Welding robot based on visual recognition

By installing a first and second camera on the welding robot for all-around visual sampling and using a fan and fume extraction system to remove smoke, the problem of difficult quality control during welding was solved, and the stability and efficiency of welding quality were improved.

CN224322583UActive Publication Date: 2026-06-05INNER MONGOLIA QIUSHI INTELLIGENT TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Utility models(China)
Current Assignee / Owner
INNER MONGOLIA QIUSHI INTELLIGENT TECH CO LTD
Filing Date
2025-06-17
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing welding robots cannot provide real-time image feedback during the welding process, making it difficult to control welding quality. At the same time, strong light and smoke affect the information acquisition of the camera, resulting in unstable welding quality.

Method used

A vision-based welding robot was designed, which uses a first camera and a second camera for omnidirectional visual sampling, and combines a drive motor and gear structure to realize the rotation of the camera. It is equipped with a fan and smoke extraction pipe system to remove smoke, and uses a filter to protect the camera.

Benefits of technology

It enables real-time quality monitoring of welding points, improves the stability and efficiency of welding quality, avoids interference from smoke on the camera, and ensures visualization and high quality of the welding process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN224322583U_ABST
    Figure CN224322583U_ABST
Patent Text Reader

Abstract

The utility model discloses a kind of welding robots based on visual identification, including first rotating end, the one side of first rotating end is rotatably connected with second rotating end, one end of second rotating end is rotatably connected with third rotating end, the one end of third rotating end is equipped with welding end, the one side of welding end is equipped with mounting end, the side wall of mounting end is equipped with driving motor, one end of driving motor is equipped with first camera, the one side of mounting end is equipped with driving mechanism for rotating drive to first camera.The utility model can carry out all-around visual sampling to welding point welding position by the rotary rotation of first camera in mounting end, improve the welding quality and visual monitoring of equipment, control welding quality, by setting second camera and fan, the smoke of welding position can be guided and discharged by fan driving suction pipe, cooperate with optical filter to avoid the problem caused by the use of second camera.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This utility model relates to the field of industrial robot technology, and in particular to a welding robot based on vision recognition. Background Technology

[0002] In modern industrial production, welding is a crucial process. Traditional welding methods rely heavily on manual operation, which is not only labor-intensive and inefficient, but also significantly affects welding quality due to the worker's skill level and working condition, making it difficult to guarantee consistent and stable welding quality.

[0003] With the continuous advancement of technology, welding robots are increasingly being applied in industrial production, greatly improving welding efficiency and quality. However, existing welding robots cannot provide real-time image feedback on the welding points during the welding process, resulting in an inability to control the welding quality. In addition, the strong light and smoke generated during the welding process can affect and interfere with the information acquisition of the camera and the video quality of the welding. Utility Model Content

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a welding robot based on vision recognition.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A vision-based welding robot includes a first rotating end, a second rotating end rotatably connected to one side of the first rotating end, a third rotating end rotatably connected to one end of the second rotating end, a welding end at one end of the third rotating end, a mounting end at one side of the welding end, a drive motor on the side wall of the mounting end, a first camera at one end of the drive motor, a drive mechanism for rotating the first camera on one side of the mounting end, a connecting pipe fixedly connected to the side wall of the third rotating end, a fixing pipe fixedly connected to one end of the connecting pipe, a second camera inside the fixing pipe, and a protective mechanism for protecting the second camera at one end of the fixing pipe.

[0007] Preferably, the driving mechanism includes a rotating tube rotatably connected to the side wall of the mounting end, a driving motor fixedly connected to the rotating tube, a gear fixedly connected to the rotating shaft of the driving motor, and a gear ring fixedly connected to the side wall of the mounting end, wherein the gear meshes with the gear ring.

[0008] Preferably, the protective mechanism includes a placement groove opened in a fixed tube, a filter is provided in the placement groove, and a pressure ring is slidably connected in the placement groove, with one end of the pressure ring abutting against the filter.

[0009] Preferably, both the fixing tube and the pressure ring are fixedly connected to a mounting ring on one side wall, and the mounting ring has multiple circumferentially arranged mounting holes on one side.

[0010] Preferably, the inner wall of the placement groove is provided with a plurality of circumferentially arranged limiting grooves, and the outer wall of the pressure ring is fixedly connected with a plurality of circumferentially arranged limiting blocks, the limiting blocks being slidably connected in the limiting grooves.

[0011] Preferably, the side wall of the fixed pipe is fixedly connected to a plurality of circumferentially arranged smoke pipes, the fixed pipe has a plurality of circumferentially arranged flues, one end of the fixed pipe is fixedly connected to a fan, the air inlet of the fan is connected to the plurality of flues, and the smoke pipes are connected to the flues.

[0012] Compared with the prior art, the advantages of this utility model are as follows:

[0013] 1. This utility model is equipped with a rotating tube, a gear ring, a gear, a first camera, and a drive motor. By rotating the first camera at the mounting end, the welding position of the welding point can be visually sampled from all directions, thereby improving the welding quality of the equipment and visual monitoring and control of the welding quality.

[0014] 2. This utility model is equipped with a fixed pipe, a fan, a placement groove, a pressure ring, a smoke extraction pipe, a flue, and a second camera. By setting up the second camera and the fan, the smoke extraction pipe driven by the fan can guide and discharge the smoke from the welding part. With the help of the filter, the problem of affecting the use of the second camera can be avoided. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the front view structure of a welding robot based on vision recognition proposed in this utility model;

[0016] Figure 2 This is a schematic diagram of the drive mechanism structure of a welding robot based on vision recognition proposed in this utility model;

[0017] Figure 3 This is a schematic diagram of the fixed pipe bottom structure of a welding robot based on vision recognition proposed in this utility model;

[0018] Figure 4 This is a schematic diagram of the side structure of a fixed pipe of a welding robot based on vision recognition proposed in this utility model.

[0019] Figure 5 This is a schematic diagram of the flue structure of a welding robot based on vision recognition proposed in this utility model.

[0020] In the diagram: 1 First rotating end, 2 Second rotating end, 3 Third rotating end, 4 Welding end, 5 Mounting end, 6 Rotating tube, 7 Drive motor, 8 First camera, 9 Gear ring, 10 Gear, 11 Connecting tube, 12 Fixing tube, 13 Fan, 14 Placement groove, 15 Pressure ring, 16 Limiting groove, 17 Smoke pipe, 18 Flue, 19 Second camera. Detailed Implementation

[0021] To make the above-mentioned objectives, features, and advantages of this utility model more apparent and understandable, the specific embodiments of this utility model are described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a full understanding of this utility model. However, this utility model can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of this utility model. Therefore, this utility model is not limited to the specific embodiments disclosed below.

[0022] Reference Figure 1-5 A visual recognition-based welding robot includes a first rotating end 1, a second rotating end 2 rotatably connected to one side of the first rotating end 1, a third rotating end 3 rotatably connected to one end of the second rotating end 2, a welding end 4 at one end of the third rotating end 3, an installation end 5 at one side of the welding end 4, a drive motor 7 on the side wall of the installation end 5, a first camera 8 at one end of the drive motor 7, and a drive mechanism for rotating the first camera 8 on one side of the installation end 5. The drive mechanism includes a rotating tube 6 rotatably connected to the side wall of the installation end 5, the drive motor 7 fixedly connected to the rotating tube 6, a gear 10 fixedly connected to the rotating shaft of the drive motor 7, and a gear ring 9 fixedly connected to the side wall of the installation end 5. The gear 10 meshes with the gear ring 9.

[0023] A connecting pipe 11 is fixedly connected to the side wall of the third rotating end 3. A fixing pipe 12 is fixedly connected to one end of the connecting pipe 11. Mounting rings are fixedly connected to one side wall of the fixing pipe 12 and the pressure ring 15. Multiple circumferential mounting holes are opened on one side of the mounting ring. Multiple circumferentially arranged smoke pipes 17 are fixedly connected to the side wall of the fixing pipe 12. Multiple circumferentially arranged flues 18 are opened inside the fixing pipe 12. A fan 13 is fixedly connected to one end of the fixing pipe 12. The air inlet of the fan 13 is connected to multiple flues 18. The smoke pipe 17 is connected to the flues 18.

[0024] A second camera 19 is installed inside the fixed tube 12. One end of the fixed tube 12 is provided with a protective mechanism for protecting the second camera 19. The protective mechanism includes a placement groove 14 opened inside the fixed tube 12. Multiple circumferentially arranged limiting grooves 16 are opened on the inner wall of the placement groove 14. Multiple circumferentially arranged limiting blocks are fixedly connected to the outer wall of the pressure ring 15. The limiting blocks are slidably connected in the limiting grooves 16. A filter is installed inside the placement groove 14. The pressure ring 15 is slidably connected inside the placement groove 14. One end of the pressure ring 15 abuts against the filter.

[0025] When using this utility model, such as Figure 1-5 In use, the angle and position of the welding end 4 are first adjusted by the first rotating end 1, the second rotating end 2, and the third rotating end 3. Then, the drive motor 7 drives the gear 10 to mesh with the gear ring 9, which drives the rotation of the rotating tube 6. The rotating tube 6 drives the drive motor 7 and the first camera 8 on it to perform multi-angle and multi-directional rotational visual monitoring of the welding end 4. Then, supported by the connecting tube 11, the second camera 19 on the fixed tube 12 can perform fixed-angle visual recognition of the welding end 4. At this time, the filter is placed in the placement groove 14 and pressed and fixed by the pressure ring 15. The filter is positioned, fixed, and pressed by the limiting groove 16 and the limiting block. Then, the fan 13 drives the suction, and the smoke generated during the welding process is guided by the flue 18 and the smoke extraction pipe 17 to avoid the smoke from affecting or interfering with the visual recognition process of the second camera 19.

[0026] The above description is only a preferred embodiment of the present utility model, but the protection scope of the present utility model is not limited thereto. Any equivalent substitutions or changes made by those skilled in the art within the technical scope disclosed in the present utility model, based on the technical solution and the inventive concept of the present utility model, should be included within the protection scope of the present utility model.

Claims

1. A vision-based welding robot, comprising a first rotating end (1), characterized in that, A second rotating end (2) is rotatably connected to one side of the first rotating end (1), and a third rotating end (3) is rotatably connected to one end of the second rotating end (2). A welding end (4) is provided at one end of the third rotating end (3), and an installation end (5) is provided on one side of the welding end (4). A drive motor (7) is provided on the side wall of the installation end (5). A first camera (8) is provided at one end of the drive motor (7). A drive mechanism for rotating the first camera (8) is provided on one side of the installation end (5). A connecting pipe (11) is fixedly connected to the side wall of the third rotating end (3). A fixing pipe (12) is fixedly connected to one end of the connecting pipe (11). A second camera (19) is provided inside the fixing pipe (12). A protective mechanism for protecting the second camera (19) is provided at one end of the fixing pipe (12).

2. The welding robot based on vision recognition according to claim 1, characterized in that, The driving mechanism includes a rotating tube (6) rotatably connected to the side wall of the mounting end (5), a driving motor (7) fixedly connected to the rotating tube (6), a gear (10) fixedly connected to the rotating shaft of the driving motor (7), a gear ring (9) fixedly connected to the side wall of the mounting end (5), and the gear (10) meshing with the gear ring (9).

3. The welding robot based on vision recognition according to claim 2, characterized in that, The protective mechanism includes a placement groove (14) opened in the fixed tube (12), a filter is provided in the placement groove (14), and a pressure ring (15) is slidably connected in the placement groove (14), with one end of the pressure ring (15) abutting against the filter.

4. A welding robot based on vision recognition according to claim 3, characterized in that, The fixed tube (12) and the pressure ring (15) are both fixedly connected to one side wall of the mounting ring, and the mounting ring has multiple circumferentially arranged mounting holes on one side.

5. A welding robot based on vision recognition according to claim 4, characterized in that, The inner wall of the placement groove (14) is provided with a plurality of circumferentially arranged limiting grooves (16), and the outer wall of the pressure ring (15) is fixedly connected with a plurality of circumferentially arranged limiting blocks, which are slidably connected in the limiting grooves (16).

6. A welding robot based on vision recognition according to claim 5, characterized in that, The side wall of the fixed pipe (12) is fixedly connected to a plurality of circumferentially arranged smoke pipes (17), and a plurality of circumferentially arranged flues (18) are opened inside the fixed pipe (12). One end of the fixed pipe (12) is fixedly connected to a fan (13), and the air inlet of the fan (13) is connected to the plurality of flues (18). The smoke pipes (17) are connected to the flues (18).