CN110153584A - The rapid workpiece welding method accelerated based on figure video card - Google Patents
The rapid workpiece welding method accelerated based on figure video card Download PDFInfo
- Publication number
- CN110153584A CN110153584A CN201910496565.6A CN201910496565A CN110153584A CN 110153584 A CN110153584 A CN 110153584A CN 201910496565 A CN201910496565 A CN 201910496565A CN 110153584 A CN110153584 A CN 110153584A
- Authority
- CN
- China
- Prior art keywords
- welding
- workpiece
- server
- point cloud
- control server
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/02—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to soldering or welding
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/0081—Programme-controlled manipulators with master teach-in means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
Abstract
The invention discloses a kind of rapid workpiece welding methods accelerated based on figure video card.A kind of rapid workpiece welding method accelerated based on figure video card of the present invention, comprising: welded workpiece is placed on welding platform;Obtain the 3D point cloud model of welding workpiece;The 3D point cloud model is transmitted to control server and is stored in the database by data acquisition server.Data acquisition server is connected with control server by high-speed local area network, and control server is controlled database cluster again.Beneficial effects of the present invention: not needing the operation that operator puts one by one, do not need teaching, and workload is small, and welding quality is high.
Description
Technical field
The present invention relates to 3D visual fields, and in particular to a kind of rapid workpiece welding method accelerated based on figure video card.
Background technique
Electroplating equipment wielding machine arm is before carrying out welding at present, it usually needs the movement road of prior butt welding machine tool arm welding
Diameter, track carry out teaching.And to robot teaching, it mainly uses teaching machine matched with robot to carry out, needs operator
The operation that member puts one by one is modified robot pose and is saved into robot controller.Teaching machine method is intuitive, accurate, but wants
A large amount of taught points are carried out, workload is quite huge.Meanwhile welding effect detection is also to measure the important indicator of welding quality.
There are following technical problems for traditional technology:
Welding producing line is still mainly detected using artificial trick at present, and the amount of labour used is big, and testing result otherness is big.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of rapid workpiece welding methods accelerated based on figure video card.
In order to solve the above-mentioned technical problems, the present invention provides a kind of rapid workpiece welding sides accelerated based on figure video card
Method, comprising:
Welded workpiece is placed on welding platform;
Obtain the 3D point cloud model of welding workpiece;
The 3D point cloud model is transmitted to control server and is stored in the database by data acquisition server.Data are adopted
Collection server is connected with control server by high-speed local area network, and control server is controlled database cluster again;
A cloud is transmitted to arithmetic server by control server, and arithmetic server controls GPU high-performance workstation cluster.Institute
Have calculating all by arithmetic server parallelization, 3D point cloud is decoupled, by after partition data and algorithm routine be distributed to respectively
A GPU high-performance workstation, then arithmetic server regathers each GPU high-performance workstation calculated result, is integrated into algorithm
Calculated result towards entire point cloud.For the different step of program computational flow, this process is repeated;
Arithmetic server passes the path of welding calculated back control server, and stores in the database;
Path of welding is sent electroplating equipment wielding machine arm control server by control server, then starts electroplating equipment wielding machine arm and completes
Welding;
Line laser 3D scanner scans workpiece again after completing welding, and 3D point cloud data transmission to arithmetic server is calculated
Method server first removes noise to point cloud data, then analyzes and determines welding quality, provides welding quality inspection report.
The welding platform can access assembly line, automatic loading/unloading in one of the embodiments,.
The welding platform is as a working position, artificial loading and unloading in one of the embodiments,.
In one of the embodiments, if it is assembly line, 3D line laser scanner is motionless, and welded workpiece is by assembly line
It drives and passes through 3D line laser scanner.
In one of the embodiments, for the position that works independently, linear motor drives line laser 3D scanner to fast move,
Scanning workpiece simultaneously generates 3D point cloud model.
In one of the embodiments, according to welded workpiece complexity, GP configuring U high-performance workstation cluster is calculated
Time can be controlled in 2 seconds and completes.
Noise first is removed to point cloud data in one of the embodiments, then the straight bead in calculating point cloud, and according to
Candidate pad is tentatively found out according to the intersection point of straight line, the feature for being then based on workpiece further selects accurate pad, finally
Algorithm is based on pad and automatically generates path of welding.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes any one the method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
The step of any one the method.
A kind of processor, the processor is for running program, wherein described program executes described in any item when running
Method.
Beneficial effects of the present invention:
The operation that operator puts one by one is not needed, teaching is not needed, workload is small, and welding quality is high.
Detailed description of the invention
Fig. 1 is the schematic diagram of the rapid workpiece welding method accelerated the present invention is based on figure video card.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples, so that those skilled in the art can be with
It more fully understands the present invention and can be practiced, but illustrated embodiment is not as a limitation of the invention.
Refering to fig. 1, welded workpiece step 1: is placed on welding platform.Welding platform can access assembly line, automatically
Loading and unloading, can also be separately as a working position, artificial loading and unloading;
Step 2: if it is assembly line, 3D line laser scanner is motionless, and welded workpiece is driven by assembly line passes through 3D line
Laser scanner.For the position that works independently, linear motor drives line laser 3D scanner to fast move, and scans workpiece and generates 3D
Point cloud model;
Step 3: 3D point cloud model is transmitted to control server and is stored in the database by data acquisition server.Number
It is connected by high-speed local area network with control server according to acquisition server, control server is controlled database cluster again;
Step 4: a cloud is transmitted to arithmetic server by control server, and arithmetic server controls GPU high-performance workstation
Cluster.All calculating decouple 3D point cloud all by arithmetic server parallelization, by the data and algorithm routine point after partition
It is dealt into each GPU high-performance workstation, then arithmetic server regathers each GPU high-performance workstation calculated result, integration
Calculated result of the preconceived plan normal plane to entire point cloud.For the different step of program computational flow, this process is repeated.The present invention
The straight bead that noise first is removed to point cloud data without teaching automatic soldering method, then calculates in point cloud provided, and foundation
The intersection point of straight line tentatively finds out candidate pad, and the feature for being then based on workpiece further selects accurate pad, finally calculates
Method is based on pad and automatically generates path of welding, according to welded workpiece complexity, GP configuring U high-performance workstation cluster, meter
Evaluation time can be controlled in 2 seconds and completes;
Step 5: arithmetic server passes the path of welding calculated back control server, and stores in the database;
Step 6: path of welding is sent electroplating equipment wielding machine arm control server by control server, then starts bonding machine
Tool arm completes welding.
Step 7: line laser 3D scanner scans workpiece again after completing welding, and 3D point cloud data transmission to algorithm is taken
Business device, arithmetic server first remove noise to point cloud data, then analyze and determine welding quality, provide welding quality inspection report.It is whole
A program computational flow all utilizes GPU high-performance workstation to accelerate, according to welded workpiece complexity, GP configuring U high-performance work
Make station cluster, the calculating time can be controlled in 2 seconds and completes.
A concrete application scene of the invention is described below:
In conjunction with Fig. 1 schematic diagram, the present invention is explained in further detail.It is flat that welded workpiece is placed on welding first
Platform.Welding platform can access assembly line, and automatic loading/unloading can also be separately as a working position, artificial loading and unloading;If
It is assembly line, 3D line laser scanner is motionless, and welded workpiece is driven by assembly line passes through 3D line laser scanner.For independent
Working position, linear motor drive line laser 3D scanner to fast move, and scan workpiece and generate 3D point cloud model;3D point cloud model
It is transmitted to control server and is stored in the database by data acquisition server.Data acquisition server passes through high-speed local area network
It is connected with control server, control server is controlled database cluster again;Then a cloud is transmitted to algorithm clothes by control server
Business device, arithmetic server control GPU high-performance workstation cluster.All calculating are all by arithmetic server parallelization, to 3D point cloud
Decoupled, by after partition data and algorithm routine be distributed to each GPU high-performance workstation, then arithmetic server is received again
Collect each GPU high-performance workstation calculated result, is integrated into calculated result of the algorithm towards entire point cloud.Program is calculated and is flowed
The different step of journey, this process repeat.No teaching automatic soldering method provided by the invention first makes an uproar to point cloud data removal
Then point calculates the straight bead in point cloud, and the intersection point according to straight line tentatively finds out candidate pad, is then based on workpiece
Feature further selects accurate pad, and last algorithm is based on pad and automatically generates path of welding, according to welded workpiece
Complexity, GP configuring U high-performance workstation cluster, calculating time can be controlled in 2 seconds and complete;Then arithmetic server will calculate
Path of welding pass control server back, and store in the database;Then path of welding is sent welding by control server
Then mechanical arm control server starts electroplating equipment wielding machine arm and completes welding.Line laser 3D scanner scans again after completing welding
Workpiece, by 3D point cloud data transmission to arithmetic server, arithmetic server first removes noise to point cloud data, then analyzes and determines
Welding quality provides welding quality inspection report.Entire program computational flow all utilizes GPU high-performance workstation to accelerate, according to be welded
Workpiece complexity, GP configuring U high-performance workstation cluster are connect, the calculating time can be controlled in 2 seconds and completes.
Embodiment described above is only to absolutely prove preferred embodiment that is of the invention and being lifted, protection model of the invention
It encloses without being limited thereto.Those skilled in the art's made equivalent substitute or transformation on the basis of the present invention, in the present invention
Protection scope within.Protection scope of the present invention is subject to claims.
Claims (10)
1. a kind of rapid workpiece welding method accelerated based on figure video card characterized by comprising
Welded workpiece is placed on welding platform;
Obtain the 3D point cloud model of welding workpiece;
The 3D point cloud model is transmitted to control server and is stored in the database by data acquisition server.Data acquisition clothes
Business device is connected with control server by high-speed local area network, and control server is controlled database cluster again;
A cloud is transmitted to arithmetic server by control server, and arithmetic server controls GPU high-performance workstation cluster;All meters
Calculate all by arithmetic server parallelization, 3D point cloud is decoupled, by after partition data and algorithm routine be distributed to each GPU
High-performance workstation, then arithmetic server regathers each GPU high-performance workstation calculated result, is integrated into algorithm towards whole
The calculated result of a cloud.For the different step of program computational flow, this process is repeated;
Arithmetic server passes the path of welding calculated back control server, and stores in the database;
Path of welding is sent electroplating equipment wielding machine arm control server by control server, then starts electroplating equipment wielding machine arm and completes weldering
It connects;
Line laser 3D scanner scans workpiece again after completing welding, by 3D point cloud data transmission to arithmetic server, algorithm clothes
Device be engaged in first to point cloud data removal noise, then analyzes and determines welding quality, provides welding quality inspection report.
2. the rapid workpiece welding method accelerated as described in claim 1 based on figure video card, which is characterized in that the welding
Platform can access assembly line, automatic loading/unloading.
3. the rapid workpiece welding method accelerated as described in claim 1 based on figure video card, which is characterized in that the welding
Platform is as a working position, artificial loading and unloading.
4. the rapid workpiece welding method accelerated as described in claim 1 based on figure video card, which is characterized in that if it is stream
Waterline, 3D line laser scanner is motionless, and welded workpiece is driven by assembly line passes through 3D line laser scanner.
5. the rapid workpiece welding method accelerated as described in claim 1 based on figure video card, which is characterized in that for independent
Working position, linear motor drive line laser 3D scanner to fast move, and scan workpiece and generate 3D point cloud model.
6. the rapid workpiece welding method accelerated as described in claim 1 based on figure video card, which is characterized in that according to be welded
Workpiece complexity, GP configuring U high-performance workstation cluster are connect, the calculating time can be controlled in 2 seconds and completes.
7. the rapid workpiece welding method accelerated as described in claim 1 based on figure video card, which is characterized in that first to a cloud
Data remove noise, then calculate the straight bead in point cloud, and the intersection point according to straight line tentatively finds out candidate pad, then
Feature based on workpiece further selects accurate pad, and last algorithm is based on pad and automatically generates path of welding.
8. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any one of claims 1 to 7 the method when executing described program
Step.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claims 1 to 7 the method is realized when row.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit requires 1 to 7 described in any item methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910496565.6A CN110153584A (en) | 2019-06-10 | 2019-06-10 | The rapid workpiece welding method accelerated based on figure video card |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910496565.6A CN110153584A (en) | 2019-06-10 | 2019-06-10 | The rapid workpiece welding method accelerated based on figure video card |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110153584A true CN110153584A (en) | 2019-08-23 |
Family
ID=67628297
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910496565.6A Pending CN110153584A (en) | 2019-06-10 | 2019-06-10 | The rapid workpiece welding method accelerated based on figure video card |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110153584A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112453648A (en) * | 2020-11-17 | 2021-03-09 | 上海智殷自动化科技有限公司 | Off-line programming laser welding seam tracking system based on 3D vision |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103639583A (en) * | 2013-12-10 | 2014-03-19 | 中国航空工业集团公司北京航空制造工程研究所 | Method and system for carrying out welding through symmetrical electron beam welding track |
CN104076804A (en) * | 2013-03-28 | 2014-10-01 | 株式会社神户制钢所 | Operation path information setting device, program and operation path information setting method |
CN105710496A (en) * | 2016-05-06 | 2016-06-29 | 广州锐速智能科技股份有限公司 | Double-station intelligent welding robot and control system thereof |
CN206321582U (en) * | 2016-12-01 | 2017-07-11 | 太仓世钟汽车配件有限公司 | A kind of welding detection device |
CN107914084A (en) * | 2017-11-16 | 2018-04-17 | 惠州市契贝科技有限公司 | Curved sheets and its method for laser welding, laser welding system |
CN108213775A (en) * | 2016-12-13 | 2018-06-29 | 宁德时代新能源科技股份有限公司 | Battery module scanning system and method |
CN207642480U (en) * | 2017-12-07 | 2018-07-24 | 四川航天长征装备制造有限公司 | A kind of weld seam scanning system being used for five axis agitating frictions welding equipment |
CN108555423A (en) * | 2018-01-16 | 2018-09-21 | 中国计量大学 | Three-dimensional automatic welding line recognition device and method |
-
2019
- 2019-06-10 CN CN201910496565.6A patent/CN110153584A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104076804A (en) * | 2013-03-28 | 2014-10-01 | 株式会社神户制钢所 | Operation path information setting device, program and operation path information setting method |
CN103639583A (en) * | 2013-12-10 | 2014-03-19 | 中国航空工业集团公司北京航空制造工程研究所 | Method and system for carrying out welding through symmetrical electron beam welding track |
CN105710496A (en) * | 2016-05-06 | 2016-06-29 | 广州锐速智能科技股份有限公司 | Double-station intelligent welding robot and control system thereof |
CN206321582U (en) * | 2016-12-01 | 2017-07-11 | 太仓世钟汽车配件有限公司 | A kind of welding detection device |
CN108213775A (en) * | 2016-12-13 | 2018-06-29 | 宁德时代新能源科技股份有限公司 | Battery module scanning system and method |
CN107914084A (en) * | 2017-11-16 | 2018-04-17 | 惠州市契贝科技有限公司 | Curved sheets and its method for laser welding, laser welding system |
CN207642480U (en) * | 2017-12-07 | 2018-07-24 | 四川航天长征装备制造有限公司 | A kind of weld seam scanning system being used for five axis agitating frictions welding equipment |
CN108555423A (en) * | 2018-01-16 | 2018-09-21 | 中国计量大学 | Three-dimensional automatic welding line recognition device and method |
Non-Patent Citations (1)
Title |
---|
李思昆等: "《大规模流场科学计算可视化》", 31 August 2013, 国防工业出版社 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112453648A (en) * | 2020-11-17 | 2021-03-09 | 上海智殷自动化科技有限公司 | Off-line programming laser welding seam tracking system based on 3D vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103753015B (en) | A kind of laser-beam welding machine seam tracking system and welding seam tracking method | |
CN101101277B (en) | High-resolution welding seam supersonic image-forming damage-free detection method | |
Callieri et al. | RoboScan: an automatic system for accurate and unattended 3D scanning | |
CN110988586B (en) | Distribution network live working robot operation accurate positioning method and system | |
CN110176078A (en) | A kind of mask method and device of training set data | |
CN1730248A (en) | Reverse engineering robot system | |
CN111496786A (en) | Point cloud model-based mechanical arm operation processing track planning method | |
CN110153584A (en) | The rapid workpiece welding method accelerated based on figure video card | |
CN111340834B (en) | Lining plate assembly system and method based on laser radar and binocular camera data fusion | |
CN113319859B (en) | Robot teaching method, system and device and electronic equipment | |
CN114581368A (en) | Bar welding method and device based on binocular vision | |
CN111435400A (en) | Part repairing method and device and 3D printer | |
CN101694584A (en) | Aero-engine labyrinth disc hot list processing thickness information extraction system | |
CN109977884A (en) | Target follower method and device | |
CN110154054A (en) | Work piece cut method is automated without teaching based on the high speed of distributed computing | |
CN113744245A (en) | Method and system for positioning structural reinforcing rib welding seam in point cloud | |
Brown et al. | Automated full matrix capture for industrial processes | |
CN107705312A (en) | A kind of method based on line scan data extraction postwelding weld edge point | |
CN117047286B (en) | Method for processing workpiece surface by laser, processing system, processor and storage medium | |
CN208895506U (en) | A kind of robot and vision system assemble testing station | |
Hatami | Data requirements for analysis of manufacturing systems using computer simulation | |
CN115709484B (en) | Mobile robot safety simulation detection method and system | |
US20220319109A1 (en) | Completing point cloud data and processing point cloud data | |
KR102428740B1 (en) | Point Cloud Completion Network Creation and Point Cloud Data Processing | |
WO2022208142A1 (en) | Completing point cloud data and processing point cloud data |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190823 |