Product automatic identification and positioning device, system and implementation method thereof
By combining a flexible vibratory feeder, a material handling robot, and a vision camera module, the system achieves precise product identification, positioning, and grasping, solving the problem of insufficient precision in traditional equipment and improving production efficiency and quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GREATECH MOLD & PLASTIC
- Filing Date
- 2024-11-29
- Publication Date
- 2026-07-07
AI Technical Summary
Traditional product gripping equipment lacks precision, requiring manual assistance for material feeding, which increases the risk and reduces production efficiency and quality, failing to meet high precision requirements.
By combining a flexible vibratory feeder, a material handling robot, upper and lower vision camera modules, and vision software modules, the system achieves accurate product identification, positioning, and grasping through vision algorithms. Combined with a linear speed belt and a swivel fixture, it enables automatic loading and unloading and precise positioning.
It improves the efficiency and accuracy of automatic product identification and positioning, reduces repetitive manual work, lowers risks, and enhances production efficiency and product quality.
Smart Images
Figure CN119328726B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of automated positioning technology, specifically to an automatic product identification and positioning device, system, and implementation method. Background Technology
[0002] With the advancement of technology, especially the development of microelectronics, computer science, artificial intelligence, and robotics, strong technical support has been provided for automation. These technologies enable machines to complete complex tasks more intelligently and flexibly. Economic globalization has intensified market competition, and enterprises are constantly seeking ways to improve production efficiency and reduce costs in order to enhance their competitiveness. Automation has become a key means to achieve this goal. Intelligent manufacturing is a new stage in the development of automation. It integrates multiple technologies such as automation, informatization, the Internet, and artificial intelligence, aiming to achieve the intelligent upgrading of the manufacturing industry.
[0003] In the automated production of high-precision instruments, automatic identification and guidance positioning of products are crucial, and are one of the important requirements for maintaining the qualified rate of finished products. However, the current traditional equipment for grasping products is not precise enough, which means that some of the materials still need to be manually assisted in feeding, increasing a lot of repetitive manual work, which is also dangerous and affects efficiency and quality. Therefore, it cannot meet the ever-increasing requirements for high precision. Summary of the Invention
[0004] To address the shortcomings of existing technologies, this invention provides an automatic product identification and positioning device, system, and implementation method. It has the advantages of accurately identifying and positioning products, thereby reducing repetitive manual work, avoiding danger, and improving efficiency and quality. It solves the problems of insufficient accuracy in traditional product grasping equipment and the efficiency and quality issues caused by manual material feeding.
[0005] To achieve the aforementioned goal of accurately identifying and locating products, thereby reducing repetitive manual work, avoiding danger, and improving efficiency and quality, this invention provides the following technical solution: an automatic product identification and positioning device, comprising a machine base, a flexible vibrating plate, a material handling robot, and a lower vision camera module disposed on the top of the machine base, a linear speed belt disposed on one side of the machine base, a cover disposed on the upper surface of the machine base, and an upper vision camera module disposed on the inner top wall of the cover corresponding to the position of the flexible vibrating plate.
[0006] Preferably, the top of the machine tool is also provided with a tray fixture.
[0007] Preferably, a three-color warning light is provided on the top of the machine cover.
[0008] Preferably, the number of the flexible vibratory plate, the linear speed belt, and the upper vision camera module are all in two sets, left and right.
[0009] An automatic product identification and positioning system includes a vision software module, a TCP server, a Modbus TCP client, a robot TCP client, and a PLC Modbus TCP server;
[0010] The vision software module includes upper vision grasping process, calibration process, and lower vision grasping process algorithm control;
[0011] The TCP server waits for the robot TCP client to connect and request, and provides the data from the vision software module to the robot TCP client;
[0012] The Modbus TCP client actively initiates a connection and uses the Modbus protocol to communicate with the PLC Modbus TCP server to receive data or send control commands.
[0013] The robot TCP client sends control commands to the robot and receives the robot's position and speed, as well as data information from the vision software module.
[0014] The PLC Modbus TCP server communicates with the Modbus TCP client to exchange data and transmit control commands.
[0015] Preferably, the upper vision grasping process uses the upper vision camera module to take pictures and uses an algorithm to obtain the center coordinates of the product to be loaded and send them to the robot TCP client, and the judgment result is sent to the PLC Modbus TCP server. The robot TCP client then parses the data, and the robot accurately picks up the product and moves it to the position captured by the lower vision camera module.
[0016] Preferably, the calibration process includes real-time monitoring of the robot after it moves a certain distance and sending the data to the vision software module via the TCP server communication, as well as writing the circle coordinates matched each time into the calibration tool, ultimately realizing the affine transformation of the pixel and the matrix of the mechanism, i.e., the point.
[0017] Preferably, the lower vision grasping process includes taking pictures using a lower vision camera module, calculating the product's correction angle and the center coordinates of the material placement using a visual algorithm, and then using a robot to correct the product's deviation and place the material accurately.
[0018] Preferably, the number of upper vision camera modules used in the upper vision grasping process increases according to the number of linear speed belts. After the upper vision camera modules take pictures of the product, the visual algorithm can distinguish the front and back of the product. The specific number of lower vision grasping processes increases according to the number of fixtures. Each fixture records at least two coordinate positions to improve the accuracy of positioning.
[0019] A method for automatic product identification and positioning includes the following steps:
[0020] 1) System data preparation: First, the left and right upper vision camera modules facing the left and right flexible vibrating plates are calibrated by nine-point translation to establish a matrix relationship; at the same time, the lower vision camera module is calibrated by 12-point rotation and translation to establish a matrix relationship; record the coordinates of the robot's position when it moves to the center of the lower vision camera module and the coordinates of its position when it moves to the material feeding position.
[0021] 2) Model preparation: Create and save high-precision templates for the product gripping position under the field of view of the left and right upper vision camera modules. Let the robot grip the product from the material placement position and move it to the center field of view of the lower vision camera module to create and save high-precision templates.
[0022] 3) Product feeding: Place the incoming product flat on the linear speed belt, and the linear speed belt will transport the product to the flexible vibrating plates on the left and right sides.
[0023] 4) Material feeding identification: First, the upper vision camera module takes a picture to determine whether there is material on the left and right flexible vibrating plates. If there is material, the product is identified and positioned. Otherwise, the vision software module sends a signal to the PLC Modbus TCP server to drive the automatic feeding of the linear speed belt.
[0024] 5) Positioning and recognition: When the left and right upper vision camera modules detect that there is material in the flexible vibrating plate, but the vision software module does not recognize the standard template product, the vision software module sends a signal to the PLC Modbus TCP server to drive the flexible vibrating plate to re-vibrate in the combination mode until the product automatically flips over and the vision software module recognizes the standard template product.
[0025] 6) Upper vision combined with grasping: After the standard template product in the flexible vibrating plate is identified by two sets of upper vision camera modules, the coordinate data of all products is sent to the robot's TCP client via TCP protocol, driving the robot to grasp the product and move it to the position captured by the lower vision camera module.
[0026] 7) Lower vision positioning and correction: After taking pictures through the lower vision camera module, the vision algorithm will calculate the correction angle and the center coordinates of the material, so that the robot can correct the deviation and accurately place it in the coordinate position to ensure the product fits precisely.
[0027] Compared with the prior art, the present invention provides an automatic product identification and positioning device, system and implementation method thereof, which has the following beneficial effects:
[0028] 1. This automatic identification and positioning device uses a linear speed belt to feed products into a flexible vibratory feeder, where a picking robot picks them up and places them onto a tray fixture, thus achieving automatic product loading and unloading. The flexible vibratory feeder allows the device to automatically flip products up, down, left, and right through vibration. The combination of two sets of flexible vibratory feeders, a linear speed belt, and an upper vision camera module greatly improves the device's automatic identification, positioning, and loading efficiency.
[0029] 2. The automatic identification and positioning system of this product uses an upper vision camera module to take pictures and obtain the center coordinates of the product being loaded using an algorithm. After taking pictures using a lower vision camera module, the system monitors the robot in real time after it moves a certain distance and sends the data to the vision software module via the TCP server. The coordinates of the circle matched each time are also written into the calibration tool. Finally, the system realizes the affine transformation of the matrix of pixels and the mechanism, i.e., the points. The vision algorithm calculates the product's correction angle and the center coordinates of the loading, so that the robot can accurately fit the product.
[0030] 3. A method for automatic product identification and positioning, which establishes a matrix relationship by performing translational calibration with nine points using an upper vision camera module and rotational calibration with 12 points using a lower vision camera module. Then, a high-precision template for grasping and moving is used to ensure accurate material picking and positioning. During operation, repeated identification and positioning are performed to further ensure precise product fit, thereby achieving accurate identification and positioning of incoming products. This reduces repetitive manual work, avoids danger, and improves efficiency and quality. Attached Figure Description
[0031] Figure 1 This is a schematic diagram of the structure of an automatic product identification and positioning device proposed in this invention;
[0032] Figure 2 This is a schematic diagram of an automatic product identification and positioning system proposed in this invention;
[0033] Figure 3 This is a schematic diagram of the implementation process of an automatic product identification and positioning method proposed in this invention.
[0034] In the diagram: 1. Machine platform; 2. Flexible vibratory feeder; 3. Material handling robot; 4. Lower vision camera module; 5. Linear speed belt; 6. Machine cover; 7. Upper vision camera module; 8. Tray fixture; 9. Three-color warning light. Detailed Implementation
[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0036] Please see Figure 1 An automatic product identification and positioning device includes a machine base 1, characterized in that: a flexible vibrating plate 2, a material handling robot 3, and a lower vision camera module 4 are arranged on the top of the machine base 1; a tilting jig 8 is also arranged on the top of the machine base 1; a linear speed belt 5 is arranged on one side of the machine base 1; a cover 6 is arranged on the upper surface of the machine base 1; a three-color warning light 9 is arranged on the top of the cover 6; and an upper vision camera module 7 is arranged on the inner top wall of the cover 6 corresponding to the position of the flexible vibrating plate 2. The number of flexible vibrating plate 2, linear speed belt 5, and upper vision camera module 7 are all two sets, one on the left and one on the right.
[0037] Please see Figure 2 An automatic product identification and positioning system includes a vision software module, a TCP server, a Modbus TCP client, a robot TCP client, and a PLC Modbus TCP server.
[0038] The vision software module includes upper vision grasping process, calibration process, and lower vision grasping process algorithm control. The upper vision grasping process uses the upper vision camera module to take pictures, and then uses algorithms to obtain the center coordinates of the product being loaded. These coordinates are sent to the robot's TCP client, and the judgment results are sent to the PLC Modbus TCP server. The robot's TCP client then parses the data, and the robot accurately picks up the product and moves it to the position captured by the lower vision camera module. The number of upper vision camera modules used in the upper vision grasping process increases with the number of linear speed belts. After taking pictures of the product, the upper vision camera modules can use vision algorithms to distinguish the front and back of the product, combined with... Figure 1 The grasping process of the left and right upper vision camera modules is the same. The only difference between the left and right flexible vibrating disks is the calibration file in the calibration conversion tool.
[0039] The calibration process includes real-time monitoring of the robot after it moves a certain distance and sending the data to the vision software module via TCP server communication, as well as writing the circle coordinates matched each time into the calibration tool, ultimately realizing the affine transformation of the matrix of pixels and the mechanism, i.e., the points.
[0040] The downward vision grasping process includes taking pictures using a downward vision camera module, calculating the product's correction angle and center coordinates for placement using visual algorithms, and then using a robot to correct the product's deviation and accurately place it. The specific number of downward vision grasping steps increases depending on the number of fixtures. Each fixture records at least two coordinate positions to improve positioning accuracy. Figure 1 The middle plate fixture holds two products, which means that four lower vision camera modules need to be inspected. These are the first and second positions of fixture A, and the first and second positions of fixture B. The only difference between the four lower vision camera module processes is the single-point correction and the set position coordinates in the variable calculation tool; their action processes are the same.
[0041] The TCP server waits for connections and requests from the robot's TCP client and provides the data from the vision software module to the robot's TCP client.
[0042] The Modbus TCP client actively initiates a connection and communicates with the PLC Modbus TCP server using the Modbus protocol to receive data or send control commands.
[0043] The robot TCP client sends control commands to the robot and receives data information from the robot's position and speed, as well as data from the vision software module.
[0044] The PLC Modbus TCP server communicates with the Modbus TCP client to exchange data and transmit control commands.
[0045] Please see Figure 3 A method for automatic product identification and positioning includes the following steps:
[0046] 1) System data preparation: First, the left and right upper vision camera modules facing the left and right flexible vibrating plates are calibrated by nine-point translation to establish a matrix relationship; at the same time, the lower vision camera module is calibrated by 12-point rotation and translation to establish a matrix relationship; record the coordinates of the robot's position when it moves to the center of the lower vision camera module and the coordinates of its position when it moves to the material feeding position.
[0047] 2) Model preparation: Create and save high-precision templates for the product gripping position under the field of view of the left and right upper vision camera modules. Let the robot grip the product from the material placement position and move it to the center field of view of the lower vision camera module to create and save high-precision templates.
[0048] 3) Product feeding: Place the incoming product flat on the linear speed belt, and the linear speed belt will transport the product to the flexible vibrating plates on the left and right sides.
[0049] 4) Material feeding identification: First, the upper vision camera module takes a picture to determine whether there is material on the left and right flexible vibrating plates. If there is material, the product is identified and positioned. Otherwise, the vision software module sends a signal to the PLC Modbus TCP server to drive the automatic feeding of the linear speed belt.
[0050] 5) Positioning and recognition: When the left and right upper vision camera modules recognize that there is material in the flexible vibratory feeder, but the vision software module does not recognize the standard template product, the vision software module sends a signal to the PLC Modbus TCP server to drive the flexible vibratory feeder to re-vibrate in the combination mode until the product automatically flips over and the vision software module recognizes the standard template product.
[0051] 6) Upper vision combined with grasping: After the standard template product in the flexible vibrating plate is identified by two sets of upper vision camera modules, the coordinate data of all products is sent to the robot's TCP client via TCP protocol, driving the robot to grasp the product and move it to the position captured by the lower vision camera module.
[0052] 7) Lower vision positioning and correction: After taking pictures through the lower vision camera module, the vision algorithm will calculate the correction angle and the center coordinates of the material placement, so that the robot can correct itself and accurately place the product in the coordinate position. After the product is placed in the material placement position and meets the station requirements, the robot moves to a safe position and the injection molding machine is also in a safe position. Immediately send a signal to allow the injection molding machine to pick up the material, so as to realize the safe linkage between the whole machine and the injection molding machine.
[0053] Combination Figure 1 The device can arrange products in six different self-combination modes:
[0054] 1. The robot can pick up the product from the left flexible vibratory feeder separately, shield the right flexible vibratory feeder, and place the swing plate fixture at the left A1 station;
[0055] 2. The robot can pick up the product from the right flexible vibrating plate independently, shield the left flexible vibrating plate, and place the swing plate fixture at station A1 on the right.
[0056] 3. The robot can pick up the product from the left flexible vibratory feeder separately, shield the right flexible vibratory feeder, and place the swing jig at the left A1 and A2 stations;
[0057] 4. The robot can pick up the product from the right flexible vibratory feeder independently, shield the left flexible vibratory feeder, and place the swing jig at stations A1 and A2 on the right.
[0058] 5. The robot can independently pick up the product from the left flexible vibratory feeder, shield the right flexible vibratory feeder, and place the swing jig at the left A2 station;
[0059] 6. The robot can pick up the product from the right flexible vibratory feeder separately, shield the left flexible vibratory feeder, and place the swing plate fixture at the right A2 station.
[0060] All electrical components mentioned in this article are connected to an external main controller and 380V AC mains power, and the main controller can be a conventional known device such as a computer that provides control.
[0061] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0062] In this application, the terms "upper," "lower," "inner," "middle," "outer," "front," and "rear," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.
[0063] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.
[0064] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A method for automatic product identification and positioning, based on an automatic product identification and positioning device, characterized in that: The product automatic identification and positioning device includes a machine base (1), a flexible vibrating plate (2), a material handling robot (3) and a lower vision camera module (4) are provided on the top of the machine base (1), a linear speed belt (5) is provided on one side of the machine base (1), a cover (6) is provided on the upper surface of the machine base (1), and an upper vision camera module (7) is provided on the inner top wall of the cover (6) corresponding to the position of the flexible vibrating plate (2); the number of the flexible vibrating plate (2), the linear speed belt (5) and the upper vision camera module (7) are all two sets, left and right. The method includes the following steps: 1) System data preparation: First, the left and right upper vision camera modules facing the left and right flexible vibrating plates are calibrated by nine-point translation to establish a matrix relationship; at the same time, the lower vision camera module is calibrated by 12-point rotation and translation to establish a matrix relationship; record the coordinates of the robot's position when it moves to the center of the lower vision camera module and the coordinates of its position when it moves to the material feeding position. 2) Model preparation: Create and save high-precision templates for the product gripping position under the field of view of the left and right upper vision camera modules. Let the robot grip the product from the material placement position and move it to the center field of view of the lower vision camera module to create and save high-precision templates. 3) Product feeding: Place the incoming product flat on the linear speed belt, and the linear speed belt will transport the product to the flexible vibrating plates on the left and right sides. 4) Material feeding identification: First, the upper vision camera module takes a picture to determine whether there is material on the left and right flexible vibrating plates. If there is material, the product is identified and positioned. Otherwise, the vision software module sends a signal to the PLC Modbus TCP server to drive the automatic feeding of the linear speed belt. 5) Positioning and recognition: When the left and right upper vision camera modules detect that there is material in the flexible vibrating plate, but the vision software module does not recognize the standard template product, the vision software module sends a signal to the PLC Modbus TCP server to drive the flexible vibrating plate to re-vibrate in the combination mode until the product automatically flips over and the vision software module recognizes the standard template product. 6) Upper vision combined with grasping: After the standard template product in the flexible vibrating plate is identified by two sets of upper vision camera modules, the coordinate data of all products is sent to the robot's TCP client via TCP protocol, driving the robot to grasp the product and move it to the position captured by the lower vision camera module. 7) Lower vision positioning and correction: After taking pictures through the lower vision camera module, the vision algorithm will calculate the correction angle and the center coordinates of the material, so that the robot can correct the deviation and accurately place it in the coordinate position to ensure the product fits precisely.
2. The method for automatic product identification and positioning according to claim 1, characterized in that: The top of the machine (1) is also provided with a tray fixture (8).
3. The method for automatic product identification and positioning according to claim 1, characterized in that: The top of the hood (6) is equipped with a three-color warning light (9).