CN114536109A - Polishing device for automatically identifying blank defects based on AI vision and use method thereof - Google Patents
Polishing device for automatically identifying blank defects based on AI vision and use method thereof Download PDFInfo
- Publication number
- CN114536109A CN114536109A CN202210190989.1A CN202210190989A CN114536109A CN 114536109 A CN114536109 A CN 114536109A CN 202210190989 A CN202210190989 A CN 202210190989A CN 114536109 A CN114536109 A CN 114536109A
- Authority
- CN
- China
- Prior art keywords
- camera
- product
- vision
- robot
- automatically identifying
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B1/00—Processes of grinding or polishing; Use of auxiliary equipment in connection with such processes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B19/00—Single-purpose machines or devices for particular grinding operations not covered by any other main group
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B41/00—Component parts such as frames, beds, carriages, headstocks
- B24B41/02—Frames; Beds; Carriages
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B51/00—Arrangements for automatic control of a series of individual steps in grinding a workpiece
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/005—Manipulators for mechanical processing tasks
- B25J11/0065—Polishing or grinding
Abstract
The invention relates to a polishing device for automatically identifying blank defects based on AI vision, which comprises a workbench, a robot, a camera bracket, a flange, a polishing tool, a communication cable, a power supply cable and a camera, wherein the workbench is arranged near the robot; the workbench is used for placing or fixing a product; the front end of the robot is provided with a flange, and a polishing tool is arranged on the flange; a camera bracket is arranged on one side of the flange, a camera is arranged on the camera bracket, a communication cable and a power cable are arranged at the tail of the camera, and the communication cable is used for realizing data interaction between the camera and an upper computer; the method is based on the AI identification technology, automatically identifies the blank defects, automatically generates the optimization program technology, simplifies the product defect identification and repair process, and is simple and efficient to operate; the arrangement of the groove on the workbench enables the camera to detect the surface condition of the back of the product without drilling into the lower part of the product, so that the detection efficiency is improved, and the dead angle of the surface of the back of the partial product can be easily detected.
Description
Technical Field
The invention belongs to the field of robot application, and particularly relates to a polishing device for automatically identifying blank defects based on AI vision and a using method thereof.
Background
Quality is controlled and defect restoration is an indispensable ring in the product production flow, traditional product quality is controlled and is mostly observed and found through different angles under the highlight through the eyes of quality inspectors, then the found product defects are optimized through a manual restoration mode, the states of quality inspectors detected in different working time periods are different, and the control of each quality inspector on the detection standard is not completely consistent, so that defective products flow into the next procedure, if the defective products can be found in time, the waste of production resources and manpower is brought, if the defective products cannot be found in time, the defective products are likely to flow into terminal clients, public praise of production enterprises is influenced, and the influence on the defect is huge.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a polishing device for automatically identifying the defects of a blank based on AI vision, which combines an AI identification technology and an upper computer software self-generation optimization program technology, simplifies the product defect identification and repair process, and is simple and efficient to operate.
The polishing device comprises a workbench, a robot, a camera bracket, a flange, a polishing tool, a communication cable, a power supply cable and a camera, wherein the workbench is arranged near the robot; the workbench is used for placing or fixing a product; the front end of the robot is provided with a flange, and a polishing tool is arranged on the flange;
a camera bracket is arranged on one side of the flange, a camera is arranged on the camera bracket, a communication cable and a power cable are arranged at the tail of the camera, and the communication cable is used for realizing data interaction between the camera and an upper computer;
the camera is a D-camera configured with a depth sensor to adapt to two-dimensional scenes and three-dimensional scenes.
Furthermore, a groove is arranged on the table top of the workbench, and the opening of the groove is formed in the upper end face of the workbench and one side face close to the robot.
Further, the bottom of the groove is a reflecting mirror surface capable of reflecting the surface condition of the back of the product.
Further, the mirror surface is one of concave, planar, or convex.
Furthermore, a light supplementing device is arranged in the groove.
Further, the reflecting mirror surface is inclined toward the side close to the robot.
Further, a blowing device is arranged on the higher side in the groove.
A use method of a polishing device for automatically identifying blank defects based on AI vision comprises the following steps:
s1: photographing the product through a camera;
s2: comparing the blank with a sample by using an AI identification technology, identifying the blank defects, automatically generating a defect optimization program through upper computer software, and sending the defect optimization program to the robot;
s3: the robot carries a polishing tool to polish the defective part of the product;
s4: and after polishing is finished, the camera takes a picture of the product again, the quality of the polished product is confirmed, if the polishing effect is not good, the S and S operations are repeated, and quality closed-loop control is formed.
Further, in S1, the front surface of the product and the reflective mirror surface at the bottom of the groove are photographed by a camera; before the mirror surface is photographed, the mirror surface is blown and cleaned by a blowing device.
Further, in S2, the front photograph of the product is first compared with the front side of the sample by using the AI recognition technique, and then the back photograph of the product is compared with the back side of the sample by using the AI recognition technique.
The method is based on the AI identification technology, automatically identifies the blank defects, automatically generates the optimization program technology, simplifies the product defect identification and repair process, and is simple and efficient to operate; due to the arrangement of the groove in the workbench, the camera can detect the surface condition of the back of the product without drilling into the lower part of the product, so that the detection efficiency is improved, and part of dead corners (difficult to enter or shoot) on the surface of the back of the product can be easily detected; the robot can be adapted to various brands of robots, the universality is strong, and the controllability and the reliability of quality control are improved; compared with the current situation that the traditional product quality control depends on manual work, the method can greatly reduce the dependence of the product quality control on human, can effectively identify and repair the product defects with consistent quality standards, and avoids the adverse effects on enterprises caused by the fact that defective products flow into the next process to increase the production cost and defective products flow into terminal clients.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a partial view of the end of the robot of the present invention;
FIG. 3 is a side view of the present invention;
fig. 4 is a schematic structural diagram of another workbench.
The reference numbers in the drawings are respectively: 1. workstation, 2, product, 3, robot, 4, camera support, 5, flange, 6, grinding tool, 7, communication cable, 8, power cable, 9, camera, 10, recess, 11, speculum face, 12, light filling device, 13, blow the device.
Detailed Description
The following embodiments of the present invention are described in detail with reference to the accompanying drawings, and the embodiments and specific operations of the embodiments are provided on the premise of the technical solution of the present invention, but the scope of the present invention is not limited to the following embodiments.
Example 1
Embodiment of the invention as shown in fig. 1 to 3, a polishing device for automatically identifying blank defects based on AI vision comprises a workbench 1, a robot 3, a camera bracket 4, a flange 5, a polishing tool 6, a communication cable 7, a power cable 8 and a camera 9, wherein the workbench 1 is arranged near the robot 3; the workbench 1 is used for placing or fixing a product 2; a flange 5 is arranged at the front end of the robot 3, and a polishing tool 6 is arranged on the flange 5;
the camera support 4 is installed to 5 one side-mounting of flange, installs camera 9 on the camera support 4, and 9 afterbody of camera are equipped with communication cable 7 and power cable 8, and communication cable 7 is used for realizing the data interaction between camera 9 and the host computer.
The camera 9 is a 3D camera equipped with a depth sensor to adapt to two-dimensional and three-dimensional scenes.
A use method of a polishing device for automatically identifying blank defects based on AI vision comprises the following steps:
s1: the product 2 is photographed by the camera 9;
s2: comparing the AI identification technology with the sample piece, identifying the blank defects, automatically generating a defect optimization program through upper computer software, and sending the defect optimization program to the robot 2;
s3: the robot 2 carries a polishing tool 6 to polish the defective part of the product 2;
s4: after polishing is finished, the camera 9 photographs the product 2 again, the quality of the polished product 2 is confirmed, if the polishing effect is not good, the operations of S3 and S4 are repeated, and quality closed-loop control is formed; if the quality requirement is met, the message box prompts 'OK' information; if the detected product 2 still does not meet the quality requirement, the message box prompts NG information, the defect optimization program which can be identified and executed by the robot 3 is automatically generated again according to the current defect and sent to the robot 3, and the robot 3 carries the tail end grinding tool 6 to execute the defect repairing program again, and the process is repeated in a circulating mode.
Example 2
As shown in fig. 4, similar to embodiment 1, the difference is that a groove 10 is provided on the table top of the working table 1, and the groove 10 is opened on the upper end surface of the working table 1 and on a side surface near the robot 3.
The bottom of the groove 10 is a reflecting mirror surface 11 capable of reflecting the back surface condition of the product 2. The size of the product 2 should be adapted to the groove or not larger than the groove, and if the supporting strength of the product 2 is weak, a plurality of supporting columns may be disposed on the groove to support the product 2.
The mirror surface 11 is one of a concave surface, a flat surface, or a convex surface. The concave, planar or convex surface can be adapted to different conditions of the back surface of the product 2, in this embodiment the mirror surface is planar.
And a light supplementing device 12 is arranged in the groove.
The reflecting mirror surface 11 inclines towards one side close to the robot 3, so that the shooting is facilitated, and dust, residues and the like on the reflecting mirror surface can be cleaned by the blowing device.
And a blowing device 13 is arranged at the higher side in the groove.
In S1, the front surface of the product 2 and the reflecting mirror surface at the bottom of the groove are photographed by a camera 9; before photographing the mirror surface 11, the mirror surface is cleaned by blowing with a blowing device 13.
In S2, the front photograph of the product 2 is first compared with the sample by using the AI recognition technique, and the back photograph of the product 2 is then compared with the back of the sample by using the AI recognition technique.
It is worth to be noted that, for the product with the defect detected on the back surface of the product, the product can be ground after being turned over by a robot or the grinding tool 6 is directly extended into the groove to grind the back surface of the product; and the quality requirement on the surface condition of the back of the product is lower under more conditions, and the back of the product does not need to be processed when the serious defect on the back of the product is not identified.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention.
Claims (10)
1. A polishing device for automatically identifying blank defects based on AI vision is characterized by comprising a workbench (1), a robot (3), a camera bracket (4), a flange (5), a polishing tool (6), a communication cable (7), a power cable (8) and a camera (9), wherein the workbench (1) is arranged near the robot (3); the workbench (1) is used for placing or fixing the product (2); a flange (5) is arranged at the front end of the robot (3), and a polishing tool (6) is arranged on the flange (5);
a camera support (4) is installed on one side of the flange (5), a camera (9) is installed on the camera support (4), a communication cable (7) and a power supply cable (8) are arranged at the tail of the camera (9), and the communication cable (7) is used for realizing data interaction between the camera (9) and an upper computer;
the camera (9) is a 3D camera equipped with a depth sensor to adapt to two-dimensional and three-dimensional scenes.
2. The grinding device for automatically identifying the defects of the blanks based on the AI vision as claimed in claim 1, wherein the table top of the workbench (1) is provided with a groove (10), and the groove (10) is opened at the upper end surface of the workbench (1) and one side surface close to the robot (3).
3. The AI vision-based grinding device for automatically identifying defects of blanks as recited in claim 2, wherein the bottom of the groove (10) is a reflecting mirror surface (11) capable of reflecting the back surface condition of the product (2).
4. The AI vision-based grinding device for automatically identifying billet defects according to claim 3, wherein the mirror surface (11) is one of concave, planar or convex.
5. The AI vision based grinding device for automatically identifying defects of blanks as recited in claim 3, wherein a light supplement device (12) is arranged in the groove.
6. The AI-vision-based grinding device for automatically identifying billet defects according to claim 3, characterized in that the mirror surface (11) is inclined to the side close to the robot (3).
7. The AI vision-based grinding device for automatically identifying defects of blanks according to claim 6, characterized in that a blowing device (13) is arranged at the upper side in the groove (10).
8. A use method of a polishing device for automatically identifying blank defects based on AI vision is characterized by comprising the following steps:
s1: photographing the product (2) by means of a camera (9);
s2: comparing the AI identification technology with the sample piece, identifying the blank defects, automatically generating a defect optimization program through upper computer software, and sending the defect optimization program to the robot (2);
s3: the robot (2) carries a polishing tool (6) to polish the defective part of the product (2);
s4: after the grinding is finished, the camera (9) takes a picture of the product (2) again, the quality of the ground product (2) is confirmed, if the grinding effect is poor, the operations of S3 and S4 are repeated, and quality closed-loop control is formed.
9. The use method of the grinding device for automatically identifying the blank defects based on AI vision as claimed in claim 8, characterized in that in S1, the front surface of the product (2) and the reflection mirror surface of the bottom of the groove are photographed by the camera (9); before the mirror surface (11) is photographed, the mirror surface is cleaned by blowing with a blowing device (13).
10. The method for using a sanding device for automatic AI-vision-based blank defect recognition according to claim 9, wherein in S2, the front photograph of the product (2) is first compared with the front side of the sample piece using AI recognition technology, and then the back photograph of the product (2) is compared with the back side of the sample piece using AI recognition technology.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210190989.1A CN114536109B (en) | 2022-03-01 | 2022-03-01 | Polishing device capable of automatically identifying blank defects based on AI vision and application method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210190989.1A CN114536109B (en) | 2022-03-01 | 2022-03-01 | Polishing device capable of automatically identifying blank defects based on AI vision and application method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114536109A true CN114536109A (en) | 2022-05-27 |
| CN114536109B CN114536109B (en) | 2023-07-21 |
Family
ID=81662507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210190989.1A Active CN114536109B (en) | 2022-03-01 | 2022-03-01 | Polishing device capable of automatically identifying blank defects based on AI vision and application method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114536109B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115301573A (en) * | 2022-07-12 | 2022-11-08 | 成都合创视达科技有限公司 | Automatic detection device system for surface quality of automobile stamping parts |
| CN117347383A (en) * | 2023-12-06 | 2024-01-05 | 中材新材料装备科技(天津)有限公司 | System and method for detecting and automatically repairing surface defects of calcium silicate plate |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101504376A (en) * | 2009-03-11 | 2009-08-12 | 张勇 | Optical detection method and apparatus for spherical object surface |
| CN109955122A (en) * | 2019-04-23 | 2019-07-02 | 四川工程职业技术学院 | Full-automatic sanding system and full-automatic sanding method based on machine vision |
| CN113008138A (en) * | 2021-02-23 | 2021-06-22 | 中科(深圳)智慧信息科技有限公司 | Product processing positioning system and method based on visual identification technology |
-
2022
- 2022-03-01 CN CN202210190989.1A patent/CN114536109B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101504376A (en) * | 2009-03-11 | 2009-08-12 | 张勇 | Optical detection method and apparatus for spherical object surface |
| CN109955122A (en) * | 2019-04-23 | 2019-07-02 | 四川工程职业技术学院 | Full-automatic sanding system and full-automatic sanding method based on machine vision |
| CN113008138A (en) * | 2021-02-23 | 2021-06-22 | 中科(深圳)智慧信息科技有限公司 | Product processing positioning system and method based on visual identification technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115301573A (en) * | 2022-07-12 | 2022-11-08 | 成都合创视达科技有限公司 | Automatic detection device system for surface quality of automobile stamping parts |
| CN117347383A (en) * | 2023-12-06 | 2024-01-05 | 中材新材料装备科技(天津)有限公司 | System and method for detecting and automatically repairing surface defects of calcium silicate plate |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114536109B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114536109A (en) | Polishing device for automatically identifying blank defects based on AI vision and use method thereof | |
| CN108709890B (en) | Curved glass defect detection device and method based on machine vision | |
| CN109239100B (en) | Lithium battery surface detection equipment | |
| CN111402251B (en) | Visual detection method and system for 3D defect detection | |
| CN105890669A (en) | Universal image visual inspection robot | |
| CN206113866U (en) | Six automatic check out test sets of inductance | |
| CN207613290U (en) | A kind of shoes side track scanning device | |
| CN113333998A (en) | Automatic welding system and method based on cooperative robot | |
| US20200269820A1 (en) | Car body repair system and method thereof | |
| CN116183623B (en) | Intelligent wafer surface defect detection method and device | |
| CN114399461A (en) | Intelligent toe welding mechanical polishing fatigue life prolonging method | |
| CN216348416U (en) | Rivet quality inspection equipment and image and contour acquisition equipment thereof | |
| CN114113129B (en) | Lens micro defect recognition and grabbing system and method | |
| CN113804692A (en) | Visual defect detection device and method for hot-pressing light guide plate | |
| CN207198051U (en) | A kind of mobile phone shell surface automatic checkout system | |
| CN111105413B (en) | Intelligent spark plug appearance defect detection system | |
| CN111993420A (en) | Fixed binocular vision 3D guide piece feeding system | |
| CN115139535A (en) | 3D printer inverse feedback detection method and system based on three-dimensional reconstruction technology | |
| CN110567983B (en) | Method and system for detecting appearance problem of robot | |
| CN209850559U (en) | Robot system of polishing with three-dimensional vision | |
| CN113705487A (en) | Precise workpiece identification and process parameter correlation system and identification method | |
| CN113237895A (en) | Metal surface defect detection system based on machine vision | |
| CN113759435A (en) | Device and method for detecting foreign matters on processing table board | |
| CN209850113U (en) | Automatic optical identification location radium carving machine | |
| CN113500593A (en) | Method for grabbing designated part of shaft workpiece for loading |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |