Method and device for determining migration state of proppant

Abstract

The invention provides a method and device for determining the migration state of a proppant, and the method comprises the steps: obtaining a migration image of the proppant in a target crack; carrying out gray scale transformation on the migration image to obtain a gray scale image; carrying out smoothing processing on the grayscale image to obtain a smoothed image; carrying out edge detection on the smoothed image to obtain a detected image; and performing threshold segmentation on the detected image, and separating the proppant and the tracer particles in the detected image to determine the migration state of the proppant in the target crack. By means of the scheme, efficient separation of the proppant and the tracer particles in the image is achieved, and therefore the migration state of the proppant in the crack can be accurately determined.

Description

Technical Field

[0001] This application belongs to the technical field of petroleum engineering, and particularly relates to a method and device for determining the migration state of proppants. Background Art

[0002] In the field of petroleum engineering, in order to determine the movement state of fluids in fractures, fluid tracers are generally used for monitoring. However, since both proppants and tracers exist in the fractures simultaneously, it is very difficult to accurately obtain the distribution and movement trajectories of proppants.

[0003] Based on this, with the development of computer vision and image processing technologies, it is possible to consider combining artificial intelligence, image processing, etc. to determine the movement state of proppants, thereby improving the analysis accuracy of solid-liquid (proppant and sand-carrying fluid) two-phase flow. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for determining the migration state of proppants, which can accurately determine the migration state of proppants.

[0005] The method and device for determining the migration state of proppants provided by this application are implemented as follows:

[0006] A method for determining the migration state of proppants, the method includes:

[0007] Obtain the migration image of proppants in the target fracture;

[0008] Perform gray-scale transformation on the migration image to obtain a gray-scale image;

[0009] Perform smoothing processing on the gray-scale image to obtain a smoothed image;

[0010] Perform edge detection on the smoothed image to obtain a detected image;

[0011] Perform threshold segmentation on the detected image to separate the proppants and tracer particles in the detected image, so as to determine the migration state of proppants in the target fracture.

[0012] In one embodiment, obtaining the migration image of proppants in the target fracture includes:

[0013] Real-time and continuously obtain the image data of the two-phase flow in the target fracture at multiple time points through an image acquisition device, so as to obtain multiple state images during the flow process of proppants;

[0014] Use the multiple state images as the migration image of the proppants;

[0015] Among them, the resolution and sensitivity of the image acquisition device meet the requirements for capturing the microscopic changes of proppants and tracer particles.

[0016] In one embodiment, performing gray-scale transformation on the migration image to obtain a gray-scale image, including:

[0017] Adjusting the brightness of the migration image to obtain the adjusted gray-scale value of each pixel point in the migration image, where the adjusted gray-scale value is expressed as:

[0018] G1 = G0 * G a +b

[0019] Wherein, G1 represents the adjusted gray-scale value, G0 represents the original gray-scale value, G a represents the brightness gain, and b represents the brightness offset;

[0020] For each pixel point in the migration image after brightness adjustment, performing gray-scale linear transformation, where the formula for gray-scale linear transformation is:

[0021] g(x, y) = k[f(x, y) - a] + c

[0022] Wherein, f(x, y) represents the gray-scale value after brightness adjustment, f(x, y) ∈ [a, b], g(x, y) represents the gray-scale value after gray-scale linear transformation, g(x, y) ∈ [c, d], where k represents the gain factor of linear transformation, (x, y) represents the coordinates in the original image, a represents the minimum value in the gray-scale value range of the migration image after brightness adjustment, b represents the maximum value in the gray-scale value range of the migration image after brightness adjustment, c represents the minimum value in the gray-scale value range of the image after gray-scale linear transformation, and d represents the maximum value in the gray-scale value range of the image after gray-scale linear transformation.

[0023] In one embodiment, performing smoothing processing on the gray-scale image to obtain a smoothed image, including:

[0024] Calculating the gray-scale value of the pixels in the neighborhood of the gray-scale image through a 3*3 mean filter to replace the original pixel value to obtain an intermediate image;

[0025] Calculating the median of the pixels in the neighborhood of the intermediate image through a median filter as the new pixel value to obtain a smoothed image.

[0026] In one embodiment, performing edge detection on the smoothed image to obtain a detected image, including:

[0027] Calculating the gradient magnitude and gradient direction of each pixel point in the smoothed image according to the following formula:

[0028]

[0029] Among them, I represents the image after smoothing processing, and G x represents the gradient of the image in the horizontal direction, and G y represents the gradient of the image in the vertical direction;

[0030] Compare the gradient magnitude of each pixel with the pixel values on both sides in its gradient direction to determine the local maximum in the gradient direction;

[0031] Suppress the pixel points outside the local maximum to obtain the suppressed gradient map;

[0032] Obtain a preset first threshold and a second threshold, where the first threshold is greater than the second threshold;

[0033] Take the pixel points in the suppressed gradient map with gradient magnitudes greater than the first threshold as strong edges, take the pixel points in the suppressed gradient map with gradient magnitudes less than or equal to the first threshold and greater than or equal to the second threshold as weak edges, and remove the pixel points in the suppressed gradient map with gradient magnitudes less than the second threshold to obtain the detected image.

[0034] In one embodiment, perform threshold segmentation on the detected image to separate the proppant and tracer particles in the detected image, including:

[0035] Perform histogram statistics on the detected image to determine the number of pixels at each gray level;

[0036] According to the statistical results, determine the pixel probability distribution at each gray level to form a normalized probability histogram;

[0037] Within each gray level, traverse each possible threshold, and calculate the pixel probability and gray mean on both sides of each threshold;

[0038] According to the pixel probability and gray mean on both sides of each threshold, calculate the between-class variance of each threshold;

[0039] Take the threshold corresponding to the maximum between-class variance as the target threshold;

[0040] Perform binary processing on the detected image through the target threshold to divide the pixel points in the detected image into background and foreground, and realize the separation of the proppant and tracer particles.

[0041] In one embodiment, according to the pixel probability and gray mean on both sides of each threshold, calculate the between-class variance of each threshold, including:

[0042] Calculate the between-class variance of the current threshold according to the following formula:

[0043]

[0044] Among them, represents the between-class variance of the current threshold t, ω1(t) and ω2(t) represent the pixel probabilities on both sides of the current threshold t, and μ1(t) and μ2(t) respectively represent the gray-scale means on both sides of the current threshold t.

[0045] A device for determining the migration state of proppants, comprising:

[0046] An acquisition module, configured to acquire a migration image of proppants in a target fracture;

[0047] A gray-scale transformation module, configured to perform gray-scale transformation on the migration image to obtain a gray-scale image;

[0048] A smoothing processing module, configured to perform smoothing processing on the gray-scale image to obtain a smoothed image;

[0049] An edge detection module, configured to perform edge detection on the smoothed image to obtain a detected image;

[0050] A segmentation module, configured to perform threshold segmentation on the detected image to separate proppants and tracer particles in the detected image, so as to determine the migration state of proppants in the target fracture.

[0051] An electronic device, comprising a processor and a memory for storing processor-executable instructions, and when the processor executes the instructions, the steps of the above method are implemented.

[0052] A computer-readable storage medium, on which a computer program / instructions are stored, and when the computer program / instructions are executed by a processor, the steps of the above method are implemented.

[0053] The method for determining the migration state of proppants provided by this application performs gray-scale transformation, smoothing processing, edge detection, and threshold segmentation on the migration image of proppants in a target fracture, so as to separate proppants and tracer particles in the image, and determine the migration state of proppants in the target fracture. Through the above solution, efficient separation of proppants and tracer particles in the image is achieved, so that the migration state of proppants in the fracture can be accurately determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0055] Figure 1 It is a flowchart of a method for an embodiment of a method for determining the transport state of proppants provided by this application;

[0056] Figure 2 It is a flowchart of an implementation method for edge detection provided by this application;

[0057] Figure 3 It is a flowchart of an implementation method for separating proppants and tracer particles in a detected image provided by this application;

[0058] Figure 4 It is a schematic diagram of the original image provided by this application;

[0059] Figure 5 It is a schematic diagram of the image after smoothing provided by this application;

[0060] Figure 6 It is a schematic diagram of the separated proppant image provided by this application;

[0061] Figure 7 It is a schematic diagram of the separated tracer particle image provided by this application;

[0062] Figure 8 It is a schematic diagram of the PIV velocity field provided by this application;

[0063] Figure 9 It is a schematic diagram of the PTV velocity field provided by this application;

[0064] Figure 10 It is a schematic diagram of two kinds of particle images after gray-level transformation and filtering processing of the original image to obtain a gray-level image and image separation provided by this application;

[0065] Figure 11 It is a schematic diagram of the results of analyzing the separated tracer particle image and proppant image using the PIV algorithm and the PTV algorithm respectively provided by this application;

[0066] Figure 12 It is a block diagram of the hardware structure of an electronic device for a method for determining the transport state of proppants provided by this application;

[0067] Figure 13 It is a schematic diagram of the module structure of an embodiment of a device for determining the transport state of proppants provided by this application. Detailed implementation manners

[0068] To enable those skilled in the art to better understand the technical solutions in this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0069] In this example, considering that if the captured image can be subjected to particle segmentation, the position information of the proppant and tracer particles can be effectively extracted, thereby studying the migration state of the proppant in the fracture. Through this method, the distribution and movement trajectories of the proppant and fluid can be determined more accurately to monitor the fluid movement state. Specifically, the position information of the proppant and tracer particles can be extracted by processing the two-phase flow image in the fracture, thereby determining the migration state of the proppant in the fracture.

[0070] Figure 1 It is a flowchart of a method for an embodiment of the method for determining the migration state of the proppant provided by this application. Although this application provides method operation steps or device structures as shown in the following embodiments or drawings, more or fewer operation steps or module units may be included in the method or device based on routine or non-creative labor. In steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure described in the embodiments of this application and shown in the drawings. When the method or module structure is applied to an actual device or terminal product, it can be executed sequentially or in parallel according to the method or module structure connection shown in the embodiments or drawings (for example, in an environment of parallel processors or multi-threaded processing, or even a distributed processing environment).

[0071] Specifically, as Figure 1 shown, the method for determining the migration state of the proppant described above may include the following steps:

[0072] Step 101: Obtain the migration image of the proppant in the target fracture;

[0073] Specifically, image data of the two-phase flow in the target fracture can be continuously and real-time obtained by an image acquisition device at multiple time points to obtain multiple state images during the flow of the proppant; the multiple state images are used as the migration image of the proppant; wherein, the resolution and sensitivity of the image acquisition device meet the requirements for capturing the microscopic changes of the proppant and tracer particles.

[0074] For example, when acquiring the migration image, the image acquisition device can be used to acquire the image data of the two-phase flow in the fracture in real time. Among them, the resolution and sensitivity of the selected image acquisition device need to meet the requirements of capturing the microscopic changes of the proppant and tracer particles. Image acquisition can be continuously performed at different time points to obtain multiple state images during the flow process.

[0075] Step 102: Perform gray-scale transformation on the migration image to obtain a gray-scale image;

[0076] When implemented, performing gray-scale transformation on the migration image to obtain a gray-scale image may include:

[0077] S1: Adjust the brightness of the migration image to obtain the adjusted gray-scale values of each pixel point in the migration image, where the adjusted gray-scale value is expressed as:

[0078] G1 = G0 * G a +b

[0079] where G1 represents the adjusted gray-scale value, G0 represents the original gray-scale value, G a represents the brightness gain, and b represents the brightness offset;

[0080] S2: Perform gray-scale linear transformation on each pixel point in the migration image after brightness adjustment. The formula for gray-scale linear transformation is:

[0081] g(x,y) = k[f(x,y) - a] + c

[0082] where f(x,y) represents the gray-scale value after brightness adjustment, f(x,y) ∈ [a, b], g(x,y) represents the gray-scale value after gray-scale linear transformation, g(x,y) ∈ [c, d], where k represents the gain factor of linear transformation, (x,y) represents the coordinates in the original image, a represents the minimum value in the gray-scale value range of the migration image after brightness adjustment, b represents the maximum value in the gray-scale value range of the migration image after brightness adjustment, c represents the minimum value in the gray-scale value range of the image after gray-scale linear transformation, and d represents the maximum value in the gray-scale value range of the image after gray-scale linear transformation.

[0083] Step 103: Perform smoothing processing on the gray-scale image to obtain a smoothed image;

[0084] Smoothing the grayscale image to obtain the smoothed image can be achieved by using a filter to remove noise from the image. Specifically, a 3*3 mean filter can be applied for image smoothing. This filter replaces the original pixel value by calculating the grayscale mean of the pixels in the neighborhood, thereby effectively reducing noise. Then, a median filter is used to calculate the median of the pixels in the neighborhood and take the calculated median as the new pixel value to further process the outliers and noise in the image. Through the collaborative effect of these two filters, the main features of the image can be retained while improving the image quality.

[0085] That is, smoothing the grayscale image to obtain the smoothed image may include: calculating the grayscale values of the pixels in the neighborhood of the grayscale image by a 3*3 mean filter to replace the original pixel values, obtaining an intermediate image; calculating the median of the pixels in the neighborhood of the intermediate image by a median filter as the new pixel value to obtain the smoothed image.

[0086] Step 104: Performing edge detection on the smoothed image to obtain the detected image;

[0087] Step 105: Performing threshold segmentation on the detected image to separate the proppant and tracer particles in the detected image, so as to determine the migration state of the proppant in the target fracture.

[0088] In the above example, performing edge detection on the smoothed image to obtain the detected image can be achieved by first using an operator for edge detection. That is, the edges in the image are identified by the operator to facilitate subsequent particle segmentation. When performing edge detection by the operator, the places with large gradient changes in the image can be searched, because the places with large gradient changes in the image are the edges of the image. In implementation, performing edge detection by the operator may include: gradient calculation, non-maximum suppression, and double-threshold edge tracking. Specifically, performing edge detection can be as Figure 2 shown and includes the following steps:

[0089] Step 201: Calculate the gradient magnitude and gradient direction of each pixel point in the smoothed image according to the following formula:

[0090]

[0091] where I represents the smoothed image, G x represents the gradient of the image in the horizontal direction, and G y represents the gradient of the image in the vertical direction;

[0092] Step 202: Compare the gradient magnitude of each pixel point with the pixel values on both sides in its gradient direction to determine the local maximum value in the gradient direction;

[0093] Step 203: Suppress the pixel points outside the local maximum values to obtain a suppressed gradient map;

[0094] Step 204: Obtain a preset first threshold and a second threshold, where the first threshold is greater than the second threshold;

[0095] Step 205: Take the pixel points in the suppressed gradient map whose gradient magnitudes are greater than the first threshold as strong edges, take the pixel points in the suppressed gradient map whose gradient magnitudes are less than or equal to the first threshold and greater than or equal to the second threshold as weak edges, and remove the pixel points in the suppressed gradient map whose gradient magnitudes are less than the second threshold to obtain a detected image.

[0096] That is, after calculating the gradient magnitude and gradient direction of each pixel point, non-maximum suppression can be performed. Specifically, by comparing the gradient magnitude of each pixel point with the pixel values on both sides in its gradient direction, the local maximum value in the gradient direction can be selected, and then other non-maximum pixels can be suppressed to refine the edge. The gradient map is divided into three categories: strong edges, weak edges, and non-edges through a double-threshold strategy. When classifying, it can be classified according to the defined high threshold (T high ) and low threshold (T low ). If the gradient magnitude is greater than T high , it is marked as a strong edge. If the gradient magnitude is between T high and T low , it is marked as a weak edge, and the pixels with a gradient magnitude less than T low are removed.

[0097] Furthermore, threshold segmentation is performed on the detected image, and separating the proppants and tracer particles in the detected image can be as Figure 3 shown, including the following steps:

[0098] Step 301: Perform histogram statistics on the detected image to determine the number of pixel points at each gray level;

[0099] Step 302: According to the statistical results, determine the pixel probability distribution at each gray level to form a normalized probability histogram;

[0100] Step 303: Within each gray level, traverse each possible threshold, and calculate the pixel probability and gray mean value on both sides of each threshold;

[0101] Step 304: Calculate the between-class variance of each threshold according to the pixel probability and gray mean value on both sides of each threshold;

[0102] Specifically, the between-class variance of the current threshold can be calculated according to the following formula:

[0103]

[0104] Among them, represents the between-class variance of the current threshold t, ω1(t) and ω2(t) represent the pixel probabilities on both sides of the current threshold t, and μ1(t) and μ2(t) respectively represent the gray-scale means on both sides of the current threshold t.

[0105] Step 305: Use the threshold corresponding to the maximum between-class variance as the target threshold;

[0106] Step 306: Perform binarization processing on the detected image through the target threshold to divide the pixel points in the detected image into background and foreground, so as to separate the proppant and the tracer particles.

[0107] That is, by traversing all possible thresholds, the threshold that maximizes the between-class variance can be found. This maximum threshold is the output of the algorithm. After finding this optimal threshold, the image can be binarized through the determined optimal threshold to divide the pixels into two categories (foreground and background). That is to say, through optimizing the between-class variance, adaptive image segmentation is achieved, which is especially suitable for images with bimodal histograms, where one peak represents the background and the other peak represents the foreground. Then, the particle segmentation can be performed according to the threshold to separate the tracer particles and the proppant.

[0108] The above method will be described below in conjunction with a specific embodiment. However, it should be noted that this specific embodiment is only for better explaining the present application and does not constitute an improper limitation to the present application.

[0109] In this example, a method for analyzing the transport state of proppant using an image processing algorithm is provided. By performing particle segmentation on the captured image, the position information of the proppant and the tracer particles can be effectively extracted, so as to study the transport state of the proppant in the fracture. Through this method, the distribution and movement trajectory of the proppant and the fluid can be determined more accurately to monitor the movement state of the fluid. Specifically, by processing the two-phase flow image in the fracture, the extraction of the position information of the proppant and the tracer particles is realized, so as to determine the transport state of the proppant in the fracture.

[0110] The method for analyzing the transport state of proppant using an image processing algorithm provided in this example may include the following steps:

[0111] S1: Obtain the transport image of the proppant in the target fracture;

[0112] S2: Perform gray-scale transformation on the transport image to obtain a gray-scale image;

[0113] S3: Perform smoothing processing on the gray-scale image to obtain a smoothed image;

[0114] S4: Perform edge detection on the smoothed image based on the Canny operator to obtain the detected image;

[0115] S5: Perform threshold segmentation on the detected image by the OSTU maximum inter-class variance method to separate the proppant and tracer particles.

[0116] In the above step S1, when obtaining the migration image, the image data of the two-phase flow in the fracture can be obtained in real time through an image acquisition device. Among them, the resolution and sensitivity of the selected image acquisition device need to meet the requirements of capturing the microscopic changes of the proppant and tracer particles. Image acquisition can be continuously performed at different time points to obtain multiple state images during the flow process.

[0117] In step S2, by performing gray-scale transformation on the migration image, the subsequent processing steps can be simplified. The gray-scale transformation can include the following steps:

[0118] S21: Adjust the brightness of the original image (i.e., the above-mentioned migration image) to obtain the adjusted gray value G1:

[0119] G1 = G0 * G a + b

[0120] where G0 represents the original gray value, G a represents the brightness gain, and b represents the brightness offset.

[0121] S22: Perform gray-scale linear transformation: linearly expand each pixel, that is, expand the dynamic range and contrast of the image to improve the visual effect.

[0122] Assume that the gray value of the original image f(x, y) ∈ [a, b], and the gray value of the linearly transformed image g(x, y) ∈ [c, d]. Then the gray-scale linear transformation is:

[0123] g(x, y) = k[f(x, y) - a] + c.

[0124] In step S3, perform smoothing processing on the gray-scale image. The smoothed image obtained can be to remove the noise in the image using a filter. Specifically, a 3*3 mean filter can be applied for the smoothing processing of the image. This filter replaces the original pixel value by calculating the gray mean of the pixels in the neighborhood, thereby effectively reducing the noise. Then, use a median filter to calculate the median of the pixels in the neighborhood and use the calculated median as the new pixel value to further process the outliers and noise in the image. Through the synergistic effect of these two filters, while improving the image quality, the main features of the image are retained. As Figure 4 shown, is the original image, as Figure 5As shown, it is the image after smoothing processing.

[0125] In step S5, the detected image is subjected to threshold segmentation by the OSTU method of maximum inter-class variance to separate the proppant and tracer particles, that is, particle segmentation is required to divide the image into a proppant region and a tracer particle region. Specifically, an operator can be used for edge detection first, that is, the edges in the image are identified by the operator to facilitate subsequent particle segmentation. When performing edge detection by the operator, the places with large gradient changes in the image can be searched, because the way with large gradient changes in the image is the edge of the image. Specifically, using the operator for edge detection can include: gradient calculation, non-maximum suppression, and double-threshold edge tracking.

[0126] Specifically, the image can be convolved by the Sobel operator first to calculate the gradient magnitude and gradient direction of each pixel point, where the gradient direction points to the direction of the maximum gradient increase.

[0127]

[0128] Among them, I represents the input image, G x represents the gradient of the image in the horizontal direction, and G y represents the gradient of the image in the vertical direction.

[0129] After calculating the gradient magnitude and gradient direction of each pixel point, non-maximum suppression can be performed. Specifically, by comparing the gradient magnitude of each pixel point with the pixel values on both sides in its gradient direction, the local maximum value in the gradient direction is selected, and then other non-maximum pixels are suppressed to refine the edge. The gradient map is divided into three categories: strong edges, weak edges, and non-edges by the double-threshold strategy. When classifying, it can be classified according to the defined high threshold (T high ) and low threshold (T low ). If the gradient magnitude is greater than T high , it is marked as a strong edge. If the gradient magnitude is between T high and T low , it is marked as a weak edge, and the pixels with a gradient magnitude less than T low are removed.

[0130] The maximum inter-class variance method is used for threshold segmentation of the image after edge detection to adaptively select the optimal threshold, so that the inter-class variance in the segmented image is the largest, that is, the difference between the proppant and tracer particles is the most significant. Specifically, the histogram of the grayscale image to be segmented can be statistically calculated first to obtain the number of pixels at each gray level. Then, the histogram is normalized to obtain the pixel probability distribution at each gray level to form a normalized probability histogram.

[0131]

[0132] where P (i) is the normalized probability of gray level i, n i is the number of pixels of gray level i, and N is the total number of pixels.

[0133] Then, calculate the cumulative distribution of the normalized probability histogram and the corresponding average gray value.

[0134]

[0135] Then, within the range of gray levels, traverse each possible threshold. For each threshold, calculate the pixel probabilities and gray means on both sides of it, and then use the between-class variance formula to calculate the between-class variance at the current threshold.

[0136]

[0137] where represents the between-class variance, ω1(t) and ω2(t) represent the pixel probabilities on both sides of threshold t, and μ1(t) and μ2(t) represent the gray means on both sides of threshold t, respectively.

[0138] That is, the difference degree between the foreground and background of the image is characterized by the between-class variance. Specifically, by traversing all possible thresholds, the threshold that makes the between-class variance the largest is found. This largest threshold is the output of the algorithm. After finding this optimal threshold, the image can be binarized by the determined optimal threshold to divide the pixels into two categories (foreground and background). That is to say, through optimizing the between-class variance, adaptive image segmentation is achieved, especially suitable for images with bimodal histograms, where one peak represents the background and the other peak represents the foreground. Subsequently, particle segmentation is performed according to the threshold to separate the tracer particles and the proppant. As Figure 6 shown, it is the image of the separated proppant.

[0139] After particle segmentation, PIV (Particle Image Velocimetry) analysis can be performed on the tracer particle image and the proppant image. Specifically, the time of each image captured by the image recorder can be set to Δt. The position coordinates of the tracer particle (x, y) after Δt time are (x + Δx, y + Δy). Specifically, the flow field image at time t1 is represented as I1(x, y) = I(x, y) + n1(x, y). When the flow field is relatively stable and the time interval between consecutive images captured by the image recorder is small enough, the flow field image at time t2 can be represented as I2(x, y) = I(x + Δx, y + Δy) + n2(x, y), where n1(x, y) and n2(x, y) are random noises generated during the experimental image capture. Subsequently, the cross-correlation function γ of I1(x, y) and I2(x, y) is calculated 12 (τ x +τ y ) gives:

[0140]

[0141] The autocorrelation function of I(x, y) can be obtained from the definition of the autocorrelation function:

[0142]

[0143] Therefore, the above equation can be transformed into γ 12 (τ x ,τ y ) = γ(τ x +Δx,τ y +Δy). Since the autocorrelation function is an even function of itself and has a maximum at the origin, i.e., γ(τ x ,τ y ) ≤ γ(0, 0), the following inequality can be deduced:

[0144] γ 12 (τ x ,τ y ) ≤ γ 12 (-Δx, -Δy).

[0145] Taking the relative displacement of the tracer particle in two consecutive images captured by the image recorder within Δt as the maximum value of the cross-correlation function, the velocity of the tracer particle in the proppant transport experiment can be deduced and calculated, which is the fluid velocity. PIV can only detect tracer particles. As Figure 7 shown, it is the image of the separated tracer particles. As Figure 8 shown, it is the schematic diagram of the PIV velocity field.

[0146] When performing PTV analysis on the proppant particle image, the digital masking method can be used for particle recognition. A grayscale particle image that follows a Gaussian distribution is selected as the particle template, and the cross-correlation coefficient between the region of the same size as the particle template and the particle template within the detection window centered at (x0, y0) is calculated. Among them, the cross-correlation coefficient can be expressed as:

[0147]

[0148] Among them, γ(x0, y0) is the cross-correlation coefficient at the point (x0, y0), I(i, j) is the grayscale value of the original image at the point (i, j), and I m (i, j) is the grayscale value of the particle template at the point (i, j). The size of the detection window is m*n, and m = n = 1.5σ m , and are the average grayscale values within the detection windows of the original image and the particle template, respectively. Based on this, all pixels of the original image can be scanned with the particle template to obtain the correlation coefficient map.

[0149] After identifying the proppant image particles separated from two frames through the above method, the particles in the two frames are matched. For example: Matching can be based on the relaxation algorithm. Specifically, the distance threshold formula can be used to determine the reference range for particle matching in the two frames. Among them, x i and y j represent the displacement vectors of particle i in the first frame image X and particle j in the second frame image Y respectively, and R s is the maximum value of the particle displacement:

[0150] |x i -y j | < R s

[0151] Then, the matching probability is calculated, and the non-matching probability is introduced to reduce the false matching.

[0152] Assume that the probability of particle i in the first frame matching particle j in the second frame is P ij , and the non-matching probability of particle i is P i * , and the formula is as follows:

[0153]

[0154] The matching probability is updated through iterative calculation until a stable value is reached.

[0155] Finally, select the particle with the highest matching probability as the matching result. By describing particle matching through probability in this way, false matching can be reduced. At the same time, the matching probability is updated according to adjacent particles, improving the matching accuracy. As Figure 9 shown, it is a schematic diagram of the PTV velocity field.

[0156] By comparing and analyzing the velocity fields of the solid-liquid two-phase flow, the movement characteristics of the proppant in the fracture and its following fluid characteristics can be deeply understood, so that the migration state of the proppant can be monitored and analyzed in real time.

[0157] As Figure 10 shown, it is a schematic diagram of two kinds of particle images obtained by performing gray-scale transformation and filtering on the original image to obtain a gray-scale image and image separation. Among them, Figure 10 a in it is the original image, Figure 10 b in it is the processed image, Figure 10 c in it is the proppant image, Figure 10 d in it is the tracer particle image.

[0158] Capture, process and separate the images at the initial moment, intermediate moment, and steady state moment during the proppant migration experiment. The results of analyzing the separated tracer particle image and proppant image using the PIV algorithm and PTV algorithm respectively can be as Figure 11 shown, Figure 11 a in it represents the image of the tracer particle at the initial moment, Figure 11 b in it represents the image of the tracer particle at the intermediate moment, Figure 11 c in it represents the image of the tracer particle at the steady state moment, Figure 11 d in it represents the image of the proppant at the initial moment, Figure 11 e in it represents the image of the proppant at the intermediate moment, Figure 11 f in it represents the image of the proppant at the steady state moment. In Figure 11 velocity represents speed.

[0159] The method embodiments provided in the above embodiments of the present application can be executed on a mobile terminal, a computer terminal or a similar computing device. Taking running on an electronic device as an example, Figure 12 is a hardware structure block diagram of an electronic device for a method of determining the migration state of a proppant provided by the present application. As Figure 12 shown, the electronic device 10 may include one or more (only one is shown in the figure) processors 02 (the processor 02 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 04 for storing data, and a transmission module 06 for communication functions. Those of ordinary skill in the art can understand, Figure 12The structure shown is only schematic and does not limit the structure of the above-mentioned electronic device. For example, the electronic device 10 may further include more or fewer components than those shown in Figure 12 or have a different configuration from that shown in Figure 12 .

[0160] The memory 04 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the method for determining the proppant transport state in the embodiments of the present application. The processor 02 executes various functional applications and data processing by running the software programs and modules stored in the memory 04, that is, implements the method for determining the proppant transport state of the above application program. The memory 04 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 04 may further include a memory remotely provided relative to the processor 02, and these remote memories can be connected to the electronic device 10 through a network. Examples of the above networks include, but are not limited to, the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof.

[0161] The transmission module 06 is used to receive or send data via a network. Specific examples of the above network may include the wireless network provided by the communication provider of the electronic device 10. In one instance, the transmission module 06 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission module 06 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0162] At the software level, the above-mentioned device for determining the proppant transport state can be as shown in Figure 13 and includes:

[0163] An acquisition module 1301, configured to acquire the transport image of the proppant in the target fracture;

[0164] A grayscale transformation module 1302, configured to perform grayscale transformation on the transport image to obtain a grayscale image;

[0165] A smoothing processing module 1303, configured to perform smoothing processing on the grayscale image to obtain a smoothed image;

[0166] An edge detection module 1304, configured to perform edge detection on the smoothed image to obtain a detected image;

[0167] A segmentation module 1305 is used to perform threshold segmentation on the detected image, separate the proppant and tracer particles in the detected image, so as to determine the migration state of the proppant in the target fracture.

[0168] In one embodiment, the acquisition module 1301 can specifically obtain the image data of the two-phase flow in the target fracture in real time and continuously at multiple time points through an image acquisition device, so as to obtain multiple state images during the proppant flow process; use the multiple state images as the migration images of the proppant; wherein, the resolution and sensitivity of the image acquisition device meet the requirements of capturing the microscopic changes of the proppant and tracer particles.

[0169] In one embodiment, the gray-scale transformation module 1302 can specifically adjust the brightness of the migration image to obtain the adjusted gray-scale values of each pixel point in the migration image, where the adjusted gray-scale value is expressed as:

[0170] G1 = G0 * G a + b

[0171] wherein, G1 represents the adjusted gray-scale value, G0 represents the original gray-scale value, G a represents the brightness gain, and b represents the brightness offset;

[0172] For each pixel point in the migration image after brightness adjustment, perform gray-scale linear transformation, where the formula for gray-scale linear transformation is:

[0173] g(x, y) = k[f(x, y) - a] + c

[0174] wherein, f(x, y) represents the gray-scale value after brightness adjustment, f(x, y) ∈ [a, b], g(x, y) represents the gray-scale value after gray-scale linear transformation, g(x, y) ∈ [c, d], where k represents the gain factor of linear transformation, (x, y) represents the coordinates in the original image, a represents the minimum value in the gray-scale value range of the migration image after brightness adjustment, b represents the maximum value in the gray-scale value range of the migration image after brightness adjustment, c represents the minimum value in the gray-scale value range of the image after gray-scale linear transformation, and d represents the maximum value in the gray-scale value range of the image after gray-scale linear transformation.

[0175] In one embodiment, the smoothing processing module 1303 can specifically calculate the gray-scale values of the pixels in the neighborhood of the gray-scale image through a 3*3 mean filter to replace the original pixel values to obtain an intermediate image; calculate the median of the pixels in the neighborhood of the intermediate image as the new pixel value to obtain the smoothed image.

[0176] In one embodiment, the edge detection module 1304 may specifically calculate the gradient magnitude and gradient direction of each pixel point in the smoothed image according to the following formula:

[0177]

[0178]

[0179] where I represents the smoothed image, G x represents the gradient of the image in the horizontal direction, and G y represents the gradient of the image in the vertical direction;

[0180] Compare the gradient magnitude of each pixel point with the pixel values on both sides in its gradient direction to determine the local maximum value in the gradient direction;

[0181] Suppress the pixel points outside the local maximum value to obtain a suppressed gradient map;

[0182] Obtain a pre-set first threshold and a second threshold, where the first threshold is greater than the second threshold;

[0183] Take the pixel points in the suppressed gradient map whose gradient magnitude is greater than the first threshold as strong edges, take the pixel points in the suppressed gradient map whose gradient magnitude is less than or equal to the first threshold and greater than or equal to the second threshold as weak edges, and remove the pixel points in the suppressed gradient map whose gradient magnitude is less than the second threshold to obtain a detected image.

[0184] In one embodiment, the segmentation module 1305 may specifically perform histogram statistics on the detected image to determine the number of pixel points at each gray level; according to the statistical results, determine the pixel probability distribution at each gray level to form a normalized probability histogram; within each gray level, traverse each possible threshold, calculate the pixel probability and gray mean on both sides of each threshold; calculate the between-class variance of each threshold according to the pixel probability and gray mean on both sides of each threshold; take the threshold corresponding to the maximum between-class variance as the target threshold; perform binary processing on the detected image through the target threshold to divide the pixel points in the detected image into the background and the foreground, and realize the separation of the proppant and the tracer particles.

[0185] In one embodiment, the between-class variance of the current threshold can be calculated according to the following formula:

[0186]

[0187] where It represents the between-class variance of the current threshold t. ω1(t) and ω2(t) represent the pixel probabilities on both sides of the current threshold t, and μ1(t) and μ2(t) respectively represent the gray-scale means on both sides of the current threshold t.

[0188] An embodiment of the present application also provides a specific implementation manner of an electronic device that can implement all steps in the method for determining the proppant transport state in the above embodiments. The electronic device specifically includes the following: a processor, a memory, a communication interface, and a bus; wherein, the processor, the memory, and the communication interface complete mutual communication through the bus; the processor is used to call the computer program in the memory, and when the processor executes the computer program, it implements all steps in the method for determining the proppant transport state in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0189] Step 1: Obtain the transport image of the proppant in the target fracture.

[0190] Step 2: Perform gray-scale transformation on the transport image to obtain a gray-scale image.

[0191] Step 3: Perform smoothing processing on the gray-scale image to obtain a smoothed image.

[0192] Step 4: Perform edge detection on the smoothed image to obtain a detected image.

[0193] Step 5: Perform threshold segmentation on the detected image to separate the proppant and tracer particles in the detected image, so as to determine the transport state of the proppant in the target fracture.

[0194] An embodiment of the present application also provides a computer-readable storage medium that can implement all steps in the method for determining the proppant transport state in the above embodiments. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements all steps in the method for determining the proppant transport state in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0195] Step 1: Obtain the transport image of the proppant in the target fracture.

[0196] Step 2: Perform gray-scale transformation on the transport image to obtain a gray-scale image.

[0197] Step 3: Perform smoothing processing on the gray-scale image to obtain a smoothed image.

[0198] Step 4: Perform edge detection on the smoothed image to obtain the detected image;

[0199] Step 5: Perform threshold segmentation on the detected image to separate the proppant and tracer particles in the detected image, so as to determine the migration state of the proppant in the target fracture.

[0200] As can be seen from the above description, in the embodiment of the present application, by performing gray-scale transformation, smoothing processing, edge detection, and threshold segmentation on the migration image of the proppant in the target fracture, the proppant and tracer particles in the image are separated, so as to determine the migration state of the proppant in the target fracture. Through the above solution, efficient separation of the proppant and tracer particles in the image is achieved, so that the migration state of the proppant in the fracture can be accurately determined.

[0201] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program type embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0202] The specific embodiments of this specification are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0203] Although the present application provides method operation steps as described in the embodiments or flowcharts, based on routine or non-creative labor, there may be more or fewer operation steps. The step order listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the method order shown in the embodiments or the drawings or in parallel (for example, in an environment of parallel processors or multithreaded processing).

[0204] The systems, devices, modules or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, an in-vehicle human-machine interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0205] Although the method operation steps as described in the embodiments of this specification are provided as in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual device or terminal product executes, it can be executed in the order of the method shown in the embodiments or the drawings or executed in parallel (for example, in an environment of parallel processors or multi-threaded processing, or even in a distributed data processing environment). The term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, product or device. Without further limitation, there is no exclusion of additional identical or equivalent elements in the process, method, product or device including the said elements.

[0206] For the convenience of description, the above devices are described by dividing them into various modules according to their functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules implementing the same function can be realized by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0207] Those skilled in the art also know that, in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to achieve the same function by logically programming the method steps so that the controller is implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0208] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0209] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0210] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0211] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0212] Memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0213] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for information storage. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0214] Those skilled in the art will appreciate that the embodiments of this specification may be provided as a method, system, or computer program product. Accordingly, the embodiments of this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0215] The embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The embodiments of this specification may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

[0216] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and for related parts, reference can be made to the description of the method embodiments. In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification. In this specification, the schematic expression of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples.

[0217] The above is only the embodiment of the embodiments of this specification and is not used to limit the embodiments of this specification. For those skilled in the art, various changes and modifications can be made to the embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A method for determining the transport state of proppants, characterized in that, The method includes: Obtaining a migration image of proppant in a target fracture; Performing grayscale transformation on the migration image to obtain a grayscale image; Performing smoothing processing on the grayscale image to obtain a smoothed image; Performing edge detection on the smoothed image to obtain a detected image; Performing threshold segmentation on the detected image to separate the proppant and tracer particles in the detected image, so as to determine the migration state of the proppant in the target fracture.

2. The method according to claim 1, wherein Obtaining a migration image of proppant in a target fracture includes: Continuously and real-time obtaining image data of two-phase flow in the target fracture at multiple time points through an image acquisition device to obtain multiple state images during the flow process of the proppant; Using the multiple state images as the migration image of the proppant; Wherein, the resolution and sensitivity of the image acquisition device meet the requirements of capturing microscopic changes of the proppant and tracer particles.

3. The method according to claim 1, characterized in that, Performing grayscale transformation on the migration image to obtain a grayscale image includes: Adjusting the brightness of the migration image to obtain the adjusted grayscale value of each pixel point in the migration image, wherein the adjusted grayscale value is expressed as: G1 = G0 * G a + b Among them, G1 represents the adjusted gray value, G0 represents the original gray value, G a represents the brightness gain, and b represents the brightness offset; Performing grayscale linear transformation on each pixel point in the migration image after brightness adjustment, wherein the formula for grayscale linear transformation is: g(x,y) = k[f(x,y) - a] + c Wherein, f(x,y) represents the grayscale value after brightness adjustment, f(x,y) ∈ [a,b], g(x,y) represents the grayscale value after grayscale linear transformation, g(x,y) ∈ [c,d], where k represents the gain factor of linear transformation, (x,y) represents the coordinates in the original image, a represents the minimum value in the grayscale value range of the migration image after brightness adjustment, b represents the maximum value in the grayscale value range of the migration image after brightness adjustment, c represents the minimum value in the grayscale value range of the image after grayscale linear transformation, and d represents the maximum value in the grayscale value range of the image after grayscale linear transformation.

4. The method according to claim 1, wherein Performing smoothing processing on the grayscale image to obtain a smoothed image includes: Calculating the grayscale value of the pixels in the neighborhood of the grayscale image through a 3*3 mean filter to replace the original pixel value to obtain an intermediate image; Calculating the median of the pixels in the neighborhood of the intermediate image through a median filter as the new pixel value to obtain a smoothed image.

5. The method according to claim 1, characterized in that, Performing edge detection on the smoothed image to obtain a detected image includes: Calculating the gradient magnitude and gradient direction of each pixel point in the smoothed image according to the following formula: Among them, I represents the smoothed image, and G x represents the gradient of the image in the horizontal direction, and G y represents the gradient of the image in the vertical direction; Comparing the gradient magnitude of each pixel point with the pixel values on both sides in its gradient direction to determine the local maximum value in the gradient direction; Suppressing the pixel points outside the local maximum value to obtain a suppressed gradient map; Obtaining a preset first threshold and a second threshold, wherein the first threshold is greater than the second threshold; Pixels with gradient magnitudes greater than the first threshold in the suppressed gradient map are regarded as strong edges, pixels with gradient magnitudes less than or equal to the first threshold and greater than or equal to the second threshold in the suppressed gradient map are regarded as weak edges, and pixels with gradient magnitudes less than the second threshold in the suppressed gradient map are removed to obtain the detected image.

6. The method according to claim 1, characterized in that Performing threshold segmentation on the detected image to separate the proppant and tracer particles in the detected image, including: Performing histogram statistics on the detected image to determine the number of pixels at each gray level; According to the statistical results, determining the pixel probability distribution at each gray level to form a normalized probability histogram; Within each gray level, traversing each possible threshold and calculating the pixel probability and gray mean on both sides of each threshold; Calculating the between-class variance of each threshold according to the pixel probability and gray mean on both sides of each threshold; Taking the threshold corresponding to the maximum between-class variance as the target threshold; Performing binarization processing on the detected image through the target threshold to divide the pixels in the detected image into background and foreground, and realizing the separation of the proppant and tracer particles.

7. The method according to claim 6, wherein Calculating the between-class variance of each threshold according to the pixel probability and gray mean on both sides of each threshold, including: Calculating the between-class variance of the current threshold according to the following formula: Among them, represents the between-class variance of the current threshold t, ω1(t) and ω2(t) represent the pixel probabilities on both sides of the current threshold t, and μ1(t) and μ2(t) respectively represent the gray-scale means on both sides of the current threshold t.

8. A device for determining the transport state of proppants, characterized in that, Including: An acquisition module for acquiring the migration image of the proppant in the target fracture; A gray-scale transformation module for performing gray-scale transformation on the migration image to obtain a gray-scale image; A smoothing processing module for performing smoothing processing on the gray-scale image to obtain a smoothed image; An edge detection module for performing edge detection on the smoothed image to obtain a detected image; A segmentation module for performing threshold segmentation on the detected image to separate the proppant and tracer particles in the detected image to determine the migration state of the proppant in the target fracture.

9. An electronic device, comprising a processor and a memory for storing processor-executable instructions, characterized in that, When the processor executes the instructions, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having computer programs / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images