Junction box cover grabbing system and method based on visual inspection

Abstract

The invention provides a junction box cover grabbing system and method based on visual inspection. The method comprises the steps that S1, image information of a junction box cover in a flexible vibration disc is obtained through a visual inspection device; s2, for each junction box cover, judging whether the junction box cover meets a preset size requirement or not according to the corresponding size data, and taking the junction box cover meeting the preset size requirement as a target junction box cover; s3, for each target junction box cover, judging whether the target junction box cover meets the grabbing requirement or not according to the corresponding line data; and S4, when the grabbing requirement is met, the box cover picking device is controlled to grab the box cover to a target area based on the corresponding position data. According to the terminal box cover grabbing system, through the synergistic effect of all the assemblies in the terminal box cover grabbing system, the compatibility of different box cover types is improved, the stability and the automation level of the production process are improved, and therefore the modern automatic production requirement for frequent cutting is met.

Description

Technical Field

[0001] This application relates to the technical field of visual inspection, and particularly to a grabbing system and method for junction box covers based on visual inspection. Background Art

[0002] Domestic photovoltaic module factories have adopted automatic installation production lines for module junction box covers. Currently, in the domestic photovoltaic field, more and more component production companies choose to provide OEM services for leading module factories. The market urgently needs a highly adaptable junction box cover machine. Therefore, the identification, detection, and positioning of various junction box covers are important parts of grabbing the junction box covers.

[0003] Traditional junction box cover machines use a conch vibrating disk in cooperation with a runner for cyclic feeding. The conch vibrating disk solution cannot meet the current concept of automated production with frequent cutting patterns, is prone to jamming the box covers, and cannot be compatible with different types of box covers. There are deficiencies in terms of compatibility and stability.

[0004] Based on this, this application provides a grabbing system and method for junction box covers based on visual inspection. Summary of the Invention

[0005] In order to overcome the above-mentioned technical deficiencies, this application provides a grabbing system and method for junction box covers based on visual inspection.

[0006] The objectives of this application are achieved by adopting the following technical solutions:

[0007] In a first aspect, this application provides a grabbing system for junction box covers based on visual inspection, including a conveying device, and further including a flexible vibrating disk, a visual inspection device, a box cover picking device, and a controller; the flexible vibrating disk is arranged at the end of the conveying device for receiving the junction box covers conveyed by the conveying device; the visual inspection device, the picking device, and the controller are communicatively connected, and the controller is configured to:

[0008] S1, use the visual inspection device to obtain the image information of the junction box covers in the flexible vibrating disk, where the image information includes the size data, texture data, and position data of each junction box cover;

[0009] S2, for each junction box cover, determine whether it meets the preset size requirements according to its corresponding size data, and regard the junction box covers that meet the preset size requirements as target junction box covers;

[0010] S3, for each target junction box cover, determine whether it meets the grabbing requirements according to its corresponding texture data;

[0011] S4, when it meets the grabbing requirements, control the box cover picking device to grab it to the target area based on its corresponding position data.

[0012] The beneficial effects of this technical solution are as follows. The use of a flexible vibrating bowl solves the problem that traditional conch vibrating bowls cannot be compatible with multiple types of box lids, and can meet the automated production requirements of frequent die-cutting, improving the flexibility and adaptability of the production line. By collecting image information through a vision detection device and combining double judgments of size and texture, it is ensured that only the junction box lids that meet the requirements are picked up, improving the accuracy of detection and grasping, reducing the defective rate, and enhancing the quality of the final product.

[0013] In summary, through the collaborative work of the flexible vibrating bowl, the vision detection device, and the box lid picking device, this technical solution realizes the efficient, accurate, and intelligent grasping of junction box lids.

[0014] Preferably, the vision detection device includes a high-definition camera, and the high-definition camera is used to collect two-dimensional images inside the flexible vibrating bowl;

[0015] The controller is configured to use the vision detection device to obtain the image information of the junction box lids inside the flexible vibrating bowl, including:

[0016] According to the two-dimensional image, obtain the two-dimensional image contour data of each junction box lid;

[0017] According to the two-dimensional image contour data of each junction box lid, delete the size data, texture data, and position data of adjacent and overlapping junction box lids, and use the remaining size data, texture data, and position data of the junction box lids as image information.

[0018] The beneficial effects of this technical solution are as follows. By extracting the two-dimensional image contour data, the contour of each junction box lid can be accurately identified, ensuring that only the data of non-overlapping junction box lids are retained, improving the accuracy and efficiency of subsequent processing. By deleting the data of overlapping junction box lids, the situation of mis-grasping or grasping failure caused by superposition is avoided, ensuring the success rate of the grasping operation.

[0019] Preferably, the box lid picking device includes a suction cup manipulator, and the suction cup manipulator is used to adsorb the front side of the junction box lid; the methods for judging whether the junction box lid meets the grasping requirements include:

[0020] Obtain the preset texture data of the target junction box lid to be grasped, and the preset texture data is collected when the junction box lid to be grasped is face up;

[0021] Obtain the similarity between the texture data of the target junction box lid and the preset texture data, and consider that the target junction box lid with a similarity not less than the preset similarity meets the grasping requirements.

[0022] The beneficial effects of this technical solution are as follows. By comparing with the preset texture data, it is ensured that only the junction box covers meeting the requirements (surface texture features) are grasped, improving the accuracy and reliability of grasping. Through the update of the preset texture data, different types of junction box covers can be quickly switched, enhancing the compatibility and flexibility of the method. Through similarity calculation and intelligent judgment, manual intervention is reduced, and production efficiency is improved.

[0023] Preferably, the controller is further configured to:

[0024] When the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating bowl is lower than the first preset number of box covers, control the conveying device to operate and convey junction box covers to the flexible vibrating bowl until the number of target junction box covers in the flexible vibrating bowl is not lower than the second preset number of box covers; the first preset number of box covers is lower than the second preset number of box covers.

[0025] The beneficial effects of this technical solution are as follows. It can automatically detect the number of junction box covers in the flexible vibrating bowl and automatically trigger the conveying device to replenish when the number is insufficient, reducing manual intervention and improving production efficiency. By setting the first preset number of box covers and the second preset number of box covers, the number range of junction box covers in the bowl can be accurately controlled to ensure the continuity and stability of the production process. Through the combination of visual detection and intelligent control, an intelligent production process management is achieved, enhancing the overall automation level and intelligence degree of production.

[0026] Preferably, the flexible vibrating bowl includes a four-axis motor and a vibrating bowl body. The four-axis motor is used to turn over and adjust the position of the junction box covers placed in the vibrating bowl body through vibration. When the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating bowl is not lower than the first preset number of box covers, and the number of target junction box covers meeting the grasping requirements is lower than the preset grasping number, the controller is further configured to:

[0027] Control the flexible vibrating bowl to vibrate until the number of target junction box covers meeting the grasping requirements is not lower than the preset grasping number; then execute S4;

[0028] When the number of target junction box covers meeting the grasping requirements is lower than the preset grasping number within the preset time duration, generate a warning message and send it to the warning device.

[0029] The beneficial effects of this technical solution are as follows. It can automatically detect and adjust the state of the junction box covers in the flexible vibrating bowl to ensure that there are enough target junction box covers meeting the grasping requirements, reducing manual intervention and improving production efficiency.

[0030] Second aspect, the present application further provides a method for grasping a junction box cover based on visual detection, which is applied to the junction box cover grasping system described in any item of the first aspect. The method includes:

[0031] S1. Use a visual detection device to obtain image information of the junction box covers in the flexible vibrating disk. The image information includes size data, texture data, and position data of each junction box cover.

[0032] S2. For each junction box cover, judge whether it meets the preset size requirement according to its corresponding size data, and regard the junction box cover that meets the preset size requirement as the target junction box cover.

[0033] S3. For each target junction box cover, judge whether it meets the grasping requirement according to its corresponding texture data.

[0034] S4. When it meets the grasping requirement, based on its corresponding position data, control the box cover picking device to grasp it to the target area.

[0035] Preferably, the visual detection device includes a high-definition camera, and the high-definition camera is used to collect a two-dimensional image in the flexible vibrating disk.

[0036] The step of using the visual detection device to obtain image information of the junction box covers in the flexible vibrating disk includes:

[0037] According to the two-dimensional image, obtain two-dimensional image contour data of each junction box cover.

[0038] According to the two-dimensional image contour data of each junction box cover, delete the size data, texture data, and position data of adjacent and overlapping junction box covers, and use the remaining size data, texture data, and position data of the junction box covers as the image information.

[0039] Preferably, the box cover picking device includes a suction cup manipulator, and the suction cup manipulator is used to adsorb the front side of the junction box cover. The method for judging whether the junction box cover meets the grasping requirement includes:

[0040] Obtain the preset texture data of the target junction box cover to be grasped, and the preset texture data is collected when the junction box cover to be grasped is face up.

[0041] Obtain the similarity between the texture data of the target junction box cover and the preset texture data, and consider that the target junction box cover with a similarity not less than the preset similarity meets the grasping requirement.

[0042] Preferably, the method further includes:

[0043] When the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating disk is lower than the first preset number of box covers, control the conveying device to operate and convey the junction box covers to the flexible vibrating disk until the number of target junction box covers in the flexible vibrating disk is not lower than the second preset number of box covers; the first preset number of box covers is lower than the second preset number of box covers.

[0044] Preferably, the flexible vibrating disk includes a four-axis motor and a vibrating disk body. The four-axis motor is used to turn over and adjust the position of the junction box covers placed on the vibrating disk body through vibration. When the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating disk is not lower than the first preset number of box covers, and the number of target junction box covers meeting the grasping requirements is lower than the preset grasping number, the method further includes:

[0045] Controlling the flexible vibrating disk to vibrate until the number of target junction box covers meeting the grasping requirements is not lower than the preset grasping number; then execute S4;

[0046] When the number of target junction box covers meeting the grasping requirements within the preset time period is lower than the preset grasping number, generate a warning message and send it to the warning device. Description of the Drawings

[0047] The present application will be further described below in conjunction with the drawings and embodiments.

[0048] Figure 1 FIG. is a schematic flowchart of a method for grasping a junction box cover based on visual detection provided by an embodiment of the present application.

[0049] Figure 2 FIG. is a schematic flowchart of a method for obtaining image information provided by an embodiment of the present application.

[0050] Figure 3 FIG. is a structural block diagram of a junction box cover grasping system provided by an embodiment of the present application. Detailed Embodiments

[0051] Next, in conjunction with the drawings and specific embodiments, the present application will be further described. It should be noted that, on the premise of no conflict, the following-described embodiments or technical features can be arbitrarily combined to form new embodiments. The following will illustrate the implementation procedures of the present application with reference to the drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation procedures. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for explaining the present application, rather than for limiting the protection scope of the present application.

[0052] Regarding the traditional junction box cover machine mentioned in the background art, a conch vibrating bowl is used in cooperation with a runner for cyclic feeding. The conch vibrating bowl solution cannot meet the current concept of automated production with frequent cutting patterns, is prone to jamming the box covers, and cannot be compatible with different types of box covers. There are deficiencies in terms of compatibility and stability.

[0053] The junction box cover grasping system mentioned in this application includes components such as a conveying device, a flexible vibrating bowl, a visual detection device, a box cover picking device, and a controller. The flexible vibrating bowl is arranged at the end of the conveying device and is used to receive the junction box covers conveyed by the conveying device; the conveying device, the visual detection device, the picking device, and the controller are communicatively connected. The visual detection device includes a high-definition camera, and the high-definition camera is used to collect two-dimensional images inside the flexible vibrating bowl. The box cover picking device includes a suction cup manipulator, and the suction cup manipulator is used to adsorb the front side of the junction box cover. The flexible vibrating bowl includes a four-axis motor and a vibrating bowl body, and the four-axis motor is used to turn over and adjust the position of the junction box covers placed in the vibrating bowl body through vibration.

[0054] Among them, compared with the conch vibrating bowl, the flexible vibrating bowl can adapt to box covers of different shapes and sizes, avoid the phenomenon of jamming the box covers. At the same time, the visual detection device can accurately identify and locate various types of box covers, providing reliable information for subsequent grasping and assembly. The controller can adjust the working state of the conveying device, the vibration condition of the vibrating bowl, and the actions of the picking device according to the feedback of the visual detection device to ensure the stable conveying and accurate grasping of the box covers. Through the coordinated action of each component of the entire system, not only the compatibility with different box cover types is improved, but also the stability and automation level of the production process are enhanced, so as to meet the requirements of modern automated production with frequent cutting patterns. The method will be described first below, and then the system and others will be described.

[0055] Method embodiment.

[0056] See Figure 1 , Figure 1 which is a schematic flow chart of a method for grasping a junction box cover based on visual detection provided by an embodiment of this application.

[0057] An embodiment of this application provides a method for grasping a junction box cover based on visual detection, which is applied to the junction box cover grasping system described above. The method includes:

[0058] S101, using the visual detection device to obtain the image information of the junction box covers inside the flexible vibrating bowl, where the image information includes the size data, texture data, and position data of each junction box cover;

[0059] A vision detection device (such as a high-definition camera) is installed above or around the flexible vibrating bowl, and is used to collect image information of the junction box cover in the flexible vibrating bowl in real time. The collected image information includes the size data (such as length, width, and height), texture data (such as surface texture features), and position data (such as the coordinate position in the vibrating bowl) of the junction box cover.

[0060] S102. For each junction box cover, determine whether it meets the preset size requirements according to its corresponding size data, and use the junction box cover that meets the preset size requirements as the target junction box cover;

[0061] According to the preset size requirements (such as the standard size range of the junction box cover), compare the collected size data. The junction box cover that meets the preset size requirements is marked as the target junction box cover and enters the next texture judgment link. The junction box covers that do not meet the size requirements are excluded to avoid unnecessary subsequent processing.

[0062] S103. For each target junction box cover, determine whether it meets the grasping requirements according to its corresponding texture data;

[0063] For each target junction box cover, analyze its texture data to determine whether it meets the grasping requirements. The junction box covers that meet the grasping requirements will be further processed.

[0064] S104. When the grasping requirements are met, based on its corresponding position data, control the cover picking device to grasp it to the target area.

[0065] When the junction box cover passes the double judgment of size and texture, control the cover picking device (such as a suction cup manipulator) to accurately move to the corresponding position according to its position data. The picking device completes the grasping action and transfers the junction box cover to the target area (such as an assembly station or a temporary storage area).

[0066] Thus, the use of the flexible vibrating bowl solves the problem that the traditional conch vibrating bowl cannot be compatible with multiple cover models, can adapt to the automated production requirements of frequent die-cutting, and improves the flexibility and adaptability of the production line. By collecting image information through the vision detection device and combining the double judgment of size and texture, it is ensured that only the junction box covers that meet the requirements are picked up, improving the accuracy of detection and grasping, reducing the defective rate, and improving the quality of the final product.

[0067] In summary, through the collaborative work of the flexible vibrating bowl, the vision detection device, and the cover picking device, the present technical solution realizes the efficient, accurate, and intelligent grasping of the junction box cover.

[0068] See Figure 2 , Figure 2 which is a schematic flowchart of a process for obtaining image information provided by an embodiment of the present application.

[0069] In some embodiments, obtaining the image information of the junction box cover in the flexible vibrating bowl by using the vision detection device includes:

[0070] S201. Obtain the two-dimensional image contour data of each junction box cover according to the two-dimensional image;

[0071] The vision detection device is installed above or around the flexible vibrating bowl and is used to collect the two-dimensional image of the junction box cover in the flexible vibrating bowl in real time. The collected two-dimensional image contains the contour information of the junction box cover. For example, the two-dimensional image contour data of each junction box cover can be extracted from the two-dimensional image through an image processing algorithm (such as an edge detection algorithm).

[0072] S202. Delete the size data, texture data, and position data of adjacent and overlapping junction box covers according to the two-dimensional image contour data of each junction box cover, and use the remaining size data, texture data, and position data of the junction box covers as the image information.

[0073] According to the extracted two-dimensional image contour data, judge whether there is an overlapping situation between the junction box covers. For adjacent and overlapping junction box covers, delete their corresponding size data, texture data, and position data. The remaining junction box cover data that does not overlap with other junction box covers is used as the image information for subsequent processing.

[0074] Thus, by extracting the two-dimensional image contour data, the contour of each junction box cover can be accurately identified, ensuring that only the data of non-overlapping junction box covers is retained, improving the accuracy and efficiency of subsequent processing. By deleting the data of overlapping junction box covers, the situation of mis-grasping or grasping failure caused by overlapping is avoided, ensuring the success rate of the grasping operation.

[0075] In some embodiments, the method for judging whether the junction box cover meets the grasping requirements includes:

[0076] Obtain the preset texture data of the target junction box cover to be grasped, where the preset texture data is collected when the junction box cover to be grasped is face up;

[0077] Obtain the similarity between the texture data of the target junction box cover and the preset texture data, and consider that the target junction box cover with a similarity not less than the preset similarity meets the grasping requirements.

[0078] During the production or initialization stage of the junction box cover, the texture data of the to-be-gripped junction box cover when it is face-up is pre-collected and stored as preset texture data, which serves as the criterion for subsequent judgment. In the flexible vibrating bowl, the vision detection device continuously collects the texture data of the current junction box cover. The texture data includes the texture features on the surface of the junction box cover, such as lines, patterns, etc. Through image processing and pattern recognition algorithms, the similarity between the currently collected texture data and the preset texture data is calculated. Multiple algorithms can be used for similarity calculation, such as template matching, feature point comparison, etc. A preset similarity threshold is set. When the calculated similarity is not less than this preset similarity, it is considered that the current junction box cover meets the gripping requirements and can be gripped; otherwise, if the similarity is lower than the preset threshold, it is considered that it does not meet the gripping requirements. The preset similarity is, for example, 0.90, 0.93, 0.98.

[0079] Thus, by comparing with the preset texture data, it is ensured that only the junction box covers that meet the requirements (surface texture features) are gripped, improving the accuracy and reliability of gripping. Through the update of the preset texture data, different types of junction box covers can be quickly switched, improving the compatibility and flexibility of the method. Through similarity calculation and intelligent judgment, manual intervention is reduced and production efficiency is improved.

[0080] In some embodiments, controlling the lid picking device to grip it to the target area based on its corresponding position data includes:

[0081] According to the similarity value corresponding to each junction box cover that meets the gripping requirements, the lid picking device is controlled in order of size to grip the corresponding junction box cover to the target area. It can be considered that the junction box covers that meet the gripping requirements are sorted according to the similarity value, and the junction box covers with higher similarity values are gripped first.

[0082] In some embodiments, the method further includes:

[0083] When the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating bowl is lower than the first preset lid number, control the conveying device to operate and convey junction box covers to the flexible vibrating bowl until the number of target junction box covers in the flexible vibrating bowl is not less than the second preset lid number; the first preset lid number is lower than the second preset lid number.

[0084] The visual detection device collects the two-dimensional images of the junction box covers in the flexible vibrating bowl in real time, and identifies and counts the number of target junction box covers through image processing algorithms. Compare the currently recognized number of target junction box covers with the preset first preset number of box covers. When the number of target junction box covers is lower than the first preset number of box covers, the controller triggers the conveying device to start running. The conveying device conveys new junction box covers from the upstream station to the flexible vibrating bowl. As the conveying device runs, new junction box covers are continuously fed into the flexible vibrating bowl, and the visual detection device continuously monitors the number of junction box covers in the bowl. When the number of target junction box covers in the bowl reaches or exceeds the second preset number of box covers, the controller sends a signal to stop the operation of the conveying device. The first preset number of box covers is, for example, 10, 15, 20; the second preset number of box covers is, for example, 22, 25, 30.

[0085] Thus, it is possible to automatically detect the number of junction box covers in the flexible vibrating bowl, and automatically trigger the conveying device to replenish when the number is insufficient, reducing manual intervention and improving production efficiency. By setting the first preset number of box covers and the second preset number of box covers, the number range of junction box covers in the bowl can be accurately controlled to ensure the continuity and stability of the production process. Through the combination of visual detection and intelligent control, an intelligent production process management is achieved, improving the overall automation level and intelligence degree of production.

[0086] In some embodiments, when the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating bowl is not lower than the first preset number of box covers, and the number of target junction box covers that meet the grasping requirements is lower than the preset grasping number, the method further includes:

[0087] S105; control the flexible vibrating bowl to vibrate until the number of target junction box covers that meet the grasping requirements is not lower than the preset grasping number; then execute S104;

[0088] S106; when the number of target junction box covers that meet the grasping requirements is lower than the preset grasping number within the preset time period, generate a warning message and send it to the warning device.

[0089] The vision detection device collects two-dimensional images of the junction box covers in the flexible vibrating bowl in real time, identifies and counts the number of target junction box covers, and at the same time determines the number of target junction box covers that meet the grasping requirements. Compare the currently identified number of target junction box covers with the first preset number of box covers, and check whether the number of target junction box covers that meet the grasping requirements reaches the preset grasping number. When the number of target junction box covers is not less than the first preset number of box covers, but the number of target junction box covers that meet the grasping requirements is less than the preset grasping number, control the flexible vibrating bowl to vibrate. The flexible vibrating bowl vibrates to rearrange and turn over the junction box covers, so as to increase the number of target junction box covers that meet the grasping requirements. It is possible to continuously monitor the number of target junction box covers that meet the grasping requirements, and when the number reaches the preset grasping number, perform the grasping operation (S104). If within the preset time period (for example, 3 minutes, 5 minutes), the number of target junction box covers that meet the grasping requirements still does not reach the preset grasping number (for example, 3, 5), generate a warning message and send it to the warning device to prompt the operator to intervene. Among them, the value of the preset grasping number is, for example, the proportional number of the number of target junction box covers. For example, if there are 15 target junction boxes and the preset grasping number is 60% of the number of target junction boxes, that is, 9. Thus, it is possible to automatically detect and adjust the state of the junction box covers in the flexible vibrating bowl, ensure that there are enough target junction box covers that meet the grasping requirements, reduce manual intervention, and improve production efficiency.

[0090] As an example, a method for grasping a junction box cover based on vision detection is provided, including:

[0091] P1. Use the vision detection device to obtain a two-dimensional image in the flexible vibrating bowl, and according to the two-dimensional image, obtain the two-dimensional image contour data of each junction box cover; when the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating bowl is lower than the first preset number of box covers, control the conveying device to run and convey junction box covers to the flexible vibrating bowl until the number of target junction box covers in the flexible vibrating bowl is not less than the second preset number of box covers; the first preset number of box covers is lower than the second preset number of box covers;

[0092] When the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating bowl is not less than the first preset number of box covers, or when controlling the conveying device to run and convey junction box covers to the flexible vibrating bowl until the number of target junction box covers in the flexible vibrating bowl is not less than the second preset number of box covers, delete the size data, texture data and position data of adjacent and overlapping junction box covers according to the two-dimensional image contour data of each junction box cover, and use the remaining size data, texture data and position data of the junction box covers as image information;

[0093] P2. For each junction box cover, determine whether it meets the preset size requirements according to its corresponding size data, and regard the junction box cover that meets the preset size requirements as the target junction box cover. Specifically, obtain the preset texture data of the target junction box cover to be grasped, where the preset texture data is collected when the junction box cover to be grasped is face up; obtain the similarity between the texture data of the target junction box cover and the preset texture data, and consider that the target junction box cover with a similarity not less than the preset similarity meets the grasping requirements.

[0094] P3. For each target junction box cover, determine whether it meets the grasping requirements according to its corresponding texture data; when the two-dimensional image indicates that the number of target junction box covers in the flexible vibrating disk is not less than the first preset number of box covers, and the number of target junction box covers that meet the grasping requirements is less than the preset grasping number, control the flexible vibrating disk to vibrate until the number of target junction box covers that meet the grasping requirements is not less than the preset grasping number; then execute P4; when the number of target junction box covers that meet the grasping requirements within the preset time is less than the preset grasping number, generate a warning message and send it to the warning device.

[0095] P4. For the junction box covers that meet the grasping requirements, control the box cover picking device to grasp them to the target area based on their corresponding position data.

[0096] In this technical solution, the vision detection device real-time collects the two-dimensional images of the junction box covers in the flexible vibrating disk and extracts the two-dimensional image contour data of each junction box cover. According to the two-dimensional image, determine whether the number of target junction box covers in the flexible vibrating disk is less than the first preset number of box covers. If so, control the conveying device to operate and convey the junction box covers to the flexible vibrating disk until the number reaches the second preset number of box covers. When the number of target junction box covers is not less than the first preset number of box covers, further process the image data, delete the data of adjacent and overlapping junction box covers, and retain the data of non-overlapping junction box covers as the image information for subsequent processing. For each junction box cover, determine whether it meets the preset size requirements according to its size data, and the junction box covers that meet the size requirements are marked as target junction box covers. Obtain the preset texture data and the current texture data of the target junction box covers, calculate the similarity between the two, and the junction box covers with a similarity not less than the preset similarity are considered to meet the grasping requirements (i.e., the surface to be grasped is the front). When the number of target junction box covers is not less than the first preset number of box covers, but the number of target junction box covers that meet the grasping requirements is less than the preset grasping number (such as 1 or 2), control the flexible vibrating disk to vibrate to increase the number of target junction box covers that meet the grasping requirements. If the number of target junction box covers that meet the grasping requirements still does not reach the preset grasping number within the preset time, generate a warning message and send it to the warning device. For the junction box covers that meet the grasping requirements, control the box cover picking device to grasp them to the target area based on their corresponding position data.

[0097] The method for grasping the junction box cover based on visual detection combines a flexible vibrating disk, machine vision, and image processing technology, and is applicable to application scenarios with frequent cutting of various box covers. To a certain extent, it solves the two problems of inspection speed and compatibility. It monitors the number of junction box covers in the flexible vibrating disk in real time through a visual detection device. When the number is lower than the first preset value, the conveying device is automatically triggered to replenish materials until the number reaches the second preset value, realizing automatic material replenishment, reducing manual intervention, and improving production efficiency. It can accurately control the number range of junction box covers in the disk to ensure production continuity and stability. Through visual detection and texture similarity judgment, it can efficiently grasp the junction box covers that meet the requirements, improving the grasping success rate and efficiency. In addition, it can record and analyze the grasping data for quality traceability and data analysis, and prompt the operator to intervene through a warning mechanism when necessary to avoid production accidents.

[0098] System embodiment.

[0099] See Figure 3 , Figure 3 is the structural block diagram of a junction box cover grasping system provided by an embodiment of the present application.

[0100] An embodiment of the present application provides a junction box cover grasping system based on visual detection. Its specific implementation manner is consistent with the implementation manner and the achieved technical effects recorded in the above method implementation manner, and some contents will not be repeated.

[0101] The junction box cover grasping system includes a conveying device, and also includes a flexible vibrating disk, a visual detection device, a box cover picking device, and a controller; the flexible vibrating disk is arranged at the end of the conveying device and is used to receive the junction box covers conveyed by the conveying device; the visual detection device, the picking device, and the controller are communicatively connected, and the conveying device and the warning device mentioned below can also be communicatively connected to the controller. The warning device is, for example, one or a combination of a buzzer, a light alarm, and an alarm display screen; the controller is configured to:

[0102] S1. Use the visual detection device to obtain the image information of the junction box covers in the flexible vibrating disk, where the image information includes the size data, texture data, and position data of each junction box cover;

[0103] S2. For each junction box cover, judge whether it meets the preset size requirement according to its corresponding size data, and regard the junction box cover that meets the preset size requirement as the target junction box cover;

[0104] S3. For each target junction box cover, judge whether it meets the grasping requirement according to its corresponding texture data;

[0105] S4. When the grasping requirements are met, based on the corresponding position data, control the lid picking device to pick it up to the target area.

[0106] In some embodiments, the vision detection device includes a high-definition camera, and the high-definition camera is used to collect two-dimensional images inside the flexible vibrating disk.

[0107] The controller is configured to use the vision detection device to obtain the image information of the junction box lid inside the flexible vibrating disk, including:

[0108] According to the two-dimensional image, obtain the two-dimensional image contour data of each junction box lid.

[0109] According to the two-dimensional image contour data of each junction box lid, delete the size data, texture data, and position data of adjacent and overlapping junction box lids, and use the remaining size data, texture data, and position data of the junction box lids as the image information.

[0110] In some embodiments, the lid picking device includes a suction cup manipulator, and the suction cup manipulator is used to adsorb the front side of the junction box lid. The method for determining whether the junction box lid meets the grasping requirements includes:

[0111] Obtain the preset texture data of the target junction box lid to be grasped, and the preset texture data is collected when the junction box lid to be grasped is face up.

[0112] Obtain the similarity between the texture data of the target junction box lid and the preset texture data, and consider that the target junction box lid with a similarity not less than the preset similarity meets the grasping requirements.

[0113] In some embodiments, the controller is further configured to:

[0114] When the two-dimensional image indicates that the number of target junction box lids inside the flexible vibrating disk is lower than the first preset lid number, control the conveying device to run and convey junction box lids to the flexible vibrating disk until the number of target junction box lids inside the flexible vibrating disk is not less than the second preset lid number; the first preset lid number is lower than the second preset lid number.

[0115] In some embodiments, the flexible vibrating disk includes a four-axis motor and a vibrating disk body, and the four-axis motor is used to turn over and adjust the position of the junction box lid placed on the vibrating disk body through vibration. When the two-dimensional image indicates that the number of target junction box lids inside the flexible vibrating disk is not less than the first preset lid number, and the number of target junction box lids that meet the grasping requirements is lower than the preset grasping number, the controller is further configured to:

[0116] Control the vibration of the flexible vibrating disk until the number of target junction box covers that meet the grasping requirements is not less than the preset grasping quantity; then execute S4;

[0117] When the number of target junction box covers that meet the grasping requirements within the preset time period is lower than the preset grasping quantity, generate a warning message and send it to the warning device.

[0118] It should be noted that, in the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of a single item or multiple items. For example, at least one (item) of a, b, or c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple. It should be noted that "at least one (item)" can also be interpreted as "one (item) or more (items)".

[0119] The terms "first", "second", etc. in the description, claims, and the above-mentioned drawings of the present application are configured to distinguish similar objects and do not necessarily need to be configured to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0120] From the perspectives of usage purpose, efficacy, progress, and novelty, the present application has been described and has met the functional enhancement and usage requirements emphasized by the patent law. The above description and the accompanying drawings of the present application are only preferred embodiments of the present application and do not limit the present application thereto. Therefore, all those that are similar or identical to the structure, device, features, etc. of the present application, that is, all equivalent replacements or modifications made according to the scope of the patent application of the present application, shall fall within the scope of the patent application protection of the present application.

Claims

1. A junction box cover grabbing system based on visual inspection, comprising a conveying device, characterized in that: It also includes a flexible vibration plate, a visual inspection device, a box cover picking device and a controller; the flexible vibration plate is arranged at the end of the conveying device, and is used to receive the junction box cover conveyed by the conveying device; the visual inspection device, the picking device and the controller are in communication connection, and the controller is configured as follows: S1, using the visual inspection device to obtain image information of the junction box cover in the flexible vibration plate, wherein the image information includes size data, texture data and position data of each junction box cover; S2, for each junction box cover, judging whether it meets the preset size requirement according to its corresponding size data, and taking the junction box cover that meets the preset size requirement as the target junction box cover; S3, for each target junction box cover, judging whether it meets the grasping requirements according to its corresponding texture data; S4, when the grabbing requirements are met, the box cover picking device is controlled based on its corresponding position data to grab it to the target area.

2. The junction box cover grabbing system according to claim 1, characterized in that: The visual inspection device includes a high-definition camera, which is used to collect a two-dimensional image inside the flexible vibration plate; The controller is configured to obtain image information of the junction box cover in the flexible vibration plate by using the visual detection device, including: According to the two-dimensional image, acquiring two-dimensional image contour data of each junction box cover; According to the two-dimensional image contour data of each junction box cover, the size data, texture data and position data of adjacent overlapping junction box covers are deleted, and the size data, texture data and position data of the remaining junction box covers are used as image information.

3. The junction box cover grabbing system according to claim 2, characterized in that: The box cover picking device includes a suction cup manipulator, and the suction cup manipulator is used to absorb the front of the junction box cover; the method for judging whether the junction box cover meets the grasping requirements includes: Acquire preset texture data of a target junction box cover to be grasped, wherein the preset texture data is collected when the junction box cover to be grasped is facing up; The similarity between the texture data of the target junction box cover and the preset texture data is obtained, and the target junction box cover whose similarity is not less than the preset similarity is considered to meet the grasping requirements.

4. The junction box cover grabbing system according to claim 3, characterized in that: The controller is also configured to: When the two-dimensional image indicates that the target number of junction box covers in the flexible vibration tray is lower than the first preset number of box covers, the conveying device is controlled to operate and convey the junction box covers to the flexible vibration tray until the target number of junction box covers in the flexible vibration tray is not lower than the second preset number of box covers; and the first preset number of box covers is lower than the second preset number of box covers.

5. The junction box cover grabbing system according to claim 4, characterized in that: The flexible vibration plate comprises a four-axis motor and a vibration plate body, wherein the four-axis motor is used to realize the turning over and position adjustment of the junction box cover placed on the vibration plate body through vibration; when the two-dimensional image indicates that the number of target junction box covers in the flexible vibration plate is not less than the first preset number of covers, and the number of target junction box covers that meet the grasping requirements is less than the preset grasping number, the controller is further configured to: Controlling the flexible vibration plate to vibrate until the number of target junction box covers that meet the grasping requirements is not less than a preset grasping number; then executing S4; When the number of target junction box covers that meet the grasping requirements within the preset time period is lower than the preset grasping quantity, a warning message is generated and sent to the warning device.

6. A method for grabbing a junction box cover based on visual inspection, characterized in that: The method applied to the junction box cover grabbing system according to any one of claims 1 to 5 comprises: S1, using a visual inspection device to obtain image information of the junction box covers in the flexible vibration plate, wherein the image information includes size data, texture data and position data of each junction box cover; S2, for each junction box cover, judging whether it meets the preset size requirement according to its corresponding size data, and taking the junction box cover that meets the preset size requirement as the target junction box cover; S3, for each target junction box cover, judging whether it meets the grasping requirements according to its corresponding texture data; S4, when the grabbing requirements are met, the box cover picking device is controlled based on its corresponding position data to grab it to the target area.

7. The method for grabbing the junction box cover according to claim 6, characterized in that: The visual inspection device includes a high-definition camera, which is used to collect a two-dimensional image inside the flexible vibration plate; The method of obtaining image information of the junction box cover in the flexible vibration plate by using a visual detection device includes: According to the two-dimensional image, acquiring two-dimensional image contour data of each junction box cover; According to the two-dimensional image contour data of each junction box cover, the size data, texture data and position data of adjacent overlapping junction box covers are deleted, and the size data, texture data and position data of the remaining junction box covers are used as image information.

8. The method for grabbing the junction box cover according to claim 7, characterized in that: The box cover picking device includes a suction cup manipulator, and the suction cup manipulator is used to absorb the front of the junction box cover; the method for judging whether the junction box cover meets the grasping requirements includes: Acquire preset texture data of a target junction box cover to be grasped, wherein the preset texture data is collected when the junction box cover to be grasped is facing up; The similarity between the texture data of the target junction box cover and the preset texture data is obtained, and the target junction box cover whose similarity is not less than the preset similarity is considered to meet the grasping requirements.

9. The method for grabbing the junction box cover according to claim 8, characterized in that: The method further comprises: When the two-dimensional image indicates that the target number of junction box covers in the flexible vibration tray is lower than the first preset number of box covers, the conveying device is controlled to operate and convey the junction box covers to the flexible vibration tray until the target number of junction box covers in the flexible vibration tray is not lower than the second preset number of box covers; and the first preset number of box covers is lower than the second preset number of box covers.

10. The method for grabbing the junction box cover according to claim 9, characterized in that: The flexible vibration plate comprises a four-axis motor and a vibration plate body, wherein the four-axis motor is used to realize the turning over and position adjustment of the junction box cover placed on the vibration plate body through vibration; when the two-dimensional image indicates that the number of target junction box covers in the flexible vibration plate is not less than the first preset number of covers, and the number of target junction box covers that meet the grasping requirements is less than the preset grasping number, the method further comprises: Controlling the flexible vibration plate to vibrate until the number of target junction box covers that meet the grasping requirements is not less than a preset grasping number; then executing S4; When the number of target junction box covers that meet the grasping requirements within the preset time period is lower than the preset grasping quantity, a warning message is generated and sent to the warning device.

Images