CN108226164A - A kind of the robot polishing process and system of view-based access control model detection - Google Patents
A kind of the robot polishing process and system of view-based access control model detection Download PDFInfo
- Publication number
- CN108226164A CN108226164A CN201711470467.2A CN201711470467A CN108226164A CN 108226164 A CN108226164 A CN 108226164A CN 201711470467 A CN201711470467 A CN 201711470467A CN 108226164 A CN108226164 A CN 108226164A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- defect
- robot
- image
- polishing
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- B24B21/00—Machines or devices using grinding or polishing belts; Accessories therefor
-
- 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
- B24B21/00—Machines or devices using grinding or polishing belts; Accessories therefor
- B24B21/18—Accessories
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
The invention discloses the robot polishing process and system of a kind of detection of view-based access control model, system includes robot, shielding case, polishing belt sander, computer, the camera for the end clamp of clamping workpiece and for acquiring image, the camera is mounted in shielding case, the robot is connect with end clamp, the computer is connect respectively with robot, camera and polishing belt sander, and the computer includes：Workpiece mobile module, defects detection module and defect processing module, the present invention passes through integrated workpiece, defect detection and grinding workpieces, production efficiency is substantially increased, the present invention can be widely applied to as the robot polishing process and system of a kind of view-based access control model detection of function admirable in work pieces process technical field.
Description
Technical field
A kind of detected the present invention relates to work pieces process technical field more particularly to view-based access control model robot polishing process and
System.
Background technology
In manufacturing industry, sanding and polishing is one of crucial process, and the quality of polishing often determines the class of product.It passes
The polishing process of system has manual polishing, special purpose machine tool polishing and numerically-controlled machine tool three kinds of operating modes of polishing.Wherein, manual polishing is
Most important operating mode, but there are many disadvantages, for example worker is when being polished, by dust and the shadow of noise
It rings, is susceptible to the occupational diseases such as pneumoconiosis, the health of worker is on the hazard, and manual polishing inefficiency, product life
Time-consuming for production, and handwork flaw is more, and detecting step is cumbersome；Special purpose machine tool versatility is bad, is only suitable for producing in batches；Numerical control machine
The processing cost of bed is higher.
Invention content
In order to solve the technical issues of above-mentioned, the robot the purpose of the present invention is to provide a kind of detection of view-based access control model is beaten
Mill method, another object of the present invention is to provide a kind of robot polishing system of view-based access control model detection.
The technical solution used in the present invention is：
A kind of robot polishing process of view-based access control model detection, includes the following steps：
Workpiece is moved to Sanding Area and polished by S1, control robot；
Workpiece is moved to vision-based detection region by S2, control robot；
S3, control camera carry out the position to be detected of workpiece Image Acquisition successively, obtain all positions to be detected of workpiece
Image and after carrying out image procossing, judge that workpiece with the presence or absence of defect, if there is no defects, is put into certified products by workpiece
Area, conversely, performing step S4；
S4, the position coordinates for obtaining defect simultaneously generate classification process instruction corresponding to defect, and then control robot root
Classification grinding process is carried out to workpiece according to defective locations coordinate and classification process instruction；
S5, Image Acquisition is carried out, and then whether judge workpiece according to the image of acquisition to the workpiece after classification grinding process
Also existing defects finally control robot that the qualified workpiece of polishing is put into certified products area.
Further, it is further comprising the steps of：
S0, the tool coordinates of robot and the coordinate of polishing belt sander and camera are established into correspondence.
Further, after the image at all positions to be detected of workpiece is obtained in the step S3 and carries out image procossing, judge
Workpiece whether there is the step of defect, specifically include：
S31, the image for obtaining all positions to be detected of workpiece；
S32, the image progress traverse scanning for treating detection position；
S33, to image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
S34, edge detection and contours extract are carried out to image according to the coordinate value；
S35, the profile extracted is compared with preset defect profile database, if obtaining the defects of corresponding,
Judge workpiece existing defects, otherwise judge that defect is not present in workpiece.
Further, the step S4 includes step：
S41, the position coordinates for obtaining defect；
S42, the surface area for calculating defect；
S43, the classification process instruction according to corresponding to the surface area of defect generates defect；
S44, control robot carry out classification grinding process according to defective locations coordinate and classification process instruction to workpiece.
Further, the classification process instruction in the step S43 corresponding to defect generates in the following manner：
Surface area in response to defect is 0-1.0mm2Situation, generation coagulation instruction；
Surface area in response to defect is 1.1mm2-2.0mm2Situation, generation two stage treatment instruction；
Surface area in response to defect is 2.1mm2-3.0mm2Situation, generation tertiary treatment instruction；
It is more than 3mm in response to the surface area of defect2Situation, generate level Four process instruction.
Further, the classification process instruction is configured as：
The coagulation instructs：Robot tooling center points are deviated into 0.5mm, workpiece is moved to polishing belt sander
Position polishes to defect；
The two stage treatment instructs：Robot tooling center points are deviated into 1.0mm, workpiece is moved to polishing belt sander
Position polishes to defect；
The tertiary treatment instructs：Robot tooling center points are deviated into 1.5mm, workpiece is moved to polishing belt sander
Position polishes to defect；
The level Four process instruction is：Workpiece is put into NonConforming Parts Area.
Further, the step S5 is specially：After workpiece is moved to vision-based detection region by control robot, camera is controlled
It carries out Image Acquisition successively to the position to be detected of workpiece, obtain the image at all positions to be detected of workpiece and carries out image procossing
Afterwards, workpiece is judged with the presence or absence of defect, if it is judged that the existing defects and surface area of defect is greater than or equal to 0.5mm2, then
Grinding workpieces are unqualified, and the control robot underproof workpiece that will polish is put into NonConforming Parts Area, conversely, grinding workpieces are qualified,
The qualified workpiece of polishing is put into certified products area by control robot.
A kind of robot polishing system of view-based access control model detection, including robot, shielding case, polishing belt sander, computer,
Camera for the end clamp of clamping workpiece and for acquiring image, the camera are mounted in shielding case, the robot
It is connect with end clamp, the computer is connect respectively with robot, camera and polishing belt sander, and the computer includes：
Polishing control module, polishes for controlling robot that workpiece is moved to Sanding Area；
Workpiece mobile module, for controlling robot that workpiece is moved to vision-based detection region；
Defects detection module for camera to be controlled to carry out Image Acquisition successively to the position to be detected of workpiece, obtains workpiece
The image at all positions to be detected and after carrying out image procossing, judges workpiece with the presence or absence of defect, if there is no defect, by work
Part is put into certified products area, conversely, performing defect processing module；
Defect processing module, for obtaining the position coordinates of defect and generating the classification process instruction corresponding to defect, into
And robot is controlled to carry out classification grinding process to workpiece according to defective locations coordinate and classification process instruction；
Secondary detection processing module, for carrying out Image Acquisition, and then according to acquisition to the workpiece after classification grinding process
Image judge whether workpiece goes back existing defects, the robot qualified workpiece that will polish finally is controlled to be put into certified products area.
Further, the defects detection module includes：
Figure unit is taken, for obtaining the image at all positions to be detected of workpiece；
Scanning element carries out traverse scanning for treating the image of detection position；
Demarcate unit, for image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
Extraction unit, for carrying out edge detection and contours extract to image according to the coordinate value；
Judging unit, for the profile extracted to be compared with preset defect profile database, if being corresponded to
The defects of, then judge workpiece existing defects, otherwise judge that defect is not present in workpiece.
Further, the defect processing module includes：
Acquiring unit, for obtaining the position coordinates of defect；
Computing unit, for calculating the surface area of defect；
Generation unit, for the classification process instruction according to corresponding to the surface area of defect generation defect；
Processing unit is beaten for robot to be controlled to carry out classification to workpiece according to defective locations coordinate and classification process instruction
Mill processing.
The beneficial effects of the invention are as follows：A kind of robot polishing process of view-based access control model detection, by integrating workpiece, defect
Detection and grinding workpieces, substantially increase production efficiency, by the way that camera is controlled to carry out image successively to the position to be detected of workpiece
Acquisition after obtaining the image at all positions to be detected of workpiece and carrying out image procossing, judges that workpiece with the presence or absence of defect, can detect
To workpiece it is subtle the defects of, by control robot according to position coordinates the defects of receiving and classification process instruction to workpiece
Defect is handled, and ensure that the precision of polishing.
The present invention another advantageous effect be：A kind of robot polishing system of view-based access control model detection, including robot, screen
Cover cover, polishing belt sander, computer, the camera for the end clamp of clamping workpiece and for acquiring image, the camera peace
In shielding case, the robot is connect with end clamp, the computer respectively with robot, camera and polishing abrasive band
Machine connects, and the computer includes：Workpiece mobile module, defects detection module and defect processing module are lacked by integrated workpiece
Detection and grinding workpieces are fallen into, production efficiency is substantially increased, by defects detection module and defect processing module, detects and controls
Robot polishing defect, it is ensured that polishing precision further ensures the qualification rate of workpiece by secondary detection processing module.
Description of the drawings
Fig. 1 is a kind of flow diagram of the robot polishing process specific embodiment of view-based access control model detection of the present invention；
The step of Fig. 2 is a kind of step S3 of robot polishing process specific embodiment of view-based access control model detection of the present invention is flowed
Cheng Tu；
The step of Fig. 3 is a kind of step S4 of robot polishing process specific embodiment of view-based access control model detection of the present invention is flowed
Cheng Tu；
Fig. 4 is a kind of structure diagram of the robot polishing system specific embodiment of view-based access control model detection of the present invention；
Fig. 5 is a kind of module frame chart of the robot polishing system specific embodiment of view-based access control model detection of the present invention；
The defects of Fig. 6 is a kind of robot polishing system specific embodiment of view-based access control model detection of present invention detection module
Structure diagram；
The defects of Fig. 7 is a kind of robot polishing system specific embodiment of view-based access control model detection of present invention processing module
Structure diagram.
Specific embodiment
With reference to Fig. 1, a kind of robot polishing process of view-based access control model detection includes the following steps：
Workpiece is moved to Sanding Area and polished by S1, control robot；
Workpiece is moved to vision-based detection region by S2, control robot；
S3, control camera carry out the position to be detected of workpiece Image Acquisition successively, obtain all positions to be detected of workpiece
Image and after carrying out image procossing, judge that workpiece with the presence or absence of defect, if there is no defects, is put into certified products by workpiece
Area, conversely, performing step S4；
S4, the position coordinates for obtaining defect simultaneously generate classification process instruction corresponding to defect, and then control robot root
Classification grinding process is carried out to workpiece according to defective locations coordinate and classification process instruction；
S5, Image Acquisition is carried out, and then whether judge workpiece according to the image of acquisition to the workpiece after classification grinding process
Also existing defects finally control robot that the qualified workpiece of polishing is put into certified products area.
Preferred embodiment is further used as, it is further comprising the steps of：
S0, the tool coordinates of robot and the coordinate of polishing belt sander and camera are established into correspondence.
With reference to Fig. 2, preferred embodiment is further used as, all positions to be detected of workpiece are obtained in the step S3
Image and after carrying out image procossing, judges the step of workpiece whether there is defect, specifically includes：
S31, the image for obtaining all positions to be detected of workpiece；
S32, the image progress traverse scanning for treating detection position；
S33, to image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
S34, edge detection and contours extract are carried out to image according to the coordinate value；
S35, the profile extracted is compared with preset defect profile database, if obtaining the defects of corresponding,
Judge workpiece existing defects, otherwise judge that defect is not present in workpiece.
With reference to Fig. 3, preferred embodiment is further used as, the step S4 includes step：
S41, the position coordinates for obtaining defect；
S42, the surface area for calculating defect；
S43, the classification process instruction according to corresponding to the surface area of defect generates defect；
S44, control robot are handled according to defective locations coordinate and classification process instruction workpiece.
It is further used as preferred embodiment, the classification process instruction in the step S43 corresponding to defect is to pass through
In the following manner generation：
Surface area in response to defect is 0-1.0mm2Situation, generation coagulation instruction；
Surface area in response to defect is 1.1mm2-2.0mm2Situation, generation two stage treatment instruction；
Surface area in response to defect is 2.1mm2-3.0mm2Situation, generation tertiary treatment instruction；
It is more than 3mm in response to the surface area of defect2Situation, generate level Four process instruction.
Preferred embodiment is further used as, the classification process instruction is configured as：
The coagulation instructs：Robot tooling center points are deviated into 0.5mm, workpiece is moved to polishing belt sander
Position polishes to defect；
The two stage treatment instructs：Robot tooling center points are deviated into 1.0mm, workpiece is moved to polishing belt sander
Position polishes to defect；
The tertiary treatment instructs：Robot tooling center points are deviated into 1.5mm, workpiece is moved to polishing belt sander
Position polishes to defect；
The level Four process instruction is：Workpiece is put into NonConforming Parts Area.
Preferred embodiment is further used as, the step S5 is specially：Workpiece is moved to vision by control robot
After detection zone, control camera carries out the position to be detected of workpiece Image Acquisition successively, obtains all positions to be detected of workpiece
Image and after carrying out image procossing, workpiece is judged with the presence or absence of defect, if it is judged that the surface of existing defects and defect
Product is greater than or equal to 0.5mm2, then grinding workpieces are unqualified, and the control robot underproof workpiece that will polish is put into defective work
Area, conversely, grinding workpieces are qualified, the qualified workpiece of polishing is put into certified products area by control robot.
With reference to Fig. 4 and Fig. 5, a kind of robot polishing system of view-based access control model detection, including robot, shielding case, polishing
Belt sander, computer, the camera for the end clamp of clamping workpiece and for acquiring image, the camera are mounted on shielding case
Interior, the robot is connect with end clamp, and the computer is connect respectively with robot, camera and polishing belt sander, institute
Computer is stated to include：
Polishing control module, polishes for controlling robot that workpiece is moved to Sanding Area；
Workpiece mobile module, for controlling robot that workpiece is moved to vision-based detection region；
Defects detection module for camera to be controlled to carry out Image Acquisition successively to the position to be detected of workpiece, obtains workpiece
The image at all positions to be detected and after carrying out image procossing, judges workpiece with the presence or absence of defect, if there is no defect, by work
Part is put into certified products area, conversely, performing defect processing module；
Defect processing module, for obtaining the position coordinates of defect and generating the classification process instruction corresponding to defect, into
And robot is controlled to carry out classification grinding process to workpiece according to defective locations coordinate and classification process instruction；
Secondary detection processing module, for carrying out Image Acquisition, and then according to acquisition to the workpiece after classification grinding process
Image judge whether workpiece goes back existing defects, the robot qualified workpiece that will polish finally is controlled to be put into certified products area.
With reference to Fig. 6, preferred embodiment is further used as, the defects detection module includes：
Figure unit is taken, for obtaining the image at all positions to be detected of workpiece；
Scanning element carries out traverse scanning for treating the image of detection position；
Demarcate unit, for image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
Extraction unit, for carrying out edge detection and contours extract to image according to the coordinate value；
Judging unit, for the profile extracted to be compared with preset defect profile database, if being corresponded to
The defects of, then judge workpiece existing defects, otherwise judge that defect is not present in workpiece.
With reference to Fig. 7, preferred embodiment is further used as, the defect processing module includes：
Acquiring unit, for obtaining the position coordinates of defect；
Computing unit, for calculating the surface area of defect；
Generation unit, for the classification process instruction according to corresponding to the surface area of defect generation defect；
Processing unit is beaten for robot to be controlled to carry out classification to workpiece according to defective locations coordinate and classification process instruction
Mill processing.
With reference to specific embodiment, the invention will be further described, by taking faucet surface of polishing as an example.
With reference to Fig. 1, a kind of robot polishing process of view-based access control model detection includes the following steps：
S0, the tool coordinates of robot and the coordinate of polishing belt sander and camera are established into correspondence.
Workpiece is moved to Sanding Area and polished by S1, control robot；
Tap is moved to vision-based detection region by S2, control robot, i.e., below light source and in camera fields of view；
In the present embodiment, it is placed in using camera as origin, on the basis of three-dimensional coordinate XYZ, coordinate is the position of (200,0,0)
It puts.
S3, control camera carry out the position to be detected of tap Image Acquisition successively, and it is all to be detected to obtain tap
The image at position and after carrying out image procossing, judges that tap with the presence or absence of defect, if there is no defects, performs step S5,
Conversely, perform step S4；
In the present embodiment, tap has 26 positions to be detected, and control camera acquires the image at 26 positions to be detected
And it is sent in sequence to computer.
With reference to Fig. 2, after the image at all positions to be detected of tap is obtained in step S3 and carries out image procossing, water is judged
Tap whether there is the step of defect, specifically include step S31~S35：
S31, the image for obtaining all positions to be detected of tap；
S32, the image progress traverse scanning for treating detection position；
S33, to image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
S34, edge detection and contours extract are carried out to image according to the coordinate value；
S35, the profile extracted is compared with preset defect profile database, if obtaining the defects of corresponding,
Judge tap existing defects, otherwise judge that defect is not present in tap.
In the present embodiment, traverse scanning is carried out using src.rows functions and src.cols function pairs image, is obtained entire
The length and width of image, using threshold function table threshold to image carry out binary conversion treatment, using Canny operators to image into
Row edge detection carries out contours extract using Findcontours function pairs image.
Wherein, what defect profile database was recorded is various defects and outline data associated therewith, various defects
Outline data extracts in the following manner：Obtain the image of various defects；Traverse scanning is carried out to the image of defect；To figure
As carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；Edge inspection is carried out to image according to the coordinate value
Survey and contours extract；Extract the outline data of defect.The extraction of contour data step of defect and above mentioned steps S3 1~S34 phases
Together.
S4, the position coordinates for obtaining defect simultaneously generate classification process instruction corresponding to defect, and then control robot root
Tap is handled according to defective locations coordinate and classification process instruction；
Specifically, with reference to Fig. 3, step S4 includes step S41~S43：
S41, the position coordinates for obtaining defect；
S42, the surface area for calculating defect；
The surface area of defect is calculated in the present embodiment by contourArea functions, furthermore it is also possible to by using
CvPerspectiveTransform functions and vReprojectImageTo3D functions, after the depth for calculating defect, according to depth
Different range, to generate corresponding classification process instruction.
S43, the classification process instruction according to corresponding to the surface area of defect generates defect；
Wherein, it is 0-1.0mm in response to the surface area of defect2Situation, generation coagulation instruction, that is, control robot
Robot tooling center points TCP is deviated into 0.5mm, tap is moved to polishing belt sander position, is polished defect；It rings
Should be 1.1mm in the surface area of defect2-2.0mm2Situation, generation two stage treatment instruction, that is, control robot machine is artificial
Have central point TCP offset 1.0mm, tap is moved to polishing belt sander position, is polished defect；In response to defect
Surface area is 2.1mm2-3.0mm2Situation, generation tertiary treatment instruction controls robot by robot tooling center points TCP
1.5mm is deviated, tap is moved to polishing belt sander position, is polished defect；It is more than in response to the surface area of defect
3mm2Situation, generate level Four process instruction, that is, control robot tap is put into NonConforming Parts Area.
S44, control robot are handled tap according to defective locations coordinate and classification process instruction.
Tap is moved to vision-based detection region by S5, control robot, and control camera is to be detected to 26 of tap
Position carries out Image Acquisition successively, after obtaining the image at all positions to be detected of tap and carrying out image procossing, judges the fire hose
Head is with the presence or absence of defect, if it is judged that the existing defects and surface area of defect is greater than or equal to 0.5mm2, then tap beat
Grind unqualified, the control robot underproof tap that will polish is put into NonConforming Parts Area, conversely, tap polishing is qualified, control
The qualified tap of polishing is put into certified products area by robot processed.
Wherein, it obtains the image at all positions to be detected of tap by performing 1~S35 of above mentioned steps S3 and carries out figure
After processing, judge that tap whether there is defect.
Reference Fig. 4 and Fig. 5, for performing the robot polishing system of the view-based access control model of above-mentioned polishing process detection, including
Robot 1, shielding case 3, polishing belt sander 4, computer, the phase for the end clamp 2 of clamping workpiece and for acquiring image
Machine further includes the light source for providing illumination for camera, and the wherein camera lens of camera uses 16mm mega pixel industrial lens, light source
Using white, width 100mm, length is the arc light source of 150mm, and light source and camera are installed in shielding case 3, described
Robot 1 is connect with end clamp 2, and the computer is connect respectively with robot 1, camera and polishing belt sander 4, computer
Including：
Coordinate matching module, for by the tool coordinates of robot with polishing belt sander and camera coordinate foundations it is corresponding pass
System.
Polishing control module, polishes for controlling robot that workpiece is moved to Sanding Area；
Workpiece mobile module, for controlling robot that workpiece is moved to vision-based detection region；
Defects detection module for camera to be controlled to carry out Image Acquisition successively to the position to be detected of workpiece, obtains workpiece
The image at all positions to be detected and after carrying out image procossing, judges workpiece with the presence or absence of defect, if there is no defect, by work
Part is put into certified products area, conversely, performing defect processing module；
Defect processing module, for obtaining the position coordinates of defect and generating the classification process instruction corresponding to defect, into
And robot is controlled to carry out classification grinding process to workpiece according to defective locations coordinate and classification process instruction；
Secondary detection processing module, for carrying out Image Acquisition, and then according to acquisition to the workpiece after classification grinding process
Image judge whether workpiece goes back existing defects, the robot qualified workpiece that will polish finally is controlled to be put into certified products area.
With reference to Fig. 6, defects detection module includes：
Figure unit is taken, for obtaining the image at all positions to be detected of workpiece；
Scanning element carries out traverse scanning for treating the image of detection position；
Demarcate unit, for image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
Extraction unit, for carrying out edge detection and contours extract to image according to the coordinate value；
Judging unit, for the profile extracted to be compared with preset defect profile database, if being corresponded to
The defects of, then judge workpiece existing defects, otherwise judge that defect is not present in workpiece.
With reference to Fig. 7, defect processing module includes：
Acquiring unit, for obtaining the position coordinates of defect；
Computing unit, for calculating the surface area of defect；
Generation unit, for the classification process instruction according to corresponding to the surface area of defect generation defect；
Processing unit is beaten for robot to be controlled to carry out classification to workpiece according to defective locations coordinate and classification process instruction
Mill processing.
Wherein, it is 0-1.0mm in response to the surface area of defect2Situation, generation coagulation instruction, that is, control robot
Robot tooling center points TCP is deviated into 0.5mm, tap is moved to polishing belt sander position, is polished defect；It rings
Should be 1.1mm in the surface area of defect2-2.0mm2Situation, generation two stage treatment instruction, that is, control robot machine is artificial
Have central point TCP offset 1.0mm, tap is moved to polishing belt sander position, is polished defect；In response to defect
Surface area is 2.1mm2-3.0mm2Situation, generation tertiary treatment instruction controls robot by robot tooling center points TCP
1.5mm is deviated, tap is moved to polishing belt sander position, is polished defect；It is more than in response to the surface area of defect
3mm2Situation, generate level Four process instruction, that is, control robot tap is put into NonConforming Parts Area.
It is that the preferable of the present invention is implemented to be illustrated, but the present invention is not limited to the embodiment above, it is ripe
Various equivalent variations or replacement can also be made under the premise of without prejudice to spirit of the invention by knowing those skilled in the art, this
Equivalent deformation or replacement are all contained in the application claim limited range a bit.
Claims (10)
1. a kind of robot polishing process of view-based access control model detection, which is characterized in that include the following steps：
Workpiece is moved to Sanding Area and polished by S1, control robot；
Workpiece is moved to vision-based detection region by S2, control robot；
S3, control camera carry out the position to be detected of workpiece Image Acquisition successively, obtain the figure at all positions to be detected of workpiece
As and after carrying out image procossing, judge that workpiece with the presence or absence of defect, if there is no defects, is put into certified products area, instead by workpiece
It, performs step S4；
S4, the position coordinates for obtaining defect simultaneously generate classification process instruction corresponding to defect, and then control robot according to scarce
It falls into position coordinates and classification process instruction carries out classification grinding process to workpiece；
S5, Image Acquisition is carried out, and then judge whether workpiece is also deposited according to the image of acquisition to the workpiece after classification grinding process
In defect, finally control robot that the qualified workpiece of polishing is put into certified products area.
2. a kind of robot polishing process of view-based access control model detection according to claim 1, which is characterized in that further include with
Lower step：
S0, the tool coordinates of robot and the coordinate of polishing belt sander and camera are established into correspondence.
A kind of 3. robot polishing process of view-based access control model detection according to claim 1, which is characterized in that the step
After the image at all positions to be detected of workpiece is obtained in S3 and carries out image procossing, the step of workpiece whether there is defect is judged,
It specifically includes：
S31, the image for obtaining all positions to be detected of workpiece；
S32, the image progress traverse scanning for treating detection position；
S33, to image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
S34, edge detection and contours extract are carried out to image according to the coordinate value；
S35, the profile extracted with preset defect profile database is compared, if obtaining the defects of corresponding, judged
Otherwise workpiece existing defects judge that defect is not present in workpiece.
A kind of 4. robot polishing process of view-based access control model detection according to claim 3, which is characterized in that the step
S4 includes step：
S41, the position coordinates for obtaining defect；
S42, the surface area for calculating defect；
S43, the classification process instruction according to corresponding to the surface area of defect generates defect；
S44, control robot carry out classification grinding process according to defective locations coordinate and classification process instruction to workpiece.
A kind of 5. robot polishing process of view-based access control model detection according to claim 4, which is characterized in that the step
Classification process instruction described in S43 corresponding to defect generates in the following manner：
The situation that surface area in response to defect is 0-1.0, generation coagulation instruction；
The situation that surface area in response to defect is 1.1-2.0, generation two stage treatment instruction；
The situation that surface area in response to defect is 2.1-3.0, generation tertiary treatment instruction；
It is more than 3 situation in response to the surface area of defect, generates level Four process instruction.
A kind of 6. robot polishing process of view-based access control model detection according to claim 5, which is characterized in that the classification
Process instruction is configured as：
The coagulation instructs：Robot tooling center points are deviated into 0.5mm, workpiece is moved to polishing abrasive band seat in the plane
It puts, polishes defect；
The two stage treatment instructs：Robot tooling center points are deviated into 1.0mm, workpiece is moved to polishing abrasive band seat in the plane
It puts, polishes defect；
The tertiary treatment instructs：Robot tooling center points are deviated into 1.5mm, workpiece is moved to polishing abrasive band seat in the plane
It puts, polishes defect；
The level Four process instruction is：Workpiece is put into NonConforming Parts Area.
A kind of 7. robot polishing process of view-based access control model detection according to claim 6, which is characterized in that the step
S5 is specially：After workpiece is moved to vision-based detection region by control robot, control camera to the position to be detected of workpiece successively
Image Acquisition is carried out, after obtaining the image at all positions to be detected of workpiece and carrying out image procossing, judges workpiece with the presence or absence of scarce
It falls into, if it is judged that existing defects and the surface area of defect are greater than or equal to 0.5, then grinding workpieces are unqualified, control machine
People's underproof workpiece that will polish is put into NonConforming Parts Area, conversely, grinding workpieces are qualified, control robot is by qualified work of polishing
Part is put into certified products area.
8. a kind of robot polishing system of view-based access control model detection, which is characterized in that including robot, shielding case, polishing abrasive band
Machine, computer, the camera for the end clamp of clamping workpiece and for acquiring image, the camera are mounted in shielding case,
The robot is connect with end clamp, and the computer is connect respectively with robot, camera and polishing belt sander, the meter
Calculation machine includes：
Polishing control module, polishes for controlling robot that workpiece is moved to Sanding Area；
Workpiece mobile module, for controlling robot that workpiece is moved to vision-based detection region；
Defects detection module for camera to be controlled to carry out Image Acquisition successively to the position to be detected of workpiece, obtains workpiece and owns
The image at position to be detected and after carrying out image procossing, judges that with the presence or absence of defect, if there is no defects, workpiece is put for workpiece
To certified products area, conversely, performing defect processing module；
Defect processing module for obtaining the position coordinates of defect and generating the classification process instruction corresponding to defect, and then is controlled
Robot processed carries out classification grinding process according to defective locations coordinate and classification process instruction to workpiece；
Secondary detection processing module, for carrying out Image Acquisition, and then according to the figure of acquisition to the workpiece after classification grinding process
As judging whether workpiece goes back existing defects, finally control robot that the qualified workpiece of polishing is put into certified products area.
A kind of 9. robot polishing system of view-based access control model detection according to claim 8, which is characterized in that the defect
Detection module includes：
Figure unit is taken, for obtaining the image at all positions to be detected of workpiece；
Scanning element carries out traverse scanning for treating the image of detection position；
Demarcate unit, for image carry out binary conversion treatment, and in uncalibrated image each pixel coordinate value；
Extraction unit, for carrying out edge detection and contours extract to image according to the coordinate value；
Judging unit, for the profile extracted to be compared with preset defect profile database, if obtaining corresponding lack
It falls into, then judges workpiece existing defects, otherwise judge that defect is not present in workpiece.
10. the robot polishing system of a kind of view-based access control model detection according to claim 9, which is characterized in that described to lack
Sunken processing module includes：
Acquiring unit, for obtaining the position coordinates of defect；
Computing unit, for calculating the surface area of defect；
Generation unit, for the classification process instruction according to corresponding to the surface area of defect generation defect；
Processing unit, for robot to be controlled to carry out classification burnishing part to workpiece according to defective locations coordinate and classification process instruction
Reason.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711470467.2A CN108226164B (en) | 2017-12-29 | 2017-12-29 | Robot polishing method and system based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711470467.2A CN108226164B (en) | 2017-12-29 | 2017-12-29 | Robot polishing method and system based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108226164A true CN108226164A (en) | 2018-06-29 |
| CN108226164B CN108226164B (en) | 2021-05-07 |
Family
ID=62646832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711470467.2A Active CN108226164B (en) | 2017-12-29 | 2017-12-29 | Robot polishing method and system based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108226164B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109030384A (en) * | 2018-07-04 | 2018-12-18 | 中国航空制造技术研究院 | A method of on-line monitoring polishing quality |
| CN109986447A (en) * | 2019-05-14 | 2019-07-09 | 中铁隧道局集团有限公司 | Pipeline outer wall sander |
| CN110170922A (en) * | 2019-06-03 | 2019-08-27 | 北京石油化工学院 | Automate polishing process, device and equipment |
| CN110625491A (en) * | 2019-08-29 | 2019-12-31 | 中车青岛四方机车车辆股份有限公司 | Polishing apparatus and polishing method |
| CN110977767A (en) * | 2019-11-12 | 2020-04-10 | 长沙长泰机器人有限公司 | Casting defect distribution detection method and casting polishing method |
| CN111195843A (en) * | 2018-11-19 | 2020-05-26 | 中冶宝钢技术服务有限公司 | Device and method for removing surface defects of steel billet |
| CN111203805A (en) * | 2020-01-08 | 2020-05-29 | 苏州德龙激光股份有限公司 | Full-automatic glass scratch repairing method |
| CN111558854A (en) * | 2020-05-20 | 2020-08-21 | 山西太钢不锈钢股份有限公司 | Surface grinding method for high-grade stainless steel plate for vehicle |
| CN111922496A (en) * | 2020-08-11 | 2020-11-13 | 四川工程职业技术学院 | Workpiece defect eliminating method and system based on plasma air gouging |
| CN113400102A (en) * | 2021-05-25 | 2021-09-17 | 广东长盈精密技术有限公司 | Automatic damaged product repairing system and method |
| CN113485245A (en) * | 2021-07-05 | 2021-10-08 | 西安交通大学 | Coarse and fine step-by-step screening method for defect coordinates of three-axis numerical control machining G code |
| CN114714161A (en) * | 2022-05-17 | 2022-07-08 | 昆山健博密封件科技有限公司 | Method and device for producing oil seal sealing element |
| CN114789389A (en) * | 2022-04-27 | 2022-07-26 | 北京机科国创轻量化科学研究院有限公司 | Automatic grinding production line for vertical ring |
| CN115106871A (en) * | 2022-08-29 | 2022-09-27 | 成都中科卓尔智能科技集团有限公司 | Flexible high-precision repairing device and process for surface defects of semiconductor material |
| CN116245877A (en) * | 2023-05-08 | 2023-06-09 | 济南达宝文汽车设备工程有限公司 | Material frame detection method and system based on machine vision |
| CN117197133A (en) * | 2023-11-06 | 2023-12-08 | 湖南睿图智能科技有限公司 | Control system and method for vision robot in complex industrial environment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102120307A (en) * | 2010-12-23 | 2011-07-13 | 中国科学院自动化研究所 | System and method for grinding industrial robot on basis of visual information |
| CN106041946A (en) * | 2016-05-23 | 2016-10-26 | 广东工业大学 | Image-processing-based robot polishing production method and production system applying same |
| CN106770331A (en) * | 2017-02-10 | 2017-05-31 | 南京航空航天大学 | A kind of workpiece, defect detecting system based on machine vision |
| CN107052950A (en) * | 2017-05-25 | 2017-08-18 | 上海莫亭机器人科技有限公司 | A kind of complex-curved sanding and polishing system and method |
-
2017
- 2017-12-29 CN CN201711470467.2A patent/CN108226164B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102120307A (en) * | 2010-12-23 | 2011-07-13 | 中国科学院自动化研究所 | System and method for grinding industrial robot on basis of visual information |
| CN106041946A (en) * | 2016-05-23 | 2016-10-26 | 广东工业大学 | Image-processing-based robot polishing production method and production system applying same |
| CN106770331A (en) * | 2017-02-10 | 2017-05-31 | 南京航空航天大学 | A kind of workpiece, defect detecting system based on machine vision |
| CN107052950A (en) * | 2017-05-25 | 2017-08-18 | 上海莫亭机器人科技有限公司 | A kind of complex-curved sanding and polishing system and method |
Non-Patent Citations (3)
| Title |
|---|
| BERND KUHLENKOETTER ET AL.: "A Robot System for High Quality Belt Grinding and Polishing Processes", 《CUTTING EDGE ROBOTICS》 * |
| YIXU SONG ET AL.: "A method for grinding removal control of a robot belt grinding system", 《JOURNAL OF INTELLIGENT MANUFACTURING》 * |
| 杨庆华 等: "基于机器视觉的PCB裸板缺陷自动检测方法", 《中国机械工程》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109030384A (en) * | 2018-07-04 | 2018-12-18 | 中国航空制造技术研究院 | A method of on-line monitoring polishing quality |
| CN111195843A (en) * | 2018-11-19 | 2020-05-26 | 中冶宝钢技术服务有限公司 | Device and method for removing surface defects of steel billet |
| CN109986447A (en) * | 2019-05-14 | 2019-07-09 | 中铁隧道局集团有限公司 | Pipeline outer wall sander |
| CN110170922B (en) * | 2019-06-03 | 2020-12-04 | 北京石油化工学院 | Automatic grinding method, device and equipment |
| CN110170922A (en) * | 2019-06-03 | 2019-08-27 | 北京石油化工学院 | Automate polishing process, device and equipment |
| CN110625491A (en) * | 2019-08-29 | 2019-12-31 | 中车青岛四方机车车辆股份有限公司 | Polishing apparatus and polishing method |
| CN110977767B (en) * | 2019-11-12 | 2021-07-02 | 长沙长泰机器人有限公司 | Casting defect distribution detection method and casting polishing method |
| CN110977767A (en) * | 2019-11-12 | 2020-04-10 | 长沙长泰机器人有限公司 | Casting defect distribution detection method and casting polishing method |
| CN111203805A (en) * | 2020-01-08 | 2020-05-29 | 苏州德龙激光股份有限公司 | Full-automatic glass scratch repairing method |
| CN111558854A (en) * | 2020-05-20 | 2020-08-21 | 山西太钢不锈钢股份有限公司 | Surface grinding method for high-grade stainless steel plate for vehicle |
| CN111922496A (en) * | 2020-08-11 | 2020-11-13 | 四川工程职业技术学院 | Workpiece defect eliminating method and system based on plasma air gouging |
| CN113400102A (en) * | 2021-05-25 | 2021-09-17 | 广东长盈精密技术有限公司 | Automatic damaged product repairing system and method |
| CN113485245A (en) * | 2021-07-05 | 2021-10-08 | 西安交通大学 | Coarse and fine step-by-step screening method for defect coordinates of three-axis numerical control machining G code |
| CN114789389A (en) * | 2022-04-27 | 2022-07-26 | 北京机科国创轻量化科学研究院有限公司 | Automatic grinding production line for vertical ring |
| CN114714161A (en) * | 2022-05-17 | 2022-07-08 | 昆山健博密封件科技有限公司 | Method and device for producing oil seal sealing element |
| CN114714161B (en) * | 2022-05-17 | 2022-12-27 | 昆山健博密封件科技有限公司 | Method and device for producing oil seal sealing element |
| CN115106871A (en) * | 2022-08-29 | 2022-09-27 | 成都中科卓尔智能科技集团有限公司 | Flexible high-precision repairing device and process for surface defects of semiconductor material |
| CN116245877A (en) * | 2023-05-08 | 2023-06-09 | 济南达宝文汽车设备工程有限公司 | Material frame detection method and system based on machine vision |
| CN116245877B (en) * | 2023-05-08 | 2023-11-03 | 济南达宝文汽车设备工程有限公司 | Material frame detection method and system based on machine vision |
| CN117197133A (en) * | 2023-11-06 | 2023-12-08 | 湖南睿图智能科技有限公司 | Control system and method for vision robot in complex industrial environment |
| CN117197133B (en) * | 2023-11-06 | 2024-01-30 | 湖南睿图智能科技有限公司 | Control system and method for vision robot in complex industrial environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108226164B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108226164A (en) | A kind of the robot polishing process and system of view-based access control model detection | |
| CN109571152B (en) | Automatic workpiece polishing method based on offline programming | |
| CN108144873B (en) | Visual detection system and method | |
| CN111230593A (en) | Milling cutter abrasion loss visual measurement method based on dynamic image sequence | |
| CN103995934B (en) | The implementation method and device of automatically grinding | |
| CN207953500U (en) | A kind of adaptive surface sanding and polishing system based on robot | |
| JPH03505998A (en) | Optical robotic canopy polishing equipment | |
| CN114571326B (en) | Method, device and system for grinding deformed curved surface based on computer vision | |
| CN204053644U (en) | A kind of complex part sanding surface polishing device | |
| CN109648202B (en) | Additive manufacturing forming precision control method for non-flat surface autonomous recognition robot | |
| CN105215792A (en) | A kind of complex part sanding surface polishing device and treatment process thereof | |
| CN108284360A (en) | A kind of polishing grinding workpieces system of processing | |
| CN107598775A (en) | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished | |
| CN109035241A (en) | A kind of sole processing method and system | |
| CN205703724U (en) | A kind of classification machining type laser detection grinding machine | |
| CN113379704A (en) | Component weld joint surface defect identification positioning and polishing method, controller and system | |
| Xu et al. | Methodology for the immediate detection and treatment of wheel wear in contour grinding | |
| CN108655898B (en) | Automatic correction and generation method of faucet polishing program | |
| US11904433B2 (en) | Automatic gemstone polishing robot | |
| CN105538097A (en) | Furniture surface grinding process based on full-automatic robot grinding production line | |
| CN110076689A (en) | Workpiece based on industrial robot integrates polishing system and method | |
| TW202026097A (en) | Polishing auxiliary method | |
| CN112903693A (en) | Image acquisition system, method, product, equipment and terminal based on gear shaft visual detection | |
| Hosseininia et al. | Flexible automation in porcelain edge polishing using machine vision | |
| CN208514344U (en) | The polishing pad image detecting system of chemical mechanical grinding |
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 |