Two-fold box machine and glue path detection method thereof

Abstract

The application is suitable for the technical field of box pasting machine, and particularly relates to a two-fold box pasting machine and a glue path detection method thereof. The method comprises the following steps: collecting original images of a first glue path and original images of a second glue path, and processing the original images to obtain a binary image of the first glue path and a binary image of the second glue path; calculating and measuring the binary image of the first glue path and the binary image of the second glue path to obtain an L-shaped inflection point position deviation value and a width consistency deviation value, a U-shaped center point position deviation value and a parallelism deviation value, and obtain first glue path quality data and second glue path quality data; obtaining a occlusion relationship state according to the spatial occlusion relationship between a longitudinal glue line segment and a U-shaped opening end; and obtaining a glue path detection result according to the first glue path quality data, the second glue path quality data and the occlusion relationship state. The two-fold box pasting machine and the glue path detection method thereof can solve the problem of poor product forming regularity caused by position and size deviation of the glue path.

Description

Technical Field

[0001] This application belongs to the field of box gluing machine technology, and particularly relates to a two-fold box gluing machine and its glue path detection method. Background Technology

[0002] Two-fold gluing machines are important pieces of equipment in the packaging and printing industry. They are mainly used to apply glue, fold, and bond printed cardboard to form boxes of various shapes.

[0003] When using two-fold gluing machines in related technologies for mass production, the products produced often exhibit issues such as skewed sides, uneven bottoms, and raised corners that prevent proper adhesion after folding. Furthermore, existing gluing circuit inspection methods for two-fold gluing machines suffer from inaccurate quantification of glue circuit position and dimensional deviations, ineffective detection of glue circuit interlocking relationships, and low efficiency and subjectivity of traditional inspection methods. This results in poor product molding regularity, insufficient adhesion reliability, and ultimately, fluctuations in product quality. Summary of the Invention

[0004] This application provides a two-fold gluing machine and its glue path detection method, which can solve the problems of poor product molding regularity and insufficient bonding reliability caused by the inability to accurately quantify the deviation of glue path position and size, and the failure to effectively detect the glue path co-interlocking relationship.

[0005] In a first aspect, embodiments of this application provide a method for detecting the glue path of a two-fold gluing machine, including: The original images of the first adhesive path and the second adhesive path on the unfolded flat cardboard sheet are acquired sequentially. The original images of the first adhesive path and the original images of the second adhesive path are processed respectively to obtain corresponding binarized images of the first adhesive path and the second adhesive path. The binarized image of the first adhesive path is calculated and measured to obtain the L-shaped inflection point position deviation value and the width consistency deviation value; wherein, the width consistency deviation value is obtained by measuring the transverse adhesive line segment and the longitudinal adhesive line segment; The binarized image of the second adhesive path is calculated and measured to obtain the position deviation value of the U-shaped center point and the parallelism deviation value; wherein, the parallelism deviation value is obtained by measuring the bottom adhesive line segment; The L-shaped inflection point position deviation and the width consistency deviation value are compared with the preset side adhesive path threshold to obtain the first adhesive path quality data; wherein, the first adhesive path quality data is used to indicate whether the first adhesive path is qualified. The deviation value of the U-shaped center point and the parallelism deviation value are compared with the preset bottom adhesive path threshold to obtain the second adhesive path quality data; wherein, the second adhesive path quality data is used to indicate whether the second adhesive path is qualified; The engagement relationship is obtained based on the spatial engagement relationship between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path; Based on the first adhesive path quality data, the second adhesive path quality data, and the engagement relationship status, the adhesive path detection result is obtained.

[0006] The technical solutions described in this application embodiment have at least the following technical effects: The glue path detection method for a two-fold gluing machine provided in this application involves sequentially acquiring original images of the first glue path and the second glue path on an unfolded sheet of cardboard; processing the original images of the first and second glue paths respectively to obtain corresponding binarized images of the first and second glue paths; calculating and measuring the binarized image of the first glue path to obtain the L-shaped inflection point position deviation value and the width consistency deviation value; calculating and measuring the binarized image of the second glue path to obtain the U-shaped center point position deviation value and the parallelism deviation value; and comparing the L-shaped inflection point position deviation value and the width consistency deviation value with a preset side glue path threshold to obtain the quality of the first glue path. The data is obtained by comparing the deviation values ​​of the U-shaped center point position and parallelism with the preset bottom glue path threshold. The interlocking relationship status is obtained based on the spatial interlocking relationship between the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path. Based on the glue path quality data, the second glue path quality data and the interlocking relationship status, the glue path detection results are obtained. This enables precise quantitative detection of the glue path of the two-fold gluing machine, effectively solving the problem of inaccurate quantification of glue path position and size deviation. Through effective detection of the interlocking relationship of the glue path, the interlocking situation can be detected in time, reducing the problems of poor product molding regularity and insufficient bonding reliability caused by poor interlocking relationship.

[0007] Secondly, embodiments of this application provide a glue path detection system for a two-fold gluing machine, comprising: The acquisition unit is used to sequentially acquire the original images of the first adhesive path and the second adhesive path on the unfolded flat cardboard sheet; The analysis unit is used to process the original image of the first adhesive path and the original image of the second adhesive path respectively to obtain the corresponding binarized image of the first adhesive path and the binarized image of the second adhesive path. The first processing unit is used to calculate and measure the binarized image of the first adhesive path to obtain the L-shaped inflection point position deviation value and the width consistency deviation value; wherein, the width consistency deviation value is obtained by measuring the transverse adhesive line segment and the longitudinal adhesive line segment; The second processing unit is used to calculate and measure the binarized image of the second adhesive path to obtain the position deviation value of the U-shaped center point and the parallelism deviation value; wherein, the parallelism deviation value is obtained by measuring the bottom adhesive line segment; The first comparison unit is used to compare the L-shaped inflection point position deviation value and the width consistency deviation value with a preset side adhesive path threshold to obtain first adhesive path quality data; wherein, the first adhesive path quality data is used to indicate whether the first adhesive path is qualified. The second comparison unit is used to compare the deviation value of the U-shaped center point position and the parallelism deviation value with the preset bottom adhesive path threshold to obtain the second adhesive path quality data; wherein, the second adhesive path quality data is used to indicate whether the second adhesive path is qualified; The unit is used to obtain the engagement relationship state based on the spatial engagement relationship between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path. The result unit is used to obtain the glue path detection result based on the first glue path quality data, the second glue path quality data and the engagement relationship status.

[0008] Thirdly, embodiments of this application provide a two-fold gluing machine, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method described in any of the first aspects above.

[0009] Fourthly, embodiments of this application provide a computer program product that, when running on a two-fold gluing machine, causes the two-fold gluing machine to perform the glue path detection method of the two-fold gluing machine described in any of the first aspects above.

[0010] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1This is a schematic diagram of the structure of a two-fold gluing box machine provided in one embodiment of this application; Figure 2 This is a schematic flowchart of a glue path detection method for a two-fold gluing machine provided in an embodiment of this application; Figure 3 This is a schematic diagram of the implementation process of step S200 in the glue path detection method of a two-fold gluing machine provided in an embodiment of this application; Figure 4 This is a schematic diagram of the implementation process of step S300 in the glue path detection method of a two-fold gluing machine provided in an embodiment of this application; Figure 5 This is a schematic diagram of the implementation process of step S400 in the glue path detection method of a two-fold gluing machine provided in an embodiment of this application; Figure 6 This is a schematic diagram of the implementation process of step S310 in the glue path detection method of a two-fold gluing machine provided in an embodiment of this application; Figure 7 This is a schematic diagram of the implementation process of step S410 in the glue path detection method of a two-fold gluing machine provided in an embodiment of this application; Figure 8 This is a schematic diagram of the glue path detection system of the two-fold gluing machine provided in the embodiments of this application; Figure 9 This is a schematic diagram of the control device provided in the embodiments of this application.

[0013] The following are the labeling elements in the figure: 100. Two-fold box gluing machine; 10. Frame; 20. Adhesive coating assembly; 21. Coating head; 22. Robotic arm; 30. Folding device; 31. Upper folding plate; 32. Lower folding plate; 40. Conveyor belt; 50. Drive mechanism; 6. Control device. Detailed Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0015] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0016] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0017] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0018] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0020] In related technologies, when two-fold gluing machines are used for mass production, the products produced may exhibit issues such as skewed sides, uneven bottoms, and curled corners that prevent proper adhesion after folding. Furthermore, in existing two-fold gluing machine glue path inspections, the position and size deviations of single glue paths cannot be accurately quantified, the collaborative interlocking relationship of dual glue paths is not effectively detected, and traditional inspection methods are inefficient and highly subjective. This results in poor product molding regularity, insufficient adhesion reliability, and ultimately, fluctuations in product quality.

[0021] To address the aforementioned problems, this application provides a two-fold gluing machine and its glue path detection method. In this method, original images of the first glue path and the second glue path are sequentially acquired on an unfolded sheet of cardboard. The original images of the first and second glue paths are processed to obtain corresponding binarized images of the first and second glue paths. The binarized image of the first glue path is calculated and measured to obtain the L-shaped inflection point position deviation value and the width consistency deviation value. The binarized image of the second glue path is calculated and measured to obtain the U-shaped center point position deviation value and the parallelism deviation value. The L-shaped inflection point position deviation value and the width consistency deviation value are compared with a preset side glue path threshold to obtain the first glue path quality data. The U-shaped center point position deviation value and the width consistency deviation value are then compared with a preset side glue path threshold to obtain the first glue path quality data. The center point position deviation value and parallelism deviation value are compared with the preset bottom glue path threshold to obtain the quality data of the second glue path; the interlocking relationship status is obtained based on the spatial interlocking relationship between the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path; based on the quality data of the first glue path, the quality data of the second glue path, and the interlocking relationship status, the glue path detection result is obtained, thereby enabling precise quantitative detection of the glue path of the two-fold gluing machine, effectively solving the problem of inaccurate quantification of the position and size deviation of a single glue path. Through effective detection of the interlocking relationship of the glue path, the interlocking situation can be detected in time, reducing the problems of poor product molding regularity and insufficient bonding reliability caused by poor interlocking relationship.

[0022] The glue path detection method for a two-fold gluing machine provided in this application embodiment can be applied to a two-fold gluing machine. In this case, the two-fold gluing machine is the subject of the glue path detection method for the two-fold gluing machine provided in this application embodiment. This application embodiment does not limit the specific type of two-fold gluing machine.

[0023] Please refer to the structural diagram of the two-fold gluing machine 100. Figure 1 The two-fold box gluing machine 100 may include a frame 10, an adhesive coating assembly 20, a folding device 30, a conveyor belt 40, a drive mechanism 50 for driving the conveyor belt 40, and a control device 6. The control device 6 is communicatively connected to the adhesive coating assembly 20, the folding device 30, and the drive mechanism 50. The control device 6 may be an independent module integrated inside the two-fold box gluing machine 100, or it may be an external device communicatively connected to the two-fold box gluing machine 100. The control device 6 may include a processor, such as a central processing unit, a graphics processing unit, or other types of dedicated processors. By running a computer program stored in its memory, the control device 6 is able to execute the adhesive path detection method of the two-fold box gluing machine 100 provided in this application embodiment.

[0024] Specifically, the adhesive coating assembly 20 is located at the output end of the conveyor belt 40. The adhesive coating assembly 20 may include two independent coating heads 21, corresponding to the coating positions of the first adhesive path and the second adhesive path, respectively. By precisely controlling the glue dispensing amount and movement trajectory of the coating heads 21, the width, length, and positional accuracy of the adhesive path are ensured. Alternatively, the adhesive coating assembly 20 may have only one coating head 21. Under the control of the control device 6, the coating head 21 can complete the coating tasks of the first and second adhesive paths in a time-sharing or zone-sharing manner. The coating head 21 may be mounted on a robotic arm 22, which is connected to the control device 6. The control device 6 controls the movement of the robotic arm 22 so that the coating head 21 completes the coating task under the action of the robotic arm 22. The folding device 30 is located at the output end of the adhesive coating assembly 20 and is used to fold the flat cardboard coated with adhesive paths to form a two-fold structure. The folding device 30 includes an upper folding plate 31 and a lower folding plate 32. The upper folding plate 31 and the lower folding plate 32 are arranged opposite each other and can move relative to each other. When the flat cardboard is conveyed to the position of the folding device 30, the upper folding plate 31 and the lower folding plate 32 move towards each other, folding the flat cardboard along the preset fold lines to form a two-fold structure. The conveyor belt 40 can run through the entire two-fold gluing machine 100 and is used to convey the flat cardboard. From the initial feeding position, it passes through the glue coating assembly 20, the folding device 30 and other components in sequence, and finally completes the folding operation and outputs the finished product. The drive mechanism 50 is connected to the conveyor belt 40 and provides power for the movement of the conveyor belt 40. The drive mechanism 50 can be driven by a motor. By controlling the speed and direction of the motor, the movement speed and direction of the conveyor belt 40 can be precisely controlled to ensure the accurate conveying of the flat cardboard between each station.

[0025] To better understand the glue path detection method for the two-fold gluing machine provided in this application embodiment, the specific implementation process of the glue path detection method for the two-fold gluing machine provided in this application embodiment will be described by way of example below.

[0026] Figure 2 A schematic flowchart of the glue path detection method for a two-fold box gluing machine provided in this application embodiment is shown. The glue path detection method for the two-fold box gluing machine includes: S100 sequentially acquires the original images of the first adhesive path and the second adhesive path on the unfolded flat cardboard sheet.

[0027] It can be understood that the first adhesive path is an L-shaped continuous adhesive line coated along the longitudinal edge of the cardboard, with its transverse section used for side bonding and its longitudinal section used for bonding with the subsequently formed box bottom part; the second adhesive path is a U-shaped continuous adhesive line coated at a predetermined position on the cardboard, with its two open ends used for interlocking with the longitudinal section of the first adhesive path.

[0028] For example, the original images can be acquired using an industrial camera. The industrial camera can be mounted at a specific location on a two-fold gluing machine, such as at the glue application assembly of the two-fold gluing machine, so that it can clearly and accurately capture the original images of the first and second glue paths on the unfolded flat sheet of cardboard.

[0029] In one possible implementation, before sequentially acquiring the original images of the first adhesive path and the second adhesive path on the unfolded flat cardboard sheet, step S100 includes: S101, behind the glue application unit of the box gluing machine, a first collection component corresponding to the first fold side bonding area and a second collection component corresponding to the second fold bottom bonding area are respectively set.

[0030] It is understood that both the first and second acquisition devices can be high-precision industrial cameras. By setting the positions of the first and second acquisition devices—for example, the first acquisition device could be positioned near the side-adhesion area of ​​the first fold, and the second acquisition device near the bottom-adhesion area of ​​the second fold—they can be mounted on a bracket above the conveyor belt and perpendicular to the direction of cardboard movement. The first acquisition device would face the side-adhesion area of ​​the first fold, and the second acquisition device would face the bottom-adhesion area of ​​the second fold. The side-adhesion area of ​​the first fold can be understood as the area where the side of the cardboard needs to be glued during the first fold, and the bottom-adhesion area of ​​the second fold is the area where the bottom of the cardboard needs to be glued after the second fold.

[0031] This setup ensures that the first and second acquisition units accurately capture the original images of the first and second adhesive paths, respectively, providing an accurate data foundation for subsequent image processing and adhesive path detection.

[0032] S200, process the original images of the first adhesive path and the second adhesive path respectively to obtain the corresponding binarized images of the first adhesive path and the second adhesive path.

[0033] It can be understood that the binarized image of the first adhesive path can be understood as converting the original image of the first adhesive path into an image with only black and white colors through a specific image processing algorithm, such as thresholding. The white part represents the adhesive path area, and the black part represents the background area, thus highlighting the outline and features of the first adhesive path more clearly. Similarly, the binarized image of the second adhesive path is obtained by processing the original image of the second adhesive path in the same way, and also using black and white colors to distinguish the adhesive path from the background, which facilitates the accurate calculation and measurement of various parameters of the second adhesive path in the future.

[0034] For example, obtaining the corresponding first adhesive path binarized image and second adhesive path binarized image can be achieved by performing grayscale transformation on the original images of the first adhesive path and the original images of the second adhesive path respectively to enhance the grayscale difference. Within a pre-set detection window, based on the grayscale distribution characteristics of the colloid's bright areas, adaptive segmentation thresholds are obtained for each, resulting in the initial binary images of the first adhesive path and the second adhesive path. The first adhesive path binarized image and the second adhesive path binarized image can then be obtained by performing elimination and connection processing on the initial binary images of the first adhesive path and the second adhesive path binarized image respectively.

[0035] In one possible implementation, please refer to Figure 3 S200, the original images of the first adhesive path and the second adhesive path are processed respectively to obtain corresponding binarized images of the first adhesive path and the second adhesive path, including: S210, perform grayscale transformation on the original images of the first adhesive path and the second adhesive path respectively, and enhance the grayscale difference between the bright areas of the adhesive and the background of the cardboard by adjusting the image contrast and brightness.

[0036] For example, grayscale transformation is performed on the original images of the first adhesive path and the second adhesive path respectively. When performing grayscale transformation, methods such as histogram equalization can be used to readjust the grayscale distribution of the original image, so that the pixels originally concentrated in a certain grayscale range are distributed to a wider grayscale range, thereby enhancing the grayscale difference between the bright areas of the adhesive and the background of the cardboard, making the adhesive path part more prominent in the image.

[0037] S220: For the original images of the first adhesive path and the second adhesive path after image enhancement, within a pre-set detection window, the adaptive segmentation thresholds for each are obtained based on the grayscale distribution characteristics of the highlight areas of the adhesive.

[0038] For example, within a pre-defined detection window, for the original image of the first adhesive path, the grayscale distribution of the highlighted areas of the adhesive within the window is analyzed. This includes, for example, counting the frequency of different grayscale values ​​and calculating the central tendency of the grayscale values. A threshold that can effectively separate the highlighted areas of the adhesive from the cardboard background is then determined. This threshold is the adaptive segmentation threshold for the first adhesive path. Similarly, for the original image of the second adhesive path, the same method is used. Within the corresponding detection window, the adaptive segmentation threshold for the second adhesive path is obtained based on the grayscale distribution characteristics of its highlighted areas.

[0039] Furthermore, the size and position of the detection window can be flexibly set according to actual needs. For example, it can be determined based on factors such as the width and length of the adhesive path and its distribution on the cardboard, so as to accurately capture the grayscale features of the highlighted areas of the adhesive. Obtaining the segmentation threshold in this adaptive manner, compared to using a fixed threshold, can better adapt to the grayscale variations of the adhesive path and background in different images, improving the accuracy and reliability of image segmentation.

[0040] S230, the pixels in the image are divided into foreground and background according to the adaptive segmentation threshold to obtain the initial binary image of the first adhesive path and the initial binary image of the second adhesive path; wherein, the position and size of the detection window are determined according to the preset coating path of the first adhesive path and the second adhesive path.

[0041] It can be understood that foreground and background can be understood as follows: in image processing, after adaptive segmentation thresholding, the foreground usually refers to the target area we are interested in in the image, which in the context of this application is the colloid part of the first and second glue paths. These areas are presented as white pixels in the binary image; while the background refers to other parts such as cardboard outside the colloid area, which are presented as black pixels in the binary image.

[0042] For example, obtaining the initial binary image of the first adhesive path and the initial binary image of the second adhesive path can be achieved by comparing the gray values ​​of the pixels in the image with a determined adaptive segmentation threshold, dividing the pixels into two categories: pixels with gray values ​​greater than the threshold are classified into one category (usually set to white, representing the adhesive path area), and pixels with gray values ​​less than the threshold are classified into another category (usually set to black, representing the background area), thereby obtaining the initial binary image.

[0043] S240, the initial binary image of the first adhesive path and the initial binary image of the second adhesive path are respectively processed by elimination and connection to obtain the binarized image of the first adhesive path and the binarized image of the second adhesive path.

[0044] It is understandable that the initial binary image may contain some isolated noise points or small holes within the adhesive path area. Elimination processing can remove these isolated noise points, making the image cleaner; while concatenation processing can connect some broken parts in the adhesive path area, ensuring the integrity of the adhesive path outline, ultimately resulting in a higher-quality first and second binarized adhesive path image.

[0045] For example, obtaining the first and second binarized images of the adhesive path can be achieved using morphological processing algorithms. For instance, an opening operation is first performed, which erodes small noise points in the image, followed by a dilation operation to restore the main shape of the adhesive path region and remove isolated noise points. Then, a closing operation is performed, which involves dilation followed by erosion, connecting small voids and broken sections within the adhesive path region, thus obtaining the first and second binarized images of the adhesive path. The initial binary images of the first and second adhesive paths are then processed by elimination and connection. This elimination and connection process can involve first removing small voids and discrete noise points caused by tiny bubbles or uneven reflection on the adhesive surface, and then connecting small breaks caused by image noise or minor breaks in the adhesive. This ensures that the first and second binarized images of the adhesive path accurately reflect the morphological characteristics of the actual adhesive path. For example, in the initial binary image of the first adhesive path, if there are small local holes caused by factors such as the shooting angle of the industrial camera or light reflection, the closing operation in morphological processing can effectively fill these holes, making the first adhesive path appear more continuous and complete in the image. As for the discrete noise points that may appear in the initial binary image of the second adhesive path due to uneven adhesive application, the opening operation can accurately remove them, avoiding interference from these noise points in the subsequent calculation of adhesive path parameters. This can improve connectivity and make the subsequent detection of the position, size, and cooperative interlocking relationship of the adhesive path more accurate and reliable.

[0046] S300, calculate and measure the binarized image of the first adhesive path to obtain the L-shaped inflection point position deviation value and the width consistency deviation value; wherein, the width consistency deviation value is obtained by measuring the transverse adhesive line segment and the longitudinal adhesive line segment.

[0047] The width consistency deviation value can be understood as the measurement of the width of the horizontal and vertical adhesive line segments at different positions in the binarized image of the first adhesive path, and then the difference between these width measurements is calculated. The inflection point position deviation value can be understood as the position difference value calculated by comparing the actual position of the L-shaped inflection point in the binarized image of the first adhesive path with the preset standard position.

[0048] For example, when calculating and measuring the binarized image of the first adhesive path, the position of the L-shaped inflection point is first determined, that is, the coordinates of the L-shaped inflection point are accurately located in the binarized image of the first adhesive path. Then, the coordinates are compared with the preset standard L-shaped inflection point coordinates to obtain the L-shaped inflection point position deviation value. For measuring the width consistency deviation value, the width of the transverse adhesive line segment and the longitudinal adhesive line segment of the first adhesive path are measured respectively. On the transverse adhesive line segment, multiple measurement points are selected, and the average width of these measurement points is calculated as the average width of the transverse adhesive line segment. Similarly, multiple measurement points are also selected on the longitudinal adhesive line segment, and its average width is calculated. The average width of the transverse adhesive line segment and the average width of the longitudinal adhesive line segment are compared with the preset standard width to obtain the difference between the two and the standard width, and thus obtain the width consistency deviation value.

[0049] In one possible implementation, please refer to Figure 4 S300 calculates and measures the binarized image of the first adhesive path to obtain the L-shaped inflection point position deviation value and width consistency deviation value, including: S310: Recognize the binarized image of the first adhesive path to obtain the pixel coordinates of the L-shaped inflection point.

[0050] For example, the pixel coordinates of the L-shaped inflection point can be obtained by performing edge detection on the binarized image of the first adhesive path, identifying the set of pixels along the edge of the adhesive path in the image, and then using corner detection algorithms, such as Harris corner detection or Shi-Tomasi corner detection, to accurately locate the pixel coordinates of the L-shaped inflection point from the set of edge pixels. These corner detection algorithms can determine whether a point is a corner based on the grayscale changes in the neighborhood around the pixel, and can accurately obtain its pixel coordinates for obvious corner features such as L-shaped inflection points.

[0051] In one possible implementation, please refer to Figure 6 S310, the binarized image of the first adhesive path is identified to obtain the pixel coordinates of the L-shaped inflection point, including: S311, perform contour extraction on the binarized image of the first adhesive path to obtain the set of pixels of the first adhesive path contour.

[0052] For example, when extracting the contour of the binarized image of the first adhesive path, an edge detection algorithm, such as the Canny edge detection algorithm, can be used. This algorithm determines the edge by finding pixels with drastic gray-level changes in the image, that is, by performing Gaussian filtering on the image to remove noise, then calculating the gradient magnitude and direction of the image, then refining the edge by non-maximum suppression, and finally using double threshold detection and edge connection to obtain the pixel set of the first adhesive path contour.

[0053] S312, perform polygon approximation processing on the set of pixels to obtain a polygonal outline composed of multiple vertices, and calculate the included angle between the two sides formed by three adjacent vertices based on the vertex sequence of the polygonal outline.

[0054] For example, when performing polygon approximation on a set of pixels, the Douglas-Peucker algorithm can be used. This algorithm recursively filters pixels on the contour according to a preset threshold, removing those that have little impact on the contour shape, thus obtaining a polygon contour composed of multiple vertices. After obtaining the polygon contour, the vertex sequence of the polygon contour is traversed. For each vertex, the included angle between the two sides formed by its three adjacent vertices is calculated. For example, for vertex Vi, its adjacent vertices are Vi-1 and Vi+1. Vector operations are used to obtain vectors Vi-1Vi and ViVi+1, and then the included angle between these two sides is calculated using the formula for the included angle between vectors.

[0055] S313, identify vertices with included angles within a preset angle range as candidate L-shaped inflection points, and among the candidate L-shaped inflection points, select vertices that are simultaneously located at the intersection of the horizontal and vertical adhesive line segments as the final L-shaped inflection points based on the directional characteristics of the L-shaped adhesive path, and obtain the pixel coordinates of the L-shaped inflection points; wherein, the preset angle range is the standard corner angle of the L-shaped adhesive path and its tolerance range.

[0056] For example, the preset angle range can be set based on the standard corner angle of the L-shaped adhesive path in actual production, taking into account a certain tolerance range. For instance, if the standard corner angle is 90 degrees and the tolerance range is set to ±5 degrees, then the preset angle range is 85 degrees to 95 degrees. After identifying the vertices with included angles within this preset angle range, since there may be multiple candidate vertices that meet the conditions, they are filtered according to the directional characteristics of the L-shaped adhesive path. The L-shaped adhesive path has clear horizontal and vertical directions. By analyzing the overall direction of the adhesive path in the image, the intersection position of the horizontal adhesive line segment and the vertical adhesive line segment is determined. Only candidate vertices that are simultaneously located at this intersection position can be identified as the final L-shaped inflection point, thereby obtaining the pixel coordinates.

[0057] This setup accurately determines the position of the L-shaped inflection point in the binarized image of the first adhesive path, providing a precise data foundation for subsequent calculations of the L-shaped inflection point position deviation. By employing contour extraction, polygon approximation, angle calculation, and directional feature filtering, the accuracy and reliability of L-shaped inflection point recognition are effectively improved, reducing recognition errors caused by image noise, uneven adhesive application, and other factors.

[0058] S320: Calculate the deviation between the pixel coordinates of the L-shaped inflection point and the preset L-shaped reference template to obtain the L-shaped inflection point position deviation value.

[0059] For example, when calculating the deviation, the pixel coordinates of the actually identified L-shaped inflection point are compared with the standard pixel coordinates based on the standard pixel coordinates of the L-shaped inflection point in the preset L-shaped reference template. By calculating the difference between the two coordinates in the horizontal and vertical directions, and combining methods such as the Pythagorean theorem, the position deviation value of the L-shaped inflection point is obtained. For example, if the actual L-shaped inflection point pixel coordinates are (x1, y1) and the standard L-shaped inflection point pixel coordinates are (x0, y0), then the deviation in the horizontal direction is Δx = x1 - x0, and the deviation in the vertical direction is Δy = y1 - y0. The position deviation value D = √(Δx² + Δy²). Through calculation, the deviation between the actual position of the L-shaped inflection point in the binarized image of the first adhesive path and the preset standard position can be accurately quantified, providing an important basis for subsequent evaluation of the adhesive path quality.

[0060] S330, then measure and calculate the transverse and longitudinal adhesive segments along the adhesive path to obtain the width consistency deviation value of the transverse and longitudinal adhesive segments.

[0061] For example, during measurement calculation, the measurement areas for the horizontal and vertical adhesive line segments are first determined along the trajectory of the adhesive line in the binarized image of the first adhesive line. For the horizontal adhesive line segment, multiple measurement points are uniformly selected along its length, and the width of the measurement point is determined by counting the number of white pixels (representing the adhesive line area) in the column where each measurement point is located. Similarly, for the vertical adhesive line segment, multiple measurement points are uniformly selected along its length, and the width is determined by counting the number of white pixels in the row where each measurement point is located. The average width of all measurement points on the horizontal adhesive line segment is calculated to obtain the average width of the horizontal adhesive line segment; the average width of all measurement points on the vertical adhesive line segment is calculated to obtain the average width of the vertical adhesive line segment. The average width of the horizontal adhesive line segment is compared with a preset standard width to obtain the horizontal width deviation value; the average width of the vertical adhesive line segment is compared with a preset standard width to obtain the vertical width deviation value. Then, based on the horizontal width deviation value and the vertical width deviation value, the width consistency deviation value between the horizontal and vertical adhesive line segments is obtained.

[0062] This setup allows for precise measurement of the consistency in width between the horizontal and vertical adhesive line segments in the binarized image of the first adhesive path. This meticulous measurement and calculation method can promptly identify width inconsistencies during adhesive application, such as excessively wide or narrow sections of horizontal adhesive lines, or abnormal width fluctuations in vertical adhesive lines. Comparing the measured average widths of the horizontal and vertical adhesive lines with preset standard widths clearly reveals the degree of deviation between the adhesive path width and the standard requirements.

[0063] S400 calculates and measures the binarized image of the second adhesive path to obtain the position deviation value of the U-shaped center point and the parallelism deviation value; among which, the parallelism deviation value is obtained by measuring the bottom adhesive line segment.

[0064] The U-shaped center point position deviation value can be understood as the positional difference calculated by comparing the actual position of the center point of the U-shaped structure in the binarized image of the second adhesive path with the preset standard position. The parallelism deviation value, on the other hand, is the degree of deviation between the bottom adhesive line segment in the binarized image of the second adhesive path and the preset standard parallelism state, which is measured.

[0065] For example, when obtaining the deviation value of the center point of the U-shape, the center point position of the U-shape structure is first determined to obtain the pixel coordinates of the center point of the U-shape, and the deviation between the actual position of the center point of the U-shape and the preset standard position is determined based on the pixel coordinates.

[0066] In one possible implementation, please refer to Figure 5 S400 calculates and measures the binarized image of the second adhesive path to obtain the U-shaped center point position deviation value and parallelism deviation value, including: S410: Recognize the binarized image of the second adhesive path to obtain the pixel coordinates of the two endpoints of the U-shaped opening.

[0067] For example, the edge detection of the binarized image of the second adhesive path can be performed first by determining the center point position of the U-shaped structure to obtain the edge contour of the U-shaped adhesive path, and then the geometric center calculation method can be used, for example, for a U-shaped contour composed of multiple pixels, to calculate the average value of the coordinates of all its pixels, thereby obtaining the pixel coordinates of the center point of the U-shape.

[0068] In one possible implementation, please refer to Figure 7 S410, the binarized image of the second adhesive path is identified to obtain the pixel coordinates of the two endpoints of the U-shaped opening, including: S411, perform contour extraction on the binarized image of the second adhesive path to obtain the set of pixels of the second adhesive path contour.

[0069] For example, when extracting the contour of the binarized image of the second adhesive path, the Canny edge detection algorithm can also be used. This algorithm first performs Gaussian filtering on the image to remove noise interference, making the image smoother and reducing the generation of false edges. Then, it calculates the gradient magnitude and direction of the image. The gradient magnitude reflects the degree of gray-level change in the image, and the gradient direction indicates the direction of gray-level change. Then, it refines the gradient magnitude through non-maximum suppression, retaining only the pixels with local maximum gradient magnitudes, thus obtaining refined edges. Finally, it uses dual threshold detection and edge connection, setting a high threshold and a low threshold. Pixels with gradient magnitudes greater than the high threshold are identified as strong edge points, while pixels with gradient magnitudes less than the low threshold are discarded. Pixels with gradient magnitudes between the high and low thresholds are retained if they are connected to strong edge points, otherwise they are discarded. This process connects the pixels to form a complete edge, resulting in the pixel set of the second adhesive path contour.

[0070] S412, Based on the positional distribution of the glue path area in the binarized image of the second glue path, and taking the paperboard conveying direction as the reference direction, determine the opening direction of the U-shaped glue path.

[0071] For example, when determining the opening direction of the U-shaped adhesive path, based on the overall positional distribution of the adhesive path area in the binarized image of the second adhesive path, and considering the specific orientation of the cardboard during transport, the cardboard transport direction is used as a reference direction to observe the direction and layout of the adhesive path in the image. For instance, if the adhesive path in the image extends along the cardboard transport direction and has an opening on one side, the opening direction of the U-shaped adhesive path can be accurately determined by combining the continuity and orientation characteristics of the adhesive path edge.

[0072] S413, in the set of pixels, search for the pixel furthest from the center as candidate endpoints in two opposite directions perpendicular to the opening direction of the U-shaped adhesive path.

[0073] For example, after determining the opening direction of the U-shaped adhesive path, a straight line direction perpendicular to the opening direction is determined in the pixel set, using the opening direction as a reference. The search then proceeds along two opposite directions of this perpendicular direction, starting from the center position. This center position can be determined based on the geometric center of the pixel set or the approximate central region of the adhesive path. During the search, the distance between each pixel and the currently furthest pixel is continuously compared, and pixels farther away are recorded as new candidate endpoints. This process continues until the entire pixel set has been searched or a preset search range limit is reached, thus obtaining the candidate endpoints.

[0074] S414, verify each candidate endpoint, and take the verified candidate endpoint as the two endpoints of the U-shaped opening to obtain the pixel coordinates of the two endpoints of the U-shaped opening; wherein, the two endpoints correspond to the left endpoint and right endpoint of the U-shaped adhesive path at the opening, respectively.

[0075] For example, when verifying each candidate endpoint, the judgment can be based on the geometric features of the U-shaped adhesive path and its positional relationship in the image. For instance, observe the local image features at the location of the candidate endpoint to see if it conforms to the typical shape of a U-shaped opening endpoint, such as whether the direction and angle of the surrounding adhesive path edges are consistent with expectations. At the same time, combine the already determined opening direction of the U-shaped adhesive path and the overall outline to determine whether the candidate endpoint is in a reasonable position. For the candidate endpoints that pass the verification, i.e., the points that conform to the characteristics of a U-shaped opening endpoint, they are taken as the two endpoints of the U-shaped opening, and their pixel coordinates are recorded. These two endpoints correspond to the left and right endpoints of the U-shaped adhesive path at the opening, respectively.

[0076] This setup allows for accurate and reliable acquisition of the pixel coordinates of the two endpoints of the U-shaped opening, providing data for subsequent calculation of the deviation value of the U-shaped center point position. This effectively reduces misidentification caused by image interference or algorithm errors and improves the accuracy of coordinate acquisition.

[0077] S420 calculates the deviation between the pixel coordinates of the two ends of the U-shaped opening and the preset U-shaped reference template to obtain the deviation value of the center point of the U-shape.

[0078] For example, the deviation value of the U-shaped center point can be obtained by comparing the pixel coordinates of the U-shaped center point with the preset standard pixel coordinates of the U-shaped center point, calculating the difference between the two coordinates in the horizontal and vertical directions, and then using methods such as the Pythagorean theorem to obtain the deviation value of the U-shaped center point. For example, if the actual pixel coordinates of the U-shaped center point are (x2, y2) and the standard pixel coordinates of the U-shaped center point are (x3, y3), then the deviation in the horizontal direction is Δx'=x2-x3, and the deviation in the vertical direction is Δy'=y2-y3. The position deviation value D'=√(Δx'²+Δy'²), which can accurately quantify the deviation between the actual position of the U-shaped center point and the preset standard position in the binarized image of the second adhesive path.

[0079] S430, then measure and calculate the parallelism of the bottom glue line segment relative to the edge of the cardboard to obtain the parallelism deviation value of the bottom glue line segment.

[0080] For example, the measurement of parallelism deviation can be achieved by determining the coordinates of the two endpoints of the bottom adhesive line segment in the binarized image of the second adhesive path, obtaining the pixel set of the bottom adhesive line segment through edge detection and contour extraction, and then determining the endpoint coordinates. Based on these two endpoint coordinates, the straight line equation of the bottom adhesive line segment can be calculated. By setting a reference straight line equation that is parallel to a preset standard direction of the bottom adhesive line segment, the angle between the straight line of the bottom adhesive line segment and the reference straight line can be calculated. The size of this angle can be used as a measure of the parallelism deviation. Alternatively, the parallelism deviation can be determined by calculating the vertical distances from multiple points on the bottom adhesive line segment to the reference straight line, and statistically analyzing the distribution of these vertical distances, such as calculating the standard deviation of the vertical distances.

[0081] This setup allows for the precise acquisition of the pixel coordinates of the two endpoints of the U-shaped opening in the binarized image of the second adhesive path. This enables accurate calculation of the deviation value of the U-shaped center point and the parallelism deviation value of the bottom adhesive line segment. Through detailed contour extraction, opening direction determination, and candidate endpoint search and verification operations on the binarized image of the second adhesive path, the accuracy of endpoint recognition is effectively improved, providing a reliable data foundation for subsequent deviation calculations. Simultaneously, employing multiple methods to measure the parallelism deviation value allows for a more comprehensive and accurate assessment of the degree of deviation between the bottom adhesive line segment and the preset standard parallel state. This timely detection of problems in the position and shape of the adhesive path provides a strong basis for adjusting and optimizing the adhesive application process of the two-fold gluing machine, contributing to improved product quality and production efficiency.

[0082] S500, compare the L-shaped inflection point position deviation value and width consistency deviation value with the preset side adhesive path threshold to obtain the first adhesive path quality data; wherein, the first adhesive path quality data is used to indicate whether the first adhesive path is qualified.

[0083] For example, when comparing the L-shaped inflection point position deviation value and the width consistency deviation value with the preset side adhesive path threshold, reasonable threshold ranges are set for these two deviation values. For the L-shaped inflection point position deviation value, a maximum allowable position deviation threshold is preset. If the calculated L-shaped inflection point position deviation value is less than or equal to this threshold, it indicates that the position of the L-shaped inflection point meets the requirements; otherwise, it indicates that the position deviation is too large, which may affect the connection effect of the adhesive path. For the width consistency deviation value, a reasonable width deviation threshold is also set. When the width consistency deviation value of the horizontal adhesive line segment and the vertical adhesive line segment is less than or equal to this threshold, it indicates that the width uniformity of the adhesive path is good; if it is greater than this threshold, it means that there is a problem of uneven width in the adhesive path. After comparing these two deviation values ​​with the corresponding thresholds, the first adhesive path is judged as qualified based on the comparison results. If both the L-shaped inflection point position deviation value and the width consistency deviation value are within their respective preset threshold ranges, the first adhesive path is judged as qualified; otherwise, if any deviation value exceeds the threshold range, the first adhesive path is judged as unqualified. This method allows for accurate and objective evaluation of the quality of the first gluing path, providing a clear basis for subsequent production adjustments and quality control, and helping to improve the overall quality stability of products produced by the two-fold gluing machine.

[0084] S600, compare the position deviation of the U-shaped center point and the parallelism deviation with the preset bottom adhesive path threshold to obtain the second adhesive path quality data; wherein, the second adhesive path quality data is used to indicate whether the second adhesive path is qualified.

[0085] For example, when comparing the deviation of the U-shaped center point position and the parallelism deviation with the preset bottom adhesive path threshold, reasonable threshold ranges can be set for each of these deviation values. For the deviation of the U-shaped center point position, a maximum allowable position deviation threshold is preset. If the calculated deviation of the U-shaped center point position is less than or equal to this threshold, it indicates that the position of the U-shaped center point meets the requirements and can ensure the accurate connection of the adhesive path at a specific position. Conversely, if the position deviation value is greater than this threshold, it indicates that the position deviation is too large, which may affect the bonding effect and overall stability of the adhesive path at the U-shaped structure. For the parallelism deviation value, a reasonable parallelism deviation threshold is set. When the parallelism deviation value of the bottom adhesive line segment is less than or equal to this threshold, it indicates that the deviation between the bottom adhesive line segment and the preset standard parallel state is within an acceptable range, and the adhesive path is relatively neat. If the parallelism deviation value is greater than this threshold, it means that there is an obvious tilt or non-parallelism problem in the bottom adhesive line segment, which may affect the folding and bonding quality of the cardboard. After comparing these two deviation values ​​with the corresponding thresholds, the second adhesive path is judged as qualified based on the comparison results. If both the deviation value of the U-shaped center point position and the parallelism deviation value are within their respective preset threshold ranges, the second glue path is deemed qualified; conversely, if either deviation value exceeds the threshold range, the second glue path is deemed unqualified. This rigorous comparison method allows for accurate and reliable evaluation of the quality of the second glue path, timely detection of problems in the position and shape of the glue path, and provides precise basis for adjusting and optimizing the glue application process of the two-fold box gluing machine, thereby helping to improve the overall product quality and production efficiency.

[0086] S700, the engagement relationship state is obtained based on the spatial engagement relationship between the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path.

[0087] It can be understood that the interlocking relationship can be understood as the spatial coordination and connection between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path.

[0088] For example, when obtaining the interlocking relationship status, based on the relative positions of the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path on the cardboard, and based on the image of the cardboard after glue application by the two-fold gluing machine, the specific positional coordinate range of the longitudinal glue line segment of the first glue path and the positional coordinate range of the U-shaped opening end of the second glue path are determined. Based on the coordinate information, the spatial positional relationship between the two can be determined. For example, if the longitudinal glue line segment of the first glue path can be accurately embedded into the U-shaped opening end of the second glue path, and there is no obvious gap or excessive overlap between the two, then the interlocking relationship status can be determined to be good; if there is a large gap between the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path, resulting in a loose glue connection, or if there is excessive overlap, resulting in irregular glue application and affecting the folding and gluing of the cardboard, then the interlocking relationship status is poor. Accurately assessing the interlocking relationship status between the first and second glue paths and timely identifying potential problems during glue application helps improve product quality.

[0089] In one possible implementation, S700, the engagement relationship state is obtained based on the spatial engagement relationship between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path, including: S710, calculate the minimum distance between the end of the longitudinal adhesive line segment of the first adhesive path and the corresponding point of the U-shaped opening end of the second adhesive path.

[0090] For example, when calculating the minimum distance between the end of the longitudinal adhesive line segment of the first adhesive path and the corresponding point of the U-shaped opening end of the second adhesive path, the specific position coordinates of the end of the longitudinal adhesive line segment can be used. For the corresponding point of the U-shaped opening end of the second adhesive path, the characteristics of the U-shaped opening end, such as the midpoint of the opening end or a point at a specific position, can be used as the corresponding point. Its coordinates can also be obtained through image processing technology. Then, using the distance formula between two points, if the coordinates of the end of the longitudinal adhesive line segment are (x4, y4) and the coordinates of the corresponding point of the U-shaped opening end are (x5, y5), then the minimum distance D = √((x4-x5)²+(y4-y5)²), thereby clarifying the degree of proximity between the end of the longitudinal adhesive line segment of the first adhesive path and the corresponding point of the U-shaped opening end of the second adhesive path.

[0091] S720 compares the minimum distance with the effective occlusal distance range to obtain the occlusal relationship status.

[0092] For example, when comparing the minimum distance with the effective interlocking distance range, a reasonable effective interlocking distance range that meets actual production requirements is pre-set. This range takes into account various factors such as the material and thickness of the cardboard, the application characteristics of the adhesive path, and the process requirements of the two-fold gluing machine. If the calculated minimum distance is within this effective interlocking distance range, it indicates that the spatial relationship between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path meets the standard and can form a good interlock. At this time, the interlocking relationship is judged to be good. Conversely, if the minimum distance is less than the lower limit of the effective interlocking distance range, it means that the distance between the two is too close, which may result in excessive overlap, leading to irregular adhesive application and affecting the folding and gluing effect of the cardboard. If the minimum distance is greater than the upper limit of the effective interlocking distance range, it indicates that there is a large gap between the two, and the adhesive path connection is not tight, which also affects the quality of the product. By comparing the minimum distance with the effective bite distance range, the bite relationship can be accurately and intuitively determined, and potential problems in the adhesive application process can be identified in a timely manner, providing a basis for subsequent production adjustments and helping to improve the overall product quality.

[0093] S800 obtains the glue path detection results based on the quality data of the first glue path, the quality data of the second glue path, and the engagement relationship status.

[0094] For example, when obtaining the glue path inspection result based on the quality data of the first glue path, the quality data of the second glue path, and the interlocking relationship, if the quality data of the first glue path indicates that the first glue path is qualified, the quality data of the second glue path indicates that the second glue path is qualified, and the interlocking relationship is good, then the glue path inspection result can be determined to be qualified. This indicates that the glue application process of the two-fold gluing machine has met the expected standards in terms of position, shape, and mutual cooperation, and can guarantee the folding and gluing quality of the product. Conversely, if either the quality data of the first glue path or the quality data of the second glue path indicates that it is unqualified, or if the interlocking relationship is poor, the glue path inspection result is determined to be unqualified. For example, if the first adhesive path fails due to an L-shaped inflection point deviation exceeding a preset threshold, even if the second adhesive path is qualified and the interlocking relationship is good, the overall adhesive path test result will still be unqualified because the problem with the first adhesive path may affect the overall quality of the product. Similarly, if the second adhesive path fails due to excessive parallelism deviation, or if the interlocking relationship shows a large gap or excessive overlap between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path, the adhesive path test result will also be deemed unqualified.

[0095] This setup enables precise quantitative detection of the glue path in a two-fold gluing machine, effectively solving the problem of inaccurate quantification of glue path position and size deviations. By effectively detecting the interlocking relationship of the glue path, interlocking issues can be identified in a timely manner, reducing problems such as poor product molding regularity and insufficient bonding reliability caused by poor interlocking.

[0096] In one possible implementation, S800 obtains the adhesive path detection result based on the first adhesive path quality data, the second adhesive path quality data, and the engagement relationship status, including: S801, if the quality data of the first glue path and the quality data of the second glue path are both qualified, and the interlocking relationship status is that the interlocking distance is qualified, then the glue path test result is that the current cardboard glue path is qualified.

[0097] For example, when both the quality data of the first glue path and the quality data of the second glue path are qualified, and the interlocking relationship is qualified in terms of interlocking distance, it indicates that the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path are well matched in space, and there is no excessive gap or excessive overlap. In this case, it can be determined that the current glue path coating process of the paperboard has met the expected requirements, and the glue path test result is that the current paperboard glue path is qualified.

[0098] S802, if the quality data of the first adhesive path is unqualified, the adhesive path inspection result is the first adhesive path defect.

[0099] For example, if the quality data of the first adhesive path is unqualified, it proves that there is a problem with the position or shape of the first adhesive path. For example, the deviation value of the L-shaped inflection point exceeds the preset threshold range, or the width consistency deviation value is too large. Therefore, in this case, the adhesive path detection result is directly determined to be a defect of the first fold adhesive path.

[0100] S803, if the quality data of the second adhesive path is unqualified, the adhesive path inspection result is a defect in the second adhesive path.

[0101] For example, when the quality data of the second glue path is unqualified, it means that the second glue path does not meet the standard in terms of position or shape. For example, the deviation value of the center point of the U-shape is too large, or the parallelism deviation value of the bottom glue line segment exceeds the allowable range. This will cause the glue path to be applied irregularly, affecting the folding and pasting of the cardboard. Therefore, the glue path test result is determined to be a defect in the second fold glue path.

[0102] S804. If the occlusal relationship is characterized by an excessively close or excessively far occlusal distance, the glue path test result indicates an occlusal relationship defect.

[0103] For example, if the interlocking relationship status shows that the interlocking distance is unqualified, that is, the minimum distance between the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path is not within the effective interlocking distance range, it indicates that there is a large gap or excessive overlap between the two, which may affect the tightness of the glue path connection and the folding and pasting effect of the cardboard. Therefore, the glue path detection result is determined to be a glue path interlocking defect.

[0104] This setup, by meticulously defining the criteria for judging glue path inspection results under different conditions, allows for more precise identification of problems in the glue path. Whether it's deviations in the position or shape of the first glue path, similar quality issues in the second glue path, or imperfect interlocking between the two, all can be accurately identified and categorized into the corresponding defect types. This enables the rapid identification of the root cause of the problem, allowing for precise adjustments to the glue application parameters and equipment components of the two-fold gluing machine, effectively improving product quality and reducing the production of defective products.

[0105] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0106] Corresponding to the glue path detection method for the two-fold gluing machine described in the above embodiments, this application also provides a glue path detection system for the two-fold gluing machine. Each unit of the system can implement each step of the glue path detection method for the two-fold gluing machine. Figure 8 The diagram shows a structural block diagram of the glue path detection system for a two-fold gluing machine provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0107] Reference Figure 8 The glue path detection system of this two-fold gluing machine includes: The acquisition unit is used to sequentially acquire the original images of the first adhesive path and the second adhesive path on the unfolded flat cardboard sheet; The analysis unit is used to process the original images of the first adhesive path and the second adhesive path respectively to obtain the corresponding binarized images of the first adhesive path and the second adhesive path. The first processing unit is used to calculate and measure the binarized image of the first adhesive path to obtain the L-shaped inflection point position deviation value and the width consistency deviation value; wherein, the width consistency deviation value is obtained by measuring the transverse adhesive line segment and the longitudinal adhesive line segment; The second processing unit is used to calculate and measure the binarized image of the second adhesive path to obtain the position deviation value of the U-shaped center point and the parallelism deviation value; wherein, the parallelism deviation value is obtained by measuring the bottom adhesive line segment; The first comparison unit is used to compare the L-shaped inflection point position deviation value and the width consistency deviation value with the preset side adhesive path threshold to obtain the first adhesive path quality data; wherein, the first adhesive path quality data is used to indicate whether the first adhesive path is qualified; The second comparison unit is used to compare the deviation value of the center point of the U-shape and the parallelism deviation value with the preset bottom adhesive path threshold to obtain the second adhesive path quality data; wherein, the second adhesive path quality data is used to indicate whether the second adhesive path is qualified; The unit is used to obtain the engagement relationship state based on the spatial engagement relationship between the longitudinal glue line segment of the first glue path and the U-shaped opening end of the second glue path. The result unit is used to obtain the glue path detection result based on the first glue path quality data, the second glue path quality data, and the bite relationship status.

[0108] It should be noted that the information interaction and execution process between the above systems / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0109] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0110] Figure 9 This is a schematic diagram of the structure of a control device provided in an embodiment of this application. Figure 9 As shown, the control device 6 in this embodiment includes: at least one processor 60 ( Figure 9 Only one is shown in the image), at least one memory 61 ( Figure 9(Only one is shown in the image) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, it causes the control device 6 to implement the steps of the glue path detection method embodiment of any of the above-described two-fold gluing machines, or causes the control device 6 to implement the functions of each module / unit in the above-described system embodiments.

[0111] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the control device 6.

[0112] The control device 6 can be a desktop computer, laptop, or other computing device. This control device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 9 This is merely an example of control device 6 and does not constitute a limitation on control device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0113] The processor 60 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0114] In some embodiments, the memory 61 may be an internal storage unit of the control device 6, such as a hard disk or memory of the control device 6. In other embodiments, the memory 61 may be an external storage device of the control device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the control device 6. Furthermore, the memory 61 may include both internal storage units and external storage devices of the control device 6. The memory 61 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0115] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0116] This application provides a computer program product that, when run on a two-fold gluing machine, enables the two-fold gluing machine to perform the steps described in any of the above method embodiments.

[0117] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the two-fold gluing machine, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0118] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0119] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0120] In the embodiments provided in this application, it should be understood that the disclosed glue path detection system, two-fold gluing machine, and method for a two-fold gluing machine can be implemented in other ways. For example, the glue path detection system and embodiments of the two-fold gluing machine described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be indirect couplings or communication connections through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting the glue path of a two-fold gluing machine, characterized in that, include: The original images of the first adhesive path and the second adhesive path on the unfolded flat cardboard sheet are acquired sequentially. The original images of the first adhesive path and the original images of the second adhesive path are processed respectively to obtain corresponding binarized images of the first adhesive path and the second adhesive path. The binarized image of the first adhesive path is calculated and measured to obtain the L-shaped inflection point position deviation value and the width consistency deviation value; wherein, the width consistency deviation value is obtained by measuring the transverse adhesive line segment and the longitudinal adhesive line segment; The binarized image of the second adhesive path is calculated and measured to obtain the position deviation value of the U-shaped center point and the parallelism deviation value; wherein, the parallelism deviation value is obtained by measuring the bottom adhesive line segment; The L-shaped inflection point position deviation value and the width consistency deviation value are compared with the preset side adhesive path threshold to obtain the first adhesive path quality data; wherein, the first adhesive path quality data is used to indicate whether the first adhesive path is qualified. The deviation value of the U-shaped center point and the parallelism deviation value are compared with the preset bottom adhesive path threshold to obtain the second adhesive path quality data; wherein, the second adhesive path quality data is used to indicate whether the second adhesive path is qualified; The engagement relationship is obtained based on the spatial engagement relationship between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path; Based on the first adhesive path quality data, the second adhesive path quality data, and the engagement relationship status, the adhesive path detection result is obtained.

2. The glue path detection method for a two-fold gluing machine as described in claim 1, characterized in that, The step of processing the original images of the first adhesive path and the second adhesive path respectively to obtain corresponding binarized images of the first adhesive path and the second adhesive path includes: The original images of the first adhesive path and the original images of the second adhesive path are subjected to grayscale transformation respectively. By adjusting the image contrast and brightness, the grayscale difference between the bright areas of the adhesive and the cardboard background is enhanced. For the original images of the first adhesive path and the second adhesive path after image enhancement, within a pre-set detection window, adaptive segmentation thresholds are obtained for each based on the grayscale distribution characteristics of the high-brightness region of the adhesive. The pixels in the image are divided into foreground and background according to the adaptive segmentation threshold to obtain the initial binary image of the first adhesive path and the initial binary image of the second adhesive path; wherein, the position and size of the detection window are determined according to the preset coating path of the first adhesive path and the second adhesive path; The initial binary images of the first adhesive path and the second adhesive path are respectively processed by elimination and connection to obtain the binarized images of the first adhesive path and the second adhesive path.

3. The glue path detection method for a two-fold gluing machine as described in claim 1, characterized in that, The calculation and measurement of the binarized image of the first adhesive path to obtain the L-shaped inflection point position deviation value and width consistency deviation value includes: The pixel coordinates of the L-shaped inflection point are obtained by identifying the binarized image of the first adhesive path; The deviation between the pixel coordinates of the L-shaped inflection point and the preset L-shaped reference template is calculated to obtain the position deviation value of the L-shaped inflection point; Then, the transverse adhesive line segment and the longitudinal adhesive line segment are measured and calculated along the adhesive path to obtain the width consistency deviation value of the transverse adhesive line segment and the longitudinal adhesive line segment.

4. The glue path detection method for a two-fold gluing machine as described in any one of claims 1 to 3, characterized in that, The calculation and measurement of the binarized image of the second adhesive path to obtain the U-shaped center point position deviation value and parallelism deviation value includes: The pixel coordinates of the two ends of the U-shaped opening are obtained by recognizing the binarized image of the second adhesive path; The deviation between the pixel coordinates of the two endpoints of the U-shaped opening and the preset U-shaped reference template is calculated to obtain the deviation value of the center point of the U-shape. The parallelism of the bottom adhesive line segment relative to the edge of the cardboard is then measured and calculated to obtain the parallelism deviation value of the bottom adhesive line segment.

5. The glue path detection method for a two-fold gluing machine as described in claim 1, characterized in that, The step of obtaining the engagement relationship state based on the spatial engagement relationship between the longitudinal adhesive line segment of the first adhesive path and the U-shaped opening end of the second adhesive path includes: Calculate the minimum distance between the end of the longitudinal adhesive line segment of the first adhesive path and the corresponding point of the U-shaped opening end of the second adhesive path; The minimum distance is compared with the effective occlusal distance range to obtain the occlusal relationship status.

6. The glue path detection method for a two-fold gluing machine as described in claim 3, characterized in that, The step of identifying the pixel coordinates of the L-shaped inflection point from the binarized image of the first adhesive path includes: Contour extraction is performed on the binarized image of the first adhesive path to obtain a set of pixels representing the contour of the first adhesive path. The set of pixels is subjected to polygon approximation processing to obtain a polygonal contour composed of multiple vertices, and the included angle between two sides formed by three adjacent vertices is calculated based on the vertex sequence of the polygonal contour. Vertices whose included angle is within a preset angle range are identified as candidate L-shaped inflection points. Among these candidate L-shaped inflection points, based on the directional characteristics of the L-shaped adhesive path, vertices located at the intersection of the horizontal adhesive line segment and the vertical adhesive line segment are selected as the final L-shaped inflection points, thus obtaining the pixel coordinates of the L-shaped inflection points. The preset angle range refers to the standard inflection angle of the L-shaped adhesive path and its tolerance range.

7. The glue path detection method for a two-fold gluing machine as described in claim 4, characterized in that, The step of recognizing the binarized image of the second adhesive path to obtain the pixel coordinates of the two endpoints of the U-shaped opening includes: Contour extraction is performed on the binarized image of the second adhesive path to obtain a set of pixels representing the contour of the second adhesive path. Based on the positional distribution of the adhesive path area in the second adhesive path binarized image, and taking the cardboard conveying direction as a reference direction, the opening direction of the U-shaped adhesive path is determined. In the set of pixels, along two opposite directions perpendicular to the opening direction of the U-shaped adhesive path, the pixel farthest from the center is searched as a candidate endpoint. Each candidate endpoint is verified, and the verified candidate endpoints are used as the two endpoints of the U-shaped opening to obtain the pixel coordinates of the two endpoints of the U-shaped opening; wherein the two endpoints correspond to the left and right endpoints of the U-shaped adhesive path at the opening, respectively.

8. The glue path detection method for a two-fold gluing machine as described in claim 1, characterized in that, The step of obtaining the adhesive path detection result based on the first adhesive path quality data, the second adhesive path quality data, and the engagement relationship status includes: If both the first adhesive path quality data and the second adhesive path quality data are qualified, and the interlocking relationship status is that the interlocking distance is qualified, then the adhesive path detection result is that the current cardboard adhesive path is qualified. If the quality data of the first adhesive path is unqualified, then the adhesive path test result is a defect in the first adhesive path. If the quality data of the second adhesive path is unqualified, then the adhesive path test result is a defect in the second adhesive path. If the bite relationship is characterized by an excessively close bite distance or an excessively far bite distance, then the glue path detection result indicates a bite relationship defect.

9. The glue path detection method for a two-fold gluing machine as described in claim 1, characterized in that, Before sequentially acquiring the original images of the first adhesive path and the second adhesive path on the unfolded flat cardboard sheet, the process includes: Behind the gluing unit of the box gluing machine, a first collecting element corresponding to the first fold side bonding area and a second collecting element corresponding to the second fold bottom bonding area are respectively set.

10. A two-fold gluing box machine, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method as claimed in any one of claims 1 to 9.

Images