CN107378780A - A kind of robot casting grinding adaptive approach of view-based access control model system - Google Patents
A kind of robot casting grinding adaptive approach of view-based access control model system Download PDFInfo
- Publication number
- CN107378780A CN107378780A CN201710588436.0A CN201710588436A CN107378780A CN 107378780 A CN107378780 A CN 107378780A CN 201710588436 A CN201710588436 A CN 201710588436A CN 107378780 A CN107378780 A CN 107378780A
- Authority
- CN
- China
- Prior art keywords
- casting
- cast
- ing
- robot
- moment
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Finish Polishing, Edge Sharpening, And Grinding By Specific Grinding Devices (AREA)
Abstract
The invention provides the robot casting grinding adaptive approach of view-based access control model system, comprise the following steps, the extraction of cast(ing) surface shape characteristic machine vision;Using surface roughness method is portrayed, the single order moment characteristics of casting height, second order moment characteristics, third moment feature and quadravalence moment characteristics are characterized into cast(ing) surface mean deviation degree, standard deviation, degreeof tortuosity and kurtosis respectively;According to surface roughness, with reference to vision measurement and localization method, Analytical Methods of Kinematics, force control method and position control servo method, generation vision self-adapting robot polishing parameter simultaneously controls polishing executive component to be polished;According in bruting process, the real-time dynamic form characteristic parameter of workpiece surface compares in real time with target morphology characteristic parameter, until the roughness of workpiece surface reaches target morphology characteristic parameter.The workpiece surface quality that the present invention can portray the acquisition of cast(ing) surface morphological feature by rank square can more comprehensively, more subtly portray cast(ing) surface morphological feature.
Description
Technical field
The present invention relates to intelligence manufacture field or milling robot field, more particularly to a kind of machine of view-based access control model system
Device people's casting grinding adaptive approach.
Background technology
Application of the industrial robot in industry of polishing is a kind of new production work in robot application scope in recent years
Skill, higher requirement, industrial robot and Digit Control Machine Tool phase are proposed to robot control system, grinding apparatus solution
It is than machining accuracy grade more far short of what is expected, how to improve machining accuracy and processing efficiency, quality of the robot in industry of polishing
It is related to the technical problem and process of every aspect.
The force parameter that existing robot polishing system obtains according to force snesor, using control servo compensation motor, bullet
Property mechanism etc., realize the control of robot polishing precision, 2014, Cao Jinxue etc. proposed Publication No. CN104149028A's
A kind of high precision machines people polishing system and its control method, polishing precision is improved by calibration system;2016, Liang Ying etc. was carried
A kind of Publication No. CN105773368A power console keyboard mill apparatus is gone out and has applied its milling robot, to improve polishing essence
Degree;2017, draw a bow etc. propose Publication No. CN106425790A a kind of die casting multirobot collaboration sanding apparatus and
Method, realize multirobot collaboration polishing.When the object of polishing is the heavy castings such as cylinder body, single calibration system, base
The quality for not ensuring that polishing casting is cooperateed with multirobot in the compensation of force snesor, casting after polishing has quality
During problem, it is impossible to detect and polish again in time.
The content of the invention
For Shortcomings in the prior art, the invention provides a kind of robot casting grinding of view-based access control model system from
Adaptive method, the workpiece surface quality that the acquisition of cast(ing) surface morphological feature is portrayed using rank square more comprehensively, can be portrayed more subtly
Cast(ing) surface morphological feature.
The present invention is to realize above-mentioned technical purpose by following technological means.
A kind of robot casting grinding adaptive approach of view-based access control model system, including following method:
S01:Cast(ing) surface shape characteristic machine vision is extracted;
S02:The multistage square of cast(ing) surface shape characteristic is portrayed:Using surface roughness method is portrayed, by casting height
Single order moment characteristics, second order moment characteristics, third moment feature and quadravalence moment characteristics characterize respectively cast(ing) surface mean deviation degree,
Standard deviation, degreeof tortuosity and kurtosis;
S03:According to surface roughness, with reference to vision measurement and localization method, Analytical Methods of Kinematics, power controlling party
Method and position control servo method, generation vision self-adapting robot polishing parameter simultaneously control polishing executive component to be polished;
S04:According in bruting process, the real-time dynamic form characteristic parameter of workpiece surface is real with target morphology characteristic parameter
When compare, until the roughness of workpiece surface reaches target morphology characteristic parameter.
Further, described step S01 is specially:Light is absorbed using the ccd video camera above cast(ing) surface is fixed on
According to image, light source irradiates cast(ing) surface photometric stereo vision from different directions, and the light source direction vector is no less than 5;Every
In secondary acquisition cast(ing) surface image process, light source is uniformly distributed in same plane ring and put, every time one light source of unlatching, and according to
Secondary unlatching, illumination cast(ing) surface image is obtained, casting pattern is obtained using multiple light courcess photometric stereo visible sensation method.
Further, described multiple light courcess photometric stereo visible sensation method is specially:Casting Three-dimensional surface is rebuild, obtains t
Cast(ing) surface image It;From cast(ing) surface image ItObtain position (i, j)tThe height at place is z (i, j)t, analysis obtains t will
The long L in fault area processing domaintWith wide Wt。
Further, described step S02 is specially:By robot control system to cast(ing) surface image ItAnalysis, is obtained
Burr, eyelet, crackle and the coarse situation of casting integral surface after to decomposition;Using surface roughness method is portrayed, divide
First moment, second moment, third moment and the quadravalence moment characteristics of casting height are analysed, the moment characteristics of image are as the input for being ground controller
Feature the knowledge feature of processing cast(ing) surface.
Further, the surface roughness method of portraying is specially:Cast(ing) surface image ItAny point (i, j)t's
Height value is z (i, j)t, the roughness of casting corresponds to each rank square of casting height:
The first moment of casting heightCast(ing) surface mean deviation degree is characterized, value is got over
Greatly, then mean deviation amount is bigger, and casting gets over out-of-flatness;
The second moment of castingThe standard deviation of cast(ing) surface each point height is characterized,
That is the degree of roughness of cast(ing) surface, value is bigger, and cast(ing) surface is more coarse;
The third moment of castingThe degreeof tortuosity of cast(ing) surface is characterized, value is bigger,
Cast(ing) surface degreeof tortuosity is higher;
The Fourth-order moment of castingThe kurtosis value of cast(ing) surface is characterized, kurtosis is higher,
Cast(ing) surface is more coarse;
Then surface roughness are:Fflat-t={ M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t, StFor casting
The knowledge feature on surface:St=It(Lt, Wt, Fflat-t)=Lt*Wt*Fflat-t。
Further, the vision measurement in the S03 steps is with localization method:With vision measurement and alignment system controller
The roughness of the cast(ing) surface of input is converted to the point-to-point speed v of grinding machine people's emery wheel t of outputr(t), emery wheel
Velocity of rotation ωr(t) the depth d (t) and joint of robot corner q of casting, are processedr(t);Vision measurement controls with alignment system
Device is completed by deep learning neutral net N, is learnt by positive training study repeatedly with reverse feedback, is established workpiece entirety table
The coarse situation in face and the point-to-point speed v of work pieces process emery wheelr(t), velocity of rotation ωr(t) with the feeding depth d (t) of workpieces processing
The incidence relation of controlling elements, (vr(t), ωr(t), d (t))=N { M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}。
Further, the Analytical Methods of Kinematics in the S03 steps is:It is with positioning using the vision measurement in t
Robots arm's tip speed v of system controllerp(t) with position p (t), revised robot is obtained by kinematics module and closed
Save corner qr-n(t) with joint of robot angular speed
Further, the force control method in the S03 steps is:Pass through power control module amendment joint of robot angular speedObtain revised joint of robot angular speed
Further, the position in the S03 steps controls the servo method to be:By position servo module by revised machine
Device person joint's corner qr-n(t), revised joint of robot angular speedThe joint rotation angle q of robot feedbackm(t)、
Joint angular speedBe converted to the real-time joint driven torque τ (t) of robot;The translation of robots arm's tip speed and emery wheel
Speed is consistent:
vr(t)、vp(t) it is the point-to-point speed and robots arm's tip speed of t emery wheel:vr(t)=vp(t)=F1(St)
=k1St;
ωr(t) it is the velocity of rotation of t emery wheel:ωr(t)=F2(St)=k2St;
D (t) is the feeding depth of t emery wheel:D (t)=F3(St)=k3St;
Wherein:Coefficient k1、k2And k3Determined according to castings material.
Further, described step S04 is specially:If M1、M2、M3、M4Respectively casting target morphology feature one, two,
3rd, Fourth-order moment Standard Eigenvalue;Respectively dynamic form characteristic parameter M1(i,j)t、M2(i,
j)t、M3(i,j)t、M4(i,j)tIn t average value, ifAnd
AndAndIt is then up-to-standard in the surface cast of t, casting
Part Current surface completes polishing, into the polishing repeat step S01-S04 on next surface;Wherein, δ1、δ2、δ3、δ4Respectively
Up-to-standard casting rank square Standard Eigenvalue allowable error scope;
If not satisfied, then expression is off quality in the surface cast of t, then t=kT, and k=k+1, wherein k are to beat
Grind number;T is from Visual Feature Retrieval Process to completing the time of needs of once polishing;Repeat step S01-S04.
The beneficial effects of the present invention are:
1. the robot casting grinding adaptive approach of view-based access control model system of the present invention, is stood using multiple light courcess luminosity
Body vision method, which obtains Casting Three-dimensional form, can more precisely determine workpiece surface quality.
2. the robot casting grinding adaptive approach of view-based access control model system of the present invention, casting is portrayed using rank square
The workpiece surface quality that surface morphology characteristics obtain can more comprehensively, more subtly portray cast(ing) surface morphological feature.
3. the robot casting grinding adaptive approach of view-based access control model system of the present invention, using deep learning nerve
Network controller completes vision measurement and positioning, and this method integrates polishing and quality testing, can adaptively complete workpiece
Polishing, vision measurement are passed through repeatedly with alignment system controller by deep learning neural fusion, deep learning neutral net
Positive training study learn with reverse feedback, establish the coarse situation of workpiece integral surface and the translation speed of work pieces process emery wheel
The incidence relation of the controlling elements such as the feeding depth of degree, velocity of rotation and workpieces processing, and then it is real-time certainly to complete robot casting
Polishing is adapted to, ensures the polishing quality of the cylinder block casting with large-scale feature, it is real when the casting after polishing has quality problems
When detect and polish again, until casting grinding is up-to-standard.
Brief description of the drawings
Fig. 1 is the flow chart of the robot casting grinding adaptive approach of view-based access control model system of the present invention.
Fig. 2 is the schematic diagram of multiple light courcess photometric stereo visible sensation method of the present invention.
Fig. 3 is robot vision adaptive robot of the present invention polishing control schematic diagram.
In figure:
1-1:Ccd video camera;1-2:Light source;1-3:Casting.
Embodiment
Below in conjunction with the accompanying drawings and specific embodiment the present invention is further illustrated, but protection scope of the present invention is simultaneously
Not limited to this.
As shown in figure 1, utilize a kind of robot casting grinding adaptive approach of view-based access control model system, automatically grinding weight
For 38kg HT300 cylinder block castings, casting volume is 400mm × 320mm × 253mm, is comprised the following steps that:
S01:Cast(ing) surface shape characteristic machine vision is extracted:
Workpieces processing is 4 cylinder cylinder bodies, using the Panasoinc WV-CP410/G type ccd video cameras being fixed on above cylinder body
To absorb light image, the focal length f=16mm of video camera, the distance u=745mm of video camera to cylinder body, pass through ccd video camera 1-
1 absorbs light image, and light source (1-2) irradiates cast(ing) surface photometric stereo vision from different directions, as shown in Fig. 2 the light
Source (1-2) direction vector is respectively S1=(65, -320,480), S2=(295, -195,480), S3=(272,74,480), S4
=(155,218,480), S5=(- 188,230,480), S6=(- 130,120,480);Cast(ing) surface image is being obtained every time
During, light source (1-2) is uniformly distributed in same plane ring to be put, and only opens a light source every time, and is opened successively, obtains light
According to cast(ing) surface image, casting pattern is obtained using multiple light courcess photometric stereo visible sensation method.
Multiple light courcess photometric stereo visible sensation method is specially:Rebuild Casting Three-dimensional surface, t cast(ing) surface image It, position
Put (i, j)tThe height at place is z (i, j)t, t wants the long L in fault area processing domaintWith wide Wt。
S02:The multistage square of cast(ing) surface shape characteristic is portrayed:By robot control system to cast(ing) surface image ItPoint
Analysis, burr, eyelet, crackle and the coarse situation of casting integral surface after being decomposed;Using portraying surface roughness side
Method, first moment, second moment, third moment and the quadravalence moment characteristics of casting height are analyzed, the moment characteristics of image are as grinding controller
Input feature processing cast(ing) surface knowledge feature.
The surface roughness method of portraying is specially:Cast(ing) surface image ItAny point (i, j)tHeight value
For z (i, j)t, the roughness of casting corresponds to each rank square of casting height:
The first moment of casting heightCast(ing) surface mean deviation degree is characterized, value is got over
Greatly, then mean deviation amount is bigger, and casting gets over out-of-flatness;
The second moment of castingThe standard deviation of cast(ing) surface each point height is characterized,
That is the degree of roughness of cast(ing) surface, value is bigger, and cast(ing) surface is more coarse;
The third moment of castingThe degreeof tortuosity of cast(ing) surface is characterized, value is bigger,
Cast(ing) surface degreeof tortuosity is higher;
The Fourth-order moment of castingThe kurtosis value of cast(ing) surface is characterized, kurtosis is higher,
Cast(ing) surface is more coarse;
Then surface roughness are:Fflat-t={ M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t,
StFor the knowledge feature of cast(ing) surface:St=It(Lt, Wt, Fflat-t)=Lt*Wt*Fflat-t。
S03:As shown in figure 3, according to surface roughness, with reference to vision measurement and localization method, kinematics analysis side
Method, force control method and position control servo method, generation vision self-adapting robot polishing parameter simultaneously control polishing to perform member
Part is polished;
Vision measurement is with localization method:With vision measurement and alignment system controller by the coarse of the cast(ing) surface of input
Degree is converted to the point-to-point speed v of grinding machine people's emery wheel t of outputr(t), the velocity of rotation ω of emery wheelr(t) casting, is processed
Depth d (t) and joint of robot corner qr(t);Vision measurement is complete by deep learning neutral net N with alignment system controller
Into being learnt by positive training study repeatedly with reverse feedback, establish the coarse situation of workpiece integral surface and work pieces process sand
The point-to-point speed v of wheelr(t), velocity of rotation ωr(t) with the incidence relation of feeding depth d (t) controlling elements of workpieces processing, (vr
(t), ωr(t), d (t))=N { M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}。
Analytical Methods of Kinematics is:Utilize the robots arm end of vision measurement and alignment system controller in t
Speed vp(t) with position p (t), revised joint of robot corner q is obtained by kinematics moduler-n(t) closed with robot
Save angular speed
Force control method is:Pass through power control module amendment joint of robot angular speedObtain revised machine
Person joint's angular speed
Position controls the servo method to be:Position servo module is crossed all by revised joint of robot corner qr-n(t)、
Revised joint of robot angular speedThe joint rotation angle q of robot feedbackm(t), joint angular speedConversion
For the real-time joint driven torque τ (t) of robot;Robots arm's tip speed is consistent with the point-to-point speed of emery wheel:
vr(t)、vp(t) it is the point-to-point speed and robots arm's tip speed of t emery wheel:vr(t)=vp(t)=F1(St)
=k1St;
ωr(t) it is the velocity of rotation of t emery wheel:ωr(t)=F2(St)=k2St;
D (t) is the feeding depth of t emery wheel:D (t)=F3(St)=k3St;
Wherein:Coefficient k1、k2And k3Determined according to castings material.
S04:According in bruting process, the real-time dynamic form characteristic parameter of workpiece surface is real with target morphology characteristic parameter
When compare, until the roughness of workpiece surface reaches target morphology characteristic parameter.With the desired geometrical morphology in target casting surface
Compare, obtain characteristic parameter of polishing in real time, according to real-time geometrical morphology, adaptively complete the polishing of casting.
Specially:If M1、M2、M3、M4Respectively casting target morphology feature one, two, three, Fourth-order moment Standard Eigenvalue, its
Middle M1=0.3 μm, M2=0.003 μm, M3=0.01 μm, M4=0.03 μm;Respectively dynamic form
Characteristic parameter M1(i,j)t、M2(i,j)t、M3(i,j)t、M4(i,j)tIn t average value, if
AndAndAndThen in t
The surface cast at moment is up-to-standard, and casting Current surface completes polishing, into the polishing repeat step S01- on next surface
S04;Wherein, δ1、δ2、δ3、δ4Respectively up-to-standard casting rank square Standard Eigenvalue allowable error scope, δ in this case1=0.05
μm, δ2=0.005 μm, δ3=0.005 μm, δ4=0.005 μm;
If not satisfied, then expression is off quality in the surface cast of t, then t=kT, and k=k+1, wherein k are to beat
Grind number;T is from Visual Feature Retrieval Process to completing the time of needs of once polishing;Repeat step S01-S04.
In present case, using adaptive polishing process, processing times have reduction by a relatively large margin, while effectively processing
Number adds, and in the processing of 30 cylinder bodies, in adaptive polishing process processing result, only 1 processing is unqualified;And
Before this, in the processing of 30 cylinder bodies, there are 3-5 parts unqualified.
The embodiment is preferred embodiment of the invention, but the present invention is not limited to above-mentioned embodiment, not
Away from the present invention substantive content in the case of, those skilled in the art can make it is any it is conspicuously improved, replace
Or modification belongs to protection scope of the present invention.
Claims (10)
1. the robot casting grinding adaptive approach of a kind of view-based access control model system, it is characterised in that including following method:
S01:Cast(ing) surface shape characteristic machine vision is extracted;
S02:The multistage square of cast(ing) surface shape characteristic is portrayed:Using surface roughness method is portrayed, by the one of casting height
Rank moment characteristics, second order moment characteristics, third moment feature and quadravalence moment characteristics characterize cast(ing) surface mean deviation degree, standard respectively
Difference, degreeof tortuosity and kurtosis;
S03:According to surface roughness, with reference to vision measurement and localization method, Analytical Methods of Kinematics, force control method with
Position controls servo method, and generation vision self-adapting robot polishing parameter simultaneously controls polishing executive component to be polished;
S04:According in bruting process, the real-time dynamic form characteristic parameter of workpiece surface compares in real time with target morphology characteristic parameter
It is right, until the roughness of workpiece surface reaches target morphology characteristic parameter.
2. the robot casting grinding adaptive approach of view-based access control model system according to claim 1, it is characterised in that institute
The step S01 stated is specially:Light image, light source are absorbed using the ccd video camera (1-1) being fixed on above cast(ing) surface
(1-2) irradiates cast(ing) surface photometric stereo vision from different directions, and light source (1-2) direction vector is no less than 5;Each
Obtaining in cast(ing) surface image process, light source (1-2) is uniformly distributed in same plane ring to be put, and only opens a light source every time,
And open successively, illumination cast(ing) surface image is obtained, casting pattern is obtained using multiple light courcess photometric stereo visible sensation method.
3. the robot casting grinding adaptive approach of view-based access control model system according to claim 2, it is characterised in that institute
The multiple light courcess photometric stereo visible sensation method stated is specially:Casting Three-dimensional surface is rebuild, obtains t cast(ing) surface image It;From
Cast(ing) surface image ItObtain position (i, j)tThe height at place is z (i, j)t, analyze and obtain the length that t wants fault area processing domain
LtWith wide Wt。
4. the robot casting grinding adaptive approach of view-based access control model system according to claim 1, it is characterised in that institute
The step S02 stated is specially:By robot control system to cast(ing) surface image ItAnalysis, burr, hole after being decomposed
Eye, crackle and the coarse situation of casting integral surface;Using surface roughness method is portrayed, the single order of casting height is analyzed
Square, second moment, third moment and quadravalence moment characteristics, the moment characteristics of image feature processing casting table as the input of grinding controller
The knowledge feature in face.
5. the robot casting grinding adaptive approach of view-based access control model system according to claim 4, it is characterised in that institute
State and portray surface roughness method and be specially:Cast(ing) surface image ItAny point (i, j)tHeight value be z (i, j)t,
The roughness of casting corresponds to each rank square of casting height:
The first moment of casting heightCast(ing) surface mean deviation degree is characterized, value is bigger,
Then mean deviation amount is bigger, and casting gets over out-of-flatness;
The second moment of castingThe standard deviation of cast(ing) surface each point height is characterized, that is, is cast
The degree of roughness on part surface, value is bigger, and cast(ing) surface is more coarse;
The third moment of castingThe degreeof tortuosity of cast(ing) surface is characterized, is worth bigger, casting
Surface deflections degree is higher;
The Fourth-order moment of castingThe kurtosis value of cast(ing) surface is characterized, kurtosis is higher, casting
Surface is more coarse;
Then surface roughness are:Fflat-t={ M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t,
StFor the knowledge feature of cast(ing) surface:St=It(Lt, Wt, Fflat-t)=Lt*Wt*Fflat-t。
6. the robot casting grinding adaptive approach of view-based access control model system according to claim 1, it is characterised in that institute
The vision measurement stated in S03 steps is with localization method:With vision measurement and alignment system controller by the cast(ing) surface of input
Roughness be converted to output grinding machine people's emery wheel t point-to-point speed vr(t), the velocity of rotation ω of emery wheelr(t), add
The depth d (t) and joint of robot corner q of work castingr(t);Vision measurement is with alignment system controller by deep learning nerve
Network N is completed, and is learnt by positive training study repeatedly with reverse feedback, is established the coarse situation of workpiece integral surface and workpiece
The point-to-point speed v of processing grinding wheelr(t), velocity of rotation ωr(t) pass is associated with feeding depth d (t) controlling elements of workpieces processing
System, (vr(t), ωr(t), d (t))=N { M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}。
7. the robot casting grinding adaptive approach of view-based access control model system according to claim 1, it is characterised in that institute
The Analytical Methods of Kinematics stated in S03 steps is:Utilize the robots arm of vision measurement and alignment system controller in t
Tip speed vp(t) with position p (t), revised joint of robot corner q is obtained by kinematics moduler-nAnd machine (t)
Person joint's angular speed
8. the robot casting grinding adaptive approach of view-based access control model system according to claim 1, it is characterised in that institute
The force control method stated in S03 steps is:Pass through power control module amendment joint of robot angular speedObtain revised
Joint of robot angular speed
9. the robot casting grinding adaptive approach of view-based access control model system according to claim 1, it is characterised in that institute
Stating the position in S03 steps controls the servo method to be:By position servo module by revised joint of robot corner qr-n
(t), revised joint of robot angular speedThe joint rotation angle q of robot feedbackm(t), joint angular speed
Be converted to the real-time joint driven torque τ (t) of robot;Robots arm's tip speed is consistent with the point-to-point speed of emery wheel:
vr(t)、vp(t) it is the point-to-point speed and robots arm's tip speed of t emery wheel:vr(t)=vp(t)=F1(St)=
k1St;
ωr(t) it is the velocity of rotation of t emery wheel:ωr(t)=F2(St)=k2St;
D (t) is the feeding depth of t emery wheel:D (t)=F3(St)=k3St;
Wherein:Coefficient k1、k2And k3Determined according to castings material.
10. dynamic form characteristic parameter according to claim 1 and target morphology characteristic parameter real-time comparison method, it is special
Sign is that described step S04 is specially:If M1、M2、M3、M4Respectively casting target morphology feature one, two, three, quadravalence
Square Standard Eigenvalue;Respectively dynamic form characteristic parameter M1(i,j)t、M2(i,j)t、M3(i,
j)t、M4(i,j)tIn t average value, ifAndAndAndIt is then up-to-standard in the surface cast of t, casting
Current surface completes polishing, into the polishing repeat step S01-S04 on next surface;Wherein, δ1、δ2、δ3、δ4Respectively matter
Measure castings rank square Standard Eigenvalue allowable error scope;
If not satisfied, then expression is off quality in the surface cast of t, then t=kT, and k=k+1, wherein k are polishing time
Number;T is from Visual Feature Retrieval Process to completing the time of needs of once polishing;Repeat step S01-S04.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710588436.0A CN107378780B (en) | 2017-07-19 | 2017-07-19 | A kind of robot casting grinding adaptive approach of view-based access control model system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710588436.0A CN107378780B (en) | 2017-07-19 | 2017-07-19 | A kind of robot casting grinding adaptive approach of view-based access control model system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107378780A true CN107378780A (en) | 2017-11-24 |
CN107378780B CN107378780B (en) | 2019-01-08 |
Family
ID=60339998
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710588436.0A Active CN107378780B (en) | 2017-07-19 | 2017-07-19 | A kind of robot casting grinding adaptive approach of view-based access control model system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107378780B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108608296A (en) * | 2018-06-15 | 2018-10-02 | 芜湖泓鹄材料技术有限公司 | Mould cast grinding apparatus |
CN108637860A (en) * | 2018-04-18 | 2018-10-12 | 武汉理工大学 | High ferro white body automation wire-drawing frame and method based on Robot Hand-eye control |
CN109605140A (en) * | 2018-12-25 | 2019-04-12 | 珞石(山东)智能科技有限公司 | Based on machine vision and have the function of that the cutter of six shaft mechanical arm of power control puts the first edge on a knife or a pair of scissors method |
CN109732625A (en) * | 2019-03-15 | 2019-05-10 | 珠海格力电器股份有限公司 | A kind of industrial robot flexibility polishing process and system based on machine vision |
CN110091221A (en) * | 2019-05-13 | 2019-08-06 | 成都工业学院 | A kind of die surface processing method |
CN110405559A (en) * | 2019-08-09 | 2019-11-05 | 珠海心怡科技有限公司 | A kind of metope intelligence sanding and polishing machine in robot |
CN110587484A (en) * | 2019-07-29 | 2019-12-20 | 苏州超徕精工科技有限公司 | Device and method for predicting removal effect in polishing process in real time |
CN111331435A (en) * | 2020-03-27 | 2020-06-26 | 中冶赛迪工程技术股份有限公司 | Intelligent surface grinding process and production line for alloy medium plate |
CN111468989A (en) * | 2020-03-30 | 2020-07-31 | 黄河水利职业技术学院 | Five-axis linkage numerical control manipulator polishing control system and method |
CN111604719A (en) * | 2020-06-02 | 2020-09-01 | 湖北大学 | Self-adaptive high-efficiency large-grinding-amount longitudinal grinding method for cylindrical grinding |
CN111906788A (en) * | 2020-08-12 | 2020-11-10 | 湖北民族大学 | Bathroom intelligent polishing system based on machine vision and polishing method thereof |
CN112345539A (en) * | 2020-11-05 | 2021-02-09 | 菲特(天津)检测技术有限公司 | Aluminum die casting surface defect detection method based on deep learning |
CN113021082A (en) * | 2019-12-24 | 2021-06-25 | 沈阳智能机器人创新中心有限公司 | Robot casting polishing method based on teleoperation and panoramic vision |
US20220126319A1 (en) * | 2019-02-05 | 2022-04-28 | 3M Innovative Properties Company | Paint repair process by scenario |
CN115026660A (en) * | 2022-08-11 | 2022-09-09 | 昆山市恒达精密机械工业有限公司 | CCD-based grinding process intelligent control method and system |
CN115100211A (en) * | 2022-08-29 | 2022-09-23 | 南通电博士自动化设备有限公司 | Intelligent regulation and control method for surface polishing speed of metal plate by robot |
CN115338709A (en) * | 2022-10-18 | 2022-11-15 | 徐州艾奇川自动化设备有限公司 | Numerical control machining intelligent monitoring control system based on industrial intelligence |
CN116967939A (en) * | 2023-09-22 | 2023-10-31 | 大儒科技(苏州)有限公司 | Special force control system for grinding and polishing |
CN116993230A (en) * | 2023-09-26 | 2023-11-03 | 山东省智能机器人应用技术研究院 | Machine polishing operation quality evaluation system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003062752A (en) * | 2001-08-20 | 2003-03-05 | For-A Co Ltd | Finishing device |
CN103831695A (en) * | 2014-03-28 | 2014-06-04 | 中国科学院自动化研究所 | Large free-form surface robot polishing system |
CN105196148A (en) * | 2015-09-25 | 2015-12-30 | 广东省自动化研究所 | Self-adaption polishing and grinding system with intelligent feed and discharge function |
CN205520871U (en) * | 2015-09-25 | 2016-08-31 | 广东省自动化研究所 | Intelligence polishing system of polishing based on vision sensor |
CN205703645U (en) * | 2016-04-13 | 2016-11-23 | 广州文冲船厂有限责任公司 | A kind of robot sanding apparatus |
-
2017
- 2017-07-19 CN CN201710588436.0A patent/CN107378780B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003062752A (en) * | 2001-08-20 | 2003-03-05 | For-A Co Ltd | Finishing device |
CN103831695A (en) * | 2014-03-28 | 2014-06-04 | 中国科学院自动化研究所 | Large free-form surface robot polishing system |
CN105196148A (en) * | 2015-09-25 | 2015-12-30 | 广东省自动化研究所 | Self-adaption polishing and grinding system with intelligent feed and discharge function |
CN205520871U (en) * | 2015-09-25 | 2016-08-31 | 广东省自动化研究所 | Intelligence polishing system of polishing based on vision sensor |
CN205703645U (en) * | 2016-04-13 | 2016-11-23 | 广州文冲船厂有限责任公司 | A kind of robot sanding apparatus |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108637860A (en) * | 2018-04-18 | 2018-10-12 | 武汉理工大学 | High ferro white body automation wire-drawing frame and method based on Robot Hand-eye control |
CN108608296B (en) * | 2018-06-15 | 2024-04-26 | 芜湖泓鹄材料技术有限公司 | Die casting polishing equipment |
CN108608296A (en) * | 2018-06-15 | 2018-10-02 | 芜湖泓鹄材料技术有限公司 | Mould cast grinding apparatus |
CN109605140A (en) * | 2018-12-25 | 2019-04-12 | 珞石(山东)智能科技有限公司 | Based on machine vision and have the function of that the cutter of six shaft mechanical arm of power control puts the first edge on a knife or a pair of scissors method |
US20220126319A1 (en) * | 2019-02-05 | 2022-04-28 | 3M Innovative Properties Company | Paint repair process by scenario |
CN109732625A (en) * | 2019-03-15 | 2019-05-10 | 珠海格力电器股份有限公司 | A kind of industrial robot flexibility polishing process and system based on machine vision |
CN109732625B (en) * | 2019-03-15 | 2020-11-27 | 珠海格力电器股份有限公司 | Industrial robot flexible polishing method and system based on machine vision |
CN110091221A (en) * | 2019-05-13 | 2019-08-06 | 成都工业学院 | A kind of die surface processing method |
CN110587484A (en) * | 2019-07-29 | 2019-12-20 | 苏州超徕精工科技有限公司 | Device and method for predicting removal effect in polishing process in real time |
CN110405559A (en) * | 2019-08-09 | 2019-11-05 | 珠海心怡科技有限公司 | A kind of metope intelligence sanding and polishing machine in robot |
CN113021082B (en) * | 2019-12-24 | 2022-06-07 | 沈阳智能机器人创新中心有限公司 | Robot casting polishing method based on teleoperation and panoramic vision |
CN113021082A (en) * | 2019-12-24 | 2021-06-25 | 沈阳智能机器人创新中心有限公司 | Robot casting polishing method based on teleoperation and panoramic vision |
CN111331435A (en) * | 2020-03-27 | 2020-06-26 | 中冶赛迪工程技术股份有限公司 | Intelligent surface grinding process and production line for alloy medium plate |
CN111468989A (en) * | 2020-03-30 | 2020-07-31 | 黄河水利职业技术学院 | Five-axis linkage numerical control manipulator polishing control system and method |
CN111468989B (en) * | 2020-03-30 | 2021-08-24 | 黄河水利职业技术学院 | Five-axis linkage numerical control manipulator polishing control system and method |
CN111604719B (en) * | 2020-06-02 | 2021-08-10 | 湖北大学 | Self-adaptive high-efficiency large-grinding-amount longitudinal grinding method for cylindrical grinding |
CN111604719A (en) * | 2020-06-02 | 2020-09-01 | 湖北大学 | Self-adaptive high-efficiency large-grinding-amount longitudinal grinding method for cylindrical grinding |
CN111906788B (en) * | 2020-08-12 | 2021-09-14 | 湖北民族大学 | Bathroom intelligent polishing system based on machine vision and polishing method thereof |
CN111906788A (en) * | 2020-08-12 | 2020-11-10 | 湖北民族大学 | Bathroom intelligent polishing system based on machine vision and polishing method thereof |
CN112345539A (en) * | 2020-11-05 | 2021-02-09 | 菲特(天津)检测技术有限公司 | Aluminum die casting surface defect detection method based on deep learning |
CN115026660A (en) * | 2022-08-11 | 2022-09-09 | 昆山市恒达精密机械工业有限公司 | CCD-based grinding process intelligent control method and system |
CN115100211A (en) * | 2022-08-29 | 2022-09-23 | 南通电博士自动化设备有限公司 | Intelligent regulation and control method for surface polishing speed of metal plate by robot |
CN115100211B (en) * | 2022-08-29 | 2022-11-18 | 南通电博士自动化设备有限公司 | Intelligent regulation and control method for surface polishing speed of metal plate by robot |
CN115338709A (en) * | 2022-10-18 | 2022-11-15 | 徐州艾奇川自动化设备有限公司 | Numerical control machining intelligent monitoring control system based on industrial intelligence |
CN116967939A (en) * | 2023-09-22 | 2023-10-31 | 大儒科技(苏州)有限公司 | Special force control system for grinding and polishing |
CN116967939B (en) * | 2023-09-22 | 2023-12-26 | 大儒科技(苏州)有限公司 | Special force control system for grinding and polishing |
CN116993230A (en) * | 2023-09-26 | 2023-11-03 | 山东省智能机器人应用技术研究院 | Machine polishing operation quality evaluation system |
CN116993230B (en) * | 2023-09-26 | 2023-12-15 | 山东省智能机器人应用技术研究院 | Machine polishing operation quality evaluation system |
Also Published As
Publication number | Publication date |
---|---|
CN107378780B (en) | 2019-01-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107378780B (en) | A kind of robot casting grinding adaptive approach of view-based access control model system | |
CN103831695B (en) | Large-scale free form surface robot polishing system | |
DE102018105334B4 (en) | Image processing device and image processing method for calculating the image probability of a target object captured from an input image | |
Shang et al. | Synchronization control in the cable space for cable-driven parallel robots | |
CN107808401A (en) | The hand and eye calibrating method of the one camera of mechanical arm tail end | |
CN113814986B (en) | Method and system for controlling SCARA robot based on machine vision | |
CN111531407B (en) | Workpiece attitude rapid measurement method based on image processing | |
Kuts et al. | Development of the internally cutting milling cutter model with radial advance for treatment of profiling rolls | |
Xia et al. | Workpieces sorting system based on industrial robot of machine vision | |
JP4770542B2 (en) | Rotating body machining center calculation method, rotator machining center calculation program, and rotator machining center calculation device | |
Mikolajczyk et al. | Adaptive control system for drill machine | |
CN108021756A (en) | A kind of Reconfigurable Machine Tools kinematic error model method for building up based on D-H representations | |
Mikolajczyk et al. | Machining with image recognition using industrial robot | |
CN104625836B (en) | numerical control gantry machine tool | |
CN101633126B (en) | Configuration method of clamping tool suitable to machine tool for processing complicated workpiece | |
DE102017128332B4 (en) | Molding system provided with a molding machine and a molded product take-out device | |
CN105312646A (en) | Method and device for processing a blank | |
CN206010440U (en) | A kind of five axle footwear mould machines | |
CN205733206U (en) | The five metals cutting machine that a kind of fixed performance is excellent | |
JP4899573B2 (en) | Rotating body processing method and rotating body processing apparatus. | |
CN103273288A (en) | Blade precision mould processing method | |
Wang et al. | The light plane calibration method of the laser welding vision monitoring system | |
DE112021002976T5 (en) | CONTROL DEVICE, ROBOT SYSTEM AND CONTROL METHOD FOR INCLUDING THE ROBOT TO PERFORM WORK ON THE WORKPIECE | |
CN107962411B (en) | Positioning method of special-shaped space component | |
DE102014100538A1 (en) | Method for calibrating a robot and a camera and system for carrying out the method |
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 |