Blanking machine hand based on visual determination

Abstract

The utility model discloses a kind of unloading machine hand based on visual determination, including moving mechanism, clamping subassembly, visual detection component, tray assembly and control system.The unloading machine hand based on visual determination in the utility model can determine product assembly state by camera, and OK product and NG product are placed to corresponding tray respectively using different clamping mode, realize the accurate sorting and efficient unloading of product.

Description

Technical Field

[0001] This utility model relates to the field of automation equipment technology, and in particular to a visual judgment-based unloading robot. Background Technology

[0002] In the unloading stage after product assembly, traditional methods rely heavily on manual sorting, which is inefficient and prone to errors. Existing automated sorting equipment often lacks the ability to accurately judge the assembly status of products, making it difficult to distinguish between successfully assembled and unassembled products. Especially for assemblies with top and bottom covers, if different gripping and placement methods are not used specifically, product damage or sorting errors can easily occur, failing to meet the demands of efficient and precise production.

[0003] The existing equipment has the following problems:

[0004] High reliance on manual labor: Many production lines still rely on manual visual inspection of product assembly status, followed by manual sorting of qualified (OK) and unqualified (NG) products. This method suffers from low efficiency, high labor costs, and susceptibility to fatigue leading to missed inspections and misjudgments, and it is difficult to meet the demands of high-speed production.

[0005] Separation of Inspection and Execution: Although some automated production lines have introduced machine vision inspection equipment, they typically adopt a separate design of "independent station quality inspection + robotic arm sorting": products are first transported to the vision inspection station by a conveyor belt, where a fixed camera takes pictures to determine their status; the determination result is transmitted to the downstream robotic arm via communication, and the robotic arm picks up the product and places it in the OK or NG area based on the result. This method requires additional conveyor belts, positioning mechanisms, and synchronous control systems, resulting in a large equipment footprint, extended process cycle time, and the multi-stage coordination is prone to failure due to communication delays or positioning errors.

[0006] The unloading function of robotic arms is limited: Most existing unloading robotic arms only perform a single action and lack online real-time quality inspection capabilities. Even when equipped with vision-guided positioning, it is only used to assist in improving gripping accuracy and cannot dynamically switch sorting logic according to product status. Furthermore, it lacks a dedicated handling mechanism for defective products.

[0007] Therefore, it can be seen that the current automation solutions for non-standard equipment unloading generally suffer from problems such as a fragmented "detection-decision-execution" chain, rigid sorting logic, and inefficient handling of non-compliant products. This results in low equipment integration, high costs, and poor adaptability, making it difficult to meet the demand for integrated real-time quality inspection and intelligent sorting in flexible production. Utility Model Content

[0008] The purpose of this invention is to provide a vision-based unloading robot to solve the problems mentioned in the background art.

[0009] To solve the above-mentioned technical problems, the technical solution adopted by this utility model is as follows:

[0010] A vision-based unloading robot includes a moving mechanism, a gripping component, a vision inspection component, a tray component, and a control system.

[0011] The moving mechanism includes a three-axis motion mechanism consisting of an X-axis assembly, a Y-axis assembly, and a Z-axis assembly, and a column. The X-axis assembly is horizontally mounted on the column. The Y-axis assembly is slidably and vertically connected to the X-axis assembly. The Z-axis assembly is slidably and vertically connected to the Y-axis assembly. The end of the Z-axis assembly is connected to the gripping assembly and the vision detection assembly.

[0012] The gripping assembly includes an upper cover gripper, a lower cover gripper, a double-rod cylinder, a first rotary cylinder, and a second rotary cylinder. The double-rod cylinder is fixed on the Z-axis assembly, and the upper cover gripper is installed at the output end of the double-rod cylinder. The first rotary cylinder is fixedly installed on the Z-axis assembly, and the second rotary cylinder is fixedly installed on the first rotary cylinder. The output end of the second rotary cylinder is connected to the lower cover gripper.

[0013] The visual inspection component includes a camera, a light source, and an image processing module. The camera acquires product images and transmits them to the image processing module. The image processing module preprocesses the image and extracts features, and the extracted features are sent to the control system.

[0014] The tray assembly includes an OK tray and an NG tray, which are installed within the range of motion of the moving mechanism.

[0015] The control system is electrically connected to the X-axis assembly, Y-axis assembly, Z-axis assembly, gripping assembly, and vision inspection assembly. The control system includes an image recognition module, a data processing module, and a control command module. The image recognition module receives product image features collected by the vision inspection assembly and determines whether the product is successfully assembled. The judgment result of the image recognition module is classified as OK or NG by the data processing module. The control command module sends a command based on the classification result to control the moving mechanism to drive the gripping assembly to move the product to the OK tray or NG tray.

[0016] Furthermore, the X-axis component and Y-axis component are constructed using KK modules.

[0017] Furthermore, a slide rail is provided on the X-axis, and the Y-axis assembly is connected to the slide rail.

[0018] Furthermore, the Z-axis assembly is driven by an electric cylinder.

[0019] Furthermore, the camera uses an industrial-grade lens with a field of view (FOV) of 27mm.

[0020] Furthermore, the camera has a resolution of 2448×2048 pixels.

[0021] Furthermore, the light source is a ring-shaped white light source.

[0022] Furthermore, the inner side of the upper cover claw is provided with an anti-slip silicone pad and an arc-shaped recessed structure.

[0023] Furthermore, the lower cover gripper is a polyurethane gripper with a grid pattern.

[0024] Beneficial effects:

[0025] The vision-based unloading robot in this invention can determine the assembly status of products through a camera and use different gripping methods to place OK and NG products onto the corresponding trays, thereby achieving accurate product sorting and efficient unloading. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the overall structure of this utility model;

[0027] Figure 2 This is the front view of the present invention;

[0028] Figure 3 This is a top view of the present invention;

[0029] Figure 4 This is the right view of the present invention;

[0030] Figure 5 This is a schematic diagram of the clamping component in this utility model;

[0031] Figure 6 This is another perspective view of the clamping component in this utility model;

[0032] Figure 7 This is a flowchart illustrating the process of this utility model.

[0033] The following are the labels in the diagram: 1. X-axis assembly; 2. Z-axis assembly; 3. Slide rail; 4. Column; 5. Y-axis assembly; 6. Lower cover gripper; 7. First rotary cylinder; 8. Second rotary cylinder; 9. Upper cover gripper; 10. Double rod cylinder; 11. Camera; 12. Light source. Detailed Implementation

[0034] In the description of this embodiment, it should be noted that the terms "upper," "lower," etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this utility model is in use. They are only for the convenience of describing this utility model and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this utility model. In addition, unless otherwise expressly specified and limited, the terms "installation," "connection," etc., should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, an indirect connection through an intermediate medium, or a connection within two components. For those skilled in the art, the specific meaning of the above terms in this utility model can be understood according to the specific circumstances.

[0035] In addition, unless otherwise specified, the components used in the following embodiments are all existing components, and their corresponding connection methods can also be achieved through conventional technical means, which will not be described in detail in this application. The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] Example

[0037] This embodiment discloses a vision-based material unloading robot, such as... Figures 1 to 6 As shown, it includes a moving mechanism, a gripping assembly, a vision inspection assembly, a carrier assembly, and a control system.

[0038] The moving mechanism includes a three-axis motion mechanism consisting of an X-axis assembly 1, a Y-axis assembly 5, and a Z-axis assembly 2, and a column 4. The X-axis assembly 1 is horizontally mounted on the column 4. The Y-axis assembly 5 is slidably and perpendicularly connected to the X-axis assembly 1. The Z-axis assembly 2 is slidably and perpendicularly connected to the Y-axis assembly 5. The end of the Z-axis assembly 2 is connected to the gripping component and the vision inspection component. The tray assembly includes an OK tray and an NG tray, which are installed within the range of motion of the moving mechanism.

[0039] Specifically, the X-axis assembly 1 and Y-axis assembly 5 are constructed using KK modules. The KK modules are characterized by high precision and high rigidity, enabling fast and stable linear motion. The column 4 maintains high levelness, keeping the X-axis assembly 1 horizontal, while the Y-axis assembly 5 moves along the X-axis assembly 1 for horizontal positioning. The Z-axis is driven by an electric cylinder, precisely controlling the lifting height for vertical positioning. Therefore, when placing products, this robotic arm can accurately align with the OK and NG trays, greatly reducing product misplacement and collision damage caused by positioning errors, effectively ensuring product quality.

[0040] Preferably, a slide rail 3 is provided on the X-axis, and the Y-axis assembly 5 is connected to the slide rail 3. The slide rail 3 can ensure the stability of the movement of the Y-axis assembly 5.

[0041] The gripping assembly includes an upper cover gripper 9, a lower cover gripper 6, a double-rod cylinder 10, a first rotary cylinder 7, and a second rotary cylinder 8. The double-rod cylinder 10 is fixed on the Z-axis assembly 2, and the upper cover gripper 9 is installed at the output end of the double-rod cylinder 10. The first rotary cylinder 7 is fixedly installed on the Z-axis assembly 2, and the second rotary cylinder 8 is fixedly installed on the first rotary cylinder 7. The output end of the second rotary cylinder 8 is connected to the lower cover gripper 6.

[0042] Specifically, the upper cover gripper 9 and the lower cover gripper 6 are respectively designed for the upper cover and lower cover assembly. The upper cover gripper 9 is raised and lowered by the extension and retraction of the double-rod cylinder 10 to grip the upper cover of OK products. The lower cover gripper 6 is fixed on the second rotary cylinder 8. Through the coordinated action of the two rotary cylinders, the lower cover gripper 6 can be adjusted at different angles and positions to cooperate with the upper cover gripper 9 to grip the upper and lower covers of NG products.

[0043] Preferably, the inner side of the upper cover gripper 9 is provided with an anti-slip silicone pad and an arc-shaped concave structure. With the precise control of the double-rod cylinder 10, a constant clamping force of 8N can be set to grip OK products, avoiding surface scratches. The lower cover gripper 6 flexibly adjusts the angle through a double rotary cylinder. The polyurethane chuck with a grid pattern can firmly clamp and not damage the product when handling NG products. Compared with traditional gripping methods, it can reduce the defect rate of products caused by gripping.

[0044] The visual inspection component includes a camera 11, a light source 12, and an image processing module. The camera 11 acquires product images and transmits them to the image processing module. The image processing module preprocesses the image and extracts features, and the extracted features are sent to the control system.

[0045] Specifically, in this embodiment, camera 11 can employ an industrial-grade lens with a 27mm field of view (FOV) and a CCD sensor with a resolution of 2448×2048 pixels. By adjusting the installation height to 180mm, the FOV covers the entire area of ​​the upper and lower cover assembly. The lens aperture is set to F2.8, with a depth of field of ±1.5mm, ensuring clear imaging of the upper and lower cover assembly surfaces. Light source 12 uses a ring-shaped white light source 12 to enhance the contrast of the upper and lower cover edge contours with low-angle illumination. The acquired images undergo preprocessing, including noise reduction, enhancement, and cropping. Subsequently, feature points and descriptors are extracted using the SIFT algorithm, and the similarity to the template is calculated using a matching algorithm. Finally, the quantized parameters are transmitted to the control system for product status judgment and sorting decisions. The specific noise reduction, enhancement, cropping, and similarity calculation with the template using the matching algorithm are conventional techniques for those skilled in the art and will not be elaborated upon here.

[0046] The control system is electrically connected to the KK module constituting the X-axis assembly 1 and Y-axis assembly 5, the electric cylinder driving the Z-axis 2, the cylinder and two rotary cylinders in the clamping assembly, and the vision inspection assembly. The control system includes an image recognition module, a data processing module, and a control command module. The image recognition module receives product image features collected by the vision inspection assembly, compares the features with preset OK product features, calculates a similarity threshold, and thus determines whether the product has been successfully assembled. The judgment result of the image recognition module is classified as OK or NG by the data processing module. The control command module sends a command based on the classification result to control the moving mechanism to drive the clamping assembly to move the product to the OK tray or NG tray.

[0047] The specific workflow is as follows:

[0048] like Figure 7 As shown, starting the equipment initializes the control system. Camera 11 in the vision inspection component captures an image of the product. The image recognition module analyzes the image to determine if the product is successfully assembled. If assembled successfully, it is considered an OK product. The X-axis assembly 1 and Y-axis assembly 5 are controlled to move Z-axis assembly 2 above the product. Then, the electric cylinder of Z-axis assembly 2 is controlled to move it downwards. The double-rod cylinder 10 drives the upper cover gripper 9 to descend and grip the product's upper cover. The Z-axis electric cylinder is controlled to rise, and the X-axis assembly 1 and Y-axis assembly 5 are controlled to move the Z-axis assembly 2, which has already gripped the product, above the OK carrier. The Z-axis electric cylinder is then controlled to descend. The upper cover gripper 9 is released to place the product in the OK tray; if the product assembly fails, the X-axis assembly 1 and Y-axis assembly 5 are controlled to move the Z-axis assembly 2 above the product, the first rotary cylinder 7 and the second rotary cylinder 8 are controlled to adjust the position of the lower cover gripper 6, the electric cylinder of the Z-axis assembly 2 is controlled to lower it, the upper cover gripper 9 and the lower cover gripper 6 are controlled to close simultaneously to grip the product, then the Z-axis electric cylinder is controlled to raise it, the X-axis assembly 1 and Y-axis assembly 5 are controlled to move the Z-axis assembly 2 above the NG tray, the Z-axis electric cylinder is controlled to lower it, and the upper cover gripper 9 and the lower cover gripper 6 are controlled to release so that the product falls into the NG tray.

[0049] Although the embodiments of this utility model have been described in the specification, these embodiments are merely illustrative and should not limit the scope of protection of this utility model. Various omissions, substitutions, and modifications made without departing from the spirit of this utility model should be included within the scope of protection of this utility model.

Claims

1. A vision-based unloading robot, characterized in that: Includes a moving mechanism, gripping assembly, vision inspection assembly, carrier assembly, and control system. The moving mechanism includes a three-axis motion mechanism consisting of an X-axis assembly, a Y-axis assembly, and a Z-axis assembly, and a column. The X-axis assembly is horizontally mounted on the column. The Y-axis assembly is slidably and perpendicularly connected to the X-axis assembly. The Z-axis assembly is slidably and perpendicularly connected to the Y-axis assembly. The end of the Z-axis assembly is connected to the gripping assembly and the vision detection assembly. The gripping assembly includes an upper cover gripper, a lower cover gripper, a double-rod cylinder, a first rotary cylinder, and a second rotary cylinder. The double-rod cylinder is fixed on the Z-axis assembly, and the upper cover gripper is installed at the output end of the double-rod cylinder. The first rotary cylinder is fixedly installed on the Z-axis assembly, and the second rotary cylinder is fixedly installed on the first rotary cylinder. The output end of the second rotary cylinder is connected to the lower cover gripper. The visual inspection component includes a camera, a light source, and an image processing module. The camera acquires product images and transmits them to the image processing module. The image processing module preprocesses the image and extracts features, and the extracted features are sent to the control system. The tray assembly includes an OK tray and an NG tray, which are installed within the range of motion of the moving mechanism. The control system is electrically connected to the X-axis assembly, Y-axis assembly, Z-axis assembly, gripping assembly, and vision inspection assembly. The control system includes an image recognition module, a data processing module, and a control command module. The image recognition module receives product image features collected by the vision inspection assembly and determines whether the product is successfully assembled. The judgment result of the image recognition module is classified as OK or NG by the data processing module. The control command module sends a command based on the classification result to control the moving mechanism to drive the gripping assembly to move the product to the OK tray or NG tray.

2. The vision-based unloading robot according to claim 1, characterized in that: The X-axis and Y-axis components are constructed using KK modules.

3. The vision-based unloading robot according to claim 1, characterized in that: A slide rail is provided on the X-axis, and the Y-axis assembly is connected to the slide rail.

4. The vision-based unloading robot according to claim 1, characterized in that: The Z-axis assembly is driven by an electric cylinder.

5. The vision-based unloading robot according to claim 1, characterized in that: The camera uses an industrial-grade lens with a field of view (FOV) of 27mm.

6. The vision-based unloading robot according to claim 1, characterized in that: The camera has a resolution of 2448×2048 pixels.

7. The vision-based unloading robot according to claim 1, characterized in that: The light source is a ring-shaped white light source.

8. The vision-based unloading robot according to claim 1, characterized in that: The inner side of the upper cover claw is provided with an anti-slip silicone pad and an arc-shaped recessed structure.

9. The vision-based unloading robot according to any one of claims 1 to 8, characterized in that: The lower cover gripper uses a polyurethane gripper with a grid pattern.

Images