Automatic material roll monitoring method
Through artificial intelligence vision technology, the automatic monitoring and management of the material rolls of the SMT piece punching machine has been solved, and the problem of frequent manual inspection and material handling in the existing technology has been realized, which has realized automatic material roll management, saving labor costs and avoiding production delays.
Patent Information
- Application Number
- CN202510511354.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-22
- Publication Date
- 2025-06-27
AI Technical Summary
The existing technology lacks automated roll monitoring and feeding methods, resulting in frequent manual inspections and feeding materials, which can easily lead to production delays.
Artificial intelligence vision technology is used to obtain the image of the spare material roll through the capture device. The controller confirms the position of the tape head of the material roll, and automatically disassembles and collects materials. By identifying the image of the material strip connection, it realizes automatic docking between the spare material roll and the working material roll.
It realizes automated roll management without manual monitoring, saves labor costs, avoids production delays caused by roll exhaustion, and improves production stability and efficiency.
Smart Images
Figure CN120224671A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to a monitoring method, and particularly to an automated tape reel monitoring method. Background Art
[0002] The surface-mount technology (SMT) mounter is an important device for printed circuit board assembly (PCBA) processing and production, mainly used for the installation of electronic components in electronic product processing.
[0003] The automated SMT mounter not only increases the output value of electronic product processing, but also provides stable and reliable quality assurance for the development of the electronic intelligent manufacturing industry.
[0004] During the operation of the SMT mounter, in order to install refined components onto a printed circuit board (PCB), a feeding device is required to stably supply the tape reels for the SMT mounter.
[0005] The existing method is to manually monitor the tape reels and perform material removal and connection when the tape reels are about to be used up. In addition to the need for personnel to frequently conduct inspections to observe whether the tape reels are about to run out, the connection also depends on operators with considerable training and experience to complete, otherwise it is easy to cause production delays.
[0006] It can be seen that there is currently a lack of an automated tape reel monitoring method in the market that can replace manual monitoring of tape reels and perform connection, so relevant operators are seeking solutions. Summary of the Invention
[0007] The purpose of the present disclosure is to provide an automated tape reel monitoring method that can completely replace manual monitoring of tape reels with artificial intelligence vision and can automatically dock the tape reels, thereby saving labor costs and avoiding production delays caused by the exhaustion of tape reels.
[0008] According to an embodiment of the present disclosure, an automated coil monitoring method is provided, including the following steps: obtaining an image of a spare coil through a capturing device. Confirming, by a controller, whether there is a coil head tape in the spare coil image and marking the position of the coil head tape as a coil head position. Controlling, by the controller, a feeding device to disassemble the material according to the coil head position. Controlling, by the controller, the feeding device to move the spare coil so that the spare coil approaches a working coil. Obtaining an image of the tape connection of the spare coil and the working coil through the capturing device. Identifying, by the controller, a head end edge of the spare coil and a tail end edge of the working coil according to the tape connection image, and controlling the feeding device according to the head end edge and the tail end edge so that a head end of the spare coil is docked with a tail end of the working coil for material connection. Judging, by the controller, a connection state of the spare coil and the working coil according to the head end edge and the tail end edge. Description of the Drawings
[0009] Figure 1 is a flowchart showing the steps of the automated coil monitoring method according to an embodiment of the present disclosure;
[0010] Figure 2 is shown in accordance with Figure 1 a schematic diagram of the spare coil image in the embodiment;
[0011] Figure 3 is shown in accordance with Figure 1 a flowchart of the steps of confirming whether there is a coil head tape in the spare coil image and disassembling the material according to the coil head position in the embodiment;
[0012] Figure 4 is shown in accordance with Figure 3 a schematic diagram of the cutting line in;
[0013] Figure 5 is shown in accordance with Figure 1 a flowchart of the step of docking for material connection in the embodiment;
[0014] Figure 6A is shown in accordance with Figure 5 a schematic diagram of docking the head end and the tail end in;
[0015] Figure 6B is shown in accordance with Figure 5 a schematic diagram of attaching a connecting tape between the head end and the tail end in;
[0016] Figure 7A is a schematic diagram showing the connection state of the spare coil and the working coil; and
[0017] Figure 7B is a schematic diagram showing another connection state of the spare coil and the working coil.
[0018] Among them, the description of the attached drawing reference numerals is as follows:
[0019] 100: Automated coil monitoring method
[0020] 110, 120, 121, 122, 123, 130, 131, 132, 133, 134, 140, 150, 160, 161, 162, 163, 164, 170: Steps
[0021] A: Spare coil image
[0022] B: Tape connection image
[0023] CT: Connecting tape
[0024] d: Spacing
[0025] HE: Head end edge
[0026] HT: Coil head tape
[0027] L: Cutting line
[0028] P: Component position
[0029] RA: Excess area
[0030] RE: Connecting coil edge
[0031] SR: Spare coil
[0032] TE: Tail end edge
[0033] TP: Coil head position
[0034] WR: Working coil Detailed implementation manners
[0035] Please refer to Figure 1 as shown in Figure 1 is a flowchart showing the steps of the automated coil monitoring method 100 according to an embodiment of the present disclosure. The automated coil monitoring method 100 includes steps 110, 120, 130, 140, 150, 160, and 170 that are executed in sequence.
[0036] The automated reel monitoring method 100 can be implemented by arbitrarily integrating components such as a feeding device, a picking device, and a controller into various combinations, and automatically monitors the reels, thereby confirming the reel splicing situation during the PCBA processing in the electronic product processing. In this embodiment, the feeding device can be a feeding device connected to a component mounter in circuit board assembly; the picking device can be a combination of multiple camera modules and a ranging sensor arranged on the feeding device; the controller can be a processor, a microprocessor, a central processing unit (CPU), a computer, a mobile device processor, a cloud processor, or other electronic computing processors, but the present disclosure is not limited thereto.
[0037] Please refer to Figure 1 and Figure 2 as shown, wherein Figure 2 is a schematic diagram showing the spare reel image A according to Figure 1 the embodiment. In step 110, the spare reel image A of the spare reel SR is obtained through the picking device. Specifically, one of the camera modules of the picking device can be installed on one side of the reel holder for placing the spare reel SR of the feeding device to capture the spare reel SR on the reel holder to obtain the spare reel image A.
[0038] In step 120, the controller confirms whether there is a reel head tape HT in the spare reel image A and marks the position of the reel head tape HT as a reel head position TP.
[0039] Please refer to Figure 1 , Figure 2 , Figure 3 as shown, wherein Figure 3 is a flowchart showing step 120 of confirming whether there is a reel head tape in the spare reel image and step 130 of unwinding the reel according to the reel head position according to Figure 1 the embodiment. Step 120 includes a step 121, a step 122, and a step 123. In step 121, the controller confirms whether there is a reel head tape HT in the spare reel image A according to an image segmentation algorithm to generate an identification result. In this embodiment, the image segmentation algorithm can be a U-Net convolutional neural network model, a Yolo-Seg deep learning model, a SETR semantic segmentation model, or a Mask R-CNN deep learning model, but the present disclosure is not limited thereto.
[0040] In step 122, the controller frames the reel head tape HT in the spare reel image A to mark the reel head position TP. In step 123, the controller controls the reel holder of the feeding device to continuously rotate to rotate the spare reel SR.
[0041] Specifically, in step 121, when the controller confirms that the spare reel image A has the reel head tape HT (i.e., the recognition result is yes), it continues to execute step 122 to mark the reel head position TP; when the controller confirms that the spare reel image A does not have the reel head tape HT (i.e., the recognition result is no), it continues to execute step 123 to continuously rotate the spare reel SR, and returns to step 121 to enable the controller to re-confirm whether there is the reel head tape HT again using the image segmentation algorithm.
[0042] In step 130, the controller controls the feeding device to disassemble the reel according to the reel head position TP.
[0043] Please refer to Figure 1 、 Figure 2 、 Figure 3 and Figure 4 as shown, where Figure 4 is a schematic diagram showing the cutting line L in accordance with Figure 3 Step 130 includes a step 131, a step 132, a step 133, and a step 134. In step 131, the controller controls the clamp of the feeding device to pull out the reel head tape HT according to the reel head position TP.
[0044] In step 132, the controller marks two component positions P on the spare reel SR at the center of the spare reel image A according to an object detection algorithm, and defines a cutting line L between the two component positions P. In this embodiment, the object detection algorithm can be a Fast R-CNN convolutional neural network model, a Yolo deep learning model, but the present disclosure is not limited thereto. In step 133, the controller controls the cutter of the feeding device to truncate the spare reel SR according to the coordinates of the cutting line L. In step 134, the controller controls the clamp of the feeding device to remove the reel head tape HT to complete the disassembly of the reel.
[0045] Specifically, as Figure 4 shown, the controller first locates two components on the spare reel SR at the center of the spare reel image A, frames the two components to mark the two component positions P, and defines a cutting line L between the two component positions P.
[0046] Thereby, by defining the cutting line L through the object detection algorithm, the situation where the cutter accidentally damages the tiny electronic components on the reel during disassembly can be avoided.
[0047] Please refer to Figure 1 、 Figure 5 、 Figure 6A and Figure 6B as shown, where Figure 5 is a flowchart showing the material receiving step 160 in docking according to the Figure 1 embodiment; Figure 6A is shown in accordance withFigure 5 Schematic diagram of docking the head end with the tail end; and Figure 6B It is shown in accordance with Figure 5 Schematic diagram of attaching the connecting tape CT between the head end and the tail end in
[0048] In step 140, the controller controls the feeding device to move the spare material roll SR so that the spare material roll SR approaches a working material roll WR. In step 150, an image B of the tape connection of the spare material roll SR and the working material roll WR is obtained through the capturing device (as Figure 6A shown).
[0049] Specifically, the controller controls the propulsion cylinder of the feeding device to move the reel holder on which the spare material roll SR is placed towards the reel holder on which the working material roll WR is placed. Another camera module of the capturing device can be installed on one side of the reel holder on which the working material roll WR is placed to photograph the material connection part of the spare material roll SR and the working material roll WR, and then obtain the tape connection image B.
[0050] In step 160, the controller identifies a head end edge HE of the spare material roll SR and a tail end edge TE of the working material roll WR based on the tape connection image B, and controls the feeding device according to the head end edge HE and the tail end edge TE so that a head end of the spare material roll SR is docked with a tail end of the working material roll WR for material connection.
[0051] Please refer to Figure 5 shown, step 160 includes a step 161, a step 162, a step 163 and a step 164. In step 161, the controller first marks the head end edge HE and the tail end edge TE through an image segmentation algorithm based on the tape connection image B.
[0052] Next, it is judged whether the spare material roll SR and the working material roll WR are parallel based on the head end edge HE and the tail end edge TE to generate a judgment result. At the same time, the controller obtains a distance d between the spare material roll SR and the working material roll WR through the distance measuring sensor of the capturing device.
[0053] In step 162, the controller controls the propulsion cylinder of the feeding device to dock the head end of the spare material roll SR with the tail end of the working material roll WR according to the distance d (as Figure 6A shown). In step 163, the controller controls the feeding device to attach a connecting tape CT between the head end of the spare material roll SR and the tail end of the working material roll WR (as Figure 6B shown) to complete the material connection. In step 164, the controller controls the feeding device to move the position of the spare material roll SR and realign it with the working material roll WR again after adjustment.
[0054] Specifically, in step 161, when the controller determines that the spare coil SR and the working coil WR are parallel (i.e., the determination result is yes), it continues to execute step 162 to dock the head end of the spare coil SR with the tail end of the working coil WR according to the spacing d; when the controller determines that the spare coil SR and the working coil WR are not parallel (i.e., the determination result is no), it continues to execute step 164 to adjust the position of the spare coil SR, and returns to step 161 for the controller to use the image segmentation algorithm to determine again whether the spare coil SR and the working coil WR are parallel.
[0055] Thereby, the technology of image segmentation can be used to clearly mark the boundaries and positions of key objects such as the head end edge HE and the tail end edge TE, and realize the automatic docking of the spare coil SR and the working coil WR.
[0056] Please refer to Figure 1 、 Figure 7A and Figure 7B as shown, where Figure 7A is a schematic diagram showing the connection state of the spare coil SR and the working coil WR; and Figure 7B is a schematic diagram showing another connection state of the spare coil SR and the working coil WR. In step 170, the controller determines a connection state of the spare coil SR and the working coil WR according to the head end edge HE and the tail end edge TE.
[0057] The controller identifies a connection coil edge RE based on the combination of the head end edge HE of the spare coil SR and the tail end edge TE of the working coil WR. In this embodiment, the controller determines the connection state of the spare coil SR and the working coil WR in a minimum rectangle fitting manner, where the minimum rectangle is a rectangle that can enclose the head end edge HE and the tail end edge TE, but the present disclosure is not limited thereto.
[0058] For example, as Figure 7A shown, when the connection coil edge RE is a rectangle, it means that the connection state of the spare coil SR and the working coil WR is aligned. At this time, the minimum rectangle is the same as the rectangle of the connection coil edge RE.
[0059] As Figure 7B shown, when the connection coil edge RE is a polygon, it means that the connection state of the spare coil SR and the working coil WR is not aligned. At this time, the minimum rectangle is the polygon of the connection coil edge RE plus two redundant regions RA. When the controller determines that the connection state of the spare coil SR and the working coil WR is not aligned, the controller can automatically notify relevant personnel for processing.
[0060] Thereby, the manual monitoring of the material roll is completely replaced by artificial intelligence vision. In addition to saving labor costs, it can also avoid the situation of production delay caused by the exhaustion of the material roll.
[0061] In addition, in step 170, the controller further includes judging whether the connecting tape CT has wrinkles or damages according to an object detection algorithm, and automatically notifying relevant personnel for handling when the connecting tape CT has wrinkles or damages. In this embodiment, the object detection algorithm can be a Yolo deep learning model or a Fast R-CNN type neural network, but the present disclosure is not limited thereto.
[0062] Thereby, it is avoided that the wrinkles or damages of the connecting tape CT affect the connection of the spare material roll SR and the working material roll WR, and it is further confirmed whether the spare material roll SR and the working material roll WR are properly connected.
[0063] In summary, the automatic material roll monitoring method provided by the present disclosure has the following advantages: First, by automatically marking the cutting line defined by the position of the material roll head and the components on the material tape, the spare material roll can be automatically disassembled without damaging the tiny electronic components on the material roll. Second, by marking the boundaries and positions of key objects such as the head end edge of the spare material roll and the tail end edge of the working material roll, it can assist the controller to judge whether the spare material roll and the working material roll are parallel, so as to facilitate the automatic docking of the spare material roll and the working material roll, and then completely replace the manual monitoring of the material roll with artificial intelligence vision. Third, through the connecting material roll edge identified by the head end edge of the spare material roll and the tail end edge of the working material roll, the connection state of the spare material roll and the working material roll can be accurately judged, and relevant personnel can be notified in real time for handling, thereby avoiding the situation of production delay caused by the exhaustion of the material roll.
[0064] Although the present disclosure has been disclosed as above with embodiments, it is not intended to limit the present disclosure. Any person skilled in the art can make some changes and modifications without departing from the concept and scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to that defined by the claims.
Claims
1. An automated roll monitoring method, characterized in that: Include: Acquire a spare material roll image of a spare material roll through a capture device; Confirming by a controller whether there is a roll head tape in the spare roll image, and marking the position of the roll head tape as a roll head position; The controller controls a feeding device to remove the material according to the position of the head of the material roll; The controller controls the feeding device to move the spare roll so that the spare roll is close to a working roll; Acquire a tape connection image of the standby material roll and the working material roll by the capture device; The controller identifies a leading edge of the standby material roll and a trailing edge of the working material roll according to the material tape connection image, and controls the feeding device according to the leading edge and the trailing edge, so that a leading end of the standby material roll is butted against a trailing end of the working material roll to connect the materials; as well as The controller determines a connection state between the standby material roll and the working material roll according to the leading edge and the trailing edge.
2. The automated roll monitoring method according to claim 1, characterized in that: The controller marks two component positions according to the spare material roll image and the material roll head position, and defines a cutting line between the two component positions.
3. The automated roll monitoring method according to claim 2, characterized in that: The controller controls the feeding device to cut off the spare material roll according to the cutting line and remove the head tape of the material roll.
4. The automated roll monitoring method according to claim 2, wherein: The controller controls the feeding device to pull out the material roll head tape according to the material roll head position, and locates two components on the standby material roll at the center of the standby material roll image to mark the positions of the two components.
5. The automated roll monitoring method according to claim 2, wherein: The controller marks the position of the head of the web and the positions of the two components according to an image segmentation algorithm.
6. The automated roll monitoring method according to claim 1, wherein: The controller determines whether the standby material roll is parallel to the working material roll according to the leading edge and the trailing edge, and simultaneously obtains a distance between the standby material roll and the working material roll.
7. The automated roll monitoring method according to claim 6, characterized in that: When the controller determines that the standby material roll is parallel to the working material roll, the head end is docked with the tail end according to the distance.
8. The automated roll monitoring method according to claim 1, wherein: Also includes: After the head end and the tail end are butted against each other, the controller controls the feeding device to attach a connecting tape between the head end and the tail end.
9. The automated roll monitoring method according to claim 8, characterized in that: The controller determines whether the connecting tape has wrinkles or is damaged according to an object detection algorithm.
10. The automated roll monitoring method according to claim 1, wherein: The controller identifies a connecting material roll edge according to the combination of the leading edge and the trailing edge to determine the connecting state.