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
- robot
- moment
- time
- vision
- 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
- 238000005266 casting Methods 0.000 title claims abstract description 173
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 70
- 238000005498 polishing Methods 0.000 claims abstract description 38
- 230000000877 morphologic effect Effects 0.000 claims abstract description 23
- 230000003746 surface roughness Effects 0.000 claims abstract description 14
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000013519 translation Methods 0.000 claims description 13
- 230000000007 visual effect Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000007547 defect Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000007517 polishing process Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 230000004807 localization Effects 0.000 abstract 1
- 238000003754 machining Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004512 die casting Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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 invention relates to the field of intelligent manufacturing or grinding robots, in particular to a robot casting grinding self-adaptive method based on a vision system.
Background
The application of the industrial robot in the polishing industry is a novel production process in the application range of the robot in recent years, higher requirements are provided for a robot control system and a polishing equipment solution, the machining precision grade of the industrial robot is much poorer than that of a numerical control machine, and the technical problem and the process method of how to improve the machining precision, the machining efficiency and the quality of the robot in the polishing industry relate to the square surface are solved.
The existing robot polishing system adopts a control servo compensation motor, an elastic mechanism and the like according to force parameters acquired by a force sensor to realize the control of the polishing precision of the robot, and the high-precision robot polishing system with the publication number of CN104149028A and a control method thereof are proposed in 2014 and Caochain science and the like, and the polishing precision is improved by a calibration system; in 2016, beam and the like propose a force-controlled grinding device with the publication number of CN105773368A and a grinding robot applying the force-controlled grinding device, so as to improve the grinding precision; in 2017, a die casting multi-robot collaborative polishing device and method with the publication number of CN106425790A are provided by Zhang Bo and the like, and multi-robot collaborative polishing is achieved. When the polished object is a large casting such as a cylinder body, the quality of the polished casting cannot be guaranteed by the single calibration system, the compensation based on the force sensor and the cooperation of multiple robots, and when the polished casting has a quality problem, the polished casting cannot be detected and polished again in time.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a robot casting polishing self-adaption method based on a vision system, and the surface quality of a workpiece obtained by describing the surface morphological characteristics of a casting by using a moment can more comprehensively and more finely describe the surface morphological characteristics of the casting.
The present invention achieves the above-described object by the following technical means.
A robot casting polishing self-adaptive method based on a vision system comprises the following steps:
s01: machine vision extraction of the surface topography of the casting;
s02: the surface topography characteristic of the casting is drawn by multi-stage moment: respectively representing the average deviation degree, the standard deviation, the distortion degree and the kurtosis of the surface of the casting by using a method for describing the roughness of the surface of the casting;
s03: according to the surface roughness of the casting, generating a vision self-adaptive robot polishing parameter and controlling a polishing execution element to polish by combining a vision measurement and positioning method, a kinematic analysis method, a force control method and a position control servo method;
s04: and comparing the real-time dynamic morphological characteristic parameters of the surface of the workpiece with the target morphological characteristic parameters in real time in the polishing process until the roughness of the surface of the workpiece reaches the target morphological characteristic parameters.
Further, the step S01 specifically includes: a CCD camera fixed above the surface of the casting is adopted to shoot illumination images, a light source irradiates photometric stereo vision of the surface of the casting from different directions, and the direction vectors of the light source are not less than 5; in the process of acquiring the surface image of the casting each time, the light sources are uniformly distributed in the same plane ring, only one light source is started each time and is started in sequence to obtain the surface image of the illuminated casting, and the morphology of the casting is obtained by using a multi-light-source photometric stereo method.
Further, the multi-light source photometric stereo vision method specifically comprises the following steps: reconstructing the three-dimensional surface of the casting to obtain a surface image I of the casting at the time tt(ii) a From casting surface image ItGet position (i, j)tThe height of the point is z (i, j)tAnalyzing the length L of the defect area to be processed at the time ttAnd width Wt。
Further, the method can be used for preparing a novel materialThe step S02 specifically includes: casting surface image I through robot control systemtAnalyzing to obtain the decomposed burrs, holes, cracks and the rough condition of the integral surface of the casting; the first moment, the second moment, the third moment and the fourth moment of the casting height are analyzed by utilizing a method for describing the surface roughness of the casting, and the moment characteristics of the image are used as the input of a grinding controller to describe the knowledge characteristics of the surface of the machined casting.
Further, the method for carving the surface roughness of the casting specifically comprises the following steps: casting surface image ItAny point (i, j)tIs z (i, j)tAnd the roughness of the casting corresponds to each step moment of the height of the casting:
first moment of casting heightThe average deviation degree of the surface of the casting is represented, and the larger the value is, the larger the average deviation is, and the more uneven the casting is;
second moment of the castingThe standard deviation of the heights of all points on the surface of the casting is represented, namely the roughness of the surface of the casting is represented, and the larger the value is, the rougher the surface of the casting is;
third moment of the castingThe distortion degree of the surface of the casting is represented, and the higher the value is, the higher the distortion degree of the surface of the casting is;
fourth order moment of castingThe kurtosis value of the surface of the casting is represented, and the higher the kurtosis is, the rougher the surface of the casting is;
the surface roughness of the casting is: fflat-t＝{M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}，StKnowledge characteristics of the casting surface: st＝It(Lt，Wt，Fflat-t)＝Lt*Wt*Fflat-t。
Further, the visual measuring and positioning method in the step S03 is as follows: converting the roughness of the surface of the casting into the translation speed v of the grinding robot grinding wheel at the moment t by using a vision measuring and positioning system controllerr(t) rotational speed ω of grinding wheelr(t), depth of machined casting d (t) and robot joint angle qr(t); the vision measurement and positioning system controller is completed by a deep learning neural network N, and the rough condition of the whole surface of the workpiece and the translation speed v of the workpiece processing grinding wheel are established through repeated forward training learning and reverse feedback learningr(t), rotational speed ωr(t) correlation with control factor for depth of feed d (t) of the workpiece to be machined, (v)r(t)，ωr(t)，d(t))＝N{M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}。
Further, the kinematic analysis method in step S03 is: robot arm tip velocity v using visual measurement and positioning system controller at time tp(t) and the position p (t), and obtaining the corrected joint rotation angle q of the robot through a kinematic moduler-n(t) angular velocity of robot joint
Further, the force control method in step S03 is: correcting robot joint angular velocity through force control moduleObtaining a corrected angular velocity of a joint of a robot
Further, the position control servo method in the step S03 is: the corrected joint rotation angle q of the robot is corrected through a position servo moduler-n(t) corrected angular velocity of robot jointJoint rotation angle q fed back by robotm(t) angular velocity of jointConverting the moment into a real-time joint driving moment tau (t) of the robot; the speed of the tail end of the robot arm is consistent with the translation speed of the grinding wheel:
vr(t)、vp(t) is the translation speed of the grinding wheel and the tail end speed of the robot arm at the moment t: v. ofr(t)＝vp(t)＝F1(St)＝k1St；
ωr(t) is the rotation speed of the grinding wheel at the time t: omegar(t)＝F2(St)＝k2St；
d (t) is the feed depth of the grinding wheel at the time t: d (t) ═ F3(St)＝k3St；
Wherein: coefficient k1、k2And k3And determining according to the casting material.
Further, the step S04 specifically includes: let M1、M2、M3、M4Respectively obtaining standard characteristic values of first, second, third and fourth moments of the target morphological characteristics of the casting;respectively being a dynamic morphological characteristic parameter M1(i,j)t、M2(i,j)t、M3(i,j)t、M4(i,j)tAverage value at time t, ifAnd isAnd isAnd isThe quality of the surface casting at the time t is qualified, the current surface of the casting is polished, and the next surface polishing step is started, and the steps S01-S04 are repeated; wherein,1、2、3、4respectively determining the allowable error ranges of the standard characteristic values of the step moments of the castings with qualified quality;
if the surface casting quality does not meet the requirement, the surface casting quality at the time t is unqualified, t is kT, and k is k +1, wherein k is the grinding times; t is the time required for finishing one-time polishing from the visual characteristics extraction; steps S01-S04 are repeated.
The invention has the beneficial effects that:
1. the robot casting polishing self-adaption method based on the vision system can obtain the three-dimensional form of the casting by adopting a multi-light-source photometric stereo vision method, and can measure the surface quality of the machined workpiece with higher precision.
2. According to the robot casting polishing self-adaption method based on the vision system, the surface quality of the workpiece obtained by describing the surface morphological characteristics of the casting by using the moment can more comprehensively and more finely describe the surface morphological characteristics of the casting.
3. The invention relates to a robot casting polishing self-adaption method based on a visual system, which adopts a deep learning neural network controller to complete visual measurement and positioning, integrates polishing and quality detection into a whole and can adaptively complete workpiece polishing, the visual measurement and positioning system controller is realized by the deep learning neural network, the deep learning neural network establishes the incidence relation between the rough condition of the whole surface of a workpiece and control factors such as the translation speed and the rotation speed of a workpiece processing grinding wheel and the feeding depth of the processed workpiece through repeated forward training learning and reverse feedback learning, so as to complete the real-time self-adaption polishing of the robot casting, ensure the polishing quality of a cylinder casting with large characteristics, and when the polished casting has a quality problem, the robot casting is detected and polished again in real time until the polishing quality of the casting is qualified.
Drawings
FIG. 1 is a flow chart of a vision system based robotic casting grinding adaptive method of the present invention.
FIG. 2 is a schematic diagram of the multi-light source photometric stereo method according to the present invention.
Fig. 3 is a schematic view of the robot vision adaptive robot polishing control according to the present invention.
In the figure:
1-1: a CCD camera; 1-2: a light source; 1-3: and (5) casting.
Detailed Description
The invention will be further described with reference to the following figures and specific examples, but the scope of the invention is not limited thereto.
As shown in figure 1, by utilizing a robot casting grinding self-adaptive method based on a vision system, HT300 cylinder castings with the weight of 38kg are automatically ground, the casting volume is 400mm multiplied by 320mm multiplied by 253mm, and the method comprises the following specific steps:
s01: machine vision extraction of the surface topography of the casting:
processing a workpiece into a 4-cylinder, taking an illumination image by using a Panasoinc WV-CP410/G type CCD camera fixed above the cylinder, wherein the focal length f of the camera is 16mm, the distance u from the camera to the cylinder is 745mm, taking the illumination image by using a CCD camera 1-1, and irradiating the surface luminosity stereo vision of a casting from different directions by using a light source (1-2), as shown in FIG. 2, the direction vectors of the light source (1-2) are 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); in the process of acquiring the surface image of the casting each time, the light sources (1-2) are uniformly distributed in the same plane ring, only one light source is started each time and is started in sequence to obtain the surface image of the illuminated casting, and the morphology of the casting is obtained by using a multi-light-source photometric stereo method.
The multi-light source luminosity stereo vision method comprises the following steps: reconstructing the three-dimensional surface of the casting, and the surface image I of the casting at the time ttPosition (i, j)tThe height of the point is z (i, j)tAnd length L of defective area to be processed at time ttAnd width Wt。
S02: the surface topography characteristic of the casting is drawn by multi-stage moment: casting surface image I through robot control systemtAnalyzing to obtain the decomposed burrs, holes, cracks and the rough condition of the integral surface of the casting; the first moment, the second moment, the third moment and the fourth moment of the casting height are analyzed by utilizing a method for describing the surface roughness of the casting, and the moment characteristics of the image are used as the input of a grinding controller to describe the knowledge characteristics of the surface of the machined casting.
The method for carving the surface roughness of the casting comprises the following steps: casting surface image ItAny point (i, j)tIs z (i, j)tAnd the roughness of the casting corresponds to each step moment of the height of the casting:
first moment of casting heightThe average deviation degree of the surface of the casting is represented, and the larger the value is, the larger the average deviation is, and the more uneven the casting is;
second moment of the castingThe standard deviation of the heights of all points on the surface of the casting is represented, namely the roughness of the surface of the casting is represented, and the larger the value is, the rougher the surface of the casting is;
third moment of the castingThe distortion degree of the surface of the casting is represented, and the higher the value is, the higher the distortion degree of the surface of the casting is;
fourth order moment of castingThe kurtosis value of the surface of the casting is represented, and the higher the kurtosis is, the rougher the surface of the casting is;
the surface roughness of the casting is: fflat-t＝{M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}，
StKnowledge characteristics of the casting surface: st＝It(Lt，Wt，Fflat-t)＝Lt*Wt*Fflat-t。
S03: as shown in fig. 3, according to the surface roughness of the casting, a vision measurement and positioning method, a kinematics analysis method, a force control method and a position control servo method are combined to generate a vision adaptive robot polishing parameter and control a polishing execution element to polish;
the visual measurement and positioning method comprises the following steps: converting the roughness of the surface of the casting into the translation speed v of the grinding robot grinding wheel at the moment t by using a vision measuring and positioning system controllerr(t) rotational speed ω of grinding wheelr(t), depth of machined casting d (t) and robot joint angle qr(t); the vision measurement and positioning system controller is completed by a deep learning neural network N, and the rough condition of the whole surface of the workpiece and the translation speed v of the workpiece processing grinding wheel are established through repeated forward training learning and reverse feedback learningr(t), rotational speed ωr(t) correlation with control factor for depth of feed d (t) of the workpiece to be machined, (v)r(t)，ωr(t)，d(t))＝N{M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}。
The kinematic analysis method comprises the following steps: robot arm tip velocity v using visual measurement and positioning system controller at time tp(t) and the position p (t), and obtaining the corrected joint rotation angle q of the robot through a kinematic moduler-n(t) angular velocity of robot joint
The force control method comprises the following steps: correcting robot joint angular velocity through force control moduleObtaining a corrected angular velocity of a joint of a robot
The position control servo method comprises the following steps: the corrected robot joint corner q is corrected through a position servo moduler-n(t) corrected angular velocity of robot jointJoint rotation angle q fed back by robotm(t) angular velocity of jointConverting the moment into a real-time joint driving moment tau (t) of the robot; the speed of the tail end of the robot arm is consistent with the translation speed of the grinding wheel:
vr(t)、vp(t) is the translation speed of the grinding wheel and the tail end speed of the robot arm at the moment t: v. ofr(t)＝vp(t)＝F1(St)＝k1St；
ωr(t) is the rotation speed of the grinding wheel at the time t: omegar(t)＝F2(St)＝k2St；
d (t) is the feed depth of the grinding wheel at the time t: d (t) ═ F3(St)＝k3St；
Wherein: coefficient k1、k2And k3And determining according to the casting material.
S04: and comparing the real-time dynamic morphological characteristic parameters of the surface of the workpiece with the target morphological characteristic parameters in real time in the polishing process until the roughness of the surface of the workpiece reaches the target morphological characteristic parameters. And comparing the real-time grinding characteristic parameters with the expected geometric morphology of the surface of the target casting to obtain real-time grinding characteristic parameters, and finishing the grinding of the casting in a self-adaptive manner according to the real-time geometric morphology.
The method specifically comprises the following steps: let M1、M2、M3、M4Respectively the standard characteristic values of first, second, third and fourth moments of the target morphological characteristics of the casting, wherein M1＝0.3μm，M2＝0.003μm，M3＝0.01μm，M4＝0.03μm；Respectively being a dynamic morphological characteristic parameter M1(i,j)t、M2(i,j)t、M3(i,j)t、M4(i,j)tAverage value at time t, ifAnd isAnd isAnd isThe quality of the surface casting at the time t is qualified, the current surface of the casting is polished, and the next surface polishing step is started, and the steps S01-S04 are repeated; wherein,1、2、3、4the standard characteristic value of the step moment of the castings with qualified quality is within an allowable error range respectively1＝0.05μm，2＝0.005μm，3＝0.005μm，4＝0.005μm；
If the surface casting quality does not meet the requirement, the surface casting quality at the time t is unqualified, t is kT, and k is k +1, wherein k is the grinding times; t is the time required for finishing one-time polishing from the visual characteristics extraction; steps S01-S04 are repeated.
In the case, the self-adaptive polishing method is adopted, the processing times are greatly reduced, meanwhile, the effective processing times are increased, and only 1 cylinder is unqualified in the processing result of the self-adaptive polishing method in the processing of 30 cylinders; before this, 3-5 cylinders are unqualified in the processing of 30 cylinders.
The present invention is not limited to the above-described embodiments, and any obvious improvements, substitutions or modifications can be made by those skilled in the art without departing from the spirit of the present invention.
Claims (10)
1. A robot casting polishing self-adaptive method based on a vision system is characterized by comprising the following steps:
s01: machine vision extraction of the surface topography of the casting;
s02: the surface topography characteristic of the casting is drawn by multi-stage moment: respectively representing the average deviation degree, the standard deviation, the distortion degree and the kurtosis of the surface of the casting by using a method for describing the roughness of the surface of the casting;
s03: according to the surface roughness of the casting, generating a vision self-adaptive robot polishing parameter and controlling a polishing execution element to polish by combining a vision measurement and positioning method, a kinematic analysis method, a force control method and a position control servo method;
s04: and comparing the real-time dynamic morphological characteristic parameters of the surface of the workpiece with the target morphological characteristic parameters in real time in the polishing process until the roughness of the surface of the workpiece reaches the target morphological characteristic parameters.
2. The vision system based robotic casting sanding adaptive method of claim 1, wherein the step S01 is embodied as: a CCD camera (1-1) fixed above the surface of the casting is adopted to shoot an illumination image, a light source (1-2) irradiates the surface luminosity stereoscopic vision of the casting from different directions, and the direction vectors of the light source (1-2) are not less than 5; in the process of acquiring the surface image of the casting each time, the light sources (1-2) are uniformly distributed in the same plane ring, only one light source is started each time and is started in sequence to obtain the surface image of the illuminated casting, and the morphology of the casting is obtained by using a multi-light-source photometric stereo method.
3. The vision system based robot casting grinding adaptive method as claimed in claim 2, characterized in that the multi-light source photometric stereo vision method is specifically as follows: reconstructing the three-dimensional surface of the casting to obtain a surface image I of the casting at the time tt(ii) a From casting surface image ItGet position (i, j)tThe height of the point is z (i, j)tAnalyzing the length L of the defect area to be processed at the time ttAnd width Wt。
4. The vision system based robotic casting sanding adaptive method of claim 1, wherein the step S02 is embodied as: casting surface image I through robot control systemtAnalyzing to obtain the decomposed burrs, holes, cracks and the rough condition of the integral surface of the casting; method for analyzing height of casting by utilizing surface roughness of carved castingThe moment features of the image are used as the input of a grinding controller to characterize the knowledge of the surface of the machined casting.
5. The vision system based robot casting grinding adaptive method according to claim 4, wherein the method for depicting the casting surface roughness specifically comprises: casting surface image ItAny point (i, j)tIs z (i, j)tAnd the roughness of the casting corresponds to each step moment of the height of the casting:
first moment of casting heightThe average deviation degree of the surface of the casting is represented, and the larger the value is, the larger the average deviation is, and the more uneven the casting is;
second moment of the castingThe standard deviation of the heights of all points on the surface of the casting is represented, namely the roughness of the surface of the casting is represented, and the larger the value is, the rougher the surface of the casting is;
third moment of the castingThe distortion degree of the surface of the casting is represented, and the higher the value is, the higher the distortion degree of the surface of the casting is;
fourth order moment of castingThe kurtosis value of the surface of the casting is represented, and the higher the kurtosis is, the rougher the surface of the casting is;
the surface roughness of the casting is: fflat-t＝{M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}，
StKnowledge characteristics of the casting surface: st＝It(Lt，Wt，Fflat-t)＝Lt*Wt*Fflat-t。
6. The vision system based robotic casting grinding adaptive method of claim 1, wherein the vision measuring and positioning method in step S03 is: converting the roughness of the surface of the casting into the translation speed v of the grinding robot grinding wheel at the moment t by using a vision measuring and positioning system controllerr(t) rotational speed ω of grinding wheelr(t), depth of machined casting d (t) and robot joint angle qr(t); the vision measurement and positioning system controller is completed by a deep learning neural network N, and the rough condition of the whole surface of the workpiece and the translation speed v of the workpiece processing grinding wheel are established through repeated forward training learning and reverse feedback learningr(t), rotational speed ωr(t) correlation with control factor for depth of feed d (t) of the workpiece to be machined, (v)r(t)，ωr(t)，d(t))＝N{M1(i,j)t,M2(i,j)t,M3(i,j)t,M4(i,j)t}。
7. The vision system based robotic casting grinding adaptive method according to claim 1, wherein the kinematic analysis method in step S03 is: robot arm tip velocity v using visual measurement and positioning system controller at time tp(t) and the position p (t), and obtaining the corrected joint rotation angle q of the robot through a kinematic moduler-n(t) angular velocity of robot joint
8. The vision system based robotic casting sanding adaptive method of claim 1, wherein the force control method in step S03 is: correcting robot joint angular velocity through force control moduleObtaining a corrected angular velocity of a joint of a robot
9. The vision system based robotic casting grinding adaptive method of claim 1, wherein the position control servo method in step S03 is: the corrected joint rotation angle q of the robot is corrected through a position servo moduler-n(t) corrected angular velocity of robot jointJoint rotation angle q fed back by robotm(t) angular velocity of jointConverting the moment into a real-time joint driving moment tau (t) of the robot; the speed of the tail end of the robot arm is consistent with the translation speed of the grinding wheel:
vr(t)、vp(t) is the translation speed of the grinding wheel and the tail end speed of the robot arm at the moment t: v. ofr(t)＝vp(t)＝F1(St)＝k1St；
ωr(t) is the rotation speed of the grinding wheel at the time t: omegar(t)＝F2(St)＝k2St；
d (t) is the feed depth of the grinding wheel at the time t: d (t) ═ F3(St)＝k3St；
Wherein: coefficient k1、k2And k3And determining according to the casting material.
10. The method according to claim 1, wherein the step S04 is specifically executed by comparing the dynamic morphological feature parameters with the target morphological feature parameters in real timeComprises the following steps: let M1、M2、M3、M4Respectively obtaining standard characteristic values of first, second, third and fourth moments of the target morphological characteristics of the casting;respectively being a dynamic morphological characteristic parameter M1(i,j)t、M2(i,j)t、M3(i,j)t、M4(i,j)tAverage value at time t, ifAnd isAnd isAnd isThe quality of the surface casting at the time t is qualified, the current surface of the casting is polished, and the next surface polishing step is started, and the steps S01-S04 are repeated; wherein,1、2、3、4respectively determining the allowable error ranges of the standard characteristic values of the step moments of the castings with qualified quality;
if the surface casting quality does not meet the requirement, the surface casting quality at the time t is unqualified, t is kT, and k is k +1, wherein k is the grinding times; t is the time required for finishing one-time polishing from the visual characteristics extraction; steps S01-S04 are repeated.
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 | 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 |
| 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 | Industrial robot flexible polishing method 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 |
|---|---|---|
| CN107378780A (en) | A kind of robot casting grinding adaptive approach of view-based access control model system | |
| CN109940605B (en) | Compliant assembly system and method integrating three-dimensional vision and contact force analysis | |
| CN109571152B (en) | Automatic workpiece polishing method based on offline programming | |
| CN104915957B (en) | A kind of matching antidote for improving industrial robot 3D vision accuracy of identification | |
| CN104154875B (en) | Three-dimensional data acquisition system and acquisition method based on two-axis rotation platform | |
| CN108582076A (en) | A kind of Robotic Hand-Eye Calibration method and device based on standard ball | |
| JP6734253B2 (en) | Imaging device including a visual sensor for imaging a workpiece | |
| CN113146172B (en) | Multi-vision-based detection and assembly system and method | |
| CN109291048B (en) | Real-time online programming system and method for grinding and polishing industrial robot | |
| Kosler et al. | Adaptive robotic deburring of die-cast parts with position and orientation measurements using a 3D laser-triangulation sensor | |
| CN111644935A (en) | Robot three-dimensional scanning measuring device and working method | |
| CN109648202B (en) | Additive manufacturing forming precision control method for non-flat surface autonomous recognition robot | |
| CN109940604B (en) | Workpiece three-dimensional positioning system and method based on point cloud data | |
| KR102096897B1 (en) | The auto teaching system for controlling a robot using a 3D file and teaching method thereof | |
| CN109514554B (en) | Tool coordinate system rapid calibration method using robot terminal vision system | |
| Hsu et al. | Development of a faster classification system for metal parts using machine vision under different lighting environments | |
| CN113267452A (en) | Engine cylinder surface defect detection method and system based on machine vision | |
| CN109940606A (en) | Robot based on point cloud data guides system and method | |
| CN112729112B (en) | Engine cylinder bore diameter and hole site detection method based on robot vision | |
| Huo et al. | Model-free adaptive impedance control for autonomous robotic sanding | |
| Tsarouchi et al. | Vision system for robotic handling of randomly placed objects | |
| CN116551048A (en) | Geometric self-adaptive machining equipment and method | |
| CN116079734A (en) | Assembly control system and method of cooperative robot based on double-vision detection | |
| CN112109072A (en) | Method for measuring and grabbing accurate 6D pose of large sparse feature tray | |
| CN116079732A (en) | Cabin assembly method based on laser tracker and binocular vision mixed guidance |
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 |