CN109604776A - A kind of robot automatic welding weld joint tracking detection method - Google Patents
A kind of robot automatic welding weld joint tracking detection method Download PDFInfo
- Publication number
- CN109604776A CN109604776A CN201811469161.XA CN201811469161A CN109604776A CN 109604776 A CN109604776 A CN 109604776A CN 201811469161 A CN201811469161 A CN 201811469161A CN 109604776 A CN109604776 A CN 109604776A
- Authority
- CN
- China
- Prior art keywords
- welding
- pool
- molten bath
- geometric parameter
- circuit
- 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.)
- Withdrawn
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
- B23K9/00—Arc welding or cutting
- B23K9/12—Automatic feeding or moving of electrodes or work for spot or seam welding or cutting
- B23K9/127—Means for tracking lines during arc welding or cutting
-
- 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
- B23K9/00—Arc welding or cutting
- B23K9/12—Automatic feeding or moving of electrodes or work for spot or seam welding or cutting
- B23K9/127—Means for tracking lines during arc welding or cutting
- B23K9/1272—Geometry oriented, e.g. beam optical trading
- B23K9/1274—Using non-contact, optical means, e.g. laser means
-
- 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
- B23K9/00—Arc welding or cutting
- B23K9/32—Accessories
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Optics & Photonics (AREA)
- Geometry (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of robot automatic welding weld joint tracking detection methods, comprising the following steps: using the dynamic process of artificial neural network algorithm analog pulse welding pool；Artificial Model of Neural Network is trained with the welding pool dynamic feature coefficient that real-time acquisition and processing obtain, carries out self study；The visual pattern that molten bath is absorbed in the short-circuit transitional processes of CO2 drippage, to obtain welding scene characteristic；Image extracts welding pool geometric parameter after computer disposal, and welding pool geometric parameter adjusts welding current according to welding pool geometric parameter for molten bath area, molten bath length, pool width and molten bath contour curve in real time, to control welding penetration.The present invention absorbs molten pool character, the interference for avoiding arc flicker, splashing and flue dust from generating camera shooting process by dripping short-circuit transitional processes in CO2.
Description
Technical field
The invention belongs to automatic welding technique fields, and in particular to a kind of robot automatic welding weld joint tracking detection side
Method.
Background technique
In the industrial robot in the existing whole world, there is 50 percent industrial robot to be applied to different welding fields, welding
There are electric welding and two kinds of basic modes of arc welding in robot.The main work taken up of welding robot is to replace in welding field
The industrial robot that worker is welded manually.A part in this kind of robots is exclusive robot, is in order to suitable
The special machine people to work under certain specific environment, most welding robot are by installing on conventional industrial robot
Soldering apparatus composition.It requires worker that can have enough proficiencys to weld task in welding processing this aspect, has a large amount of real
Experience is trampled, on the other hand, welding is that a kind of work situation is severe again, and flue dust is more, radiation and the high work of risk,
The invention of welding robot allows it is thought that going it that worker to be replaced to weld manually and mitigating the amount of labour of operator, and protect
Weld task quality is demonstrate,proved, welding efficiency is improved.
When robot is welded, the tracking and correction that carry out weld seam are generally required, avoids occurring welding partially, existing skill
Art mostly uses CCD camera to be tracked greatly, but the strong light that occurs, electric and magnetic fields can be to the figures of CCD camera when welding
It is interfered as acquiring, influences the accuracy of imaging.
Summary of the invention
It is an object of the invention to overcome above-mentioned the deficiencies in the prior art, a kind of robot automatic welding weld joint tracking is provided
Detection method.
A kind of robot automatic welding weld joint tracking detection method, comprising the following steps:
S1, using the dynamic process of artificial neural network algorithm analog pulse welding pool；
S2 trains artificial Model of Neural Network with the welding pool dynamic feature coefficient that real-time acquisition and processing obtain, carries out certainly
Study；
S3 absorbs the visual pattern in molten bath, to obtain welding scene characteristic in the short-circuit transitional processes of CO2 drippage；
S4, image extract welding pool geometric parameter after computer disposal, and welding pool geometric parameter is molten bath area, melts
Pond length, pool width and molten bath contour curve adjust welding current according to welding pool geometric parameter in real time, to control
Welding penetration；
The step of S3 are as follows: record the camera pickuping image beginning and end moment with logic control circuit, the circuit is in CO2
Occur to start to expose when short circuit when drippage, time for exposure 2ms is greater than 2ms for short circuit duration and occurs two with single exposure
The improper short circuit of secondary short circuit carries out automatic shield.
Preferably, in the step S2, the process of self study is to find out to connect the corresponding pass of weld pool geometry, welding conditions
System.
Preferably, scene characteristic is welded in the step S3 includes welding wire, molten bath, slag, welding wire short dot.
Compared with prior art, beneficial effects of the present invention:
The present invention absorbs molten pool character by dripping short-circuit transitional processes in CO2, avoids arc flicker, splashing and flue dust to camera shooting
The interference that process generates.
Specific embodiment
A kind of robot automatic welding weld joint tracking detection method, comprising the following steps:
S1, using the dynamic process of artificial neural network algorithm analog pulse welding pool；
S2 trains artificial Model of Neural Network with the welding pool dynamic feature coefficient that real-time acquisition and processing obtain, carries out certainly
Study；
S3 absorbs the visual pattern in molten bath, to obtain welding scene characteristic in the short-circuit transitional processes of CO2 drippage；
S4, image extract welding pool geometric parameter after computer disposal, and welding pool geometric parameter is molten bath area, melts
Pond length, pool width and molten bath contour curve adjust welding current according to welding pool geometric parameter in real time, to control
Welding penetration；
The step of S3 are as follows: record the camera pickuping image beginning and end moment with logic control circuit, the circuit is in CO2
Occur to start to expose when short circuit when drippage, time for exposure 2ms is greater than 2ms for short circuit duration and occurs two with single exposure
The improper short circuit of secondary short circuit carries out automatic shield.
In the step S2, the process of self study is to find out to connect weld pool geometry, welding conditions corresponding relationship.
It includes welding wire, molten bath, slag, welding wire short dot that scene characteristic is welded in the step S3.
Claims (3)
1. a kind of robot automatic welding weld joint tracking detection method, comprising the following steps:
S1, using the dynamic process of artificial neural network algorithm analog pulse welding pool；
S2 trains artificial Model of Neural Network with the welding pool dynamic feature coefficient that real-time acquisition and processing obtain, carries out certainly
Study；
S3 absorbs the visual pattern in molten bath, to obtain welding scene characteristic in the short-circuit transitional processes of CO2 drippage；
S4, image extract welding pool geometric parameter after computer disposal, and welding pool geometric parameter is molten bath area, melts
Pond length, pool width and molten bath contour curve adjust welding current according to welding pool geometric parameter in real time, to control
Welding penetration；
The step of S3 are as follows: record the camera pickuping image beginning and end moment with logic control circuit, the circuit is in CO2
Occur to start to expose when short circuit when drippage, time for exposure 2ms is greater than 2ms for short circuit duration and occurs two with single exposure
The improper short circuit of secondary short circuit carries out automatic shield.
2. a kind of tracking of robot automatic welding weld joint tracking detection method as described in claim 1, feature exist
In: in the step S2, the process of self study is to find out to connect weld pool geometry, welding conditions corresponding relationship.
3. a kind of tracking of robot automatic welding weld joint tracking detection method as described in claim 1, feature exist
In: it includes welding wire, molten bath, slag, welding wire short dot that scene characteristic is welded in the step S3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811469161.XA CN109604776A (en) | 2018-11-28 | 2018-11-28 | A kind of robot automatic welding weld joint tracking detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811469161.XA CN109604776A (en) | 2018-11-28 | 2018-11-28 | A kind of robot automatic welding weld joint tracking detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109604776A true CN109604776A (en) | 2019-04-12 |
Family
ID=66005744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811469161.XA Withdrawn CN109604776A (en) | 2018-11-28 | 2018-11-28 | A kind of robot automatic welding weld joint tracking detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109604776A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110293279A (en) * | 2019-06-27 | 2019-10-01 | 湘潭大学 | A kind of plane annular multi-pole capacitor weld seam tracking sensor |
| CN113828947A (en) * | 2021-11-23 | 2021-12-24 | 昆山宝锦激光拼焊有限公司 | BP neural network laser welding seam forming prediction method based on double optimization |
| CN113966527A (en) * | 2019-06-13 | 2022-01-21 | 株式会社V技术 | Laser repair method and laser repair device |
| CN117381105A (en) * | 2023-12-11 | 2024-01-12 | 宾采尔(广州)焊接技术有限公司 | Robot welding current control method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1215641A (en) * | 1997-10-24 | 1999-05-05 | 武汉水利电力大学 | Automatic carbon dioxide gas arc double-filament short transition narrow gap all position welding equipment |
| CN107598401A (en) * | 2016-07-12 | 2018-01-19 | 沈阳富创精密设备有限公司 | Plasma arc welding (PAW) electric current molten wide control system based on Fuzzy Reasoning Neural Network |
| CN108637435A (en) * | 2018-05-16 | 2018-10-12 | 华南理工大学 | A kind of three-dimensional seam tracking system and method for view-based access control model and arc voltage sensing |
-
2018
- 2018-11-28 CN CN201811469161.XA patent/CN109604776A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1215641A (en) * | 1997-10-24 | 1999-05-05 | 武汉水利电力大学 | Automatic carbon dioxide gas arc double-filament short transition narrow gap all position welding equipment |
| CN107598401A (en) * | 2016-07-12 | 2018-01-19 | 沈阳富创精密设备有限公司 | Plasma arc welding (PAW) electric current molten wide control system based on Fuzzy Reasoning Neural Network |
| CN108637435A (en) * | 2018-05-16 | 2018-10-12 | 华南理工大学 | A kind of three-dimensional seam tracking system and method for view-based access control model and arc voltage sensing |
Non-Patent Citations (2)
| Title |
|---|
| 覃科等: "《基于卷积神经网络的CO2焊接熔池》", 《焊接》 * |
| 陈强等: "《CO2短路过渡焊接熔池形状检测》", 《第九次全国焊接会议论文集（第2册）》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113966527A (en) * | 2019-06-13 | 2022-01-21 | 株式会社V技术 | Laser repair method and laser repair device |
| CN110293279A (en) * | 2019-06-27 | 2019-10-01 | 湘潭大学 | A kind of plane annular multi-pole capacitor weld seam tracking sensor |
| CN113828947A (en) * | 2021-11-23 | 2021-12-24 | 昆山宝锦激光拼焊有限公司 | BP neural network laser welding seam forming prediction method based on double optimization |
| CN117381105A (en) * | 2023-12-11 | 2024-01-12 | 宾采尔(广州)焊接技术有限公司 | Robot welding current control method and device, electronic equipment and storage medium |
| CN117381105B (en) * | 2023-12-11 | 2024-03-08 | 宾采尔(广州)焊接技术有限公司 | Robot welding current control method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109604776A (en) | A kind of robot automatic welding weld joint tracking detection method | |
| US20110006047A1 (en) | Method and system for monitoring and characterizing the creation of a manual weld | |
| CN106163720B (en) | Weld waveform and enhanced consumptive material using AC weld with improve galvanized workpiece welding system and method | |
| CA2821671C (en) | Welding training system | |
| CN105312741A (en) | TIP TIG welding method of LNG storage tanks | |
| CN103567607A (en) | Welding-seam tracking method | |
| WO2022088296A1 (en) | High-speed vision and electrical parameter cooperative sensing control-based high-nitrogen steel arc additive system and control method therefor | |
| CN103394796A (en) | Narrow gap groove of steel containment vessel of nuclear power station and automatic welding method thereof | |
| CN105710489A (en) | Welding process for steel structure | |
| CN112935475A (en) | Welding method for nuclear power steel containment | |
| CN104820976A (en) | Method of controlling laser welding power in real time | |
| CN103831516B (en) | The sequential welding method of the discontinuous solder joint of stainless steel cloth based on visual sensing technology | |
| CN104741789B (en) | Pipeline all-position laser and arc combined welding system | |
| CN109014502A (en) | A kind of weld seam tracing system and method based on laser sensor | |
| CN206105156U (en) | Three -dimensional rectangular robot line laser welding seam automatic tracking system | |
| CN109352127A (en) | A kind of fillet weld automatic welding device and method | |
| CN112756752B (en) | Self-adaptive adjustable double-wire consumable electrode arc welding device and method | |
| CN104588848A (en) | Consumable electrode mixed gas shielded arc welding process for steel plate with thickness being 5 mm | |
| Wang et al. | Tracking and height control in plasma robotic welding using digital CCD camera | |
| CN111014891A (en) | Welding seam tracking processing system | |
| CN110142511A (en) | A kind of method of low-alloy steel laser-MIG electric arc composite welding | |
| CN204621367U (en) | A kind of pipeline all-position laser-arc hybrid welding process welding system | |
| CN105750688A (en) | Steel structure welding technology | |
| CN206732415U (en) | A kind of intelligent robot's automatic soldering device for grid plate weld | |
| CN104588851A (en) | Consumable electrode mixed gas shielded arc welding process for steel plate with thickness below 3 mm |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190412 |
|
| WW01 | Invention patent application withdrawn after publication |