Multi-vision and precise-force-sense intelligent automatic detection labeling method and device

Abstract

The invention relates to an intelligent automatic detection labeling method and device based on multi-view vision and precise force sense, a packaging box is clamped and shaped before visual detection, the imaging quality and detection accuracy of six-face visual detection are guaranteed, and by combining an integrated weighing function and an automatic unqualified product removing mechanism, the labeling efficiency is improved. The problems that in the prior art, due to the fact that packaging boxes are irregular, detection precision is not high, manual detection efficiency is low, mistakes and omissions are prone to occurring, and special detection equipment is high in cost and single in function are solved, comprehensive, efficient and automatic quality control over the appearance and weight of the packaging boxes is achieved, equipment investment and labor cost are reduced, and the production efficiency is improved. And the production automation level and the ex-factory qualified rate of products are improved.

Description

Technical Field

[0001] The present application relates to the technical field of product defect detection, and in particular to an intelligent automatic detection and labeling method and device using multi-vision and precision force perception. Background Art

[0002] With the rapid development of consumer electronics, especially the fierce competition in the smartphone market, product appearance quality and packaging integrity have become crucial factors influencing brand image and user experience. As the first impression of a product, the clarity of printed patterns, the accuracy of label affixation, and overall neatness are all highly valued by manufacturers.

[0003] In traditional mobile phone packaging production lines, quality inspection of packaging boxes, such as for printing defects (e.g., missing or misprinted items, color deviations), and missing or misapplied labels, often relies on manual visual inspection. However, manual inspection has the following inherent drawbacks: First, it is inefficient and difficult to adapt to the demands of large-scale, high-speed production. Second, inspection results are significantly influenced by subjective factors, making missed and false detections prone to occur, making it difficult to ensure consistent inspection standards. Third, long periods of repetitive work can easily lead to fatigue among inspectors, further reducing inspection reliability.

[0004] To overcome the shortcomings of manual inspection, automated visual inspection technology is beginning to be introduced into packaging quality control. Currently, there are some automated devices on the market for packaging surface inspection. These devices utilize industrial cameras and image processing algorithms to identify surface defects. For example, some devices may focus on inspecting one or two specific surfaces of the box, or require manual flipping of the box multiple times to inspect multiple sides. This makes the inspection process complex and inefficient. Dedicated equipment on the market that can provide complete six-sided visual inspection capabilities is often expensive and lacks flexibility for subsequent maintenance and feature upgrades. In the event of a failure, the original equipment manufacturer may need to be relied upon for resolution, resulting in slow response times and impacting production continuity. Summary of the Invention

[0005] In order to solve the above problems, the present application provides an intelligent automatic detection and labeling method and device with multi-eye vision and precise force perception with good detection effect.

[0006] To achieve the above objectives, in a first aspect, embodiments of the present application provide an intelligent automatic inspection and labeling device with multi-lens vision and precision force sensing, for detecting appearance defects and weight defects of packaging boxes, comprising: a frame, on which a loading area, a visual inspection area, and a weighing area are defined; a conveying mechanism is provided on the frame, and is used to convey the packaging box to be inspected through the loading area, the visual inspection area, and the weighing area in sequence; a visual inspection mechanism is provided in the visual inspection area, and is used to collect image information of the top surface, the bottom surface, and four side surfaces connecting the top surface and the bottom surface of the packaging box; a weighing mechanism is provided in the weighing area, and is used to collect weight information of the packaging box conveyed to the weighing area; a controller is communicatively connected to the conveying mechanism, the visual inspection mechanism, and the weighing mechanism, respectively, and is used to process the acquired image information and weight information to determine whether the packaging box has appearance defects and weight defects; A labeling machine is provided downstream of the weighing area and is in communication with the controller, and is used to label qualified packaging boxes; wherein the feeding area is provided with a clamping and shaping mechanism, and the clamping and shaping mechanism includes: A driving mechanism; a first pressure plate, configured to be driven by the driving mechanism to apply pressure to the top surface of the packaging box; at least one pair of oppositely arranged second pressure plates, configured to be driven by the driving mechanism to apply pressure to the opposite sides of the packaging box; and the two second pressure plates cooperate with the first pressure plate to enclose a shaped space adapted to the radial cross-section of the packaging box.

[0007] Preferably, the driving mechanism includes at least one cylinder or electric push rod, which is used to drive the first pressure plate and the at least one pair of second pressure plates separately or in conjunction with each other; wherein, an elastic buffer layer is provided on the lower surface of the first pressure plate and / or the inner side surface of the at least one pair of second pressure plates.

[0008] Preferably, it also includes a first sensor arranged in the loading area, and the first sensor is used to detect whether the packaging box reaches the clamping and shaping position; the controller controls the driving mechanism to drive the first pressure plate and the at least one pair of second pressure plates to clamp and shape the packaging box according to the detection signal of the first sensor.

[0009] Preferably, the visual inspection mechanism includes six cameras corresponding to the positions of the top surface, bottom surface, front side surface, rear side surface, left side surface and right side surface of the packaging box respectively.

[0010] Preferably, the visual detection area is further provided with a retractable blocking member and a second sensor, the second sensor being used to detect whether the packaging box reaches a preset shooting position; the blocking member is controlled by the controller to extend and block the packaging box when it reaches the preset shooting position.

[0011] Preferably, the conveying mechanism includes a first conveyor belt, a second conveyor belt and a suspended conveying mechanism, the first conveyor belt is used to convey the packaging box from the loading area to the visual inspection area, and the second conveyor belt is used to convey the packaging box from the visual inspection area to the weighing area; the suspended conveying mechanism is arranged in the visual inspection area and located between the first conveyor belt and the second conveyor belt, and the suspended conveying mechanism is used to expose the bottom surface of the packaging box during the process of conveying it; wherein, the controller can independently control the start and stop of the first conveyor belt, the second conveyor belt and the suspended conveying mechanism.

[0012] Preferably, the suspended conveying mechanism includes two drive chains extending along the conveying direction of the packaging box and configured to move in a circular motion, the drive chains are arranged at an angle, and C-shaped brackets are provided on the links of the drive chains, and each of the C-shaped brackets is configured to support the bottom edge of the packaging box from the side and bottom when the drive chain moves; wherein each of the C-shaped brackets is provided with a compression spring and a push member inside, and the push member is driven by the compression spring to elastically press outward against the side or bottom edge of the packaging box.

[0013] Preferably, it also includes a first rejection mechanism and a second rejection mechanism controlled by the controller, the first rejection mechanism includes a first defective product collection path connected to the downstream of the visual inspection area and a pushing member for pushing the packaging box with appearance defects into the first defective product collection path; the second rejection mechanism includes a second defective product collection path connected to the downstream of the weighing area and a clamping and pushing component for moving the packaging box with weight defects into the second defective product collection path.

[0014] Preferably, the weighing mechanism includes an electronic scale and a barcode scanner arranged above the electronic scale, and the barcode scanner is used to read the identification information on the packaging box; the controller is used to associate the identification information with the collected weight information and store it.

[0015] In a second aspect, embodiments of the present application provide a method for intelligent automatic detection and labeling using multi-eye vision and precision force perception, which is applied to the intelligent automatic detection and labeling device using multi-eye vision and precision force perception described in any embodiment of the first aspect. The method comprises the following steps: a) using the conveying mechanism to convey the packaging box to be inspected through the loading area, visual inspection area and weighing area in sequence; b) using the clamping and shaping mechanism to perform a clamping and shaping process on the packaging box when the packaging box is located in the loading area, and the clamping and shaping process includes: driving the first pressing plate to apply pressure to the top surface of the packaging box, and driving the at least one pair of second pressing plates to apply pressure to the opposite sides of the packaging box to form a shaping space that matches the cross-sectional profile of the packaging box; c) using the visual inspection mechanism to collect image information of the top surface, bottom surface and four side surfaces connecting the top surface and bottom surface of the packaging box when the packaging box is located in the visual inspection area; d) using the weighing mechanism to collect weight information of the packaging box when the packaging box is located in the weighing area; e) using the controller to process the acquired image information and weight information to determine whether the packaging box has appearance defects and weight defects; f) Label the packaging boxes that pass the inspection.

[0016] The intelligent automatic inspection and labeling method and device with multi-eye vision and precision force perception designed in this application ensures the imaging quality and detection accuracy of six-sided visual inspection by clamping and shaping the packaging box before visual inspection. Combined with the integrated weighing function and the automatic rejection mechanism of unqualified products, it overcomes the problems in the existing technology of low detection accuracy caused by irregular packaging boxes, low efficiency and easy errors in manual inspection, and high cost and single function of special inspection equipment, thereby realizing comprehensive, efficient and automated quality control of the appearance and weight of the packaging boxes, reducing equipment investment and labor costs, and improving the level of production automation and product factory qualification rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the planar structure of the intelligent automatic detection and labeling device with multi-eye vision and precision force perception provided in an embodiment of the present application.

[0018] Figure 2 It is a structural diagram of the visual detection mechanism provided in an embodiment of the present application.

[0019] Figure 3 It is a structural schematic diagram of the suspended conveying mechanism provided in an embodiment of the present application.

[0020] Figure 4 yes Figure 3 Enlarged schematic diagram of point A in the middle.

[0021] Figure 5 It is a schematic diagram of the structure of the clamping and shaping mechanism provided in an embodiment of the present application.

[0022] Among them: frame 10, loading area 11, visual inspection area 12, weighing area 13, conveying mechanism 20, first conveyor belt 21, second conveyor belt 22, suspended conveying mechanism 23, drive chain 231, C-shaped bracket 232, compression spring 233, support member 234, visual inspection mechanism 30, camera 31, weighing mechanism 40, electronic scale 41, barcode scanner 42, clamping and shaping mechanism 60, driving mechanism 61, first pressure plate 62, second pressure plate 63, first sensor, first rejection mechanism 90, first defective product collection path 901, pusher 902, second rejection mechanism 91, second defective product collection path 911, clamping and pushing component 912, packaging box 100. DETAILED DESCRIPTION

[0023] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application.

[0024] First, as Figures 1 to 5 As shown, the present embodiment provides an intelligent automatic inspection and labeling device using multi-lens vision and precision force sensing, for detecting appearance defects and weight defects in packaging boxes. The device primarily comprises a frame 10, a conveyor mechanism 20, a visual inspection mechanism 30, a weighing mechanism 40, a labeling machine (not shown), and a controller (not shown) communicatively connected to the conveyor mechanism 20, the visual inspection mechanism 30, and the weighing mechanism 40. In this embodiment, the controller is, for example, a PLC control box with an industrial computer.

[0025] Reference Figure 1 As shown, a frame 10 serves as the support base of the entire apparatus, and is defined by a loading area 11, a visual inspection area 12, and a weighing area 13. These three areas are arranged sequentially along the conveying path of the packaging boxes 100. A conveying mechanism 20 is provided on the frame 10. Its function is to convey the packaging boxes 100 to be inspected from the loading area 11, through the visual inspection area 12, and finally to the weighing area 13, and then to deliver the packaging boxes 100 after inspection.

[0026] The visual inspection mechanism 30 is disposed in the visual inspection area 12 . When the packaging box 100 is conveyed to the visual inspection area 12 , the visual inspection mechanism 30 collects image information of the top surface, bottom surface, and four side surfaces connecting the top surface and bottom surface of the packaging box 100 .

[0027] When implementing it specifically, Figure 2As shown, the visual inspection mechanism 30 includes six cameras 31 corresponding to the top, bottom, front side, rear side, left side and right side positions of the packaging box 100, respectively. The six cameras 31 are arranged for the six sides of the packaging box 100: an upper camera is aimed at the top surface of the packaging box 100, a lower camera is aimed at the bottom surface of the packaging box 100, a front camera is aimed at the front side of the forward direction of the packaging box 100, a rear camera is aimed at the rear side of the packaging box 100, and the left camera and right camera located on the left and right sides of the packaging box 100 are aimed at its left and right sides, to ensure that complete six-side information is obtained.

[0028] The weighing mechanism 40 is provided in the weighing area 13 and is used to collect the weight information of the packaging box 100 transmitted to the weighing area 13. Figure 1 As shown, the weighing mechanism 40 includes an electronic scale 41 and a barcode scanner 42 arranged above the electronic scale 41, and the barcode scanner 42 is used to read the identification information on the packaging box 100; the controller is used to associate the identification information with the collected weight information and store it, accurately collect the weight information of the packaging box 100, so as to determine whether the contents of the packaging box 100 are complete or whether there are other weight-related defects.

[0029] The controller is primarily used to process the acquired image information and weight information to determine whether the packaging box 100 has any appearance defects or weight defects. Specifically, the controller receives image information acquired by each camera 31 and weight information from the electronic scale 41. The controller analyzes and processes this acquired information using an industrial computer with a built-in or connected image processing unit and data analysis algorithm, ultimately determining whether the packaging box has any appearance defects, such as printing errors, stains, damage, skewed or missing labels, and any weight defects, such as overweight or underweight.

[0030] In addition, the loading area 11 is provided with a clamping and shaping mechanism 60, which includes a driving mechanism 61, a first pressing plate 62 and at least one pair of oppositely arranged second pressing plates 63. The first pressing plate 62 is configured to be driven by the driving mechanism 61 to apply pressure to the top surface of the packaging box 100 to make the top surface flat; and the second pressing plate 63 is configured to be driven by the driving mechanism 61 to apply pressure to the opposite sides (such as the left and right sides) of the packaging box 100 to make the sides flat; and the two second pressing plates 63 cooperate with the first pressing plate 62 to enclose and form a shaping space that is adapted to the radial cross-section of the packaging box 100. That is, Figure 5As shown, the first pressure plate 62 presses down on the top surface and the second pressure plate 63 clamps the side surface, which act together on the packaging box 100 to enclose it to form a shaped space that is adapted to the expected, regular cross-sectional profile of the packaging box, thereby eliminating or reducing problems such as slight deformation, bulging or incomplete folding of the packaging box due to stacking, transportation, etc., and improving the completeness and clarity of the image information obtained by the subsequent visual inspection mechanism 30.

[0031] The labeling machine is located downstream of the weighing area 13 and is in communication with the controller, and is used to label the qualified packaging boxes 100. In specific implementation, the labeling machine can use a mature product available on the market to label the packaging boxes 100 that have been judged by the controller to have no appearance defects and weight defects, such as qualified labels. In some embodiments, Figure 1 、 Figure 5 As shown, the drive mechanism 61 includes at least one pneumatic cylinder or electric push rod, which is used to drive the first pressure plate 62 and the at least one pair of second pressure plates 63 separately or in a coordinated manner. In other words, these cylinders or electric push rods can be designed to independently control the movement of the first pressure plate 62 and each pair of second pressure plates 63, or they can be designed as a coordinated mechanism to achieve coordinated movement of all pressure plates through one or a few power sources. The lower surface of the first pressure plate 62 and / or the inner surface of the at least one pair of second pressure plates 63 are provided with an elastic buffer layer, such as a rubber pad, sponge, or other flexible material.

[0032] In some embodiments, a first sensor (not shown) is further included in the loading area 11. The first sensor 70 can be a photoelectric sensor, a proximity switch, etc., which is mainly used to detect whether the packaging box 100 reaches the clamping and shaping position; the controller controls the driving mechanism 61 to drive the first pressure plate 62 and the at least one pair of second pressure plates 63 to clamp and shape the packaging box 100 according to the detection signal of the first sensor.

[0033] In some embodiments, the visual inspection area 12 is further provided with a retractable blocking member (not shown) and a second sensor (not shown). The second sensor is used to detect whether the packaging box 100 has reached a preset shooting position. The blocking member is controlled by the controller to extend and block the packaging box 100 when it reaches the preset shooting position, thereby enhancing the completeness and clarity of the image information obtained.

[0034] In some embodiments, as Figure 1 、 Figure 3As shown, the conveying mechanism 20 includes a first conveyor belt 21, a second conveyor belt 22 and a suspended conveying mechanism 23. The first conveyor belt 21 is used to convey the packaging box 100 from the loading area 11 to the visual inspection area 12, and the second conveyor belt 22 is used to convey the packaging box 100 from the visual inspection area 12 to the weighing area 13. The suspended conveying mechanism 23 is arranged in the visual inspection area 12 and is located between the first conveyor belt 21 and the second conveyor belt 22. The suspended conveying mechanism 23 is used to expose the bottom surface of the packaging box 100 during the process of conveying the packaging box 100. The controller can independently control the start and stop of the first conveyor belt 21, the second conveyor belt 22 and the suspended conveying mechanism 23. In this embodiment, the design purpose of the suspended conveying mechanism 23 is to enable the bottom surface of the packaging box to be exposed at least when the lower camera is shooting during the process of conveying the packaging box through the visual inspection area 12, that is, the bottom is not blocked, so as to achieve precise station conversion and shooting coordination.

[0035] In some embodiments, as Figure 3 、 Figure 4 As shown, the suspended conveying mechanism 23 includes two drive chains 231 extending along the conveying direction of the packaging box 100 and configured to move in a circular motion. The drive chains 231 are arranged at an angle, and C-shaped brackets 232 are provided on the links of the drive chains 231. Each C-shaped bracket 232 is configured to support the bottom edge of the packaging box 100 from the side and bottom when the drive chain 231 moves, thereby making the bottom of the main body of the packaging box suspended in the air. Each C-shaped bracket 232 is internally provided with a compression spring 233 and a push member 234. The push member 234 is driven by the compression spring 233 to elastically press outward against the side or bottom edge of the packaging box 100, thereby providing more reliable clamping support.

[0036] In some embodiments, as Figure 1 As shown, the system further includes a first rejection mechanism 90 and a second rejection mechanism 91 controlled by the controller. The first rejection mechanism 90 can be located downstream of the visual inspection area 12 to process visually defective products. Specifically, the first rejection mechanism 90 can include a first defective product collection path 901 (e.g., a slide) that diverges from the main conveying path and a pusher 902 (e.g., a cylinder push rod). When the controller detects that a package has a visual defect, it controls the pusher 902 to move the package from the main conveying path into the first defective product collection path 901.

[0037] Similarly, the second rejection mechanism 91 can be set downstream or next to the weighing area 13 to handle weight-defective products. Specifically, it can include a second defective product collection path 911 and a clamping and pushing component 912 (such as a robotic claw). When the controller detects that a packaging box has a weight defect, it will control the clamping and pushing component 912 to operate and package the weight-defective product.

[0038] In the second aspect, the embodiment of the present application provides a multi-vision and precision force-sensing intelligent automatic detection and labeling method, which is applied to the multi-vision and precision force-sensing intelligent automatic detection and labeling device described in any embodiment of the first aspect above. Figures 1 to 5 The device structure shown in FIG. 1 includes the following steps: a) using the conveying mechanism to sequentially convey the packaging box to be inspected through the loading area, the visual inspection area and the weighing area.

[0039] b) When the packaging box is located in the loading area, the clamping and shaping mechanism is used to perform a clamping and shaping process on the packaging box, and the clamping and shaping process includes: driving the first pressure plate to apply pressure to the top surface of the packaging box, and driving the at least one pair of second pressure plates to apply pressure to the opposite sides of the packaging box to form a shaping space that is adapted to the cross-sectional profile of the packaging box.

[0040] c) When the packaging box is located in the visual inspection area, the visual inspection mechanism is used to collect image information of the top surface, the bottom surface, and four side surfaces connecting the top surface and the bottom surface of the packaging box.

[0041] d) When the packaging box is located in the weighing area, the weighing mechanism is used to collect weight information of the packaging box.

[0042] e) using the controller to process the acquired image information and weight information to determine whether the packaging box has appearance defects and weight defects; f) Label the packaging boxes that pass the inspection.

[0043] By executing the above steps, the automatic detection method provided by this application can efficiently and accurately complete comprehensive quality inspection of mobile phone packaging boxes, significantly improving the level of production automation and product quality.

[0044] The intelligent automatic inspection and labeling method and device with multi-eye vision and precision force perception provided in the embodiments of the present application ensure the imaging quality and detection accuracy of six-sided visual inspection by clamping and shaping the packaging box before visual inspection. Combined with the integrated weighing function and the automatic rejection mechanism for unqualified products, it overcomes the problems in the prior art of low detection accuracy caused by irregular packaging boxes, low efficiency and easy errors in manual inspection, and high cost and single function of special inspection equipment, thereby realizing comprehensive, efficient and automated quality control of the appearance and weight of the packaging boxes, reducing equipment investment and labor costs, and improving the level of production automation and product factory qualification rate.

[0045] In the description of this application, it should be noted that the terms "vertical", "up", "down", "horizontal", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on this application.

[0046] It should also be noted that, in the description of this application, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on specific circumstances.

[0047] Finally, it should be noted that the above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. An intelligent automatic inspection and labeling device with multi-vision and precision force sensing, used to detect appearance defects and weight defects of packaging boxes, characterized by: include: The frame has a loading area, a visual inspection area and a weighing area defined on it; a conveying mechanism, disposed on the frame, for conveying the packaging box to be inspected through the loading area, the visual inspection area, and the weighing area in sequence; a visual inspection mechanism, disposed in the visual inspection area, for collecting image information of the top surface, the bottom surface, and four side surfaces connecting the top surface and the bottom surface of the packaging box; a weighing mechanism, disposed in the weighing area, for collecting weight information of the packaging box conveyed to the weighing area; a controller, communicatively connected to the conveying mechanism, the visual inspection mechanism, and the weighing mechanism, respectively, for processing the acquired image information and weight information to determine whether the packaging box has appearance defects and weight defects; A labeling machine is provided downstream of the weighing area and is in communication with the controller, and is used to label qualified packaging boxes; wherein the loading area is provided with a clamping and shaping mechanism, and the clamping and shaping mechanism includes: A driving mechanism; a first pressure plate, configured to be driven by the driving mechanism to apply pressure to the top surface of the packaging box; at least one pair of oppositely arranged second pressure plates, configured to be driven by the driving mechanism to apply pressure to the opposite sides of the packaging box; and the two second pressure plates cooperate with the first pressure plate to enclose a shaping space adapted to the radial cross-section of the packaging box.

2. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 1 is characterized in that: The driving mechanism includes at least one cylinder or electric push rod, which is used to drive the first pressure plate and the at least one pair of second pressure plates separately or in conjunction with each other; wherein, the lower surface of the first pressure plate and / or the inner side surface of the at least one pair of second pressure plates are provided with an elastic buffer layer.

3. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 2 is characterized in that: It also includes a first sensor arranged in the loading area, which is used to detect whether the packaging box reaches the clamping and shaping position; the controller controls the driving mechanism to drive the first pressure plate and the at least one pair of second pressure plates to clamp and shape the packaging box according to the detection signal of the first sensor.

4. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 1 is characterized in that: The visual inspection mechanism includes six cameras corresponding to the top surface, bottom surface, front side surface, rear side surface, left side surface and right side surface of the packaging box respectively.

5. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 4 is characterized in that: The visual detection area is further provided with a retractable blocking member and a second sensor, wherein the second sensor is used to detect whether the packaging box reaches the preset shooting position; the blocking member is controlled by the controller to extend to block the packaging box when it reaches the preset shooting position.

6. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 4 is characterized in that: The conveying mechanism includes a first conveyor belt, a second conveyor belt and a suspended conveying mechanism, the first conveyor belt is used to convey the packaging box from the loading area to the visual inspection area, and the second conveyor belt is used to convey the packaging box from the visual inspection area to the weighing area; the suspended conveying mechanism is arranged in the visual inspection area and located between the first conveyor belt and the second conveyor belt, and the suspended conveying mechanism is used to expose the bottom surface of the packaging box during the process of conveying it; wherein, the controller can independently control the start and stop of the first conveyor belt, the second conveyor belt and the suspended conveying mechanism.

7. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 6 is characterized in that: The suspended conveying mechanism includes two drive chains extending along the conveying direction of the packaging box and configured to move in a circular motion. The drive chains are arranged at an angle, and C-shaped brackets are provided on the chain links of the drive chains. Each of the C-shaped brackets is configured to support the bottom edge of the packaging box from the side and bottom when the drive chain moves; wherein each of the C-shaped brackets is provided with a compression spring and a push member inside, and the push member is driven by the compression spring to elastically press outward against the side or bottom edge of the packaging box.

8. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 1 is characterized in that: It also includes a first rejection mechanism and a second rejection mechanism controlled by the controller, the first rejection mechanism includes a first defective product collection path connected to the downstream of the visual inspection area and a pushing member for pushing the packaging box with appearance defects into the first defective product collection path; the second rejection mechanism includes a second defective product collection path connected to the downstream of the weighing area and a clamping and pushing component for moving the packaging box with weight defects into the second defective product collection path.

9. The intelligent automatic detection and labeling device with multi-eye vision and precision force perception according to claim 8 is characterized in that: The weighing mechanism includes an electronic scale and a barcode scanner arranged above the electronic scale, and the barcode scanner is used to read the identification information on the packaging box; the controller is used to associate the identification information with the collected weight information and store it.

10. An intelligent automatic detection and labeling method using multi-eye vision and precision force perception, characterized in that: The intelligent automatic detection and labeling device with multi-eye vision and precision force perception applied to any one of claims 1 to 9 comprises the following steps: a) using the conveying mechanism to convey the packaging box to be inspected through the loading area, visual inspection area and weighing area in sequence; b) when the packaging box is located in the loading area, using the clamping and shaping mechanism to perform a clamping and shaping process on the packaging box, the clamping and shaping process comprising: driving the first pressing plate to apply pressure to the top surface of the packaging box, and driving the at least one pair of second pressing plates to apply pressure to the opposite sides of the packaging box to form a shaping space that matches the cross-sectional profile of the packaging box; c) when the packaging box is located in the visual inspection area, using the visual inspection mechanism to collect image information of the top surface, bottom surface and four side surfaces connecting the top surface and bottom surface of the packaging box; d) when the packaging box is located in the weighing area, using the weighing mechanism to collect weight information of the packaging box; e) using the controller to process the acquired image information and weight information to determine whether the packaging box has appearance defects and weight defects; f) Label the packaging boxes that pass the inspection.

Images