Reservoir remaining oil characterization method and device and computer equipment

Abstract

The invention relates to the field of a method for characterizing remaining oil after crude oil displacement, in particular to a method for characterizing remaining oil in a reservoir, which specifically comprises the following steps: segmenting an input displacement image to obtain a segmented image which comprises a solid phase, an oil phase and a displacing agent phase; on the basis of the segmented image, morphological parameters used for representing various types of remaining oil in the oil phase region in the segmented image are obtained; based on the morphological parameters, obtaining a classification standard for representing the remaining oil form in the segmented image; and based on a classification standard, obtaining the remaining oil form in the segmented image. According to the method, the remaining oil occurrence state and the dynamic change rule can be visually presented from the pore scale, and after the displacement image is segmented and morphological parameters are obtained, a classification standard capable of accurately obtaining the remaining oil form is formed, so that the formation mechanism of the remaining oil can be better defined, and effective guidance is provided for the development of a subsequent displacement agent.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of remaining oil characterization method after crude oil displacement, in particular, to a remaining oil characterization method in a reservoir, a device and a computer equipment. BACKGROUND

[0002] In the process of oilfield development, water injection is usually needed to displace crude oil, so that the crude oil is mined from the underground to the ground, and the process of water injection development is called the secondary oil recovery process. After water flooding development, 40% of the crude oil in the underground can be produced, and 60% of the crude oil still exists in the rock pores, which is called remaining oil. These remaining oils will be retained in the complex pore structure of the oilfield rock in various forms (such as drop, ring, film, etc.). In order to produce the remaining crude oil after water flooding, petroleum engineers inject polymers, surfactants and alkali, and binary or ternary systems composed of them to further produce these remaining oils. The process of injecting polymers, surfactants and alkali, and binary or ternary systems of chemicals to improve the recovery or tertiary oil recovery is usually called chemical flooding.

[0003] Although the injection of polymers or other chemicals increases the production of remaining oil on the basis of water flooding, it exacerbates the dispersibility of remaining oil in the pore structure, resulting in more complex remaining oil morphology and further exacerbating the development difficulty. Therefore, in the process of oil development, the distribution characteristics and distribution rules of the remaining oil after water flooding and chemical flooding are determined, various types of remaining oil are targeted to tap the potential, and the development plan and the design of enhanced oil recovery measures are reasonably deployed, so as to achieve the purpose of improving the production of crude oil; the formation mechanism and main control factors of various types of remaining oil are also explored, so as to help clarify the formation mechanism of remaining oil.

[0004] Since the remaining oil exists in the underground, the distribution state of the remaining oil cannot be clearly observed. In order to be able to observe the remaining oil intuitively, various technologies such as the combination of CT scanning and core displacement process have been developed. However, the current detection method is relatively fuzzy in classifying the remaining oil, which cannot determine the formation mechanism of the remaining oil, and is not conducive to designing a reasonable remaining oil tapping scheme. SUMMARY

[0005] In order to solve the above problems, the present application provides a remaining oil characterization method in a reservoir, a device and a computer equipment.

[0006] Embodiments of the present application are implemented as follows:

[0007] In a first aspect, the present application provides a remaining oil characterization method in a reservoir, comprising:

[0008] segmenting the input displacement image to obtain a segmented image, the segmented image comprising solid phase, oil phase and displacement agent phase;

[0009] Based on the segmented image, morphological parameters of each type of remaining oil in the oil phase region in the segmented image are obtained;

[0010] Based on the morphological parameters, a classification standard for representing the morphology of the remaining oil in the segmented image is obtained;

[0011] Based on the classification standard, the morphology of the remaining oil in the segmented image is obtained;

[0012] The displacement image is an image obtained by a camera device in a simulated oil displacement process. The simulated oil displacement process is a process of sequentially saturating a micro glass etching model with reservoir crude oil, reservoir formation water and chemical displacement agent under experimental temperature conditions. The micro glass etching model is a borosilicate glass substrate etched with a pore network model according to the actual rock physical parameters of the reservoir.

[0013] In a possible implementation, the classification standard for representing the morphology of the remaining oil in the segmented image based on the morphological parameters further includes:

[0014] Based on the morphological parameters, a classification parameter is calculated;

[0015] Based on the classification parameter, a classification standard is obtained;

[0016] The classification parameter includes a short-long axis ratio, a shape index, a convexity and an eccentricity.

[0017] In a possible implementation, the classification standard includes:

[0018] In a case where the short-long axis ratio is less than or equal to a first value, and the shape index is less than or equal to a second value, when the convexity is greater than or equal to a third value, and the eccentricity is less than or equal to a fourth value, the shape of the corresponding remaining oil is a first shape, otherwise, the shape of the corresponding remaining oil is a second shape;

[0019] In a case where the short-long axis ratio is less than or equal to a first value, and the shape index is greater than or equal to a fifth value, when the convexity is less than or equal to a sixth value, and the eccentricity is greater than or equal to a seventh value, the shape of the corresponding remaining oil is a third shape; when the convexity is less than or equal to the sixth value, and the eccentricity is less than or equal to an eighth value, the shape of the corresponding remaining oil is a fourth shape; when the convexity is greater than the sixth value, the shape of the corresponding remaining oil is a fifth shape.

[0020] In a possible implementation, the first value and the second value are both 1, the third value is 0.5, the fourth value is 0.2, the fifth value is 1.5, the sixth value is 0.3, the seventh value is 0.8, and the eighth value is 0.5.

[0021] In a possible implementation, the first shape is oil droplet shape, the second shape is cluster shape, the third shape is film shape, the fourth shape is blind end shape, and the fifth shape is column shape.

[0022] In a possible implementation, the method further includes the following step: based on the segmented image, obtaining a proportion of each type of remaining oil in the oil phase.

[0023] In a possible implementation, the method further includes the following steps of:

[0024] performing pixel-by-pixel classification on the displacement image to obtain core features in a target pixel field in the displacement image, the core features including RGB color features, gray gradient amplitude features, texture features, and spatial position features;

[0025] based on the core features, obtaining a high-dimensional feature vector, the high-dimensional feature vector being used to comprehensively represent semantic information of the target pixel;

[0026] based on the high-dimensional feature vector, segmenting the displacement image to obtain the segmented image.

[0027] In a second aspect, the present application provides a device for characterizing remaining oil in a reservoir, including:

[0028] an image segmentation module configured to segment an input displacement image to obtain a segmented image, the segmented image including a solid phase, an oil phase, and a displacement agent phase;

[0029] a parameter acquisition module configured to, based on the segmented image, acquire morphological parameters of various types of remaining oil in the oil phase region in the segmented image;

[0030] a standard acquisition module configured to, based on the morphological parameters, obtain classification standards for characterizing the morphology of the remaining oil in the segmented image;

[0031] a morphology characterization module configured to, based on the classification standards, acquire the morphology of the remaining oil in the segmented image.

[0032] In a third aspect, the present application provides a computer device, which includes a memory and a processor, the memory stores a computer program, and the processor invokes and executes the computer program to implement the steps of the method for characterizing remaining oil in a reservoir according to any one of the first aspect.

[0033] In a fourth aspect, the present application provides a computer storage medium, which has a computer program stored thereon, and the computer program, when executed by a processor, implements the steps of the remaining oil characterization method in any one of the first aspect.

[0034] In a fifth aspect, the present application provides a computer program product, which comprises a computer program, and the computer program, when executed by a processor, implements the steps of the remaining oil characterization method in any one of the first aspect.

[0035] The technical solutions provided by the present application can achieve at least the following beneficial effects:

[0036] By etching a glass model, a real reservoir pore structure can be simulated, and then different fluids are injected into the system to simulate different displacement processes, and a camera is used to capture the oil-water interface movement and the remaining oil formation process, so that the remaining oil occurrence state and its dynamic change rule can be intuitively presented at the pore scale, and by segmenting the displacement image and obtaining morphological parameters, a classification standard for accurately obtaining the remaining oil morphology can be formed, so that the formation mechanism of the remaining oil can be better determined, and effective guidance can be provided for the development of subsequent displacement agents. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0038] Figure 1 is a flowchart of a remaining oil characterization method in a reservoir according to an exemplary embodiment of the present application;

[0039] Figure 2 is a schematic diagram of a micro glass etching model according to an exemplary embodiment of the present application;

[0040] Figure 3 is a schematic diagram of a device for oil displacement experiments in a remaining oil characterization method in a reservoir according to an exemplary embodiment of the present application;

[0041] Figure 4 is a displacement image of the remaining oil distribution after water flooding and chemical agent flooding in a remaining oil characterization method in a reservoir according to an exemplary embodiment of the present application;

[0042] Figure 5 is a specific step flowchart of step 100 according to an exemplary embodiment of the present application;

[0043] Figure 6is a segmented image obtained by step 100 in a method for characterizing remaining oil in a reservoir according to an example embodiment of the present application;

[0044] Figure 7 is a schematic diagram for showing specific meanings of feature parameters in a method for characterizing remaining oil in a reservoir according to an example embodiment of the present application;

[0045] Figure 8 is a specific step flow chart of step 300 in a method for characterizing remaining oil in a reservoir according to an example embodiment of the present application;

[0046] Figure 9 is a classification standard obtained by step 300 in a method for characterizing remaining oil in a reservoir according to an example embodiment of the present application;

[0047] Figure 10 is a schematic diagram of microscopic remaining oil occurrence state obtained by step 400 in a method for characterizing remaining oil in a reservoir according to an example embodiment of the present application;

[0048] Figure 11 is a column chart for showing proportions of various types of remaining oil after displacement in step 500 in a method for characterizing remaining oil in a reservoir according to an example embodiment of the present application;

[0049] Figure 12 is a structural schematic diagram of a computer device according to an example embodiment of the present application;

[0050] Figure 13 is a structural schematic diagram of a device for characterizing remaining oil in a reservoir according to an example embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the objects, implementation manners and advantages of the present application clearer, the following will clearly and completely describe the example implementation manners of the present application with reference to the accompanying drawings in the example embodiments of the present application. Obviously, the described example embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not intended to limit the present application.

[0052] It should be noted that the brief description of the terms in the present application is only for the convenience of understanding the following described embodiments, and is not intended to limit the embodiments of the present application. Unless otherwise specified, these terms should be understood according to their ordinary and general meanings.

[0053] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0054] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0055] Next, the technical solutions of this application will be described in detail through embodiments and with reference to the accompanying drawings. The embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this application.

[0056] Firstly, such as Figure 1 As shown, this application provides a method for characterizing residual oil in a reservoir, which includes the following steps 100-400:

[0057] Step 100: Segment the input displacement image to obtain the segmented image. The segmented image includes the solid phase, oil phase, and displacement agent phase. The displacement image is an image acquired in real time by a camera during the simulated oil displacement process. The simulated oil displacement process is a process of sequentially using reservoir crude oil, reservoir formation water, and chemical displacement agent to saturate a microscopic glass etching model under experimental temperature conditions. The microscopic glass etching model is a borosilicate glass substrate with a pore network model etched based on the rock physical properties parameters of the actual reservoir.

[0058] Specifically, when creating a microscopic glass etching model, it is necessary to first design a pore network model similar to the actual rock pore structure of the reservoir using CAD software, based on the actual rock physical properties parameters of the reservoir, such as porosity, permeability, and pore structure characteristics. Then, laser etching technology is used to precisely etch the aforementioned pore grid model onto a borosilicate glass substrate. The porosity, permeability, pore radius, and other parameters of this glass etching model are consistent with those of the actual reservoir rock. Through the above steps, the required microscopic glass etching model can be obtained for subsequent operations.

[0059] As an example, Figure 2 Some microscopic glass etching models are shown, among which, Figure 2 (a) is a heterogeneous model using a diagonal injection-production mode, with permeabilities of 200 mD, 400 mD and 80 mD in the upper, middle and lower parts, respectively; Figure 2(b) is a heterogeneous model using a diagonal injection-production mode, with permeabilities of 10 mD, 30 mD and 50 mD in the upper, middle and lower parts, respectively; Figure 2 (c) is a homogeneous model using a diagonal injection-extraction mode with a permeability of 500 mD; Figure 2 (d) is a homogeneous model employing an injection-production mode with injection from one side and extraction from the other, with a permeability of 500 mD. This application selects... Figure 2 The homogeneous microscopic glass etching model shown in (d) serves as an example for subsequent steps.

[0060] It is understood that the microscopic glass etching model can be replaced by other transparent samples with pore structures consistent with the physical properties of real reservoir rocks, such as cast thin sections, microfluidic chips, natural core slices, etc., and this application does not make specific limitations on this.

[0061] In the process of oil displacement experiments using a microscopic glass etching model, the main devices involved in the oil displacement process include... Figure 3 As shown, the system includes a micro-pump, pressure gauge, valves, a thermostat, an optical microscopy system, and an image acquisition device. The pressure gauge, valves, and optical microscopy system are all integrated within the thermostat. The micro-pump, pressure gauge, valves, and the pores of the microscopic glass etching model are connected via conduits. The image acquisition device is electrically connected to the optical microscope. The image acquisition device includes a camera and an image display and processing device electrically connected to the camera. The camera can be a low-resolution camera, or it can be replaced by advanced imaging technologies such as CT (computed tomography) or laser confocal microscopy.

[0062] The experimental materials required for the oil displacement experiment include reservoir formation water, polyacrylamide, and crude oil. The crude oil sample used in this application comes from an oilfield and contains 62.5% saturated hydrocarbons, 21.3% aromatic hydrocarbons, 14.6% gums, and 1.6% asphaltenes. The crude oil has a viscosity of 8 mPa·s and a density of 0.85 g / cm³ at 70°C. 3 .

[0063] It is understood that reservoir formation water and polyacrylamide are the displacement agents used in this application, wherein the ionic composition of the reservoir formation water includes 3130 mg / L of Na. + 64.9 mg / L of Ca 2+ 27.8 mg / L of Mg 2+ 4047.3 mg / L Cl - 891.8 mg / L of HCO3 - SO4 696.0 mg / L 2- and 71.4 mg / L CO3 2-The total mineralization of the reservoir formation water is 8930 mg / L, and the density is 1.07 g / cm 3 The viscosity at 25℃ is 0.89 mPa·s. The molecular weight of the polyacrylamide powder used is 1800 x 10 4 Da, the polyacrylamide is a polymer, and the preparation process of the polyacrylamide solution is as follows:

[0064] ①Use a beaker to weigh 500 mL of distilled water, and then weigh 2.77 g of polyacrylamide powder. Use a mechanical stirrer to uniformly dissolve the polyacrylamide powder in the distilled water at a speed of 500 r / min. After complete dissolution, a polyacrylamide stock solution is obtained;

[0065] ②Use a beaker to weigh 350 mL of reservoir formation water, and then weigh 150 mL of the polyacrylamide stock solution. Slowly pour the weighed stock solution into the weighed reservoir formation water at a speed of 350 r / min to obtain a polyacrylamide solution with a concentration of 1500 mg / L. Under the condition of a constant temperature water bath at 70℃, the viscosity of the polymer solution with a concentration of 1500 mg / L is measured to be 30.2 mPa·s using a Brookfield viscometer.

[0066] The specific oil displacement experiment operation process is as follows: (a) Place the micro peeling etching model on the glass slide of the optical microscope. At the experimental temperature (70℃), inject the reservoir formation water into the micro glass etching model through the micro pump at a constant low speed (0.1-1 mL / min). Monitor the pressure change in real time through the pressure gauge. When the outlet end of the micro glass etching model continuously produces a stable flow of formation water, the pore space in the micro glass etching model reaches a completely saturated state;

[0067] (b) Maintain the above temperature, and inject the prepared reservoir crude oil into the micro glass etching model through the micro pump at a constant flow rate (0.1-1 mL / min). Stop the injection when the outlet end of the micro glass etching model continuously produces pure oil phase and the oil phase fills the entire model;

[0068] (c) Under the condition of maintaining the temperature at 70℃, inject the formation water at a constant speed (0.1-1 mL / min) for displacement. Use the microscopic imaging system to monitor and record the morphological changes and spatial distribution characteristics of the remaining oil during the displacement process in real time. When it is observed that the outlet end of the micro glass etching model continuously produces formation water without oil phase, i.e., the water content reaches 100%, stop the water displacement process;

[0069] (d) using the prepared polyacrylamide solution to displace the residual oil in the micro glass etching model at a constant speed (0.1-1 mL / min), and using a microscopic imaging system to record the morphology and distribution of the residual oil during the displacement process in real time, and stopping the chemical agent displacement process when it is observed that the outlet end of the micro glass etching model continuously produces polyacrylamide solution without oil phase.

[0070] The speed of the liquid in the above steps is 0.5 mL / min, and the imaging equipment records the displacement images of each process.

[0071] As shown in the above steps, the displacement images of the residual oil distribution after water displacement (e) and the displacement images of the residual oil distribution after chemical agent displacement (f) can be obtained. Figure 4 Figure 4 (e)) and the displacement images of the residual oil distribution after chemical agent displacement (f) can be obtained. Figure 4 These displacement images have poor contrast, blurred boundaries, and are difficult to distinguish between glass, pores, water phase and oil phase with the naked eye, in other words, the displacement images recorded by the imaging equipment record the original state of the oil-water distribution in the pore structure of the micro glass etching model.

[0072] After the displacement experiment is completed and the displacement images are obtained, step 100 of the present application segments the input displacement images based on the random forest algorithm to obtain segmented images, as shown in the following figure. Figure 5

[0073] Step 110, classifying the displacement images pixel by pixel to obtain the core features in the target pixel field in the displacement images, the core features including RGB color features, gray gradient amplitude features, texture features and spatial position features.

[0074] Step 120, based on the core features, obtaining a high-dimensional feature vector, the high-dimensional feature vector being used to comprehensively represent the semantic information of the target pixel.

[0075] ​​In the above steps, first, the dynamic neighborhood image data of each target pixel in the displacement image is obtained by taking the target pixel as the core, and the window size of the dynamic neighborhood image data can be dynamically calculated and determined according to the spatial resolution of the input displacement image. Second, the quantized intensity values of each target pixel in the R, G and B color channels can be directly obtained based on the original spectral information of the target pixel, as the spectral features (i.e. RGB color features) representing the basic attributes. Based on the gray scale distribution in the neighborhood range of the target pixel, the local gray scale change rate can be measured by convolution operation of the edge detection operator, and then the gradient amplitude feature representing the phase boundary contour and structural boundary can be obtained, as the gray scale gradient amplitude in the present application. Based on the spatial relationship between the pixels in the neighborhood, the texture features of the roughness, uniformity and randomness of all pixels in the neighborhood range can be obtained by calculating the gray level co-occurrence matrix and deriving its second-order statistics (such as contrast, energy, entropy), thereby providing the global position prior for the model based on the absolute two-dimensional coordinates (x, y) of each target pixel in the displacement image.

[0076] Finally, all the core features described above are fused and spliced into a unified high-dimensional numerical feature vector after normalization, which is the final input of the random forest classifier, and comprehensively encodes the spectral, morphological and spatial attributes of the target pixel, facilitating subsequent image region recognition, classification and segmentation steps.

[0077] Step 130, based on the high-dimensional feature vector, the displacement image is segmented to obtain a segmented image. In this step, after running the random forest algorithm, the displacement image can be segmented into "solid phase", "displacing agent phase" and "oil phase" according to the precise pixel level based on the high-dimensional feature vector, thereby obtaining the segmented image including the solid phase, oil phase and displacing agent phase.

[0078] It can be understood that the above segmentation process is realized based on the decision and integration mechanism of random forest, and the corresponding algorithm model needs to be trained before the above steps are executed. In the training stage of the algorithm model, in order to establish a reliable identification model, it is usually necessary to mark the solid phase (representing the solid phase of rock), the displacement agent phase (representing the displacement agent phase of oil displacement agent) and the oil phase (representing the oil phase of crude oil) in the input displacement image through manual marking. Through this data marking method, reliable training samples can be provided for subsequent random forest algorithm image segmentation. Then, the model constructs an independent training subset for each decision tree through sampling. When each node of the decision tree is split, the optimal partition is performed by randomly selecting part of the features, and finally a decision tree set with high generalization ability and low overfitting is obtained. Then, in the prediction stage of the input target displacement image, based on the input target displacement image, the high-dimensional feature vector of the target displacement image is obtained, and each decision tree is independently forward propagated and judged to obtain the class probability output of each tree for the pixel. Finally, by aggregating (such as majority voting or probability averaging) the output results of all decision trees, the target displacement image can be accurately segmented, and the segmented image includes the solid phase, the displacement agent phase and the oil phase.

[0079] The segmented image is as shown in Figure 6 Figure 6 (g) is Figure 4 (e) the corresponding segmented image, Figure 6 (h) is Figure 4 (f) the corresponding segmented image. It can be seen that Figure 6 After water flooding, most of the remaining oil exists in the form of continuous phase, the sweep efficiency is low, there are obvious un-swept areas, and there is still remaining oil retention in the swept area. After chemical agent flooding, the distribution of remaining oil is dispersed, the occurrence amount is significantly reduced, and the swept range is expanded. Furthermore, during the chemical agent flooding process, the chemical agent also produces an effective pulling effect on the remaining oil due to its viscoelasticity, which further improves the microscopic oil washing efficiency.

[0080] After completing the segmentation of the displacement image, how to accurately classify the complex morphology of the remaining oil is another key problem. The present application is carried out through the following steps.

[0081] Step 200, based on the segmented image, obtaining the morphological parameters of each type of remaining oil in the oil phase region of the segmented image. In this step, the morphological parameters of the oil phase in the segmented image obtained in step 100 can be extracted through python code, and the combination of morphological parameters can be used to accurately describe the shape.

[0082] Specifically, as shown in Figure 7 the morphological parameters that can be extracted through this step include area (A pore ), perimeter (P​pore ), equivalent diameter (D eq ), convex hull area (A convexhull ), pore long axis length (L pore ), and pore short axis length (W pore ).

[0083] wherein the pore area (A pore ) refers to the area of the target region, and is calculated by multiplying the number of pixels in the target region by the pixel area. The pore perimeter (P pore ) refers to the perimeter of the target region, and is approximately obtained by tracing the boundary pixel centers based on 4-connectivity. The equivalent diameter (D eq ) refers to the diameter of a circle having the same area as the target region. The convex hull area (A convexhull ) refers to the area of the convex hull, which is the smallest convex polygon that can enclose the target region. The pore long axis length (L pore ) refers to the long axis length of an ellipse having the same normalized second central moment as the target region. The pore short axis length (W pore ) refers to the short axis length of an ellipse having the same normalized second central moment as the target region.

[0084] At step 300, based on the morphological parameters, a classification standard for the remaining oil morphology in the segmented image is obtained. Specifically, as shown in FIG. 3, this step can include the following steps: Figure 8

[0085] At step 310, based on the morphological parameters, classification parameters are calculated, including the short-long axis ratio, the shape index, the convexity, and the eccentricity. In this step, the present application selects the short-long axis ratio (denoted as AR), the shape index (denoted as SF), the convexity (denoted as C onvexity ), and the eccentricity (denoted as E ccentricity ) to quantitatively represent the distribution morphology of the remaining oil in the pore throat structure, and determines the classification standard for the remaining oil morphology in the segmented image.

[0086] wherein the short-long axis ratio is calculated as follows: AR = W pore / L pore , wherein L pore is the long axis half-length, and W pore is the short axis half-length. The short-long axis ratio refers to the ratio of the short axis to the long axis when the remaining oil shape is fitted as an ellipse. When the value of the short-long axis ratio is 1, the shape is circular. The closer the value of the short-long axis ratio is to 0, the more elongated the shape is. The shape index is calculated as follows: SF = P pore 2 / 4πA pore , wherein P pore is the perimeter; and A pore ​Area. The shape index can be used to measure the complexity of the shape of the remaining oil boundary. When SF≈1, the shape is closer to a circle; when SF≥1.5, the shape becomes complex and diverse. The convexity is calculated as follows: C onvexity = A pore / A convexhull , where A pore is the area, and A convexhull is the convex hull area. The convexity can be used to measure the "roughness" of the shape of the remaining oil. The closer the value is to 0, the rougher the surface. The formula for calculating the eccentricity is: , where L pore is the half length of the major axis, and W pore is the half length of the minor axis. When the value of the eccentricity is 0, the ellipse becomes a circle. The closer the value of the eccentricity is to 1, the closer the ellipse is to a parabola.

[0087] Step 320, based on the classification parameters, obtaining the classification standard. Specifically, as shown in Figure 9 , the classification standard determined by the present application is as follows:

[0088] In the case where the short-long axis ratio (AR) is less than or equal to a first value, and the shape index (SF) is less than or equal to a second value, when the convexity (C onvexity ) is greater than or equal to a third value, and the eccentricity (E ccentricity ) is less than or equal to a fourth value, the shape of the corresponding remaining oil is a first shape, otherwise the shape of the corresponding remaining oil is a second shape; in the case where the short-long axis ratio (AR) is less than or equal to a first value, and the shape index (SF) is greater than or equal to a fifth value, when the convexity (C onvexity ) is less than or equal to a sixth value, and the eccentricity (E ccentricity ) is greater than or equal to a seventh value, the shape of the corresponding remaining oil is a third shape, when the convexity (C onvexity ) is less than or equal to a sixth value, and the eccentricity (E ccentricity ) is less than or equal to an eighth value, the shape of the corresponding remaining oil is a fourth shape; when the convexity (C onvexity ) is greater than the sixth value, the shape of the corresponding remaining oil is a fifth shape.

[0089] In the present application, the first value and the second value are both 1, the third value is 0.5, the fourth value is 0.2, the fifth value is 1.5, the sixth value is 0.3, the seventh value is 0.8, and the eighth value is 0.5.

[0090] The above classification parameters help to establish a simple and efficient classification standard for the remaining oil in the reservoir, which in turn helps to more accurately classify the remaining oil, providing important data support for studying the distribution pattern, occurrence state and displacement efficiency of the remaining oil. It also has important value for understanding the micro-displacement mechanism and optimizing the production scheme.

[0091] Step 400: Based on the classification criteria, obtain the morphology of residual oil in the segmented image. Specifically, the first shape is oil droplet-shaped, the second shape is cluster-shaped, the third shape is film-shaped, the fourth shape is blind-end, and the fifth shape is columnar. That is, after obtaining the classification parameters in the displacement image to be classified, the microscopic residual oil can be classified according to the classification criteria obtained in step 300. The microscopic residual oil can be mainly divided into the following 5 types: cluster-shaped residual oil, columnar residual oil, film-shaped residual oil, oil droplet-shaped residual oil, and pore blind-end residual oil. The above 5 residual oil occurrence states are as follows: Figure 10 As shown, where, Figure 10 (m) represents clustered residual oil. Figure 10 (n) represents the columnar residual oil. Figure 10 (o) represents residual oil in droplet form. Figure 10 (p) represents residual oil in film form. Figure 10 (q) represents the remaining oil at the pore blind end.

[0092] In some other specific embodiments, the following steps are also included: based on the segmented image, the proportion of each type of residual oil in the oil phase is obtained to quantitatively characterize the distribution pattern of residual oil after water flooding or chemical flooding.

[0093] In this step, the total number of pixels A in the oil phase region and the number of pixels B in the regions containing various types of residual oil in the segmented image are obtained. Then, the number of pixels B in the regions containing various types of residual oil is divided by the total number of pixels A to calculate the proportion of each type of residual oil. As a specific example, this application calculates... Figure 6 The proportions of various residual oil types in (g) and 6(h), such as Figure 11As shown, the cluster-shaped remaining oil accounts for the highest proportion (41.83%) after water flooding, followed by the oil drop-shaped remaining oil (32.67%), the columnar-shaped remaining oil (17.94%), the film-shaped remaining oil (5.26%), and the pore blind end-shaped remaining oil (2.30%) with a relatively low proportion. After chemical agent flooding, the proportion of the cluster-shaped remaining oil significantly decreases to 28.45%, the proportion of the oil drop-shaped remaining oil is 29.12%, the proportion of the film-shaped remaining oil is 12.75%, the proportion of the pore blind end-shaped remaining oil increases to 4.05%, and the proportion of the columnar-shaped remaining oil slightly decreases to 15.63%. Compared with water flooding, the cluster-shaped remaining oil and the oil drop-shaped remaining oil significantly decrease after chemical agent flooding, but the film-shaped and the pore blind end-shaped remaining oil significantly increase. This is because the high viscosity and viscoelasticity of the chemical agent solution can not only more effectively overcome the capillary force to displace the bound cluster-shaped remaining oil, but also significantly improve the sweep efficiency by improving the mobility ratio, so that the cluster-shaped remaining oil in the previously un-swept area is displaced. At the same time, the "dragging" effect of the chemical agent promotes the aggregation and migration of dispersed oil droplets, further reducing the oil drop-shaped remaining oil. However, due to the limited effect of the chemical agent on changing the wettability of the rock surface, it is difficult to strip the film-shaped remaining oil adsorbed on the rock wall, resulting in an increase in the film-shaped remaining oil. With the large-scale production of other forms of remaining oil by chemical flooding, the originally surrounded pore blind end area is exposed. Although the viscoelasticity of the chemical agent can displace part of the oil in the blind end, it cannot be completely produced, and the oil in the small pores is difficult to be swept, resulting in an increase in the pore blind end-shaped remaining oil. Since there is still a large amount of cluster-shaped, columnar-shaped and oil drop-shaped remaining oil after chemical agent flooding, methods such as changing the wettability of the rock and reducing the interfacial tension can be used to further tap these remaining oils. The methods for tapping these three types of remaining oil include binary complex flooding (polymer + surfactant), ternary complex flooding (polymer + surfactant + alkali), gas flooding (CO2), and foam flooding, etc. The specific effect of which oil displacement agent is good needs to be further judged by the method for obtaining the proportion of each type of remaining oil in the present application. It can be seen that the above method of the present application can effectively guide the development of remaining oil in the oil field and further improve the recovery of crude oil.

[0094] The above remaining oil characterization method in the reservoir is innovative in that the random forest algorithm is used to realize pixel-level segmentation of the displacement image according to the particularity of the microcosmic remaining oil image of petroleum, the threshold segmentation method is improved in terms of the identification of the gray gradient area, the segmentation accuracy of the oil-water interface is significantly improved, the defect of boundary fracture caused by the noise interference of the edge detection algorithm is overcome, the continuity of the segmentation result is ensured, the over-segmentation phenomenon caused by the excessive sensitivity of the local gradient of the watershed algorithm is avoided, and compared with the deep learning method, the training sample demand is greatly reduced while the segmentation accuracy is ensured, so that the method provides a reliable technical means for the accurate identification and quantitative analysis of the remaining oil in the complex pore structure.

[0095] In addition, the application first proposes the specific parameter combination of shape factor (SF), short-long axis ratio (AR), convexity (C onvexity ) and eccentricity (E ccentricity ) as the classification standard, establishes a more accurate remaining oil morphology identification standard through multi-parameter collaborative analysis, simplifies the classification of micro remaining oil types, has better universality and accuracy, and is convenient for better understanding the formation mechanism of remaining oil, provides effective guidance for the development of subsequent displacement agents, and has important significance for improving the recovery of crude oil.

[0096] In a second aspect, in an example embodiment, the above-mentioned remaining oil characterization method in a reservoir can be applied to Figure 12 a computer device as shown in the figure, which includes at least a processor, a memory, a communication bus, a remaining oil characterization system in a reservoir, and a communication interface. The processor can be a general central processing unit (CPU), a network processor (NP), a microprocessor, or one or more integrated circuits for implementing the scheme of the application. Alternatively, the processor can include one or more CPUs. The computer device can include multiple processors. Each of the processors can be a single-CPU or a multi-CPU.

[0097] The memory can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, or a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or any other medium capable of carrying or storing desired program codes in the form of instructions or data structures and accessible by a computer, but is not limited to this. Alternatively, the memory can exist independently and be connected to the processor through the communication bus; the memory can also be integrated with the processor.

[0098] The communication bus is used to transmit information between components, such as between the processor and the memory. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 13 only one communication bus is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0099] The communication interface is used for the computer device to communicate with other devices or communication networks. The communication interface includes a wired communication interface or a wireless communication interface.

[0100] In some embodiments, the memory is configured to store a computer program for implementing the scheme of the present application, and the processor can execute the computer program stored in the memory. For example, the computer device can invoke and execute the computer program stored in the memory by the processor to implement the steps of the method for characterizing remaining oil in a reservoir provided by the embodiments of the present application.

[0101] In a third aspect, based on the method for characterizing remaining oil in a reservoir described above, the same technical concept is adopted, and the embodiments of the present application further provide a device for characterizing remaining oil in a reservoir, which is used to implement the method for characterizing remaining oil in a reservoir. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the method embodiments. Specifically, in one exemplary embodiment, as shown in Figure 13 a device for characterizing remaining oil in a reservoir is provided, which includes:

[0102] an image segmentation module configured to segment an input displacement image to obtain a segmented image, the segmented image including a solid phase, an oil phase, and a displacement agent phase;

[0103] a parameter acquisition module configured to acquire morphological parameters for characterizing various types of remaining oil in the oil phase region of the segmented image based on the segmented image;

[0104] a standard acquisition module configured to acquire classification standards for characterizing the morphology of the remaining oil in the segmented image based on the morphological parameters;

[0105] a morphology characterization module configured to acquire the morphology of the remaining oil in the segmented image based on the classification standards.

[0106] For specific limitations of the device for characterizing remaining oil in a reservoir, refer to the limitations of the method for characterizing remaining oil in a reservoir described above, which will not be repeated here. Each module in the device for characterizing remaining oil in a reservoir can be realized by software, hardware, and a combination thereof, in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be invoked and executed by the processor to perform the operations corresponding to each module.

[0107] The fourth aspect of the embodiments of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is invoked and run by the processor, some or all steps in the above method embodiments are implemented.

[0108] As an example, the computer readable storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.

[0109] It should be understood that the technical solutions in the embodiments of the present application can be realized by means of software and a necessary general hardware platform. Therefore, the technical solutions in the embodiments of the present application can be embodied in the form of a software product, and the software product can be stored in a computer readable storage medium.

[0110] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present disclosure.

[0111] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of the present application. Therefore, the scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for characterizing residual oil in a reservoir, characterized in that, include: The input displacement image is segmented to obtain a segmented image, which includes a solid phase, an oil phase, and a displacement agent phase. Based on the segmented image, morphological parameters for representing various types of remaining oil in the oil phase region of the segmented image are obtained; Based on the morphological parameters, a classification standard for characterizing the morphology of residual oil in the segmented image is obtained; Based on the classification criteria, the remaining oil morphology in the segmented image is obtained; The displacement image is an image acquired in real time by a camera during the simulated oil displacement process. The simulated oil displacement process is a process of sequentially saturating a microscopic glass etching model with reservoir crude oil, reservoir formation water, and chemical displacement agent under experimental temperature conditions. The microscopic glass etching model is a borosilicate glass substrate with a pore network model etched based on the rock physical properties parameters of the actual reservoir.

2. The method for characterizing residual oil in a reservoir as described in claim 1, characterized in that, The step of obtaining the classification criteria for the residual oil morphology in the segmented image based on the morphological parameters further includes: Based on the morphological parameters, calculate the classification parameters; Based on the classification parameters, the classification criteria are obtained; The classification parameters include the minor axis ratio, shape index, convexity, and eccentricity.

3. The method for characterizing residual oil in a reservoir as described in claim 2, characterized in that, The classification criteria include: When the ratio of the short axis to the long axis is less than or equal to the first value and the shape index is less than or equal to the second value, when the convexity is greater than or equal to the third value and the eccentricity is less than or equal to the fourth value, the shape of the remaining oil is the first shape; otherwise, the shape of the remaining oil is the second shape. When the ratio of the short to long axis is less than or equal to the first value and the shape index is greater than or equal to the fifth value, when the convexity is less than or equal to the sixth value and the eccentricity is greater than or equal to the seventh value, the shape of the remaining oil is the third shape; when the convexity is less than or equal to the sixth value and the eccentricity is less than or equal to the eighth value, the shape of the remaining oil is the fourth shape; when the convexity is greater than the sixth value, the shape of the remaining oil is the fifth shape.

4. The method for characterizing residual oil in a reservoir as described in claim 3, characterized in that, The first and second values ​​are both 1, the third value is 0.5, the fourth value is 0.2, the fifth value is 1.5, the sixth value is 0.3, the seventh value is 0.8, and the eighth value is 0.

5.

5. The method for characterizing residual oil in a reservoir as described in claim 3, characterized in that, The first shape is droplet-shaped, the second shape is cluster-shaped, the third shape is membrane-shaped, the fourth shape is blind-end, and the fifth shape is columnar.

6. The method for characterizing residual oil in a reservoir as described in any one of claims 1-5, characterized in that, It also includes the following steps: Based on the segmented image, the percentage of remaining oil of each type in the oil phase is obtained.

7. The method for characterizing residual oil in a reservoir as described in claim 1, characterized in that, The segmentation of the input displacement image to obtain the segmented image further includes: The displacement image is classified pixel by pixel to obtain the core features within the target pixel neighborhood of the displacement image. The core features include RGB color features, grayscale gradient magnitude features, texture features, and spatial location features. Based on the core features, a high-dimensional feature vector is obtained, which is used to comprehensively characterize the semantic information of the target pixel; Based on the high-dimensional feature vector, the displacement image is segmented to obtain the segmented image.

8. A device for characterizing residual oil in a reservoir, characterized in that, include: An image segmentation module is used to segment an input displacement image to obtain a segmented image, wherein the segmented image includes a solid phase, an oil phase, and a displacement agent phase; The parameter acquisition module is used to acquire morphological parameters, based on the segmented image, to represent various types of remaining oil in the oil phase region of the segmented image. The standard acquisition module is used to obtain classification criteria for characterizing the morphology of residual oil in the segmented image based on the morphological parameters. The morphological characterization module is used to obtain the morphology of the remaining oil in the segmented image based on the classification criteria.

9. A computer device, characterized in that, The method includes a memory and a processor, the memory storing a computer program, characterized in that the processor invokes and executes the computer program from the memory to implement the steps of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images