CN109513557A - A kind of robot autonomous spraying method of ship segment spray painting of view-based access control model guidance - Google Patents
A kind of robot autonomous spraying method of ship segment spray painting of view-based access control model guidance Download PDFInfo
- Publication number
- CN109513557A CN109513557A CN201811608018.4A CN201811608018A CN109513557A CN 109513557 A CN109513557 A CN 109513557A CN 201811608018 A CN201811608018 A CN 201811608018A CN 109513557 A CN109513557 A CN 109513557A
- Authority
- CN
- China
- Prior art keywords
- target
- spraying
- image
- robot
- spray painting
- 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
- 238000005507 spraying Methods 0.000 title claims abstract description 63
- 238000007592 spray painting technique Methods 0.000 title claims abstract description 27
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 20
- 238000000576 coating method Methods 0.000 claims abstract description 17
- 239000011248 coating agent Substances 0.000 claims abstract description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 11
- 239000012636 effector Substances 0.000 claims abstract description 9
- 239000003973 paint Substances 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000005530 etching Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000004040 coloring Methods 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000010422 painting Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 3
- 239000007921 spray Substances 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000994 depressogenic effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- RSMUVYRMZCOLBH-UHFFFAOYSA-N metsulfuron methyl Chemical compound COC(=O)C1=CC=CC=C1S(=O)(=O)NC(=O)NC1=NC(C)=NC(OC)=N1 RSMUVYRMZCOLBH-UHFFFAOYSA-N 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000000505 pernicious effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000037452 priming Effects 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B15/00—Details of spraying plant or spraying apparatus not otherwise provided for; Accessories
- B05B15/80—Arrangements in which the spray area is not enclosed, e.g. spray tables
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/12—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to conditions of ambient medium or target, e.g. humidity, temperature position or movement of the target relative to the spray apparatus
- B05B12/122—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to conditions of ambient medium or target, e.g. humidity, temperature position or movement of the target relative to the spray apparatus responsive to presence or shape of target
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B13/00—Machines or plants for applying liquids or other fluent materials to surfaces of objects or other work by spraying, not covered by groups B05B1/00 - B05B11/00
- B05B13/02—Means for supporting work; Arrangement or mounting of spray heads; Adaptation or arrangement of means for feeding work
- B05B13/04—Means for supporting work; Arrangement or mounting of spray heads; Adaptation or arrangement of means for feeding work the spray heads being moved during spraying operation
- B05B13/0431—Means for supporting work; Arrangement or mounting of spray heads; Adaptation or arrangement of means for feeding work the spray heads being moved during spraying operation with spray heads moved by robots or articulated arms, e.g. for applying liquid or other fluent material to 3D-surfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B15/00—Details of spraying plant or spraying apparatus not otherwise provided for; Accessories
- B05B15/70—Arrangements for moving spray heads automatically to or from the working position
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of robot autonomous spraying methods of ship segment spray painting of view-based access control model guidance, it is sprayed by the robot autonomous paint finishing of ship segment spray painting that view-based access control model guides, it includes flowing water workbench, robot, end effector of robot, spray coating mechanical arm, controller, computer and depth industrial camera, target workpiece to be sprayed is sent to spraying area by flowing water workbench, and the posture information of target workpiece is acquired by depth industrial camera, by being detected based on the algorithm of target detection of convolutional neural networks to the target workpiece in acquisition image in computer, to obtain the posture information of coating objective workpiece, motion control is carried out to spray coating mechanical arm by controller combination end effector of robot motion control arithmetic again, it operates it and spraying operation is carried out to target workpiece.The present invention has the advantages that the present invention effectively realizes the intellectually and automatically of ship segment spray painting robot.
Description
Technical field
The present invention relates to ship spraying technology field, in particular to a kind of ship segment spray painting machine of view-based access control model guidance
The autonomous spraying method of people.
Background technique
Currently, China has been the first in the world shipbuilding big country, but domestic ship spraying industry is substantially still using traditional artificial
Operation mode, staff labor intensity is big, pernicious gas harm is healthy, coating quality is unstable, ship regurgitates rate height, serious to restrict
Productivity.Vessel coating process are as follows: raw material ball blast assembly line pretreatment → Painting Shop priming paint → steel blanking adds
Work, assembly → segmentation advance fitting-out → segmentation secondary rust removal → segmentation coating → berth combination, fitting-out → building berth secondary rust removal → bis-
Coating in secondary coating → ship launching → harbour secondary rust removal, the preceding depressed place of coating → delivery.It can be with from the coating process program of ship
Find out that painting operation has run through the overall process of shipbuilding, therefore, it is necessary to pay attention to the quality of painting operation, the especially painting of boat segmental
Dress, it is the critical process before ship general assembly.In most of shipbuilding enterprise, since the shipbuilding duration is shorter and shorter,
Vessel coating often gets the brush-off, it is only regarded as " ship makeup " process.With the development of domestic and international ship-building industry and competing
The intensification striven, vessel coating also just become important: it not only can change the appearance of ship, increase to marine ship bright
Beautiful appearance can also prevent seawater from extending the service life of ship to the corrosion of ship.But due to lacking advanced coating equipment
And technology, even if having selected good coating, coating quality is still difficult to improve.Although the product inherent quality of many shipbuilding enterprises
First-class, since coating quality is second-class, product price can only be it is third, such case is at home in many middle-size and small-size shipbuilding enterprises
It is especially prominent.
Therefore, in Vehicles Collected from Market dog-eat-dog, raw material and energy prices rise steadily and adapt to the situation of environmental requirement
Under, " improving coating for watercraft quality ", " reducing VOC (volatile organism matter) discharge ", " energy saving ", " assembly is managed in reduction
Sheet " etc. has become problem in the urgent need to address.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of ship segment spray painting of view-based access control model guidance is robot autonomous
Spraying method, building and network training, deep learning network system output end quick obtaining ship based on deep learning network
It is segmented geometry classification and posture, realizes the intellectually and automatically of ship segment spray painting robot.
In order to solve the above technical problems, the technical solution of the present invention is as follows: a kind of ship segment spray painting of view-based access control model guidance
Robot autonomous spraying method, innovative point are: the ship segment spray painting machine that the spraying method is guided by view-based access control model
Device people is autonomous, and paint finishing sprays, and the robot autonomous paint finishing of ship segment spray painting of the view-based access control model guidance includes
Flowing water workbench, robot, end effector of robot, spray coating mechanical arm, controller, computer and depth industrial camera, institute
It states target workpiece to be sprayed and spraying area is sent to by flowing water workbench, and target work is acquired by depth industrial camera
The posture information of part, by computer based on the algorithm of target detection of convolutional neural networks to acquisition image in target workpiece
It is detected, to obtain the posture information of coating objective workpiece, and workpiece is sprayed to target according to spraying profile optimization algorithm
Optimal spraying position selection is carried out, then by controller combination end effector of robot motion control arithmetic to spray coating mechanical arm
Motion control is carried out, it is operated and spraying operation is carried out to target workpiece.
Further, specific step is as follows for the algorithm of target detection:
Step 1: laser sensor triggers the conveyer belt stop motion of flowing water workbench, while depth industrial camera acquisition system
Determine area image；
Step 2: image gray processing being operated, and carries out grayscale equalization processing, improves picture contrast；
Step 3: being handled image binaryzation based on Otsu Threshold segmentation；
Step 4: the grain noise in image is filtered out by etching operation；
Step 5: the edge for the target that is corroded moderately is restored using expansive working；
Step 6: being detected by boundary pixel and determine Chinese chess boundary；
Step 7: segmentation extracts the only topography of Chinese chess and determines the centre coordinate of Chinese chess from picture；
Step 8: modification picture size is that identification is prepared；
Step 9:CNN carries out target identification classification；
Step 10: identifying successfully then output as a result, otherwise left-handed 10 ° and return step 9.
Further, CNN carries out target identification classification in the step 9, the specific steps are as follows:
(1) acquisition and pretreatment of image, acquisition target image carry out gray proces, etching operation and Threshold segmentation behaviour
Make；
(2) depth training is carried out to image pattern and extracts feature, i.e., supervised by sample of the CNN to artificial regularization
Educational inspector practises, and gets the characteristic information for most having discrimination.
Further, described image is pre-processed and is realized using Matlab image procossing library function, using Deep
The handling function of Learning oolbox realizes CNN, and CPU be Intel CoreTM i3-2100 CPU@3.10GHz, it is interior
Save as training network on the platform computer of 12G；
In the training process, by having the mean square deviation back-propagation algorithm corrective networks parameter of supervision, i.e. Minimum Mean Square Error
Method (MMSE) be for sample dataNetwork, mean square error (MSE) can be expressed as
Wherein hw.bIt (x) is network output valve, h is activation primitive, selects Sigmiod function, and W is the weight matrix of network,
B is the bias matrix that every layer of biasing b is constituted, and x is input sample matrix, y*For desired output, non-concave function J (W, b are minimized；
x,y*) optimal solution of network can be obtained；The method for generalling use gradient decline updates weight to network interative computation:
Wherein α is learning rate.
Further, the spraying profile optimization algorithm uses two step grade coupled systems of depth network composition, the first step
For selecting one group of candidate spraying area comprising body section, second step is examined on candidate region on the basis of back
It looks into and obtains optimal initial spraying position frame；First by the approximate region comprising target of acquisition, proposed adoption contains target object
Image subtract corresponding background image, obtain one include target binary map, target is then obtained according to colouring information
Approximate location, then by the minimum rectangle image comprising target respectively from binary map, cromogram, depth map and based on the table of depth map
It intercepts and comes out on the normal vector characteristic pattern of face, by operations such as rotation, whitened data, holding aspect ratios, finally obtain target workpiece
Optimal spraying position.
The present invention has the advantages that
The present invention is based on the robot autonomous spraying methods of the ship segment spray painting of vision guide, with ship segment spray painting machine
For the purpose of people independently sprays, in conjunction with vision guide technology, cooperate robot module and mechanical module, design object workpiece identification is calculated
Method and end effector of robot motion control arithmetic are realized and stablize fast spraying operation, facilitate reduction personnel and directly connect
It touches the time of spraying industrial operation, improve production efficiency, enhancing automatization level, there is the theoretical meaning in practical application；
In addition, being had the advantage that compared with the spraying of traditional artificial ship
(1) high-precision: machine vision and servo control technique combine, so that the operation precision of ship segment spray painting obtains
Significantly improve.
(2) high automation: automation is the intervention of " people " to be reduced in whole process, and meeting can be automatically completed
Defined task；This system uses vision guide, identifies target workpiece pose by vision positioning, obtains relevant information, utilizes
Servo control technique realizes the autonomous spraying operation of ship.
Detailed description of the invention
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
Fig. 1 is that the present invention is based on the structure charts of the robot autonomous paint finishing of the ship segment spray painting of vision guide.
Fig. 2 is that the present invention is based on ship segment spray paintings in the robot autonomous spraying method of the ship segment spray painting of vision guide
CNN structural model.
Fig. 3 is the flow chart that CNN carries out target identification classification in Fig. 2.
Fig. 4 is that the present invention is based on spraying position tables in the robot autonomous spraying method of the ship segment spray painting of vision guide
Show.
Specific embodiment
The following examples can make professional and technical personnel that the present invention be more fully understood, but therefore not send out this
It is bright to be limited among the embodiment described range.
Embodiment
The robot autonomous spraying method of ship segment spray painting of the present embodiment view-based access control model guidance, the spraying method pass through base
It is sprayed in the robot autonomous paint finishing of the ship segment spray painting of vision guide, as shown in Figure 1, the ship of view-based access control model guidance
It includes flowing water workbench 1, robot 2, end effector of robot 3, flush coater that oceangoing ship, which is segmented the autonomous paint finishing of spray robot,
Tool arm 4, controller 5, computer 6 and depth industrial camera 7, target workpiece 8 to be sprayed are sent to by flowing water workbench 1
Spraying area, and by the posture information of the acquisition target workpiece 8 of depth industrial camera 7, by being based on convolutional Neural in computer 6
The algorithm of target detection of network detects the target workpiece 8 in acquisition image, to obtain the pose of coating objective workpiece 8
Information, and optimal spraying position selection is carried out to target spraying workpiece according to spraying profile optimization algorithm, then pass through 5 knot of controller
It closes 3 motion control arithmetic of end effector of robot and motion control is carried out to spray coating mechanical arm, operate it and target workpiece is carried out
Spraying operation.
In the present embodiment, specific step is as follows for algorithm of target detection:
Step 1: laser sensor triggers the conveyer belt stop motion of flowing water workbench, while depth industrial camera acquisition system
Determine area image；
Step 2: image gray processing being operated, and carries out grayscale equalization processing, improves picture contrast；
Step 3: being handled image binaryzation based on Otsu Threshold segmentation；
Step 4: the grain noise in image is filtered out by etching operation；
Step 5: the edge for the target that is corroded moderately is restored using expansive working；
Step 6: being detected by boundary pixel and determine Chinese chess boundary；
Step 7: segmentation extracts the only topography of Chinese chess and determines the centre coordinate of Chinese chess from picture；
Step 8: modification picture size is that identification is prepared；
Step 9:CNN carries out target identification classification, as shown in Fig. 2, CNN model is multi-layer structure model, is divided into 3 parts:
Input layer, middle layer and full articulamentum；It is bianry image or RGB color image that input layer, which commonly enters, before the input one
As image is filtered, the pretreatment operations such as modification of dimension are to improve Network Recognition effect；Middle layer is by convolutional layer and pond
Change layer alternately to form, CNN is used as deep learning model, and depth major embodiment convolutional layer in the intermediate layer and pond layer replace
Number；When the complexity of CNN identification picture is bigger, the alternate number of middle layer also can be more, are similar to GoogLeNet mono-
The large-scale convolutional network of class will use for learning super more category images to ten several layers of convolutional layers and pond layer；CNN carries out target
Identification classification, as shown in Figure 3, the specific steps are as follows:
(1) acquisition and pretreatment of image, acquisition target image carry out gray proces, etching operation and Threshold segmentation behaviour
Make；Image preprocessing and use Matlab image procossing library function are realized, using the operation letter of Deep Learning oolbox
Number realizes CNN, and is Intel CoreTM i3-2100CPU 3.10GHz, trains on the interior platform computer for saving as 12G in CPU
Network；
In the training process, by having the mean square deviation back-propagation algorithm corrective networks parameter of supervision, i.e. Minimum Mean Square Error
Method (MMSE) be for sample dataNetwork, mean square error (MSE) can be expressed as
Wherein hw.bIt (x) is network output valve, h is activation primitive, selects Sigmiod function, and W is the weight matrix of network,
B is the bias matrix that every layer of biasing b is constituted, and x is input sample matrix, y*For desired output, non-concave function J (W, b are minimized；
x,y*) optimal solution of network can be obtained；The method for generalling use gradient decline updates weight to network interative computation:
Wherein α is learning rate；
(2) depth training is carried out to image pattern and extracts feature, i.e., supervised by sample of the CNN to artificial regularization
Educational inspector practises, and gets the characteristic information for most having discrimination；
Step 10: identifying successfully then output as a result, otherwise left-handed 10 ° and return step 9.
In the present embodiment, spraying profile optimization algorithm uses two step grade coupled systems of depth network composition, and the first step is used
It include the candidate spraying area of body section in one group of selection, second step is checked on candidate region on the basis of back
And obtain optimal initial spraying position frame；The data that will ultimately be used for robot initial spraying position are expressed as (u；v；θ), wherein
(u；V) position of centre of gravity for optimal initial spraying frame under image coordinate system, θ are the length and the image coordinate system longitudinal axis for spraying frame
Angle, position are as shown in Figure 4.Ellipse representation target to be sprayed in figure；Rectangle frame indicates actuator position, the long axis of rectangle frame
The opening direction of direction expression actuator.
First by the approximate region comprising target of acquisition, the image that proposed adoption contains target object subtracts corresponding background
Image obtains the binary map comprising target, the approximate location of target is then obtained according to colouring information, then will include target
Minimum rectangle image intercepted from binary map, cromogram, depth map and surface normal characteristic pattern based on depth map respectively
Out, final to obtain the optimal spraying position of target workpiece by operations such as rotation, whitened data, holding aspect ratios.
Basic principles and main features and advantages of the present invention of the invention have been shown and described above.The skill of the industry
Art personnel it should be appreciated that the present invention is not limited to the above embodiments, the above embodiments and description only describe
The principle of the present invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these
Changes and improvements all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and
Its equivalent thereof.
Claims (5)
1. a kind of robot autonomous spraying method of ship segment spray painting of view-based access control model guidance, it is characterised in that: the spraying side
Method is sprayed by the robot autonomous paint finishing of ship segment spray painting that view-based access control model guides, the view-based access control model guidance
The robot autonomous paint finishing of ship segment spray painting includes flowing water workbench, robot, end effector of robot, spray coating mechanical
Arm, controller, computer and depth industrial camera, the target workpiece to be sprayed are sent to spraying by flowing water workbench
Region, and by depth industrial camera acquire target workpiece posture information, by computer based on convolutional neural networks
Algorithm of target detection detects the target workpiece in acquisition image, so that the posture information of coating objective workpiece is obtained, and
Optimal spraying position selection is carried out to target spraying workpiece according to spraying profile optimization algorithm, then passes through controller combination robot
End effector motion control arithmetic carries out motion control to spray coating mechanical arm, operates it and carries out spraying operation to target workpiece.
2. the robot autonomous spraying method of ship segment spray painting of view-based access control model guidance according to claim 1, feature
Be: specific step is as follows for the algorithm of target detection:
Step 1: laser sensor triggers the conveyer belt stop motion of flowing water workbench, while area is formulated in the acquisition of depth industrial camera
Area image；
Step 2: image gray processing being operated, and carries out grayscale equalization processing, improves picture contrast；
Step 3: being handled image binaryzation based on Otsu Threshold segmentation；
Step 4: the grain noise in image is filtered out by etching operation；
Step 5: the edge for the target that is corroded moderately is restored using expansive working；
Step 6: being detected by boundary pixel and determine Chinese chess boundary；
Step 7: segmentation extracts the only topography of Chinese chess and determines the centre coordinate of Chinese chess from picture；
Step 8: modification picture size is that identification is prepared；
Step 9:CNN carries out target identification classification；
Step 10: identifying successfully then output as a result, otherwise left-handed 10 ° and return step 9.
3. the robot autonomous spraying method of ship segment spray painting of view-based access control model guidance according to claim 2, feature
Be: CNN carries out target identification classification in the step 9, the specific steps are as follows:
(1) acquisition and pretreatment of image, acquisition target image carry out gray proces, etching operation and Threshold segmentation operation；
(2) depth training is carried out to image pattern and extracts feature, i.e., exercised supervision by sample of the CNN to artificial regularization
It practises, gets the characteristic information for most having discrimination.
4. the robot autonomous spraying method of ship segment spray painting of view-based access control model guidance according to claim 3, feature
Be: described image is pre-processed and is realized using Matlab image procossing library function, using Deep Learning oolbox's
Handling function realizes CNN, and is Intel CoreTM i3-2100CPU 3.10GHz, the interior platform computer for saving as 12G in CPU
Upper trained network；
In the training process, by having the mean square deviation back-propagation algorithm corrective networks parameter of supervision, the i.e. side of Minimum Mean Square Error
Method (MMSE) is for sample dataNetwork, mean square error (MSE) can be expressed as
Wherein hw.bIt (x) is network output valve, h is activation primitive, selects Sigmiod function, and W is the weight matrix of network, and b is
The bias matrix that every layer of biasing b is constituted, x are input sample matrix, y*For desired output, non-concave function J (W, b are minimized；x,y*)
It can obtain the optimal solution of network；The method for generalling use gradient decline updates weight to network interative computation:
Wherein α is learning rate.
5. the robot autonomous spraying method of ship segment spray painting of view-based access control model guidance according to claim 1, feature
Be: the spraying profile optimization algorithm uses two step grade coupled systems of depth network composition, and the first step is for selecting one group
Candidate spraying area comprising body section, second step are checked on candidate region on the basis of back and are obtained optimal
Initial spraying position frame；First by the approximate region comprising target of acquisition, the image that proposed adoption contains target object subtracts phase
The background image answered obtains the binary map comprising target, the approximate location of target is then obtained according to colouring information, then will
Minimum rectangle image comprising target is respectively from binary map, cromogram, depth map and surface normal measure feature based on depth map
Interception comes out on figure, final to obtain the optimal spraying position of target workpiece by operations such as rotation, whitened data, holding aspect ratios.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811608018.4A CN109513557B (en) | 2018-12-27 | 2018-12-27 | Ship segment spraying robot autonomous spraying method based on visual guidance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811608018.4A CN109513557B (en) | 2018-12-27 | 2018-12-27 | Ship segment spraying robot autonomous spraying method based on visual guidance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109513557A true CN109513557A (en) | 2019-03-26 |
| CN109513557B CN109513557B (en) | 2024-05-24 |
Family
ID=65796962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811608018.4A Active CN109513557B (en) | 2018-12-27 | 2018-12-27 | Ship segment spraying robot autonomous spraying method based on visual guidance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109513557B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378870A (en) * | 2019-06-06 | 2019-10-25 | 西安交通大学 | A kind of turbine blade erosion degree method of discrimination based on ResNet-GRU network |
| CN110434860A (en) * | 2019-07-04 | 2019-11-12 | 佛山科学技术学院 | A kind of robot automatic painting method and device |
| CN110433989A (en) * | 2019-07-30 | 2019-11-12 | 天津普达软件技术有限公司 | A kind of method of workpiece surface spraying |
| CN110587609A (en) * | 2019-09-20 | 2019-12-20 | 唐山雄炜机器人有限公司 | Robot rust removal control method and system |
| CN110841850A (en) * | 2019-11-13 | 2020-02-28 | 徐州普瑞赛思物联网科技有限公司 | Intelligent robot unmanned ship body segmented coating workshop system |
| CN111354031A (en) * | 2020-03-16 | 2020-06-30 | 浙江一木智能科技有限公司 | 3D vision guidance system based on deep learning |
| CN111495635A (en) * | 2020-04-23 | 2020-08-07 | 佛山科学技术学院 | Self-adaptive spraying method |
| CN112318497A (en) * | 2019-08-05 | 2021-02-05 | 发那科株式会社 | Robot control system for simultaneously selecting workpiece and performing robot operation |
| CN112329322A (en) * | 2020-10-09 | 2021-02-05 | 清华大学 | Thermal spraying method and device based on convolutional neural network |
| CN112975955A (en) * | 2021-02-03 | 2021-06-18 | 浙江明泉工业涂装有限公司 | Visual integrated system of coating production line robot |
| CN114011608A (en) * | 2021-11-26 | 2022-02-08 | 航天科工深圳（集团）有限公司 | Spraying process optimization system based on digital twinning and spraying optimization method thereof |
| CN114025607A (en) * | 2019-05-08 | 2022-02-08 | 拜耳公司 | Unmanned air vehicle |
| CN114463752A (en) * | 2022-01-20 | 2022-05-10 | 湖南视比特机器人有限公司 | Vision-based code spraying positioning method and device |
| CN114906292A (en) * | 2022-05-17 | 2022-08-16 | 武汉理工大学 | Ship navigation control device based on mechanical arm |
| CN115179304A (en) * | 2022-06-14 | 2022-10-14 | 广东天太机器人有限公司 | Mechanical arm spraying control method and system based on high-efficiency servo drive |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130330466A1 (en) * | 2012-06-11 | 2013-12-12 | General Electric Company | Spray Plume Position Feedback for Robotic Motion to Optimize Coating Quality, Efficiency, and Repeatability |
| US20150328773A1 (en) * | 2012-12-10 | 2015-11-19 | Abb Technology Ag | Robot Program Generation For Robotic Processes |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN107442340A (en) * | 2017-07-25 | 2017-12-08 | 广东加德伟自动化有限公司 | A kind of unmanned body section Painting Shop system of intelligent robot |
| CN107908152A (en) * | 2017-12-26 | 2018-04-13 | 苏州瀚华智造智能技术有限公司 | A kind of movable robot automatic spray apparatus, control system and method |
| CN107899814A (en) * | 2017-12-20 | 2018-04-13 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of robot spraying system and its control method |
| CN209577167U (en) * | 2018-12-27 | 2019-11-05 | 海安科大机器人科技有限公司 | A kind of robot autonomous paint finishing of ship segment spray painting of view-based access control model guidance |
-
2018
- 2018-12-27 CN CN201811608018.4A patent/CN109513557B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130330466A1 (en) * | 2012-06-11 | 2013-12-12 | General Electric Company | Spray Plume Position Feedback for Robotic Motion to Optimize Coating Quality, Efficiency, and Repeatability |
| US20150328773A1 (en) * | 2012-12-10 | 2015-11-19 | Abb Technology Ag | Robot Program Generation For Robotic Processes |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN107442340A (en) * | 2017-07-25 | 2017-12-08 | 广东加德伟自动化有限公司 | A kind of unmanned body section Painting Shop system of intelligent robot |
| CN107899814A (en) * | 2017-12-20 | 2018-04-13 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of robot spraying system and its control method |
| CN107908152A (en) * | 2017-12-26 | 2018-04-13 | 苏州瀚华智造智能技术有限公司 | A kind of movable robot automatic spray apparatus, control system and method |
| CN209577167U (en) * | 2018-12-27 | 2019-11-05 | 海安科大机器人科技有限公司 | A kind of robot autonomous paint finishing of ship segment spray painting of view-based access control model guidance |
Non-Patent Citations (2)
| Title |
|---|
| 唐倩;黄耀;范秋垒;刘飞;裴林清;: "基于点云与图像匹配的自动化喷涂系统坐标变换", 计算机集成制造系统, no. 11 * |
| 樊帅权;周波;孟正大;戴先中;: "三维可视化的喷涂机器人离线轨迹规划系统", 计算机技术与发展, no. 09 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114025607A (en) * | 2019-05-08 | 2022-02-08 | 拜耳公司 | Unmanned air vehicle |
| CN114025607B (en) * | 2019-05-08 | 2024-01-12 | 拜耳公司 | Unmanned aerial vehicle |
| CN110378870B (en) * | 2019-06-06 | 2021-04-20 | 西安交通大学 | ResNet-GRU network-based turbine blade water erosion degree judging method |
| CN110378870A (en) * | 2019-06-06 | 2019-10-25 | 西安交通大学 | A kind of turbine blade erosion degree method of discrimination based on ResNet-GRU network |
| CN110434860A (en) * | 2019-07-04 | 2019-11-12 | 佛山科学技术学院 | A kind of robot automatic painting method and device |
| CN110434860B (en) * | 2019-07-04 | 2022-08-16 | 佛山科学技术学院 | Robot automatic spraying method and device |
| CN110433989A (en) * | 2019-07-30 | 2019-11-12 | 天津普达软件技术有限公司 | A kind of method of workpiece surface spraying |
| CN112318497A (en) * | 2019-08-05 | 2021-02-05 | 发那科株式会社 | Robot control system for simultaneously selecting workpiece and performing robot operation |
| CN110587609A (en) * | 2019-09-20 | 2019-12-20 | 唐山雄炜机器人有限公司 | Robot rust removal control method and system |
| CN110587609B (en) * | 2019-09-20 | 2022-07-22 | 唐山雄炜机器人有限公司 | Robot rust removal control method and system |
| CN110841850A (en) * | 2019-11-13 | 2020-02-28 | 徐州普瑞赛思物联网科技有限公司 | Intelligent robot unmanned ship body segmented coating workshop system |
| CN111354031A (en) * | 2020-03-16 | 2020-06-30 | 浙江一木智能科技有限公司 | 3D vision guidance system based on deep learning |
| CN111354031B (en) * | 2020-03-16 | 2023-08-29 | 浙江一木智能科技有限公司 | 3D vision guidance system based on deep learning |
| CN111495635A (en) * | 2020-04-23 | 2020-08-07 | 佛山科学技术学院 | Self-adaptive spraying method |
| CN112329322A (en) * | 2020-10-09 | 2021-02-05 | 清华大学 | Thermal spraying method and device based on convolutional neural network |
| CN112975955A (en) * | 2021-02-03 | 2021-06-18 | 浙江明泉工业涂装有限公司 | Visual integrated system of coating production line robot |
| CN112975955B (en) * | 2021-02-03 | 2024-02-02 | 浙江明泉工业涂装有限公司 | Robot vision integrated system for coating production line |
| CN114011608A (en) * | 2021-11-26 | 2022-02-08 | 航天科工深圳（集团）有限公司 | Spraying process optimization system based on digital twinning and spraying optimization method thereof |
| CN114463752A (en) * | 2022-01-20 | 2022-05-10 | 湖南视比特机器人有限公司 | Vision-based code spraying positioning method and device |
| CN114906292A (en) * | 2022-05-17 | 2022-08-16 | 武汉理工大学 | Ship navigation control device based on mechanical arm |
| CN115179304A (en) * | 2022-06-14 | 2022-10-14 | 广东天太机器人有限公司 | Mechanical arm spraying control method and system based on high-efficiency servo drive |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109513557B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109513557A (en) | A kind of robot autonomous spraying method of ship segment spray painting of view-based access control model guidance | |
| CN106423656B (en) | Automatic spraying system and method based on cloud and images match | |
| CN109375235B (en) | Inland ship freeboard detection method based on deep reinforcement neural network | |
| Yang et al. | A welding quality detection method for arc welding robot based on 3D reconstruction with SFS algorithm | |
| CN106251353A (en) | Weak texture workpiece and the recognition detection method and system of three-dimensional pose thereof | |
| CN106097329B (en) | A kind of container profile localization method based on edge detection | |
| CN108280856A (en) | The unknown object that network model is inputted based on mixed information captures position and orientation estimation method | |
| CN209577167U (en) | A kind of robot autonomous paint finishing of ship segment spray painting of view-based access control model guidance | |
| CN111744735B (en) | Control method based on surface spraying simulation of artware | |
| CN104268600B (en) | A kind of mineral flotation foam image texture analysis and operating mode's switch method based on Minkowski distances | |
| CN110264457A (en) | Weld seam autonomous classification method based on rotary area candidate network | |
| CN115100174B (en) | Ship sheet metal part paint surface defect detection method | |
| CN110728657A (en) | Annular bearing outer surface defect detection method based on deep learning | |
| CN110625644A (en) | Workpiece grabbing method based on machine vision | |
| CN114902872A (en) | Visual guidance method for picking fruits by robot | |
| US20220343484A1 (en) | Autonomous ship bottom inspection method by rov based on 3d model of ship in stl format | |
| Kitti et al. | An object recognition and identification system using the harris corner detection method | |
| CN116922270A (en) | Intelligent control system and method for sand blasting machine | |
| CN110852265A (en) | Rapid target detection and positioning method applied to industrial production line | |
| Huang et al. | Robotic arm grasping and placing using edge visual detection system | |
| CN114851206B (en) | Method for grabbing stove based on vision guiding mechanical arm | |
| Huang et al. | Automatic feature extraction and optimal path planning for robotic drawing | |
| Ma et al. | Depth image denoising and key points extraction for manipulation plane detection | |
| CN111932074A (en) | Intelligent ship coating process recommendation method based on knowledge | |
| CN113902803A (en) | Method for acquiring double-label welding positions of end faces of bundled rods based on image processing |
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 |