Printing and packaging product defect detection device based on machine vision

Abstract

The utility model relates to the technical field of defect detection devices, and discloses a printing and packaging product defect detection device based on machine vision, which comprises a workbench, and the top of the workbench is fixedly connected with a conveyor belt. According to the printing and packaging product defect detection device based on machine vision, through the arrangement of the detection mechanism, the cameras B, the driving mechanism and the sorting disc, during conveying, the camera B on one side photographs products on the conveying belt, the photographed pictures are transmitted to an image processor on one side to be processed, and then the products are conveyed to the sorting disc; then the processed data is transmitted to an integrated control panel on one side, and the integrated control panel controls a driving motor in the sorting table to rotate forwards and backwards, so that the products falling onto the sorting disc can fall into the corresponding collecting bins along a plurality of rollers arranged on the sorting disc to be uniformly stored, manual sorting by manpower is not needed, and the sorting efficiency is improved. The product quality on a production line is ensured, and the production efficiency is improved.

Description

Technical Field

[0001] This utility model relates to the field of defect detection device technology, and in particular to a defect detection device for printed packaging products based on machine vision. Background Technology

[0002] With the development of the modern printing industry, people have increasingly higher requirements for printing technology. Against this backdrop, fast and high-precision image detection and recognition algorithms are needed to meet the current demands for high speed and high accuracy in surface defect detection. From offline to online detection, this continuously drives the printing industry towards high quality, high efficiency, and low cost. Common surface defects include: missing prints, stains, scratches, ink smears, ink splatter, color difference, and misregistration. These issues lead to excessively high scrap rates, which seriously affect production quality. To strictly control the defect rate, it is necessary to inspect the printed surface during printing, removing as many defective products as possible during production.

[0003] Traditional inspection methods rely primarily on human visual inspection to identify and reject defective products. However, human visual inspection is prone to fatigue, slow, and inefficient. It also has a high rate of missed detection for small, densely packed markings and cannot guarantee consistent quality standards. Therefore, automated surface defect detection is gradually becoming an industry trend.

[0004] A machine vision-based defect detection device for printed packaging products, disclosed in publication number CN206583819U, includes a production line for transporting product packaging. This production line is driven by a motor. Robotic arm control devices are located on both sides of the production line. A robotic arm assembly is positioned above the control devices. A camera adjustment mechanism is located at the front end of the robotic arm assembly. Above the camera adjustment mechanism are a CCD camera assembly and a positioning robotic arm. A fixing baffle assembly and a positioning baffle assembly are located at the control devices. A control box contains a display at the top and a power supply unit inside. The control box also houses the control unit. This device allows the packaging to be placed on the production line, positioned and rotated by the robotic arm, and photographed by the CCD camera during the process. Defect identification and display are then performed using the control box and the display.

[0005] While the aforementioned patent achieves the goal of simply placing the packaging on the assembly line, using a robotic arm to position and flip the product, taking photos with a CCD camera during the process, and then using a control box and display to identify and display defects, the device lacks a mechanism for sorting defective products to ensure product quality on the production line and improve production efficiency.

[0006] Therefore, it is necessary to invent a machine vision-based defect detection device for printed packaging products to solve the above problems. Utility Model Content

[0007] The technical problem solved by this utility model is to provide a machine vision-based defect detection device for printed packaging products that is highly practical, easy to operate, and has a simple structure, thus solving the problem of lacking a mechanism for sorting defective products mentioned in the background art.

[0008] To achieve the above objectives, this utility model provides the following technical solution: a machine vision-based defect detection device for printed packaging products, comprising a worktable, a conveyor belt fixedly connected to the top of the worktable, support blocks fixedly connected to both sides of the worktable surface, a motor housing fixedly connected to the top of the support blocks, a rotating mechanism fixedly connected inside the motor housing, a camera A fixedly connected to the top of the rotating mechanism, a sorting table fixedly connected to the back of the worktable, a drive mechanism fixedly connected inside the sorting table, a sorting tray threadedly connected to the top of the drive mechanism, a support plate fixedly connected to one edge of the top surface of the sorting table, a detection mechanism fixedly connected to the top of the support plate, a camera B electrically connected to one side of the detection mechanism via a power cord, and a side of the camera A electrically connected to one end of the detection mechanism via a power cord.

[0009] As a further embodiment of this utility model, the rotating mechanism includes a servo motor fixedly connected inside the motor housing, a transmission rod connected to the output end of the servo motor via a spline, a rotating rod fixedly connected to one end of the transmission rod, and the camera A fixedly connected to the top of the rotating rod.

[0010] As a further embodiment of this utility model, the driving mechanism includes a drive motor fixedly connected inside the sorting table, and a U-shaped connector fixedly connected to the output end of the drive motor, the U-shaped connector being threadedly connected to the bottom of the sorting tray.

[0011] As a further embodiment of this utility model, the detection mechanism includes an image processor fixedly connected to the top of the support plate, one side of the image processor is electrically connected to an integrated control panel via a power cord, and one side of the integrated control panel is electrically connected to one side of the camera B via a power cord.

[0012] As a further embodiment of this utility model, two sets of baffles are fixedly connected to the top of the workbench, and the baffles are located on both sides of the conveyor belt.

[0013] As a further embodiment of this utility model, sliding rails are fixedly connected to both sides of the surface of the sorting table, and a collection bin is fixedly connected to the bottom of the sliding rails.

[0014] As a further embodiment of this utility model, the surface of the workbench is provided with four sets of threaded holes, and the internal threads of the threaded holes are connected to threaded columns.

[0015] This utility model provides a machine vision-based defect detection device for printed packaging products, which has the following beneficial effects:

[0016] 1. This machine vision-based defect detection device for printed packaging products, through the setup of a detection mechanism, camera B, drive mechanism, and sorting tray, allows the camera B on one side to take pictures of the products on the conveyor belt during transport. The captured images are transmitted to an image processor on one side for processing, and then the processed data is transmitted to an integrated control panel on one side. The integrated control panel then controls the drive motor inside the sorting tray to rotate forward and backward, so that the products falling onto the sorting tray will fall along multiple rollers on the sorting tray into the corresponding collection bins for unified storage. This eliminates the need for manual sorting, ensuring product quality on the production line and improving production efficiency.

[0017] 2. This machine vision-based defect detection device for printed packaging products, through the setting of a rotating mechanism and camera A, has cameras A set on both sides of the conveyor belt during use. The servo motor on the top can be activated, and the servo motor drives the camera A on the top rotating rod to rotate, thereby increasing the shooting range of camera A and enabling all-round defect detection of the product, reducing the possibility of missed or false detections. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the overall structure of this utility model;

[0019] Figure 2 This is a schematic diagram of the drive mechanism structure of this utility model;

[0020] Figure 3 This is a schematic diagram of the testing mechanism of this utility model;

[0021] Figure 4 This is a schematic diagram of the rotating mechanism of this utility model.

[0022] In the diagram: 1. Workbench; 2. Conveyor belt; 3. Support block; 4. Motor housing; 5. Rotating mechanism; 501. Servo motor; 502. Transmission rod; 503. Rotating rod; 6. Camera A; 7. Sorting table; 8. Drive mechanism; 801. Drive motor; 802. U-shaped connector; 9. Sorting tray; 10. Support plate; 11. Detection mechanism; 1101. Image processor; 1102. Integrated control panel; 12. Camera B; 13. Baffle; 14. Sliding rail; 15. Collection bin; 16. Threaded column. Detailed Implementation

[0023] The technical solutions of the present utility model will be clearly and completely described below with reference to the accompanying drawings of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present utility model without creative effort are within the scope of protection of the present utility model.

[0024] Please see Figures 1 to 4 This utility model provides a technical solution: a machine vision-based defect detection device for printed packaging products, including a workbench 1, a conveyor belt 2 fixedly connected to the top of the workbench 1, support blocks 3 fixedly connected to both sides of the surface of the workbench 1, a motor housing 4 fixedly connected to the top of the support blocks 3, and a rotating mechanism 5 fixedly connected inside the motor housing 4. Through the arrangement of the rotating mechanism 5 and a camera A6, defects can be detected from all angles, reducing the possibility of missed or false detections. The camera A6 is fixedly connected to the top of the rotating mechanism 5, and a sorting table 7 is fixedly connected to the back of the workbench 1. The sorting table 7 is internally fixedly connected to a drive mechanism 8. The top of the drive mechanism 8 is threadedly connected to a sorting tray 9. A support plate 10 is fixedly connected to one edge of the top surface of the sorting table 7. A detection mechanism 11 is fixedly connected to the top of the support plate 10. With the setting of the detection mechanism 11, camera B12, drive mechanism 8, and sorting tray 9, manual sorting is not required, ensuring product quality on the production line and improving production efficiency. One side of the detection mechanism 11 is electrically connected to camera B12 via a power cord, and one side of camera A6 is electrically connected to one end of the detection mechanism 11 via a power cord.

[0025] Please see Figure 4 The rotating mechanism 5 includes a servo motor 501 fixedly connected inside the motor housing 4. The output end of the servo motor 501 is splinedly connected to a transmission rod 502. One end of the transmission rod 502 is fixedly connected to a rotating rod 503. The camera A6 is fixedly connected to the top of the rotating rod 503.

[0026] Please see Figure 2 The drive mechanism 8 includes a drive motor 801 fixedly connected inside the sorting table 7. The output end of the drive motor 801 is fixedly connected to a U-shaped connector 802, which is threadedly connected to the bottom of the sorting tray 9.

[0027] Please see Figure 3 The detection mechanism 11 includes an image processor 1101 fixedly connected to the top of the support plate 10. One side of the image processor 1101 is electrically connected to an integrated control panel 1102 via a power cord. One side of the integrated control panel 1102 is electrically connected to one side of the camera B12 via a power cord.

[0028] Please see Figure 3Two sets of baffles 13 are fixedly connected to the top of the workbench 1, and the baffles 13 are located on both sides of the conveyor belt 2.

[0029] Please see Figure 3 Both sides of the sorting table 7 are fixedly connected to sliding rails 14, and the bottom of the sliding rails 14 is fixedly connected to a collection bin 15.

[0030] Please see Figure 1 The surface of the workbench 1 has four sets of threaded holes, and the internal threads of the threaded holes are connected to threaded posts 16.

[0031] The image processor 1101 is an NVIDIA; the integrated control panel 1102 is an MCU; the above parameters and models can be selected according to the actual situation.

[0032] In this invention, the working steps of the device are as follows:

[0033] First step: During the conveying process, the camera B12 on one side takes pictures of the products on the conveyor belt 2 and transmits the pictures to the image processor 1101 on one side for processing. Then, the processed data is transmitted to the integrated control panel 1102 on one side. The integrated control panel 1102 then controls the drive motor 801 inside the sorting table 7 to rotate forward and backward, so that the products falling into the sorting tray 9 will fall into the corresponding collection bin 15 along the multiple rollers set on the sorting tray 9 for unified storage.

[0034] The second step: When in use, cameras A6 are installed on both sides of the conveyor belt 2, and the servo motor 501 at the top can be started. The servo motor 501 drives the camera A6 on the top rotating rod 503 to rotate, thereby increasing the shooting range of the camera A6.

[0035] It should be noted that the device structure and accompanying drawings of this utility model mainly describe the principle of this utility model. In terms of the technical aspects of this design principle, the setting of the power mechanism, power supply system and control system of the device is not fully described. However, under the premise that those skilled in the art understand the principle of the above utility model, the specific details of its power mechanism, power supply system and control system can be clearly understood. The control method in the application document is automatic control through a controller. The control circuit of the controller can be implemented by those skilled in the art through simple programming.

[0036] All standard parts used can be purchased from the market, and can be customized according to the instructions and drawings. The specific connection methods of each part adopt conventional methods such as bolts, rivets, and welding that are mature in the existing technology. The machinery, parts and equipment adopt conventional models in the existing technology, and the structure and principle of the components known to those skilled in the art can be known by those skilled in the art through technical manuals or conventional experimental methods.

[0037] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A machine vision-based defect detection device for printed packaging products, comprising a worktable (1), characterized in that: The top of the workbench (1) is fixedly connected to a conveyor belt (2), and both sides of the surface of the workbench (1) are fixedly connected to support blocks (3). The top of the support blocks (3) is fixedly connected to a motor housing (4). The inside of the motor housing (4) is fixedly connected to a rotating mechanism (5). The top of the rotating mechanism (5) is fixedly connected to a camera A (6). The back of the workbench (1) is fixedly connected to a sorting table (7). The inside of the sorting table (7) is fixedly connected to a drive mechanism (8). The top of the drive mechanism (8) is threadedly connected to a sorting tray (9). The edge of one side of the top surface of the sorting table (7) is fixedly connected to a support plate (10). The top of the support plate (10) is fixedly connected to a detection mechanism (11). One side of the detection mechanism (11) is electrically connected to a camera B (12) via a power line. One side of the camera A (6) is electrically connected to one end of the detection mechanism (11) via a power line.

2. The machine vision-based defect detection device for printed packaging products according to claim 1, characterized in that: The rotating mechanism (5) includes a servo motor (501) fixedly connected inside the motor housing (4). The output end of the servo motor (501) is splinedly connected to a transmission rod (502). One end of the transmission rod (502) is fixedly connected to a rotating rod (503). The camera A (6) is fixedly connected to the top of the rotating rod (503).

3. The machine vision-based defect detection device for printed packaging products according to claim 1, characterized in that: The drive mechanism (8) includes a drive motor (801) fixedly connected inside the sorting table (7). The output end of the drive motor (801) is fixedly connected to a U-shaped connector (802), which is threadedly connected to the bottom of the sorting tray (9).

4. The machine vision-based defect detection device for printed packaging products according to claim 1, characterized in that: The detection mechanism (11) includes an image processor (1101) fixedly connected to the top of the support plate (10). One side of the image processor (1101) is electrically connected to an integrated control panel (1102) via a power cord. One side of the integrated control panel (1102) is electrically connected to one side of the camera B (12) via a power cord.

5. The machine vision-based defect detection device for printed packaging products according to claim 1, characterized in that: Two sets of baffles (13) are fixedly connected to the top of the workbench (1), and the baffles (13) are located on both sides of the conveyor belt (2).

6. The machine vision-based defect detection device for printed packaging products according to claim 1, characterized in that: The sorting table (7) has sliding rails (14) fixedly connected to both sides of its surface, and a collection bin (15) is fixedly connected to the bottom of the sliding rails (14).

7. The machine vision-based defect detection device for printed packaging products according to claim 1, characterized in that: The surface of the workbench (1) is provided with four sets of threaded holes, and the internal threads of the threaded holes are connected to threaded columns (16).

Images