Methods, apparatus, equipment, media, and products for determining resin injection filling rate

Abstract

This application provides a method, apparatus, equipment, medium, and product for determining resin filling rate, relating to the field of liquid molding technology. This application standardizes and discretizes the observation area of ​​each frame in an image sequence into multiple grid units, identifies the filling quantity of the first grid unit in each frame, and calculates the resin filling rate based on the ratio between the filling quantity of the first grid unit and the total number of first grid units in the observation area. This quantification method is intuitive and consistent, avoiding the errors of traditional coarse estimation and improving the accuracy of resin filling rate calculation. Simultaneously, the observation area is limited to the mold projection area, allowing the analysis to focus on the actual resin filling range, eliminating irrelevant background interference, meeting the practical application scenarios of liquid molding processes, and providing reliable data support for process optimization.

Description

Technical Field

[0001] This application belongs to the field of liquid molding technology, and particularly relates to a method, apparatus, equipment, medium and product for determining resin injection filling rate. Background Technology

[0002] In liquid molding processes, analyzing resin injection flow behavior is crucial for optimizing the process and improving molding quality. However, many existing techniques rely on manual observation or simple image comparisons to estimate filling progress, failing to provide precise quantitative analysis of resin injection flow behavior and thus hindering the practical needs for refined process optimization. Summary of the Invention

[0003] This application provides a method, apparatus, device, medium, and product for determining resin injection filling rate. It standardizes and discretizes the observation area of ​​a continuous frame image into multiple grid cells, and calculates the filling rate by the ratio of the number of filled grid cells to the total number of grid cells. This quantification method is intuitive and consistent, avoiding the errors of traditional rough estimations and improving the accuracy of filling rate calculation. Simultaneously, the observation area is limited to the mold projection area, allowing the analysis to focus on the actual resin injection range, eliminating irrelevant background interference, meeting the practical application scenarios of liquid molding processes, and providing reliable data support for process optimization.

[0004] In a first aspect, the embodiments of this application provide a method for determining the resin injection filling rate, including:

[0005] Acquire an image sequence of the resin injection process within the mold cavity, the image sequence comprising multiple frames;

[0006] The observation area of ​​each frame image is divided into multiple first grid units to obtain the target image. The observation area is the projection area of ​​the mold cavity in each frame image.

[0007] For each target image, image recognition is performed on the target image to determine the number of fillers for the first grid cell;

[0008] The resin filling rate for each frame of image is determined based on the number of cells filled in the first grid cell.

[0009] In some embodiments, before obtaining the target image, the method further includes dividing the observation area of ​​each frame image into multiple grid units according to a preset grid specification:

[0010] In response to the user's operation of selecting a region in the reference frame image using a selection box, the observation area of ​​the reference frame image is determined. The reference frame image is the initial frame image in the image sequence that is in an unperfused state.

[0011] The location information of the observation area of ​​the reference frame image is reused in the remaining images in the image sequence other than the reference frame image, and is used as the observation area of ​​the remaining images.

[0012] In some embodiments, the method further includes, prior to image recognition of the target image:

[0013] Each frame of the image, after being processed by grid division, is converted to grayscale to obtain a grayscale image;

[0014] Select the reference frame image as the background image, remove the background image from the grayscale image, and obtain the target image.

[0015] In some embodiments, the filling state of the first grid cell includes filled and unfilled. Image recognition is performed on the target image to determine the filling quantity of the first grid cell, including:

[0016] Obtain the grayscale value of each first grid cell in the target image;

[0017] If the gray value of the first grid cell is greater than or equal to the first gray value threshold, the filling state of the first grid cell is determined to be filled.

[0018] The number of first grid cells to be filled is determined based on the number of first grid cells that are filled.

[0019] Based on the number of fill cells in the first grid cell, the resin fill rate corresponding to each frame of the image is determined, including:

[0020] The resin filling rate is determined based on the number of first grid cells filled and the total number of first grid cells in the observation area.

[0021] In some embodiments, the filling state of the first grid cell includes fully filled, partially filled, and unfilled. Image recognition is performed on the target image to determine the filling quantity of the first grid cell, including:

[0022] Obtain the grayscale value of each first grid cell in the target image;

[0023] If the gray value of the first grid cell is greater than or equal to the second gray value threshold, the filling state of the first grid cell is determined to be fully filled.

[0024] The number of fully filled first grid cells is determined based on the number of first grid cells that are fully filled.

[0025] And, if the gray value of the first grid cell is greater than or equal to the first gray value threshold and the gray value is less than the second gray value threshold, the filling state of the first grid cell is determined to be partially filled, and the first gray value threshold is less than the second gray value threshold.

[0026] The first grid cell, which is partially filled, is divided into multiple second grid cells;

[0027] The number of cells to be filled in the second grid cell is determined based on the gray value of the second grid cell.

[0028] Based on the number of fill cells in the first grid cell, the resin fill rate corresponding to each frame of the image is determined, including:

[0029] The area of ​​the resin-filled region is determined based on the number of fully filled first grid cells and the number of filled second grid cells.

[0030] The resin filling rate is determined based on the area of ​​the resin-filled region and the area of ​​the observation region.

[0031] In some embodiments, determining the area of ​​the resin-filled region based on the number of fully filled first grid cells and the number of filled second grid cells includes:

[0032] The area of ​​the resin-filled region is determined based on the number of fully filled first grid cells, the number of filled second grid cells, the area of ​​the first grid cell, and the area of ​​the second grid cell.

[0033] In some embodiments, dividing a first grid cell with a partially filled state into a plurality of second grid cells includes:

[0034] Calculate the edge complexity or grayscale gradient magnitude of the resin-filled region in the current frame image;

[0035] The size of the second grid cell in the next frame image is determined based on the edge complexity or grayscale gradient magnitude. The size of the second grid cell is negatively correlated with the edge complexity or grayscale gradient magnitude.

[0036] In some embodiments, the method further includes:

[0037] The fill rate sequence is determined based on the resin fill rate and timestamp information corresponding to each frame image;

[0038] The instantaneous flow rate of the resin during resin infusion was determined based on the filling rate sequence.

[0039] In some embodiments, the method further includes:

[0040] Based on the filling rate sequence, the resin flow rate change curve during resin infusion was determined;

[0041] Based on the flow rate change curve, the time required for the resin to completely fill the observation area is predicted.

[0042] Secondly, embodiments of this application also provide a resin injection filling rate determination device, comprising:

[0043] The acquisition module is used to acquire an image sequence of the resin pouring process in the mold cavity. The image sequence includes multiple frames of images.

[0044] The partitioning module is used to divide the observation area of ​​each frame image into multiple first grid units to obtain the target image. The observation area is the projection area of ​​the mold cavity in each frame image.

[0045] The first determining module is used to perform image recognition on each target image and determine the number of fillers for the first grid cell.

[0046] The second determining module is used to determine the resin filling rate corresponding to each frame of image based on the filling quantity of the first grid cell.

[0047] Thirdly, embodiments of this application also provide an electronic device, which includes: a processor and a memory storing computer program instructions;

[0048] The processor executes computer program instructions to implement any of the above-mentioned methods for determining the resin filling rate.

[0049] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement any of the above-described methods for determining the resin injection filling rate.

[0050] Fifthly, embodiments of this application also provide a computer program product, wherein the instructions in the computer program product, when executed by the processor of an electronic device, enable the electronic device to execute any of the above-described methods for determining the resin injection filling rate.

[0051] The resin filling rate determination method, apparatus, equipment, medium, and product provided in this application embodiment standardizes and discretizes the observation area of ​​each frame of an image sequence into multiple grid units, identifies the filling quantity of the first grid unit in each frame of the image, and calculates the resin filling rate based on the ratio between the filling quantity of the first grid unit and the total number of the first grid units in the observation area. The quantification method is intuitive and uniform, avoiding the errors of traditional rough estimation and improving the accuracy of resin filling rate calculation. At the same time, the observation area is limited to the mold projection area, so that the analysis focuses on the actual resin filling range, eliminates irrelevant background interference, meets the actual application scenarios of liquid molding process, and provides reliable data support for process optimization. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic flowchart of a method for determining resin injection filling rate provided in an embodiment of this application;

[0054] Figures 2-4 yes Figure 1 The diagram shows the corresponding steps in the method for determining the resin injection filling rate.

[0055] Figure 5 This is a schematic flowchart of another method for determining resin injection filling rate provided in an embodiment of this application;

[0056] Figure 6 This is a flowchart illustrating another method for determining the resin injection filling rate provided in the embodiments of this application;

[0057] Figure 7 This is a flowchart illustrating another method for determining the resin injection filling rate provided in the embodiments of this application;

[0058] Figure 8 This is a schematic diagram of the fill rate sequence, fill fitting curve, and flow rate change curve provided in the embodiments of this application;

[0059] Figure 9 This is a schematic diagram of the structure of a resin injection filling rate determination device provided in an embodiment of this application;

[0060] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0061] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0062] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0063] In conjunction with the background section, this application provides a method, apparatus, device, medium, and product for determining resin filling rate. By standardizing and discretizing the observation area of ​​each frame in an image sequence into multiple grid units, the filling quantity of the first grid unit in each frame is identified. The resin filling rate is calculated based on the ratio between the filling quantity of the first grid unit and the total number of first grid units in the observation area. This quantification method is intuitive and consistent, avoiding the errors of traditional rough estimations and improving the accuracy of resin filling rate calculation. Simultaneously, the observation area is limited to the mold projection area, allowing the analysis to focus on the actual resin filling range, eliminating irrelevant background interference, meeting the practical application scenarios of liquid molding processes, and providing reliable data support for process optimization.

[0064] The following section first describes a method for determining the resin injection filling rate provided in the embodiments of this application.

[0065] Figure 1 This is a schematic flowchart illustrating a method for determining the resin injection filling rate provided in an embodiment of this application. Figure 1 As shown, the method for determining the resin injection filling rate may include the following steps: S110~S140.

[0066] S110. Obtain an image sequence of the resin injection process in the mold cavity, the image sequence including multiple frames of images.

[0067] The resin injection mold includes a main mold structure and a fiber preform. The cavity surface of the main mold structure has a pattern layer. The pattern layer includes multiple solid structural units that are distributed in a preset manner. There is a gap between each two adjacent solid structural units. All gaps on the pattern layer are connected to form a resin flow channel during the resin injection process. The fiber preform covers the top of the pattern layer.

[0068] The mold cavity refers to the molding area on the resin injection mold used to contain and shape the resin to be processed. It is the space where the resin actually flows, impregnates and fills during the resin injection process, that is, the space formed by the fiber preform and the pattern layer.

[0069] In this step, image sequences can be acquired using any device with image acquisition capabilities known to those skilled in the art, such as a high-speed acquisition camera, but this is not limited to that. The multiple frames in the image sequence can be video images or static time-series images.

[0070] For example, such as Figure 2 The image shown is a frame obtained during the resin injection process in the mold cavity according to an embodiment of this application. In areas where the fiber preform is not impregnated by resin, air remains in the space between the fiber preform and the pattern layer 202. Due to the difference in refractive index between the air and the fiber preform, light scattering occurs, and the corresponding area appears white, obscuring the color of the resin injection mold. In areas where the fiber preform is completely impregnated by resin, the space between the fiber preform and the pattern layer is filled with resin. The refractive index of the resin is closer to that of the fiber preform, reducing scattering and making the fiber preform more transparent, allowing the color of the resin injection mold to pass through. This transformation of optical phenomena provides a basis for visual judgment of impregnation. The impregnation state of the fiber preform can be determined based on its color, thereby determining the resin filling state.

[0071] S120. Divide the observation area of ​​each frame of image into multiple first grid units to obtain the target image.

[0072] The observation area is the projected area of ​​the mold cavity in each frame of the image, which corresponds to the spatial area where resin flows, wets, and fills. By limiting the observation area 201 to the mold projection area, the analysis focuses on the actual resin injection range, eliminating irrelevant background interference, meeting the practical application scenarios of liquid molding processes, and providing reliable data support for process optimization.

[0073] For example, such as Figure 3 As shown, Figure 2 The observation area 201 of the image shown is divided into multiple arrayed first grid cells 303. The size of the first grid cells 303 can be set as needed. For example, the size of the first grid cells 303 can be determined based on the size of the solid structure units in the pattern layer 202.

[0074] For example, the acquired image sequence is imported into Adobe Premiere software, and the observation area is divided into a first grid cell of 3.5mm × 3.5mm using the masking tool to achieve spatially resolved flow analysis.

[0075] It should be noted that the above embodiments only exemplify the use of Adobe Premiere software to perform grid division processing on the observation area. Any image processing software with masking tools known to those skilled in the art can also be used, such as Photoshop, GIMP, Canva, and Pixlr, and are not limited thereto.

[0076] In this step, the observation area of ​​each frame in the image sequence is divided into grids. The image after grid processing is used as the target image, and step S130 can be performed on it.

[0077] S130. For each target image, perform image recognition on the target image to determine the number of fillers for the first grid cell.

[0078] Since the fiber preforms in the impregnated and unimpregnated areas exhibit different colors, the impregnated and unimpregnated areas can be distinguished based on color parameters (such as grayscale values), that is, the resin-filled and resin-unfilled areas can be distinguished.

[0079] In this step, based on image recognition technology, each target image is identified separately to determine the filling state of each first grid cell in the observation area, such as... Figure 4 As shown, the number of first grid cells 3031 that are filled can be determined by counting the number of first grid cells 3031 that are filled.

[0080] S140. Determine the resin filling rate corresponding to each frame of the image based on the filling quantity of the first grid cell.

[0081] In this step, the resin filling rate corresponding to the frame image can be determined based on the number of first grid cells filled and the total number of first grid cells in the observation area. By performing the above steps on each frame image in the image sequence, the resin filling rate of each frame image can be obtained.

[0082] When executing S120, the total number of first grid cells 303 in the observation area can be directly counted. When executing S130, the number of first grid cells 3032 with an unfilled state can be counted to obtain the number of unfilled first grid cells. The sum of the number of filled first grid cells and the number of unfilled first grid cells is the total number of first grid cells in the observation area.

[0083] The resin filling rate determination method provided in this application standardizes and discretizes the observation area of ​​each frame in an image sequence into multiple grid units, identifies the filling quantity of the first grid unit in each frame, and calculates the resin filling rate based on the ratio between the filling quantity of the first grid unit and the total number of the first grid units in the observation area. The quantification method is intuitive and uniform, avoiding the errors of traditional rough estimation and improving the accuracy of resin filling rate calculation. At the same time, the calculation is based on multiple frames in the image sequence, which can capture the dynamic process of resin filling in real time, providing continuous and reliable basic data for subsequent filling parameter adjustment.

[0084] In some embodiments, such as Figure 5 As shown, before S120, the method may further include the following steps: S150~S160.

[0085] S150, in response to the user's operation of selecting a region in the reference frame image using a selection box, determine the observation area of ​​the reference frame image.

[0086] The reference frame image is the initial frame image in the image sequence that is in an uninfused state. As an example, resin infusion and image acquisition are performed synchronously. The time corresponding to the initial frame image of the image sequence (i.e., the 0th frame image) is the start time of resin infusion, denoted as "time 0", at which point the resin is still in an uninfused state.

[0087] In this step, the user uses the selection box to select a region in the reference frame image. For example, the user selects the projection area of ​​the mold cavity in the reference frame image as the selection area and uses the projection area of ​​the mold cavity in the reference frame image as the observation area.

[0088] S160 reuses the location information of the observation area of ​​the reference frame image to the remaining images in the image sequence other than the reference frame image, as the observation area of ​​the remaining images.

[0089] In this step, based on the location information of the observation area of ​​the reference frame image, the region at the same location in the remaining images of the image sequence is determined as the observation area of ​​the remaining images.

[0090] It should be noted that in this embodiment, the initial frame image is used as the reference frame image, which is suitable for simultaneous image recognition and analysis during resin infusion, thereby obtaining the resin filling rate corresponding to the current frame image, i.e., the real-time resin filling rate. For situations where image recognition and analysis are performed after resin infusion has continued for a period of time or after infusion is completed, in addition to selecting the initial frame image as the reference frame image, any frame image other than the initial frame image in the image sequence can also be selected as the reference frame image.

[0091] The resin filling rate determination method provided in this application first selects the observation area in the reference frame image, and then reuses the position information of the observation area in the remaining multiple frames. This eliminates the need to individually calibrate the observation area for each frame, significantly simplifying the operation process and reducing manual intervention costs. Simultaneously, a unified observation area helps improve the consistency of the calculation benchmark across all frames in the image sequence, avoiding observation range deviations caused by frame-by-frame calibration. This improves the comparability and continuity of the filling rate data corresponding to each frame, providing a stable data foundation for subsequent dynamic analysis, and is particularly suitable for efficient processing scenarios involving batch image data.

[0092] In some embodiments, prior to "performing image recognition on the target image", the method may further include the following steps:

[0093] Each frame of the image, after being processed by grid division, is converted to grayscale to obtain a grayscale image;

[0094] Select the reference frame image as the background image, remove the background image from the grayscale image, and obtain the target image.

[0095] The resin filling rate determination method provided in this application first unifies the image data dimension through grayscale conversion, converting the color image into a grayscale image to reduce the influence of color noise and enhance the grayscale contrast between the filled area and the background, which helps to simplify the computational complexity of subsequent filling state recognition. Then, using the unfilled reference frame image as the background image, the background interference is effectively eliminated, and net image data reflecting the real filling behavior of the resin is obtained, which improves the accuracy of filling state recognition, avoids misjudgment caused by background noise, and lays the foundation for accurate judgment of the filling state of subsequent grid cells.

[0096] As an example, ImageJ software can be used to desaturate each frame of an image sequence, converting the original color image (RGB format) into a grayscale image to reduce the impact of color noise and enhance the grayscale contrast between the filled area and the background.

[0097] In some embodiments, the fill state of the first grid cell includes filled and unfilled, correspondingly, such as Figure 6 As shown, S130 may include the following steps: S131~S133.

[0098] S131. Obtain the grayscale value of each first grid cell in the target image.

[0099] In this step, the first grid cell may include at least one pixel cell. By obtaining the grayscale value of each pixel cell in the first grid cell, the average grayscale value can also be used as the grayscale value of the first grid cell.

[0100] S132. If the gray value of the first grid cell is greater than or equal to the first gray value threshold, the filling state of the first grid cell is determined to be filled.

[0101] Combination Figure 2 Due to light scattering, the unimpregnated fiber preform appears white, and the first grid cell in this area corresponds to a smaller grayscale value. After impregnation, the space between the fiber preform and the pattern layer is filled with resin, which reduces light scattering. The fiber preform becomes more transparent, allowing the color of the resin-filled mold to pass through, and the first grid cell in this area corresponds to a larger grayscale value.

[0102] In this step, combined Figure 4 The first grid cell with a grayscale value greater than or equal to a first grayscale threshold is marked as filled. Correspondingly, the first grid cell with a grayscale value less than the first grayscale threshold is marked as unfilled.

[0103] S133. Determine the number of first grid cells to be filled based on the number of first grid cells that are filled.

[0104] In this step, the number of first grid cells in the filled state is counted to determine the number of cells in the first grid.

[0105] S140 may include the following steps: S141.

[0106] S141. Determine the resin filling rate based on the number of first grid cells filled and the total number of first grid cells in the observation area.

[0107] In this step, the ratio of the number of first grid cells filled to the total number of first grid cells in the observation area is calculated, and this ratio is determined as the resin filling rate.

[0108] As an example, the image acquired at the 10th second of resin infusion was analyzed to determine that the number of first grid cells filled was 386, the total number of first grid cells in the observation area was 1048, and the resin filling rate corresponding to this frame image was 36.83%.

[0109] As an example, the image acquired at the 15th second of resin infusion was analyzed to determine that the number of first grid cells filled was 480, the total number of first grid cells in the observation area was 1048, and the resin filling rate corresponding to this frame image was 45.80%.

[0110] The resin filling rate determination method provided in this application uses the comparison result of the gray value of the first grid cell and the first gray value threshold as the judgment basis. It can quickly complete the statistics of the filling quantity of the first grid cell. The ratio of the filling quantity of the first grid cell to the total number of the first grid cells in the observation area is used as the resin filling rate. The logic is simple and the operation is strong. Data can be output quickly without complex algorithms, taking into account both calculation efficiency and basic accuracy.

[0111] In some embodiments, the fill state of the first grid cell includes fully filled, partially filled, and unfilled. (Combined) Figure 2 Unimpregnated fiber preforms appear white, and the first grid unit in this area corresponds to a smaller grayscale value. Fully impregnated fiber preforms have resin filling the space between the fiber preform and the pattern layer, which reduces light scattering and makes the fiber preform more transparent, allowing the color of the resin-filled mold to pass through. The first grid unit in this area corresponds to a larger grayscale value. Partially impregnated fiber preforms have a transparency level in between, and the first grid unit in this area also corresponds to a grayscale value in between.

[0112] Accordingly, such as Figure 7 As shown, S130 may include the following steps: S231~S236.

[0113] S231. Obtain the grayscale value of each first grid cell in the target image.

[0114] This step is the same as S131. For details, please refer to the explanation in S131. It will not be repeated here.

[0115] S232. If the gray value of the first grid cell is greater than or equal to the second gray value threshold, the filling state of the first grid cell is determined to be fully filled.

[0116] The second grayscale threshold is greater than the first grayscale threshold.

[0117] In this step, the gray value of the first grid cell is compared with the second gray threshold. The first grid cell whose gray value is greater than or equal to the second gray threshold is marked as fully filled.

[0118] S233. Determine the number of fully filled first grid cells based on the number of first grid cells with a fully filled state.

[0119] In this step, the number of first grid cells that are fully filled is counted to determine the number of fully filled first grid cells.

[0120] S234. If the gray value of the first grid cell is greater than or equal to the first gray value threshold and less than the second gray value threshold, the filling state of the first grid cell is determined to be partially filled.

[0121] The first grayscale threshold is less than the second grayscale threshold.

[0122] In this step, the grayscale value of the first grid cell is compared with a first grayscale threshold and a second grayscale threshold. The first grid cell whose grayscale value is greater than or equal to the first grayscale threshold and less than the second grayscale threshold is marked as partially filled. Correspondingly, the first grid cell whose grayscale value is less than the first grayscale threshold is marked as unfilled.

[0123] The area where the first grid cell is partially filled corresponds to the area where the resin flow front is located. The resin flow front is in a transitional state, with longitudinal flow in the groove area being dominant and lateral penetration of the fiber preform as auxiliary.

[0124] S235. Divide the first grid cell, which is partially filled, into multiple second grid cells.

[0125] In this step, the first grid cell, which is partially filled, is further divided into multiple second grid cells of smaller size.

[0126] In some embodiments, S235 may include the following steps: calculating the edge complexity of the resin-filled region in the current frame image; and determining the size of the second grid cell in the next frame image based on the edge complexity, wherein the size of the second grid cell is negatively correlated with the edge complexity.

[0127] Among them, edge complexity refers to the quantitative index of the irregularity and detail richness of the outline of the resin-filled area.

[0128] For example, the method for calculating edge complexity may include: extracting the edge contour of the resin-filled region, calculating the total length of the effective edge contour of the filled region, calculating the perimeter of the minimum enclosing rectangle of the filled region, and determining the edge complexity as the ratio between the total length of the effective contour and the perimeter of the minimum enclosing rectangle.

[0129] For example, the method for calculating edge complexity may also include: performing polygon approximation on the edge contour, filtering out inflection points in the contour, where an inflection point is a point where the angle between adjacent line segments is <120° or >240°, counting the number of inflection points N, and determining the complexity as the ratio of the total length of the effective contour to the number of inflection points N. The greater the edge complexity, the denser the edge details.

[0130] In this embodiment, the size of the second grid cell is dynamically adjusted according to the edge complexity of the resin-filled area. Specifically, a smaller second grid cell is used when the edge is complex, which helps improve recognition accuracy; a larger second grid cell is used when the edge is simple, which helps improve processing efficiency. This avoids the contradiction between insufficient accuracy or wasted resources due to a fixed-size grid, achieving a dynamic balance between computational accuracy and processing speed, and optimizing the allocation of computational resources.

[0131] In some embodiments, S235 may further include the following steps: calculating the gray-level gradient magnitude of the resin-filled region in the current frame image; determining the size of the second grid cell in the next frame image based on the gray-level gradient magnitude, wherein the size of the second grid cell is negatively correlated with the gray-level gradient magnitude.

[0132] Gray-scale gradient magnitude is a quantitative indicator of the degree of gray-scale change of a pixel. The gradient magnitude at the edge of the resin-filled area and the gray-scale transition area is significantly higher than that in the fully filled area.

[0133] For example, the method for calculating the grayscale gradient magnitude may include: extracting the grayscale pixel matrix corresponding to the resin-filled area (or extracting only the grayscale pixel matrix in a partial filling area to reduce invalid calculations), using the Sobel operator to calculate the gradient components in the x-direction (horizontal) and y-direction (vertical) respectively, and then calculating the gradient magnitude of each pixel based on the gradient components in the x and y directions, and further calculating the mean or maximum value of the gradient magnitudes of all pixels in the partial filling area, and using it as the grayscale gradient magnitude corresponding to the current frame image.

[0134] In this embodiment, the size of the second grid cell is dynamically adjusted according to the grayscale gradient amplitude of the resin-filled area. Specifically, a smaller second grid cell is used when the grayscale gradient amplitude is large, which is beneficial to improving recognition accuracy; a larger second grid cell is used when the grayscale gradient amplitude is small, which is beneficial to improving processing efficiency. This avoids the contradiction between insufficient accuracy or wasted resources of fixed-size grids, achieving a dynamic balance between computational accuracy and processing speed, and optimizing the allocation of computational resources.

[0135] S236. Determine the number of cells to be filled in the second grid cell based on the gray value of the second grid cell.

[0136] The method for determining the grayscale value of the second grid cell is similar to that for determining the grayscale value of the first grid cell. The grayscale value of the second grid cell may include at least one pixel cell. The average grayscale value of at least one pixel cell may be used as the grayscale value of the second grid cell, or the median grayscale value of at least one pixel cell may be used as the grayscale value of the second grid cell, or the maximum (or minimum) grayscale value of at least one pixel cell may be used as the grayscale value of the second grid cell.

[0137] In this step, the grayscale value of the second grid cell is compared with the third threshold. Second grid cells with grayscale values ​​greater than or equal to the third grayscale threshold are marked as filled, thus determining the number of filled second grid cells. Correspondingly, second grid cells with grayscale values ​​less than the third grayscale threshold are marked as unfilled.

[0138] S140 may include the following steps: S241~S242.

[0139] S241. Determine the area of ​​the resin-filled region based on the number of fully filled first grid units and the number of filled second grid units.

[0140] In this step, the first area of ​​the fully filled region corresponding to the first grid unit can be determined based on the number of fully filled first grid units and the size specifications of the first grid units; the second area of ​​the actual filled region in the partially filled region can be determined based on the number of filled second grid units and the size specifications of the second grid units; by calculating the sum of the first area and the second area, the area of ​​the resin-filled region can be obtained.

[0141] In some embodiments, S241 may include the following step: determining the area of ​​the resin-filled region based on the number of fully filled first grid cells, the number of filled second grid cells, the area of ​​the first grid cell, and the area of ​​the second grid cell.

[0142] The dimensions of the first grid cell may include length and width, and the area of ​​the first grid cell can be determined by the product of its length and width; alternatively, the dimensions of the first grid cell may include its area. Similarly, the dimensions of the first grid cell may also include length and width, and the area of ​​the second grid cell can be determined by the product of its length and width; alternatively, the dimensions of the second grid cell may include its area.

[0143] In this embodiment, the first area of ​​the fully filled region corresponding to the first grid unit can be determined based on the number of fully filled first grid units and the area of ​​the first grid unit; the second area of ​​the actual filled region in the partially filled region can be determined based on the number of filled second grid units and the area of ​​the second grid unit. The sum of the first and second areas yields the area of ​​the resin-filled region. Incorporating the areas of the first and second grid units into the calculation of the filled region area overcomes the logical deficiency of relying solely on the number of grid units to determine the equivalence of contributions from different grid sizes. By quantifying the actual area of ​​different grid units, the calculation basis for the filled region area becomes more comprehensive and logically rigorous, further improving the accuracy of the fill rate calculation.

[0144] S242. Determine the resin filling rate based on the area of ​​the resin-filled region and the area of ​​the observation region.

[0145] In this step, the ratio of the area of ​​the resin-filled region to the area of ​​the observation region is determined as the resin filling rate.

[0146] In other embodiments, the second grid cell in the filled state can be further subdivided into a fully filled second grid cell and a partially filled second grid cell. The second grid cell in the partially filled state can also be divided into a third grid cell of a smaller size, and the number of third grid cells in the filled state can be counted. This process continues until the smallest grid cell contains only one pixel cell, and the number of pixel cells in the filled state is counted. Based on the number of pixel cells in the filled state and the total number of pixel cells in the observation area, the resin filling rate is determined.

[0147] The resin filling rate determination method provided in this application refines the filling state of the first grid unit into fully filled, partially filled, and unfilled, breaking through the limitation of the traditional binary judgment that ignores the partially filled area. It accurately captures the transition state of the resin flow front. At the same time, it further subdivides the partially filled first grid unit (divides it into a second grid unit) to further explore the actual filling situation of the partially filled area, greatly reducing the calculation error caused by partial filling, realizing high-precision quantification of resin filling rate, and solving the problem of insufficient accuracy caused by ignoring partial filling in the traditional method.

[0148] In some embodiments, the method further includes the following steps: determining a filling rate sequence based on the resin filling rate and timestamp information corresponding to each frame image; and determining the instantaneous flow rate of the resin during resin infusion based on the filling rate sequence.

[0149] Each image frame also includes a timestamp, and all frames in the image sequence are ordered chronologically. The fill rate sequence shows the relationship between resin fill rate and time. The fill change rate represents the change in resin fill rate per unit time.

[0150] As the filling process progresses, the resin filling rate gradually increases, and the resin filling distance also gradually increases. Due to the increase in resin flow resistance, the corresponding filling change rate gradually decreases, and the flow rate change curve shows a downward trend.

[0151] In this embodiment, combined with Figure 8Based on the resin filling rate and timestamps of the acquired images, a filling rate sequence can be obtained. Further, a filling fitting curve (with filling rate on the ordinate and time on the abscissa) can be generated. By performing time differentiation on the filling fitting curve, a flow rate change curve (with filling change rate on the ordinate and time on the abscissa) can be obtained. Alternatively, based on the filling rates corresponding to two adjacent frames, the filling rate change value between adjacent frames can be determined. Further, based on the filling rate change value and time difference between adjacent frames, a filling change rate sequence can be obtained, which includes multiple filling change rate data. Based on the filling change rate sequence, a resin flow rate change curve during the resin infusion process can be fitted. Based on the flow rate change curve, the filling change rate and filling rate corresponding to the next frame can be predicted.

[0152] The instantaneous flow rate corresponding to the latest frame image can also be obtained based on the fill rate corresponding to the previous frame image, the fill rate corresponding to the previous frame image, and the time difference between the two frames. This is the real-time instantaneous flow rate.

[0153] The resin filling rate determination method provided in this application embodiment is based on the filling rate data and timestamp information corresponding to the acquired image. It calculates the filling change rate sequence and further quantifies the instantaneous flow rate, so that the filling rate data is transformed from a static numerical level to a dynamic flow rate index. Without the need to install an additional flow rate sensor, it can realize real-time and non-invasive monitoring of the instantaneous flow rate of resin, reduce equipment costs, and provide key feedback parameters for the dynamic control of the resin filling process.

[0154] In some embodiments, the method further includes the following steps: determining the resin flow rate change curve during resin infusion based on the filling rate sequence; and predicting the time required for the resin to completely fill the observation area based on the flow rate change curve.

[0155] Referring to the previous embodiment, the resin flow rate change curve during the resin infusion process is obtained according to the filling rate sequence. By integrating the flow rate change curve, the time corresponding to the integral result being equal to 1 is the time required for the resin to completely fill the observation area, i.e., the predicted filling time.

[0156] The resin filling rate determination method provided in this application constructs a flow rate change curve based on the filling rate change sequence, thereby achieving accurate prediction of the complete filling time. This provides forward-looking data support for filling process planning and avoids process defects caused by blindly waiting or premature operation. At the same time, the flow rate change curve can intuitively reflect the stability of the filling process, providing data reference for process optimization and further improving the consistency of production efficiency and part molding quality.

[0157] Based on the resin filling rate determination method provided in the above embodiments, this application also provides specific implementation methods of the resin filling rate determination device. Please refer to the following embodiments.

[0158] First see Figure 9 The resin injection filling rate determination device 900 provided in this application embodiment includes: an acquisition module 901, a division module 902, a first determination module 903, and a second determination module 904.

[0159] The acquisition module 901 is used to acquire an image sequence of the resin pouring process in the mold cavity, the image sequence including multiple frames of images;

[0160] The partitioning module 902 is used to divide the observation area of ​​each frame image into multiple first grid units to obtain the target image. The observation area is the projection area of ​​the mold cavity in each frame image.

[0161] The first determining module 903 is used to perform image recognition on each target image and determine the number of fillers for the first grid cell.

[0162] The second determining module 904 is used to determine the resin filling rate corresponding to each frame of image based on the filling quantity of the first grid cell.

[0163] The resin filling rate determination device provided in this application standardizes and discretizes the observation area of ​​each frame in an image sequence into multiple grid units, identifies the filling quantity of the first grid unit in each frame, and calculates the resin filling rate based on the ratio between the filling quantity of the first grid unit and the total number of the first grid units in the observation area. The quantification method is intuitive and uniform, avoiding the errors of traditional rough estimation and improving the accuracy of resin filling rate calculation. At the same time, the calculation is based on multiple frames in the image sequence, which can capture the dynamic process of resin filling in real time, providing continuous and reliable basic data for subsequent filling parameter adjustment.

[0164] In some embodiments, the device may further include a selection module.

[0165] The bounding box module is used to divide the observation area of ​​each frame image into multiple grid units according to the preset grid specifications. Before obtaining the target image, in response to the user's operation of using the bounding box to select the area in the reference frame image, the observation area of ​​the reference frame image is determined. The reference frame image is the initial frame image in the image sequence that is in an uninflated state.

[0166] The bounding box module is also used to reuse the location information of the observation area of ​​the reference frame image to the remaining images in the image sequence other than the reference frame image, as the observation area of ​​the remaining images.

[0167] In some embodiments, the apparatus may further include a preprocessing module.

[0168] The preprocessing module is used to perform grayscale conversion on each frame of the image after grid division before image recognition is performed on the target image, so as to obtain a grayscale image.

[0169] The preprocessing module is also used to select a reference frame image as a background image, remove the background image from the grayscale image, and obtain the target image.

[0170] In some embodiments, the filling state of the first grid cell includes filled and unfilled. The first determining module is used to perform image recognition on the target image and determine the filling quantity of the first grid cell, including: obtaining the gray value of each first grid cell in the target image; determining that the filling state of the first grid cell is filled when the gray value of the first grid cell is greater than or equal to a first gray value threshold; and determining the filling quantity of the first grid cell based on the number of first grid cells with the filling state of filled.

[0171] The second determining module is used to determine the resin filling rate corresponding to each frame of image based on the filling quantity of the first grid cell, including: determining the resin filling rate based on the filling quantity of the first grid cell and the total number of the first grid cells in the observation area.

[0172] In some embodiments, the filling state of the first grid cell includes fully filled, partially filled, and unfilled. The first determining module is used to perform image recognition on the target image and determine the filling quantity of the first grid cell, including: obtaining the gray value of each first grid cell in the target image; determining that the filling state of the first grid cell is fully filled when the gray value of the first grid cell is greater than or equal to a second gray value threshold; determining the fully filled quantity of the first grid cell based on the number of first grid cells with fully filled filling states; and determining that the filling state of the first grid cell is partially filled when the gray value of the first grid cell is greater than or equal to a first gray value threshold and the gray value is less than a second gray value threshold, wherein the first gray value threshold is less than the second gray value threshold; dividing the first grid cell with partially filled filling states into a plurality of second grid cells; and determining the filling quantity of the second grid cells based on the gray values ​​of the second grid cells.

[0173] The second determining module is used to determine the resin filling rate corresponding to each frame of image based on the filling quantity of the first grid cell, including: determining the area of ​​the resin-filled region based on the full filling quantity of the first grid cell and the filling quantity of the second grid cell; and determining the resin filling rate based on the area of ​​the resin-filled region and the area of ​​the observation region.

[0174] In some embodiments, the second determining module is used to determine the area of ​​the resin-filled region based on the number of fully filled first grid cells and the number of filled second grid cells, including: determining the area of ​​the resin-filled region based on the number of fully filled first grid cells, the number of filled second grid cells, the area of ​​the first grid cell, and the area of ​​the second grid cell.

[0175] In some embodiments, the first determining module is used to divide a first grid cell with a partially filled state into a plurality of second grid cells, including: calculating the edge complexity or gray-scale gradient magnitude of the resin-filled region in the current frame image; and determining the size of the second grid cell in the next frame image based on the edge complexity or gray-scale gradient magnitude, wherein the size of the second grid cell is negatively correlated with the edge complexity or gray-scale gradient magnitude.

[0176] In some embodiments, the apparatus further includes a third determining module and a fourth determining module.

[0177] The third determining module is used to determine the fill rate sequence based on the resin fill rate and timestamp information corresponding to each frame image;

[0178] The fourth determination module is used to determine the instantaneous flow rate of the resin during the resin infusion process based on the filling rate sequence.

[0179] In some embodiments, the fourth determining module is further configured to: determine the resin flow rate change curve during resin infusion based on the filling rate sequence; and predict the time required for the resin to completely fill the observation area based on the flow rate change curve.

[0180] Figure 10 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0181] An electronic device may include a processor 1001 and a memory 1002 storing computer program instructions.

[0182] Specifically, the processor 1001 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0183] Memory 1002 may include mass storage for data or instructions. For example, and not limitingly, memory 1002 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1002 may include removable or non-removable (or fixed) media. Where appropriate, memory 1002 may be internal or external to an electronic device. In a particular embodiment, memory 1002 is a non-volatile solid-state memory.

[0184] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0185] The processor 1001 reads and executes computer program instructions stored in the memory 1002 to implement any of the resin injection filling rate determination methods in the above embodiments.

[0186] In one example, the electronic device may also include a communication interface 1003 and a bus 1004. For example, Figure 10 As shown, the processor 1001, memory 1002, and communication interface 1003 are connected through bus 1004 and complete communication with each other.

[0187] The communication interface 1003 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0188] Bus 1004 includes hardware, software, or both, that couples components of an online data flow metering device together. For example, and not limited to, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertext Transfer (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VESA Local Bus, VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 1004 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0189] Furthermore, in conjunction with the resin filling rate determination method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the resin filling rate determination methods in the above embodiments.

[0190] This application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the resin injection filling rate determination methods described in the above embodiments.

[0191] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0192] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable-ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0193] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0194] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0195] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0196] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific operation processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for determining the resin injection filling rate, characterized in that, include: Acquire an image sequence of the resin injection process within a mold cavity, the image sequence comprising multiple frames; The observation area of ​​each frame of the image is divided into multiple first grid units to obtain the target image, wherein the observation area is the projection area of ​​the mold cavity in each frame of the image; For each target image, image recognition is performed on the target image to determine the number of fillers for the first grid cell; Based on the number of cells filled in the first grid cell, the resin filling rate corresponding to each frame of the image is determined; The filling state of the first grid cell includes fully filled, partially filled, and unfilled. The step of performing image recognition on the target image to determine the filling quantity of the first grid cell includes: Obtain the grayscale value of each of the first grid cells in the target image; If the gray value of the first grid cell is greater than or equal to the second gray value threshold, the filling state of the first grid cell is determined to be fully filled. The number of fully filled first grid cells is determined based on the number of first grid cells that are fully filled. Furthermore, when the gray value of the first grid cell is greater than or equal to the first gray value threshold and the gray value is less than the second gray value threshold, the filling state of the first grid cell is determined to be partially filled, and the first gray value threshold is less than the second gray value threshold. The first grid cell, which is partially filled, is divided into multiple second grid cells; The number of cells to be filled is determined based on the grayscale value of the second grid cell. Determining the resin fill rate for each frame of the image based on the fill quantity of the first grid cell includes: The area of ​​the resin-filled region is determined based on the number of fully filled first grid cells and the number of filled second grid cells. The resin filling rate is determined based on the area of ​​the resin-filled region and the area of ​​the observation region.

2. The method for determining the resin injection filling rate according to claim 1, characterized in that, Before obtaining the target image, the method further includes dividing the observation region of each frame of the image into multiple first grid units: In response to a user's operation of selecting a region in a reference frame image using a selection box, the observation region of the reference frame image is determined, wherein the reference frame image is the initial frame image in the image sequence that is in an unperfused state; The location information of the observation area of ​​the reference frame image is reused in the remaining images of the image sequence other than the reference frame image, and is used as the observation area of ​​the remaining images.

3. The method for determining the resin injection filling rate according to claim 2, characterized in that, Prior to performing image recognition on the target image, the method further includes: Each frame of the image, after being processed by grid division, is converted to grayscale to obtain a grayscale image; The reference frame image is selected as the background image, and the background image in the grayscale image is removed to obtain the target image.

4. The method for determining the resin injection filling rate according to claim 1, characterized in that, Determining the area of ​​the resin-filled region based on the number of fully filled first grid cells and the number of filled second grid cells includes: The area of ​​the resin-filled region is determined based on the number of fully filled first grid cells, the number of filled second grid cells, the area of ​​the first grid cell, and the area of ​​the second grid cell.

5. The method for determining the resin injection filling rate according to claim 1, characterized in that, The step of dividing the first grid cell, which is in a partially filled state, into multiple second grid cells includes: Calculate the edge complexity or grayscale gradient magnitude of the resin-filled region in the current frame image; The size of the second grid cell in the next frame image is determined based on the edge complexity or grayscale gradient magnitude, and the size of the second grid cell is negatively correlated with the edge complexity or grayscale gradient magnitude.

6. The method for determining the resin injection filling rate according to claim 4 or 5, characterized in that, The method further includes: Based on the resin fill rate and timestamp information corresponding to each frame of the image, determine the fill rate sequence; Based on the filling rate sequence, the instantaneous flow rate of the resin during resin infusion is determined.

7. The method for determining the resin injection filling rate according to claim 6, characterized in that, The method further includes: Based on the filling rate sequence, the resin flow rate change curve during resin infusion is determined; Based on the flow rate change curve, the time required for the resin to completely fill the observation area is predicted.

8. A resin filling rate determination device, characterized in that, include: The acquisition module is used to acquire an image sequence of the resin injection process in the mold cavity, the image sequence including multiple frames of images; A segmentation module is used to divide the observation area of ​​each frame of the image into multiple first grid units to obtain a target image, wherein the observation area is the projection area of ​​the mold cavity in each frame of the image; The first determining module is used to perform image recognition on each target image to determine the number of fillers in the first grid cell; The second determining module is used to determine the resin filling rate corresponding to each frame of the image based on the filling quantity of the first grid unit; The filling state of the first grid cell includes fully filled, partially filled, and unfilled. The first determining module is further configured to: obtain the gray value of each first grid cell in the target image; determine that the filling state of the first grid cell is fully filled when the gray value of the first grid cell is greater than or equal to a second gray value threshold; and determine the number of fully filled first grid cells based on the number of first grid cells with a fully filled filling state. Furthermore, when the gray value of the first grid cell is greater than or equal to the first gray value threshold and less than the second gray value threshold, the filling state of the first grid cell is determined to be partially filled, and the first gray value threshold is less than the second gray value threshold; the first grid cell with the partially filled filling state is divided into multiple second grid cells; and the filling quantity of the second grid cells is determined according to the gray value of the second grid cells. The second determining module is further configured to: determine the area of ​​the resin-filled region based on the number of fully filled first grid cells and the number of filled second grid cells; and determine the resin filling rate based on the area of ​​the resin-filled region and the area of ​​the observation region.

9. An electronic device, characterized in that, The electronic device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the resin injection filling rate determination method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the resin injection filling rate determination method as described in any one of claims 1-7.

11. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device is able to perform the resin injection filling rate determination method as described in any one of claims 1-7.

Images