the effective fracture information of the shale gas reservoir.

10. The device for fracture identification and evaluation of a shale gas reservoir according to claim 9, characterized in that the data acquisition module includes: a sample acquisition unit, which is used to acquire a rock sample; a preprocessing unit, which is used to preprocess the rock sample to obtain a polished sample surface; a scanning unit, which is used to perform an electron beam scanning row by row on a selected area of the polished sample surface to obtain the surface image of the rock sample.

11. The device for fracture identification and evaluation of a shale gas reservoir according to claim 10, characterized in that the training module includes: a fracture determination unit, which is used to determine the fractures and their characteristic parameters of the rock sample according to the background of the surface image of the rock sample; a fracture category determination unit, which is used to determine the category of the fractures according to the characteristic parameters of the fractures; a training set establishment unit, which is used to establish a training data set according to the characteristic parameters and categories of the fractures corresponding to the surface image of the rock sample; a training unit, which is used to train a fracture identification model by using the training data set.

12. The device for fracture identification and evaluation of a shale gas reservoir according to any one of claims 9 to 11, characterized in that the effective fracture information includes: effective fracture characteristics and their quantity per unit area; the evaluation module includes: a statistics unit, which is used to determine the fracture number and effective fracture density of the shale gas reservoir according to the effective fracture information of the shale gas reservoir; a calculation unit, which is used to calculate the fracture index of the shale gas reservoir according to the number of effective fractures, the length of effective fractures, and the effective fracture density of the shale gas reservoir; an evaluation unit, which is used to determine the development degree of the fractures in the shale gas reservoir according to the fracture index of the shale gas reservoir.

Images