Pore type identification model establishment method, pore type identification method and device

Abstract

The application discloses a pore type identification model establishing method, a pore type identification method and device. The pore type identification model establishing method comprises the following steps: obtaining nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of a core sample of a set pore type, development of the set pore type and saturation of prepared formation water, nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the core sample after centrifugation, and obtaining a sample; a sample set is formed by a plurality of samples; and a selected classification model is trained by using the sample set to obtain a classification model for pore type identification. The established pore type identification model can reflect the pore characteristics of the sample as a whole, and the analysis error is small.

Description

Technical Field

[0001] This invention relates to the field of reservoir evaluation technology, and in particular to a method for establishing a pore type identification model, a pore type identification method, and an apparatus. Background Technology

[0002] The effective classification of reservoir types restricts the accurate estimation of resource quantity. Currently, pore type classification is mainly carried out through direct or indirect imaging of sample pores, such as optical microscopy, scanning electron microscopy, and X-ray CT scanning. These methods can intuitively reflect the morphology and size of pores, and methods such as electron microscopy and CT can effectively observe pore features at the nanometer and micrometer scales. However, these methods have the problem of sample representativeness. The higher the magnification of the experimental method, the smaller the observed range, and it cannot reflect the pore characteristics of the sample relatively holistically.

[0003] In addition, existing technologies also employ fluid injection methods to observe and classify pore types. These methods reflect changes in pore throats by observing changes in saturation during fluid injection. Examples include mercury intrusion porosimetry (MIP) and cryogenic gas adsorption. The changes in fluid saturation during injection are converted into changes in pore throat radius to reflect the distribution characteristics of the pore throat radius. While these methods can comprehensively reflect the proportion of pore throats of different sizes in the sample, they have limitations such as limited fluid injection into some micro-pore throats and the inability to reflect the distribution characteristics of pore throats where fluid is not injected. Furthermore, the interaction force between the fluid and the rock sample interface during injection affects the accuracy of the test, and this error cannot be eliminated.

[0004] In summary, existing methods for classifying pore types have the problem of failing to reflect the overall pore characteristics of a sample or having significant errors. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed to provide a method, apparatus and device for establishing a pore type identification model that overcomes or at least partially solves the above problems, which can reflect the pore characteristics of the sample as a whole and has a small analysis error.

[0006] In a first aspect, embodiments of the present invention provide a method for establishing a pore type identification model, comprising:

[0007] A sample is obtained by acquiring nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of core samples with a set pore type, developed with the set pore type and saturated with formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of the core samples after centrifugation.

[0008] A sample set consists of multiple of the aforementioned samples;

[0009] The selected classification model is trained using the sample set to obtain a classification model for pore type identification.

[0010] Secondly, embodiments of the present invention provide a method for identifying pore type, including:

[0011] Nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core containing saturated formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core after centrifugation, are obtained to obtain a test sample.

[0012] The test sample is input into the classification model established according to the above method, and the pore type of the core sample is determined based on the output results.

[0013] Thirdly, embodiments of the present invention provide a pore type identification model establishment device, comprising:

[0014] The sample acquisition module is used to acquire nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of core samples with a set pore type, the set pore type and saturated formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of the core samples after centrifugation, to obtain a sample.

[0015] A sample set acquisition module is used to compose a sample set from multiple samples.

[0016] The training module is used to train a selected classification model using the sample set to obtain a classification model for pore type identification.

[0017] Fourthly, embodiments of the present invention provide a pore type identification device, comprising:

[0018] The test sample acquisition module is used to acquire the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core with saturated formation water, and the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core after centrifugation, to obtain a test sample.

[0019] The pore type determination module is used to input the test sample into the classification model established according to the above method, and determine the pore type of the core sample to be tested based on the output results.

[0020] Fifthly, embodiments of the present invention provide a computer program product with pore type recognition function, including a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the above-mentioned pore type recognition model establishment method, or implements the above-mentioned pore type recognition method.

[0021] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0022] The pore type identification model establishment method provided in this invention involves acquiring nuclear magnetic resonance imaging (NMR) and nuclear magnetic resonance relaxation spectra of core samples with a defined pore type, saturated formation water, and after centrifugation, resulting in a sample. Multiple samples form a sample set. The selected classification model is then trained using this sample set to obtain a classification model for pore type identification. NMR imaging and nuclear magnetic resonance relaxation spectra combine the imaging and distribution characteristics of pores, reflecting both the morphological features and the distribution of pore radius, thus providing a relatively comprehensive reflection of the overall pore characteristics. Furthermore, the differences in NMR imaging and nuclear magnetic resonance relaxation spectra between the core samples saturated with formation water before and after centrifugation reflect the change in porosity of mobile fluids. Therefore, the final trained classification model can comprehensively reflect the pore characteristics of the sample with relatively small analytical errors.

[0023] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0024] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0025] Figure 1 This is a flowchart of the pore type identification model establishment method in Embodiment 1 of the present invention;

[0026] Figure 2 for Figure 1 The detailed implementation flowchart of step S11 is shown below;

[0027] Figure 3 Nuclear magnetic resonance imaging and relaxation spectra of core samples with different pore types after saturation and centrifugation;

[0028] Figure 4 This is a schematic diagram of the pore type identification model establishment device in an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram of the pore type identification device in an embodiment of the present invention. Detailed Implementation

[0030] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0031] It should be understood that the terminology used in this invention is merely for describing particular embodiments and is not intended to limit the invention. Furthermore, with respect to numerical ranges in this invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Every smaller range between any stated value or intermediate value within a stated range, and any other stated value or intermediate value within said range, is also included in this invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0032] Unless otherwise stated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. While only preferred methods and materials have been described herein, any methods and materials similar or equivalent to those described herein may be used in the implementation or testing of this invention. All references to this specification are incorporated by way of citation to disclose and describe methods and / or materials associated with those references. In the event of any conflict with any incorporated reference, the content of this specification shall prevail.

[0033] In the description of this invention, it should be noted that the terms "comprising", "including", "having", "containing", etc., are all open-ended terms, meaning that they include but are not limited to.

[0034] To address the problem that existing technologies for classifying pore types cannot comprehensively reflect the pore characteristics of a sample or have large errors, this invention provides a method for establishing a pore type identification model, a pore type identification method, and an apparatus that can comprehensively reflect the pore characteristics of a sample with smaller analysis errors.

[0035] Example 1

[0036] Embodiment 1 of the present invention provides a method for establishing a pore type identification model, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0037] Step S11: Obtain nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of core samples with set pore type, developed with set pore type and saturated with formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of core samples after centrifugation, to obtain a sample.

[0038] Specifically, participate Figure 2 As shown, obtaining sample data may include the following steps:

[0039] Step S111: After washing and drying the core sample with the specified pore type, saturate the formation water using a vacuum pressurized water saturation device.

[0040] Core samples with typical pore types were selected, and further, core samples with a single typical pore type were selected. The core samples mainly showed a single pore type, making the obtained samples more representative and enabling better establishment of learning standards.

[0041] The core sample selected can be a core drill plunger (plunger length 3-5cm, diameter 2.5cm), or alternatively, the core sample can be of other shapes or sizes.

[0042] The core samples are washed with a solution made of kerosene and benzene for 5 to 7 days until the solution becomes transparent. The core samples are then removed and dried.

[0043] Based on the analysis results of the formation water sample ion concentration, a formation water solution was prepared. The dried core sample was placed in a vacuum pressurization saturation device, and after being evacuated for 8 hours, the formation water was saturated at a pressure of 20 MPa for 72 hours.

[0044] Step S112: Perform nuclear magnetic resonance T2 spectrum testing and nuclear magnetic resonance imaging on the saturated core sample to obtain the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the core sample after saturation.

[0045] Based on the characteristic of nuclear magnetic resonance (NMR) of hydrogen nuclei in saturated fluid samples, a directional magnetic field is applied to the saturated sample to align the hydrogen nuclei. After the directional magnetic field is removed, it returns to its natural state. During this process, the signal intensity changes are inconsistent for core samples of different scales and fluid saturation levels. The change in NMR signal intensity with relaxation time after the magnetic field is removed reflects the porosity and fluid saturation characteristics. This change in NMR signal intensity over time can be reflected by the NMR relaxation spectrum. Based on the above principles, samples with different pore types exhibit different NMR imaging and relaxation spectra after saturation, and the changes in mobile water porosity during centrifugation also differ. Therefore, a standard for pore type classification is established.

[0046] Samples with different pore types exhibit different morphological characteristics in their nuclear magnetic resonance (NMR) relaxation spectra after fluid saturation, and the proportion of pores of different sizes varies among different pore types. Larger pore sizes in a sample correspond to longer relaxation times and stronger signal in their NMR relaxation spectra. This allows for a preliminary classification of different pore types based on the distribution characteristics of their NMR relaxation time spectra. Furthermore, samples with different pore types show different imaging characteristics after fluid saturation; the imaging characteristics of the fluid after saturation reflect the morphological characteristics of the pores, thus the NMR imaging characteristics also reflect the pore type.

[0047] The NMR relaxation spectrum of the sample can be either a directly obtained NMR T2 spectrum (with relaxation time on the x-axis and signal intensity on the y-axis) or a relaxation spectrum converted from the NMR T2 spectrum (with relaxation time on the x-axis and porosity component on the y-axis). Here, the porosity component specifically refers to the ratio of the pore volume to the sample volume corresponding to the pore radius at the given relaxation time. Therefore, the envelope area of ​​the relaxation spectrum, i.e., the area enclosed by the spectral curve and the relaxation time axis, reflects the total porosity.

[0048] The T2 spectrum of nuclear magnetic resonance (NMR) is a curve with relaxation time on the x-axis and signal intensity on the y-axis. Relaxation time is related to pore radius, and signal intensity is related to saturated fluid content. The T2 spectrum reflects information on both the pore throat radius distribution and the proportion of saturated fluid in the pore throat. Multiple rock samples with known porosity and saturated formation water can be pre-tested to obtain the correlation between porosity and NMR signal intensity. Based on this correlation, a standard calibration sample is used for calibration (keeping NMR test parameters consistent) to convert the signal intensity in the T2 spectrum into porosity.

[0049] Step S113: After centrifuging the saturated core sample at the currently set centrifugation speed and time, obtain the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum after centrifugation, until the consistency between the currently obtained nuclear magnetic resonance imaging and the most recently obtained nuclear magnetic resonance imaging meets the first set condition, and / or the consistency between the currently obtained nuclear magnetic resonance relaxation spectrum and the most recently obtained nuclear magnetic resonance relaxation spectrum meets the second set condition.

[0050] The current centrifugation speed is greater than the most recent centrifugation speed. This means that the saturated core sample is centrifuged multiple times in ascending order of speed, and nuclear magnetic resonance imaging and relaxation spectra are obtained after each centrifugation.

[0051] Step S114: Obtain nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of core samples with set pore type, developed with set pore type and saturated with formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra after each centrifugation to obtain a sample.

[0052] During the intermediate centrifugation process, the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra after each centrifugation are also added to the sample, which can play an auxiliary role in identification. Optionally, step S114 can also be performed in the following manner:

[0053] Nuclear magnetic resonance imaging (NMR) and nuclear magnetic resonance relaxation spectra of core samples with defined pore types, saturated formation water, and after the final centrifugation are obtained to obtain a sample.

[0054] Step S12: A sample set is composed of multiple samples.

[0055] For each set pore type, multiple core samples with that pore type are selected. Each core sample is processed through step 11 above to obtain a sample set. Multiple samples are combined to form a sample set.

[0056] Step S13: Train the selected classification model using the sample set to obtain a classification model for pore type identification.

[0057] The specific type of classification model is not limited in this embodiment. Multiple classification types can be selected, trained on sample sets respectively, and finally the model with the best recognition effect is selected as the final classification model to identify the pore type of the test sample, that is, the sample whose pore type is to be identified.

[0058] The pore type identification model establishment method provided in Embodiment 1 of this invention obtains nuclear magnetic resonance imaging (NMR) and NMR relaxation spectra of core samples with a defined pore type, saturated formation water, and after centrifugation, resulting in a sample. Multiple samples form a sample set. The selected classification model is trained using this sample set to obtain a classification model for pore type identification. NMR imaging and NMR relaxation spectra combine the imaging features and distribution features of pores, reflecting both the morphological characteristics and the distribution of pore radius, thus providing a relatively comprehensive reflection of the overall pore characteristics. Furthermore, the differences in NMR imaging and NMR relaxation spectra between the core samples saturated with formation water before and after centrifugation reflect the change in porosity of mobile fluids. Therefore, the final trained classification model can reflect the overall pore characteristics of the sample with relatively small analytical errors.

[0059] The following example, using the identification of pore types in lacustrine carbonate rocks of a target layer in a certain study area, illustrates the process of establishing a classification model.

[0060] The samples from this area are characterized by the following features: their composition is mainly composed of calcite, dolomite, and small amounts of detrital particles and gypsum and other salt minerals; their lithology is dominated by argillaceous / marl (dome) rock, gypsum-bearing lime (dome) rock, algal lime (dome) rock, and granular lime (dome) rock; their physical properties indicate that they belong to low-porosity / ultra-low-porosity and ultra-low-permeability reservoirs, with porosity generally ranging from 3 to 9% and permeability below 0.1 mD, and are generally dense; thin section observations suggest that the samples from this area have developed pores of various sizes, including dolomite intercrystalline pores, intercrystalline dissolution pores, algal lime dolomite framework pores, and salt mineral dissolution pores.

[0061] Core samples with multiple intergranular pores, multiple intergranular dissolution pores, multiple salt mineral dissolution pores, and multiple interlayer fractures were selected. For each core sample, a sample was obtained according to step S11 in Example 1. The sample included the core sample's pore type, saturated NMR imaging and relaxation spectra, NMR imaging and relaxation spectra after centrifugation at 0.144 MPa, 0.288 MPa, 0.576 MPa, and 1.144 MPa. See details [link to relevant documentation]. Figure 3 As shown.

[0062] Nuclear magnetic resonance imaging and relaxation spectrum analysis of core samples with well-developed intercrystalline pores after saturation and during centrifugation:

[0063] Figure 3 In the NMR spectrum, a1 shows the NMR image of a sample with intergranular pore development after saturation. The NMR fluid imaging characteristics are: planar distribution, signal intensity value around 3000, indicating a relatively small amount of saturated fluid. a2 shows the NMR image after centrifugation at 1.144 MPa. Even after centrifugation at maximum intensity, the fluid still exhibits a planar distribution, and the total fluid volume decreases only slightly during centrifugation. a3 shows the NMR relaxation spectra after saturation and each centrifugation, showing a single-peak distribution with the peak value shifted to the left. Statistical analysis of the NMR relaxation spectra of multiple samples with intergranular pore development after saturation and each centrifugation revealed that the peak relaxation time ranged from 2.23 ms to 13.89 ms, the bound water saturation ranged from 89.5% to 95.53%, with an average of 93.08%, the porosity component variation ranged from 2% to 4%, and the porosity component change rate ranged from 30% to 50%.

[0064] Figure 3 b1 shows NMR imaging of a sample with intergranular dissolved pores after saturation. The NMR-hydrodynamic imaging characteristics are: planar distribution, signal intensity values ​​mainly between 3000 and 5000, indicating a relatively large amount of saturated fluid. b2 shows NMR imaging after centrifugation at 1.144 MPa. Even after maximum centrifugation, the fluid still exhibits a planar distribution, but the signal intensity value drops to around 3000, indicating that fluid in areas with higher content is expelled. b3 shows the NMR relaxation spectra after saturation and each centrifugation, showing a single-peak distribution with the peak value shifted to the left. Statistical analysis of the NMR relaxation spectra of multiple samples with intergranular dissolved pores after saturation and each centrifugation revealed that the peak relaxation time ranged from 5.76 ms to 28.86 ms, the bound water saturation ranged from 67.81% to 96.32%, with an average of 75.93%, and the porosity component variation ranged from 4% to 6%, with a porosity component change rate of 40% to 50%.

[0065] Figure 3C1 shows NMR imaging of a saturated sample of salt minerals with well-developed pores. The NMR-hydrodynamic imaging characteristics are: irregular fluid distribution and a wide range of signal intensity values, from a minimum of around 1000 to a maximum of around 5000. C2 shows NMR imaging after centrifugation at 1.144 MPa. The signal intensity decreases significantly, becoming predominantly between 1000 and 2000, indicating that most of the fluid has been expelled from the sample. C3 shows the NMR relaxation spectra after saturation and each centrifugation, exhibiting a multi-peak distribution with the peak values ​​generally skewed to the right. Statistical analysis of the NMR relaxation spectra of multiple saturated salt minerals with well-developed pores after saturation and each centrifugation revealed that the bound water saturation ranged from 47.20% to 84.48%, with an average of 64.10%. The porosity component variation ranged from 6% to 8%, and the porosity component change rate ranged from 50% to 75%.

[0066] Figure 3 d1 is the NMR image of the sample after saturation of the interlaminar seam development. The NMR fluid imaging characteristics are: a banded distribution, with the fluid distribution direction in the same direction as the interlaminar seam. The signal intensity value in the banded region is about 3000, while the signal intensity in other regions is about 1000, indicating that the amount of saturated fluid is relatively small. d2 is the NMR image after centrifugation at 1.144 MPa. After centrifugation at the maximum intensity, the fluid is distributed in a planar manner. During centrifugation, a large amount of movable fluid is displaced from the banded region. d3 is the NMR relaxation spectrum after saturation and after each centrifugation. It is bimodal. The left peak has a high peak value and is symmetrical on both sides with a large envelope area. The right peak is low and asymmetrical. Statistical analysis of nuclear magnetic resonance relaxation spectra of multiple interlayer slit-developed samples after saturation and after each centrifugation revealed that the peak value of the left peak ranged from 13.34 ms to 23.45 ms, the peak value of the right peak ranged from 74.25 ms to 93.12 ms, the bound water saturation ranged from 75.17% to 81.91%, with an average value of 77.42%, the porosity component variation ranged from 1% to 3%, and the porosity component variation rate ranged from 20% to 30%.

[0067] In summary, during the training process of the classification model, it can learn the distribution characteristics of MRI in each sample, the magnitude of the signal intensity value, and the comparison between MRI after saturation and after centrifugation, as well as the spectral curve morphology characteristics of the relaxation spectrum (including the number and position of peaks), the size of the envelope area formed by the spectral curve and the relaxation time axis (reaction porosity), and the changes and rates of change of the bound water saturation and porosity components in the relaxation spectrum reaction.

[0068] Centrifugation can be considered as the process by which air displaces saturated formation water in the sample. The water that is displaced is considered to be mobile water in the sample. This process is repeated multiple times until the nuclear magnetic resonance relaxation spectrum after the last centrifugation no longer changes from the previous centrifugation. At this point, it is considered that the mobile water in the sample has been displaced. The change in the proportion of mobile water in the pores (mobile water porosity) before and after centrifugation can be calculated using the nuclear magnetic resonance relaxation spectrum. Different types of pores have different changes in mobile water porosity during centrifugation due to differences in pore connectivity. Therefore, the change in the mobile water porosity component during centrifugation can be used as one of the indicators for classifying pore types.

[0069] Example 2

[0070] Embodiment 2 of the present invention provides a method for identifying pore type, comprising:

[0071] Nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core containing saturated formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core after centrifugation, are obtained to obtain a test sample.

[0072] Input the test sample into the classification model established according to the above method, and determine the pore type of the rock core to be tested based on the output results.

[0073] Specifically, the data contained in the test samples are in the same format and type as the data contained in each sample in the sample set used to train the classification model; the parameters of the MRI test process are also the same.

[0074] Based on the inventive concept of this invention, embodiments of this invention also provide a pore type identification model establishment device, the structure of which is as follows: Figure 4 As shown, it includes:

[0075] The sample acquisition module 41 is used to acquire the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of a core sample with a set pore type, the core sample with the set pore type and saturated formation water, and the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the core sample after centrifugation, to obtain a sample.

[0076] Sample set acquisition module 42 is used to compose a sample set from multiple samples;

[0077] Training module 43 is used to train a selected classification model using the sample set to obtain a classification model for pore type identification.

[0078] Based on the inventive concept of this invention, embodiments of this invention also provide a pore type identification device, the structure of which is as follows: Figure 5 As shown, it includes:

[0079] The test sample acquisition module 51 is used to acquire the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core with saturated formation water, and the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core after centrifugation, to obtain a test sample.

[0080] The pore type determination module 52 is used to input the test sample into the classification model established according to the above method, and determine the pore type of the core sample to be tested based on the output results.

[0081] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0082] Based on the inventive concept of the present invention, embodiments of the present invention also provide a computer program product with pore type identification function, including a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the above-mentioned pore type identification model establishment method, or implements the above-mentioned pore type identification method.

[0083] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0084] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of the invention.

[0085] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

Claims

1. A method for establishing a pore type identification model, characterized in that, include: Nuclear magnetic resonance imaging (NMR) and nuclear magnetic resonance relaxation spectra of core samples with a defined pore type, a single defined pore type, and saturated formation water, as well as NMR and NMR relaxation spectra of the core samples after centrifugation, are used to obtain a sample; the defined pore type includes intercrystalline pores, intercrystalline dissolution pores, salt mineral dissolution pores, and interlayer fractures. A sample set consists of multiple of the aforementioned samples; The selected classification model is trained using the sample set to obtain a classification model for pore type identification; The nuclear magnetic resonance imaging (NMR) and nuclear magnetic resonance relaxation spectra of the core sample after centrifugation are obtained through the following steps: the saturated core sample is centrifuged multiple times in order of increasing centrifugation speed, and the NMR and nuclear magnetic resonance relaxation spectra are obtained after each centrifugation process; specifically, the core sample is centrifuged at the currently set centrifugation speed and time, and the NMR and nuclear magnetic resonance relaxation spectra after the current centrifugation are obtained, until the consistency between the currently obtained NMR and the most recently obtained NMR meets a first set condition, and / or the consistency between the currently obtained NMR and the most recently obtained NMR meets a second set condition; The core sample was obtained by the following steps: after washing and drying the core sample with the specified pore type, formation water was saturated and prepared for 72 hours under a vacuum pressurized water saturation device at a pressure of 20 MPa. During the training of the classification model, it learns the distribution characteristics of the nuclear magnetic resonance imaging contained in each sample, the magnitude of the signal intensity value, the comparison between the nuclear magnetic resonance imaging after saturation and after centrifugation, the spectral curve morphology of the relaxation spectrum, the size of the envelope area formed by the spectral curve and the relaxation time axis, and the changes and rates of change of the bound water saturation and porosity components reflected in the relaxation spectrum.

2. The method as described in claim 1, characterized in that, The horizontal axis of the nuclear magnetic resonance relaxation spectrum represents the relaxation time, and the vertical axis represents the porosity component.

3. A method for identifying pore type, characterized in that, include: Nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core containing saturated formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core after centrifugation, are obtained to obtain a test sample. The test sample is input into the classification model established according to the pore type identification model establishment method described in claim 1 or 2, and the pore type of the core sample is determined based on the output results.

4. A device for establishing a pore type identification model, characterized in that, The apparatus is used to perform the pore type identification model establishment method according to claim 1, the apparatus comprising: The sample acquisition module is used to acquire nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of core samples with a set pore type, the set pore type and saturated formation water, and nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectra of the core samples after centrifugation, to obtain a sample. A sample set acquisition module is used to compose a sample set from multiple samples. The training module is used to train a selected classification model using the sample set to obtain a classification model for pore type identification.

5. A pore type identification device, characterized in that, include: The test sample acquisition module is used to acquire the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core with saturated formation water, and the nuclear magnetic resonance imaging and nuclear magnetic resonance relaxation spectrum of the test core after centrifugation, to obtain a test sample. A pore type determination module is used to input the test sample into a classification model established according to the method described in claim 1 or 2, and determine the pore type of the core sample based on the output results.

6. A computer program product with pore type identification function, comprising a computer program / instructions, wherein, When the computer program / instruction is executed by the processor, it implements the pore type identification model establishment method as described in claim 1 or 2, or the pore type identification method as described in claim 3.

Images