CN113681194A - Multilayer and multichannel welding process monitoring and optimizing system and method based on image recognition - Google Patents
Multilayer and multichannel welding process monitoring and optimizing system and method based on image recognition Download PDFInfo
- Publication number
- CN113681194A CN113681194A CN202110959412.8A CN202110959412A CN113681194A CN 113681194 A CN113681194 A CN 113681194A CN 202110959412 A CN202110959412 A CN 202110959412A CN 113681194 A CN113681194 A CN 113681194A
- Authority
- CN
- China
- Prior art keywords
- welding
- test plate
- welding process
- analyzer
- monitoring
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 165
- 238000000034 method Methods 0.000 title claims abstract description 77
- 230000008569 process Effects 0.000 title claims abstract description 60
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 50
- 239000011521 glass Substances 0.000 claims abstract description 30
- 239000002184 metal Substances 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000004021 metal welding Methods 0.000 claims description 8
- 230000007547 defect Effects 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 230000006399 behavior Effects 0.000 description 6
- 238000005457 optimization Methods 0.000 description 5
- 230000007704 transition Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
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
- B23K31/12—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 investigating the properties, e.g. the weldability, of materials
- B23K31/125—Weld quality monitoring
-
- 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
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a multilayer multi-channel welding process monitoring and optimizing system and method based on image recognition, which comprises a metal test plate, a light-transmitting glass test plate, a welding gun, an industrial camera, a welding analyzer and a data processing system, wherein the metal test plate is arranged on the welding analyzer; the metal test plate is abutted against the light-transmitting glass test plate, and a groove is formed between the metal test plate and the light-transmitting glass test plate; the welding gun is used for welding and fixing the metal test plate and the light-transmitting glass test plate together; the industrial camera is used for acquiring dynamic image information of each layer of molten pool in the slope; the welding analyzer is used for collecting electric signals generated in the welding process; the data processing system is used for receiving the image information sent by the industrial camera and the electric signal sent by the welding analyzer, and then combining the recorded actual welding state information to establish a quality mapping relation among the three. The method is simple and easy to implement, has a stable implementation process, improves the accuracy of quality monitoring in the real-time welding process, and can be widely applied to welding production.
Description
Technical Field
The invention relates to the technical field of thick plate welding, in particular to a multilayer multi-pass welding process monitoring and optimizing system and method based on image recognition.
Background
With the rapid development of the manufacturing industry of high-end equipment such as large ships, rail transit, engineering machinery, pipeline welding manufacturing, military equipment and the like in China, large-size, high-performance and thick-wall metal welding structural parts are increasingly widely applied, and the requirement on the quality of welding products is gradually improved. The problems of deformation control, defect control and welding efficiency in the welding process of the thick-wall structural part are more and more concerned by the welding manufacturing industry.
As the thickness of the plate increases, multilayer and multipass welding techniques are widely used. However, because of more multi-layer and multi-pass welding process parameters and great optimization difficulty, defects such as no fusion between layers or side walls, air holes, cracks and the like are easy to occur. The traditional process parameter optimization method is based on a large amount of test data, a large amount of trial and error cost is consumed, and the efficiency is extremely low.
The existing visual monitoring means are mostly based on electric signals or acoustic signals generated in the welding process and obtain some successful application cases, however, the monitoring means are easily interfered and have limitations in the actual welding process. The collection of the sound signals is easily interfered by the site construction environment and limited; the acquisition of the electric signal is relatively easier, but the electric signal has limitations, when the relation between the signal and the welding quality is established, the subsequent mathematical analysis processing is generally required, the identification accuracy is greatly influenced by interference noise and an analysis method, the accuracy degree of the electric signal and the real-time detection conflict with each other in most of the time, and the essential relation between the signal characteristic and the welding process is difficult to establish.
Disclosure of Invention
The invention aims to provide a multilayer and multichannel welding process monitoring and optimizing system and method based on image recognition, which are simple and easy to implement, stable in implementation process, capable of improving the accuracy of quality monitoring in a real-time welding process and widely applicable to welding production.
The invention adopts the following technical scheme for realizing the aim of the invention:
the invention provides a multilayer multi-channel welding process monitoring and optimizing system based on image recognition, which comprises a metal test plate, a light-transmitting glass test plate, a welding gun, an industrial camera, a welding analyzer and a data processing system, wherein the metal test plate is arranged on the upper surface of the metal test plate;
the metal test plate is abutted against the light-transmitting glass test plate, and a groove is formed between the metal test plate and the light-transmitting glass test plate;
the welding gun is used for welding and fixing the metal test plate and the light-transmitting glass test plate together;
the industrial camera is used for acquiring dynamic image information of each layer of molten pool in the slope;
the welding analyzer is used for collecting electric signals generated in the welding process;
the data processing system is used for receiving the image information sent by the industrial camera and the electric signal sent by the welding analyzer, and then establishing a quality mapping relation among the image information, the electric signal and the actual welding state information in combination with the recorded actual welding state information.
Further, the multilayer multi-pass welding process monitoring and optimizing system based on image recognition also comprises a clamp;
the fixture is used for fixing the metal test plate and the light-transmitting glass test plate, so that the welding process is not disturbed.
Further, the industrial camera is placed on one side of the transparent glass test board, and the setting height of the industrial camera corresponds to the welding position.
Further, an optical filter is arranged on the lens of the industrial camera.
Furthermore, the light-transmitting glass test plate is a GG17 high-temperature glass test plate.
Furthermore, a metal welding wire is arranged on the welding gun, and the welding gun and the metal welding wire are positioned in the middle of a groove formed between the metal test plate and the light-transmitting glass test plate.
Further, the wire feed angle of the metal welding wire is set to 30 °.
Furthermore, the shape of the groove is V-shaped or Y-shaped.
The invention provides a multilayer and multichannel welding process monitoring and optimizing method based on image recognition, which comprises the following steps:
acquiring an electric signal generated in the welding process and acquired by a welding analyzer;
acquiring actual welding state information corresponding to each welding in the welding process;
acquiring dynamic image information of each layer of molten pool in the groove sent by an industrial camera, and establishing a welding quality mapping relation between the acquired electric signal generated by a welding analyzer and the recorded actual welding state information;
according to the established welding quality mapping relation, the monitoring accuracy of the real-time welding process and the real-time monitoring welding method are improved.
Further, recording actual welding state information corresponding to each welding in the welding process comprises:
molten pool fluctuation status, post weld formation, and defect information.
The invention has the following beneficial effects:
the method has the advantages that the welding process is simulated through the light-transmitting glass test plate, the dynamic image in the molten pool is obtained, the shielding effect of the welding gun shielding gas on the molten pool is avoided, the visualization of the welding process is realized, the method is simple and easy to realize, and the implementation process is stable;
the welding state judgment is realized through the image in the molten pool, and the mapping establishment of the characteristic information of the welding state and the electric signal is realized by combining the image information and the electric signal in the welding process, so that the accuracy of the quality monitoring in the real-time welding process is greatly improved, and the method can be widely applied to welding production;
the method has the advantages that the molten drop transition behavior in the groove is obtained through the industrial camera, the mapping establishment of the welding wire melting behavior and the electric signal characteristic information in the welding process is realized by combining the image information and the electric signal, and the cognition of the wire filling welding process is expanded, so that the welding quality is analyzed, the optimization of the test design is facilitated, and the stability of the welding process is improved;
the welding state judgment is carried out by combining the image information, the problems that data are redundant and are difficult to match with the actual welding state due to the fact that the electric signals are independently adopted for identification are solved, the types of the welding state are enriched, and the identification quality is improved.
Drawings
Fig. 1 is a diagram of a system for monitoring and optimizing a multi-layer and multi-pass welding process based on image recognition according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to specific examples. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Referring to fig. 1, the invention provides a multilayer multi-pass welding process monitoring optimization system based on image recognition, and relates to components comprising: the device comprises a metal test plate 1, a welding gun 2, a metal welding wire 3, a filling welding seam 4, a GG17 high-temperature glass test plate 5, a CCD industrial camera 6, a data processing system 7, a welding analyzer 8 and a welding machine 9.
Wherein, the same type groove and the truncated edge are processed according to the actual welding condition with GG17 high temperature glass 5 to metal test panel 1 makes it be in same horizontal plane, and the groove appearance of constitution is V-arrangement or Y shape, utilizes anchor clamps fixed position, guarantees that its welding process is not disturbed.
The welding gun 2 and the metal welding wire 3 are placed in the grooves formed in the metal test plate 1 and the GG17 high-temperature glass 5, so that the welding gun is always positioned in the middle of the groove in the moving process, and the wire feeding angle is set to be 30 degrees.
The CCD industrial camera 6 is placed on one side of GG17 high-temperature glass, the height of the CCD industrial camera is the same as the welding position, the camera shooting view field is guaranteed to be the welding position, and molten drop transition behaviors can be observed.
The image recognition-based multilayer and multi-pass welding process optimization process comprises the following steps:
a. referring to fig. 1, fixing the positions of the devices, ensuring that the metal test plate 1 is attached to the GG17 high-temperature glass 5 and is positioned on the same horizontal plane, connecting a welding analyzer 8 between a welding machine 9 and a welding gun 2, collecting electric signals such as voltage and current generated in the welding process, manually recording actual welding state information corresponding to each welding in the welding process, and recording the actual welding state information into a data processing system 7;
recording the actual welding state information means recording the welding state information corresponding to each welding in the welding process, and the welding state information is the welding result obtained by manually observing the welding result, including the fluctuation state of a molten pool, the formation after welding, the defects and the like. If the welding state corresponding to the current and voltage information and the state information of the lower molten pool is recorded during the welding of the underlying layer, the welding state is penetration/non-penetration and the like; when the filling layer is welded, recording the filling state of the position as stable/unstable and the like; and recording the welding state of the position as full/not full and the like during the cover surface welding.
b. A CCD industrial camera 6 is arranged on one side of GG17 high-temperature glass and is aligned to a welding area, so that the flowing of a molten pool and the transition behavior of molten drops can be observed in a visual field;
c. a welding gun and a welding wire are placed in a groove formed by the metal test plate and the high-temperature glass, so that good centering performance is ensured;
d. in the welding process, an optical filter, preferably a narrow-band optical filter, is placed in front of a lens of the CCD industrial camera 6 to filter arc plasma interference, and a weld pool dynamic image and a molten drop transition behavior are collected aiming at a weld pool area, and image information is transmitted to the data processing system 7;
e. the data processing system 7 combines the image information sent by the CCD industrial camera 6 and the electric signal sent by the welding analyzer 8, and then combines the recorded actual welding state information to establish a quality mapping relation among the three.
f. According to the established quality mapping relation, the corresponding welding state information can be judged according to the current and voltage collected by the welding analyzer, the monitoring accuracy of the real-time welding process is improved, and the real-time monitoring welding method is optimized.
The monitoring principle of the traditional welding analyzer is that electric signals are filtered, filtered data are extracted and analyzed according to the characteristics of a welding process to be monitored, characteristic signals of relevant welding process information are obtained, and effective judgment of welding quality is achieved.
The welding analyzer can be used for counting and obtaining an average value, an effective value, a dynamic characteristic value and the like in the welding process, and simple welding process quality monitoring can be carried out by monitoring the fluctuation condition of the characteristic signal. However, since the data amount of the electrical signal is large, the characteristic information extracted from the data amount corresponding to one welding condition is redundant, and thus the accuracy is greatly affected.
In the embodiment of the invention, the weld pool image is used as the welding state judgment standard, the judgment is clear and visible, the acquisition frequency is closer to the welding state change frequency, and the accuracy is greatly improved. In the welding process, an industrial camera is adopted to monitor the fluctuation condition of a molten pool and the melting transition behavior of the welding wire, the corresponding welding state is analyzed, and a more detailed judgment basis is provided for the analysis and the processing of electric signal data.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A multilayer multi-channel welding process monitoring and optimizing system based on image recognition is characterized by comprising a metal test plate, a light-transmitting glass test plate, a welding gun, an industrial camera, a welding analyzer and a data processing system;
the metal test plate is abutted against the light-transmitting glass test plate, and a groove is formed between the metal test plate and the light-transmitting glass test plate;
the welding gun is used for welding and fixing the metal test plate and the light-transmitting glass test plate together;
the industrial camera is used for acquiring dynamic image information of each layer of molten pool in the slope;
the welding analyzer is used for collecting electric signals generated in the welding process;
the data processing system is used for receiving the image information sent by the industrial camera and the electric signal sent by the welding analyzer, and then establishing a quality mapping relation among the image information, the electric signal and the actual welding state information in combination with the recorded actual welding state information.
2. The system for monitoring and optimizing the multi-layer and multi-pass welding process based on the image recognition is characterized by further comprising a clamp;
the fixture is used for fixing the metal test plate and the light-transmitting glass test plate, so that the welding process is not disturbed.
3. The system of claim 1, wherein the industrial camera is disposed on one side of the transparent glass test plate at a height corresponding to a welding position.
4. The system for monitoring and optimizing the multi-layer and multi-channel welding process based on the image recognition as claimed in claim 1, wherein an optical filter is arranged on a lens of the industrial camera.
5. The system of claim 1, wherein the transparent glass test panel is a GG17 high temperature glass test panel.
6. The system for monitoring and optimizing the multilayer and multichannel welding process based on the image recognition is characterized in that a metal welding wire is arranged on the welding gun, and the welding gun and the metal welding wire are positioned in the middle of a groove formed between the metal test plate and the light-transmitting glass test plate.
7. The system of claim 6, wherein the wire feed angle of the metal wire is set to 30 °.
8. The image recognition-based multi-layer and multi-channel welding process monitoring and optimizing system as claimed in claim 1, wherein the groove is V-shaped or Y-shaped in shape.
9. A multilayer and multi-pass welding process monitoring and optimizing method based on image recognition is characterized by comprising the following steps:
acquiring an electric signal generated in the welding process and acquired by a welding analyzer;
acquiring actual welding state information corresponding to each welding in the welding process;
acquiring dynamic image information of each layer of molten pool in the groove sent by an industrial camera, and establishing a welding quality mapping relation between the acquired electric signal generated by a welding analyzer and the recorded actual welding state information;
according to the established welding quality mapping relation, the monitoring accuracy of the real-time welding process and the real-time monitoring welding method are improved.
10. The system of claim 9, wherein the recording of the actual welding status information for each welding process comprises:
molten pool fluctuation status, post weld formation, and defect information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110959412.8A CN113681194A (en) | 2021-08-20 | 2021-08-20 | Multilayer and multichannel welding process monitoring and optimizing system and method based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110959412.8A CN113681194A (en) | 2021-08-20 | 2021-08-20 | Multilayer and multichannel welding process monitoring and optimizing system and method based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113681194A true CN113681194A (en) | 2021-11-23 |
Family
ID=78580983
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110959412.8A Pending CN113681194A (en) | 2021-08-20 | 2021-08-20 | Multilayer and multichannel welding process monitoring and optimizing system and method based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113681194A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1238744A1 (en) * | 2001-02-23 | 2002-09-11 | Nissan Motor Co., Ltd. | Laser weld quality monitoring method and system |
KR20070006026A (en) * | 2005-07-07 | 2007-01-11 | 삼성중공업 주식회사 | Machine vision system and method for automatic data gathering do hull forming process |
CN106735897A (en) * | 2016-12-28 | 2017-05-31 | 西南交通大学 | The device and method of simulation slab narrow gap laser filling wire welding and real-time monitoring |
CN107552932A (en) * | 2017-10-20 | 2018-01-09 | 北京工业大学 | It is a kind of based on the variable-polarity plasma welding method of quality control controlled keyhole profile and device |
CN108480823A (en) * | 2018-02-09 | 2018-09-04 | 中国东方电气集团有限公司 | A kind of long-range Quality Monitoring Control System for heating wire TIG automatic welding |
CN109530955A (en) * | 2018-12-03 | 2019-03-29 | 江苏科技大学 | The welding technological properties evaluating apparatus and method of gas shield welding wire |
-
2021
- 2021-08-20 CN CN202110959412.8A patent/CN113681194A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1238744A1 (en) * | 2001-02-23 | 2002-09-11 | Nissan Motor Co., Ltd. | Laser weld quality monitoring method and system |
KR20070006026A (en) * | 2005-07-07 | 2007-01-11 | 삼성중공업 주식회사 | Machine vision system and method for automatic data gathering do hull forming process |
CN106735897A (en) * | 2016-12-28 | 2017-05-31 | 西南交通大学 | The device and method of simulation slab narrow gap laser filling wire welding and real-time monitoring |
CN107552932A (en) * | 2017-10-20 | 2018-01-09 | 北京工业大学 | It is a kind of based on the variable-polarity plasma welding method of quality control controlled keyhole profile and device |
CN108480823A (en) * | 2018-02-09 | 2018-09-04 | 中国东方电气集团有限公司 | A kind of long-range Quality Monitoring Control System for heating wire TIG automatic welding |
CN109530955A (en) * | 2018-12-03 | 2019-03-29 | 江苏科技大学 | The welding technological properties evaluating apparatus and method of gas shield welding wire |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102463419B (en) | The detection method for quality of laser weld and equipment | |
CN102794566A (en) | Paraxial CCD (Charge Coupled Device)-based laser welding quality online monitoring device | |
CN102049613B (en) | Online diagnosis method for welding defects in laser powder-adding welding process of galvanized steel based on characteristic element plasma optical signal | |
CN103231162A (en) | Device and method for visual detection of welding quality of robot | |
CN113042862A (en) | Welding deviation detection system and detection method based on active and passive visual combination | |
CN101750416A (en) | Visual welding seam surface quality detection sensor based on line structure light | |
CN111015006B (en) | Online monitoring method for laser-arc hybrid welding quality based on spectral information | |
CN109300116A (en) | The online defect identification method of laser welding based on machine learning | |
CN1111721C (en) | Arc method for measuring orifice size of molten bath for plasma welding and signal acquisition system | |
CN108237322B (en) | Real-time monitoring device and method for quality of electron beam dynamic welding seam | |
CN108152291B (en) | End seam welding unfused defect real-time detection method based on dynamic characteristics of molten pool | |
CN109108518A (en) | A kind of online test method and device of Laser Welding hump defect | |
CN110567925A (en) | laser welding online self-adaptive penetration detection device and detection method | |
CN105312781A (en) | Method for detecting whether materials are penetrated or not by using change of gas pressure or flow | |
CN116213883A (en) | Quality monitoring system for non-consumable electrode inert gas shielded welding of deep-melting lock hole | |
CN113681194A (en) | Multilayer and multichannel welding process monitoring and optimizing system and method based on image recognition | |
CN108375581A (en) | Dual-beam laser welding process defect control method based on sound and light signal monitoring | |
CN112975075B (en) | System for monitoring a welding process | |
CN107764315A (en) | Spot-wedling electrode detection means and its detection method | |
CN202763280U (en) | Laser welding quality online monitoring device based on paraxial charge coupled device (CCD) | |
CN100590424C (en) | MIG solder quality monitoring method based on electric arc multi-spectral coverage light information sensing | |
CN107843602A (en) | A kind of detection method for quality of welding line based on image | |
CN113523508A (en) | Device and method for simulating welding process of circumferential weld narrow gap MAG and acquiring molten pool information | |
CN107984104A (en) | A kind of weld seam recognition tracks of device and automatic welding process equipment | |
CN113996918A (en) | Double-beam laser welding T-shaped joint seam detection device and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211123 |
|
RJ01 | Rejection of invention patent application after publication |