CN-121998988-A - Method, device, equipment, medium and product for determining resin filling rate

CN121998988ACN 121998988 ACN121998988 ACN 121998988ACN-121998988-A

Abstract

The application provides a method, a device, equipment, a medium and a product for determining resin filling rate, and relates to the technical field of liquid molding. According to the method, the observation area of each frame of image in the image sequence is standardized and discretized into a plurality of grid cells, the filling quantity of the first grid cells in each frame of image is identified, the resin filling rate is calculated according to the ratio between the filling quantity of the first grid cells and the total quantity of the first grid cells in the observation area, the quantization mode is visual and uniform, the error of traditional rough estimation is avoided, the accuracy of resin filling rate calculation is improved, meanwhile, the observation area is limited to be a mould projection area, so that analysis focuses on the actual resin filling range, irrelevant background interference is eliminated, the actual application scene of a liquid molding process is met, and reliable data support is provided for process optimization.

Inventors

HAN XIN
LI MENGYU
XIE GUOXIN
LUO JIANBIN

Assignees

清华大学

Dates

Publication Date: 20260508
Application Date: 20260409

Claims (13)

1. A resin infusion filling rate determination method, characterized by comprising: Acquiring an image sequence of the resin in the pouring process in a die cavity, wherein the image sequence comprises a plurality of frames of images; Dividing an observation area of each frame of the image into a plurality of first grid units to obtain a target image, wherein the observation area is a projection area of the mold cavity in each frame of the image; For each target image, carrying out image recognition on the target image, and determining the filling quantity of the first grid cells; and determining the filling rate of the resin corresponding to each frame of the image according to the filling quantity of the first grid cells.
2. The resin infusion filling rate determination method according to claim 1, wherein the method further comprises, before dividing the observation area of each frame of the image into a plurality of grid cells according to a preset grid specification to obtain the target image: determining an observation area of a reference frame image in response to a user selecting an area in the reference frame image by using a frame selection frame, wherein the reference frame image is an initial frame image in an unfilled state in the image sequence; And multiplexing the position information of the observation area of the reference frame image to the residual image except the reference frame image in the image sequence as the observation area of the residual image.
3. The resin infusion filling rate determination method according to claim 2, characterized in that before the image recognition of the target image, the method further comprises: carrying out graying conversion treatment on each frame of the image subjected to the grid division treatment to obtain a gray image; And selecting the reference frame image as a background image, and removing the background image in the gray level image to obtain the target image.
4. The resin infusion filling rate determination method according to claim 1, wherein the filling state of the first grid cell includes filled and unfilled, the image recognition of the target image, determining the filling number of the first grid cell, includes: acquiring a gray value of each first grid cell in the target image; Determining that the filling state of the first grid cell is filled under the condition that the gray value of the first grid cell is larger than or equal to a first gray threshold value; Determining the filling quantity of the first grid cells according to the quantity of the first grid cells with filled states; the determining the filling rate of the resin corresponding to each frame of the image according to the filling quantity of the first grid unit comprises the following steps: and determining the resin filling rate according to the filling quantity of the first grid cells and the total quantity of the first grid cells in the observation area.
5. The resin infusion filling rate determination method according to claim 1, wherein the filling state of the first grid cell includes full filling, partial filling, and unfilled, the image recognition of the target image, determining the filling number of the first grid cell, includes: acquiring a gray value of each first grid cell in the target image; Determining that the filling state of the first grid unit is completely filled under the condition that the gray value of the first grid unit is larger than or equal to a second gray threshold value; determining the total filling quantity of the first grid cells according to the quantity of the first grid cells with the filling states of being completely filled; 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 threshold and the gray value is less than the second gray threshold, the first gray threshold being less than the second gray threshold; dividing the first grid cells with the filling state being partially filled into a plurality of second grid cells; Determining the filling quantity of the second grid cells according to the gray values of the second grid cells; the determining the filling rate of the resin corresponding to each frame of the image according to the filling quantity of the first grid unit comprises the following steps: determining the area of a resin filling area according to the total filling quantity of the first grid cells and the filling quantity of the second grid cells; And determining the resin filling rate according to the area of the resin filling area and the area of the observation area.
6. The method of determining a filling rate of resin infusion according to claim 5, wherein determining an area of the resin filled region based on the total filling amount of the first grid cells and the filling amount of the second grid cells comprises: And determining the area of the resin filling area according to the total filling quantity of the first grid cells, the filling quantity of the second grid cells, the area of the first grid cells and the area of the second grid cells.
7. The resin infusion filling rate determination method according to claim 5, wherein the dividing the first grid cell, the filling state of which is partially filled, into a plurality of second grid cells includes: calculating the edge complexity or gray gradient amplitude of a resin filling area in the current frame image; and determining the size of the second grid unit in the next frame of image according to the edge complexity or the gray gradient amplitude, wherein the size of the second grid unit is inversely related to the edge complexity or the gray gradient amplitude.
8. The resin infusion filling rate determination method according to any one of claims 4 to 7, characterized in that the method further comprises: determining a filling rate sequence according to the resin filling rate and the time stamp information corresponding to the images of each frame; and determining the instantaneous flow rate of the resin in the resin infusion process according to the filling rate sequence.
9. The resin infusion filling rate determination method according to claim 8, characterized by further comprising: determining a flow rate change curve of the resin in the resin infusion process according to the filling rate sequence; Based on the flow rate profile, the time required for the resin to completely fill the observation region is predicted.
10. A resin filling rate determining apparatus, comprising: the acquisition module is used for acquiring an image sequence of the resin in the pouring process in the die cavity, wherein the image sequence comprises a plurality of frames of images; the dividing module is used for dividing an observation area of each frame of the image into a plurality of first grid units to obtain a target image, wherein the observation area is a projection area of the mold cavity in each frame of the image; the first determining module is used for carrying out image recognition on each target image and determining the filling quantity of the first grid cells; and the second determining module is used for determining the resin filling rate corresponding to each frame of the image according to the filling quantity of the first grid cells.
11. An electronic device comprising a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the resin infusion fill rate determination method according to any one of claims 1-9.
12. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon computer program instructions, which when executed by a processor, implement the resin infusion filling rate determination method according to any of claims 1-9.
13. A computer program product, characterized in that instructions in the computer program product, when executed by a processor of an electronic device, enable the electronic device to perform the resin infusion fill rate determination method according to any one of claims 1-9.

Description

Method, device, equipment, medium and product for determining resin filling rate Technical Field The application belongs to the technical field of liquid molding, and particularly relates to a method, a device, equipment, a medium and a product for determining a resin filling rate. Background In the liquid molding process, analysis of resin infusion flow behavior is critical to optimizing the process and improving the molding quality. The related technology relies on manual observation or simple image comparison, the filling progress is simply estimated, the accurate quantitative analysis of the resin pouring flow behavior cannot be realized, and the actual requirements of process refinement and optimization are difficult to meet. Disclosure of Invention The embodiment of the application provides a method, a device, equipment, a medium and a product for determining the filling rate of resin pouring, wherein an observation area of continuous frame images is standardized and discretized into a plurality of grid cells, the filling rate is calculated by the ratio of the number of filled grid cells to the number of total grid cells, the quantization mode is visual and uniform, the error of traditional rough estimation is avoided, the accuracy of calculating the filling rate is improved, meanwhile, the observation area is limited to a mould projection area, so that the analysis is focused on the actual pouring range of the resin, irrelevant background interference is eliminated, the actual application scene of a liquid molding process is met, and reliable data support is provided for process optimization. In a first aspect, a method for determining a filling rate of resin infusion provided by an embodiment of the present application includes: acquiring an image sequence of the resin in the pouring process in the die cavity, wherein the image sequence comprises a plurality of frames of images; dividing an observation area of each frame of image into a plurality of first grid units to obtain a target image, wherein the observation area is a projection area of a mold cavity in each frame of image; for each target image, carrying out image recognition on the target image, and determining the filling quantity of the first grid cells; and determining the filling rate of the resin corresponding to each frame of image according to the filling quantity of the first grid cells. In some embodiments, the method further includes, before dividing the observation area of each frame of image into a plurality of grid cells according to a preset grid specification to obtain the target image: Determining an observation area of a reference frame image, which is an initial frame image in an image sequence in a non-perfusion state, in response to a user's operation of selecting a frame in the reference frame image by using a frame selection frame; the position information of the observation region of the reference frame image is multiplexed to the remaining images other than the reference frame image in the image sequence as the observation regions of the remaining images. In some embodiments, prior to image recognition of the target image, the method further comprises: carrying out gray conversion treatment on each frame of image subjected to grid division treatment to obtain a gray image; and selecting the reference frame image as a background image, and removing the background image in the gray level image to obtain a target image. In some embodiments, the filling state of the first grid cell includes filled and unfilled, image recognition is performed on the target image, and determining the filling amount of the first grid cell includes: acquiring a gray value of each first grid unit in the target image; Determining that the filling state of the first grid cell is filled under the condition that the gray value of the first grid cell is larger than or equal to a first gray threshold value; determining the filling quantity of the first grid cells according to the filling state which is the quantity of the filled first grid cells; determining a resin filling rate corresponding to each frame of image according to the filling quantity of the first grid cells, wherein the method comprises the following steps: and determining the resin filling rate according to the filling quantity of the first grid cells and the total quantity of the first grid cells in the observation area. In some embodiments, the fill state of the first grid cell includes full fill, partial fill, and no fill, image recognition of the target image, and determining the fill number of the first grid cell includes: acquiring a gray value of each first grid unit in the target image; Determining that the filling state of the first grid cell is completely filled under the condition that the gray value of the first grid cell is larger than or equal to the second gray threshold value; Determining the total filling quantity of the first grid cells according to the quantity of